* [PATCH v3 01/97] target/arm: Introduce FPST_ZA, FPST_ZA_F16
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 02/97] target/arm: Use FPST_ZA for sme_fmopa_[hsd] Richard Henderson
` (95 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Rather than repeatedly copying FPST_FPCR to locals
and setting default nan mode, create dedicated float_status.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/cpu.h | 12 +++++++++++-
target/arm/cpu.c | 4 ++++
target/arm/tcg/vfp_helper.c | 12 +++++++++++-
3 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 15b47a5bfc..c5060bcb97 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -206,6 +206,8 @@ typedef struct NVICState NVICState;
* when FPCR.AH == 1 (bfloat16 conversions and multiplies,
* and the reciprocal and square root estimate/step insns);
* for half-precision
+ * ZA: the "streaming sve" fp status.
+ * ZA_F16: likewise for half-precision.
*
* Half-precision operations are governed by a separate
* flush-to-zero control bit in FPSCR:FZ16. We pass a separate
@@ -226,6 +228,12 @@ typedef struct NVICState NVICState;
* they ignore FPCR.RMode. But they don't ignore FPCR.FZ16,
* which means we need an FPST_AH_F16 as well.
*
+ * The "ZA" float_status are for Streaming SVE operations which use
+ * default-NaN and do not generate fp exceptions, which means that they
+ * do not accumulate exception bits back into FPCR.
+ * See e.g. FPAdd vs FPAdd_ZA pseudocode functions, and the setting
+ * of fpcr.DN and fpexec parameters.
+ *
* To avoid having to transfer exception bits around, we simply
* say that the FPSCR cumulative exception flags are the logical
* OR of the flags in the four fp statuses. This relies on the
@@ -239,10 +247,12 @@ typedef enum ARMFPStatusFlavour {
FPST_A64_F16,
FPST_AH,
FPST_AH_F16,
+ FPST_ZA,
+ FPST_ZA_F16,
FPST_STD,
FPST_STD_F16,
} ARMFPStatusFlavour;
-#define FPST_COUNT 8
+#define FPST_COUNT 10
typedef struct CPUArchState {
/* Regs for current mode. */
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index e025e241ed..6111b9db91 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -554,11 +554,15 @@ static void arm_cpu_reset_hold(Object *obj, ResetType type)
set_flush_inputs_to_zero(1, &env->vfp.fp_status[FPST_STD]);
set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD]);
set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD_F16]);
+ set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA]);
+ set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA_F16]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
+ arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32_F16]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+ arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD_F16]);
arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_AH]);
set_flush_to_zero(1, &env->vfp.fp_status[FPST_AH]);
diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c
index b1324c5c0a..e156e3774a 100644
--- a/target/arm/tcg/vfp_helper.c
+++ b/target/arm/tcg/vfp_helper.c
@@ -123,7 +123,7 @@ uint32_t vfp_get_fpsr_from_host(CPUARMState *env)
a64_flags |= (get_float_exception_flags(&env->vfp.fp_status[FPST_A64_F16])
& ~(float_flag_input_denormal_flushed | float_flag_input_denormal_used));
/*
- * We do not merge in flags from FPST_AH or FPST_AH_F16, because
+ * We do not merge in flags from FPST_{AH,ZA} or FPST_{AH,ZA}_F16, because
* they are used for insns that must not set the cumulative exception bits.
*/
@@ -196,6 +196,8 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64]);
set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A32_F16]);
set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64_F16]);
+ set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA]);
+ set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA_F16]);
}
if (changed & FPCR_FZ16) {
bool ftz_enabled = val & FPCR_FZ16;
@@ -203,15 +205,18 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]);
set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]);
set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]);
+ set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]);
set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32_F16]);
set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]);
set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]);
set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]);
+ set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]);
}
if (changed & FPCR_FZ) {
bool ftz_enabled = val & FPCR_FZ;
set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]);
set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64]);
+ set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA]);
/* FIZ is A64 only so FZ always makes A32 code flush inputs to zero */
set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]);
}
@@ -223,6 +228,7 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
bool fitz_enabled = (val & FPCR_FIZ) ||
(val & (FPCR_FZ | FPCR_AH)) == FPCR_FZ;
set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_A64]);
+ set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_ZA]);
}
if (changed & FPCR_DN) {
bool dnan_enabled = val & FPCR_DN;
@@ -240,9 +246,13 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask)
/* Change behaviours for A64 FP operations */
arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+ arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
+ arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
} else {
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]);
arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]);
+ arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]);
+ arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]);
}
}
/*
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 02/97] target/arm: Use FPST_ZA for sme_fmopa_[hsd]
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
2025-07-02 12:32 ` [PATCH v3 01/97] target/arm: Introduce FPST_ZA, FPST_ZA_F16 Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 03/97] target/arm: Rename zarray to za_state.za Richard Henderson
` (94 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sme_helper.c | 37 ++++++++--------------------------
target/arm/tcg/translate-sme.c | 4 ++--
2 files changed, 10 insertions(+), 31 deletions(-)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 8f33387e4b..9942d717aa 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -904,20 +904,11 @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
}
void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
- void *vpm, float_status *fpst_in, uint32_t desc)
+ void *vpm, float_status *fpst, uint32_t desc)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
uint32_t neg = simd_data(desc) << 31;
uint16_t *pn = vpn, *pm = vpm;
- float_status fpst;
-
- /*
- * Make a copy of float_status because this operation does not
- * update the cumulative fp exception status. It also produces
- * default nans.
- */
- fpst = *fpst_in;
- set_default_nan_mode(true, &fpst);
for (row = 0; row < oprsz; ) {
uint16_t pa = pn[H2(row >> 4)];
@@ -932,7 +923,7 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
if (pb & 1) {
uint32_t *a = vza_row + H1_4(col);
uint32_t *m = vzm + H1_4(col);
- *a = float32_muladd(n, *m, *a, 0, &fpst);
+ *a = float32_muladd(n, *m, *a, 0, fpst);
}
col += 4;
pb >>= 4;
@@ -946,15 +937,12 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
}
void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
- void *vpm, float_status *fpst_in, uint32_t desc)
+ void *vpm, float_status *fpst, uint32_t desc)
{
intptr_t row, col, oprsz = simd_oprsz(desc) / 8;
uint64_t neg = (uint64_t)simd_data(desc) << 63;
uint64_t *za = vza, *zn = vzn, *zm = vzm;
uint8_t *pn = vpn, *pm = vpm;
- float_status fpst = *fpst_in;
-
- set_default_nan_mode(true, &fpst);
for (row = 0; row < oprsz; ++row) {
if (pn[H1(row)] & 1) {
@@ -964,7 +952,7 @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
for (col = 0; col < oprsz; ++col) {
if (pm[H1(col)] & 1) {
uint64_t *a = &za_row[col];
- *a = float64_muladd(n, zm[col], *a, 0, &fpst);
+ *a = float64_muladd(n, zm[col], *a, 0, fpst);
}
}
}
@@ -1065,19 +1053,8 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
intptr_t row, col, oprsz = simd_maxsz(desc);
uint32_t neg = simd_data(desc) * 0x80008000u;
uint16_t *pn = vpn, *pm = vpm;
- float_status fpst_odd, fpst_std, fpst_f16;
+ float_status fpst_odd = env->vfp.fp_status[FPST_ZA];
- /*
- * Make copies of the fp status fields we use, because this operation
- * does not update the cumulative fp exception status. It also
- * produces default NaNs. We also need a second copy of fp_status with
- * round-to-odd -- see above.
- */
- fpst_f16 = env->vfp.fp_status[FPST_A64_F16];
- fpst_std = env->vfp.fp_status[FPST_A64];
- set_default_nan_mode(true, &fpst_std);
- set_default_nan_mode(true, &fpst_f16);
- fpst_odd = fpst_std;
set_float_rounding_mode(float_round_to_odd, &fpst_odd);
for (row = 0; row < oprsz; ) {
@@ -1097,7 +1074,9 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
m = f16mop_adj_pair(m, pcol, 0);
*a = f16_dotadd(*a, n, m,
- &fpst_f16, &fpst_std, &fpst_odd);
+ &env->vfp.fp_status[FPST_ZA_F16],
+ &env->vfp.fp_status[FPST_ZA],
+ &fpst_odd);
}
col += 4;
pcol >>= 4;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index fcbb350016..51175c923e 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -358,9 +358,9 @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a,
MO_32, gen_helper_sme_fmopa_h)
TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
- MO_32, FPST_A64, gen_helper_sme_fmopa_s)
+ MO_32, FPST_ZA, gen_helper_sme_fmopa_s)
TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
- MO_64, FPST_A64, gen_helper_sme_fmopa_d)
+ MO_64, FPST_ZA, gen_helper_sme_fmopa_d)
TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 03/97] target/arm: Rename zarray to za_state.za
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
2025-07-02 12:32 ` [PATCH v3 01/97] target/arm: Introduce FPST_ZA, FPST_ZA_F16 Richard Henderson
2025-07-02 12:32 ` [PATCH v3 02/97] target/arm: Use FPST_ZA for sme_fmopa_[hsd] Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 04/97] target/arm: Add isar feature tests for SME2p1, SVE2p1 Richard Henderson
` (93 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
The whole ZA state will also contain ZT0.
Make things easier in aarch64_set_svcr to zero both
by wrapping them in a common structure.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/cpu.h | 48 +++++++++++++++++++---------------
linux-user/aarch64/signal.c | 4 +--
target/arm/cpu.c | 4 +--
target/arm/helper.c | 2 +-
target/arm/machine.c | 2 +-
target/arm/tcg/sme_helper.c | 6 ++---
target/arm/tcg/translate-sme.c | 4 +--
7 files changed, 38 insertions(+), 32 deletions(-)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index c5060bcb97..052ca20283 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -714,27 +714,33 @@ typedef struct CPUArchState {
uint64_t scxtnum_el[4];
- /*
- * SME ZA storage -- 256 x 256 byte array, with bytes in host word order,
- * as we do with vfp.zregs[]. This corresponds to the architectural ZA
- * array, where ZA[N] is in the least-significant bytes of env->zarray[N].
- * When SVL is less than the architectural maximum, the accessible
- * storage is restricted, such that if the SVL is X bytes the guest can
- * see only the bottom X elements of zarray[], and only the least
- * significant X bytes of each element of the array. (In other words,
- * the observable part is always square.)
- *
- * The ZA storage can also be considered as a set of square tiles of
- * elements of different sizes. The mapping from tiles to the ZA array
- * is architecturally defined, such that for tiles of elements of esz
- * bytes, the Nth row (or "horizontal slice") of tile T is in
- * ZA[T + N * esz]. Note that this means that each tile is not contiguous
- * in the ZA storage, because its rows are striped through the ZA array.
- *
- * Because this is so large, keep this toward the end of the reset area,
- * to keep the offsets into the rest of the structure smaller.
- */
- ARMVectorReg zarray[ARM_MAX_VQ * 16];
+ struct {
+ /*
+ * SME ZA storage -- 256 x 256 byte array, with bytes in host
+ * word order, as we do with vfp.zregs[]. This corresponds to
+ * the architectural ZA array, where ZA[N] is in the least
+ * significant bytes of env->za_state.za[N].
+ *
+ * When SVL is less than the architectural maximum, the accessible
+ * storage is restricted, such that if the SVL is X bytes the guest
+ * can see only the bottom X elements of zarray[], and only the least
+ * significant X bytes of each element of the array. (In other words,
+ * the observable part is always square.)
+ *
+ * The ZA storage can also be considered as a set of square tiles of
+ * elements of different sizes. The mapping from tiles to the ZA array
+ * is architecturally defined, such that for tiles of elements of esz
+ * bytes, the Nth row (or "horizontal slice") of tile T is in
+ * ZA[T + N * esz]. Note that this means that each tile is not
+ * contiguous in the ZA storage, because its rows are striped through
+ * the ZA array.
+ *
+ * Because this is so large, keep this toward the end of the
+ * reset area, to keep the offsets into the rest of the structure
+ * smaller.
+ */
+ ARMVectorReg za[ARM_MAX_VQ * 16];
+ } za_state;
struct CPUBreakpoint *cpu_breakpoint[16];
struct CPUWatchpoint *cpu_watchpoint[16];
diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c
index bc7a13800d..d50cab78d8 100644
--- a/linux-user/aarch64/signal.c
+++ b/linux-user/aarch64/signal.c
@@ -248,7 +248,7 @@ static void target_setup_za_record(struct target_za_context *za,
for (i = 0; i < vl; ++i) {
uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i);
for (j = 0; j < vq * 2; ++j) {
- __put_user_e(env->zarray[i].d[j], z + j, le);
+ __put_user_e(env->za_state.za[i].d[j], z + j, le);
}
}
}
@@ -397,7 +397,7 @@ static bool target_restore_za_record(CPUARMState *env,
for (i = 0; i < vl; ++i) {
uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i);
for (j = 0; j < vq * 2; ++j) {
- __get_user_e(env->zarray[i].d[j], z + j, le);
+ __get_user_e(env->za_state.za[i].d[j], z + j, le);
}
}
return true;
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 6111b9db91..f7cbdd6814 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -1335,8 +1335,8 @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags)
qemu_fprintf(f, "ZA[%0*d]=", svl_lg10, i);
for (j = zcr_len; j >= 0; --j) {
qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%c",
- env->zarray[i].d[2 * j + 1],
- env->zarray[i].d[2 * j],
+ env->za_state.za[i].d[2 * j + 1],
+ env->za_state.za[i].d[2 * j],
j ? ':' : '\n');
}
}
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 889d308807..617097a9e7 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -6663,7 +6663,7 @@ void aarch64_set_svcr(CPUARMState *env, uint64_t new, uint64_t mask)
* when disabled either.
*/
if (change & new & R_SVCR_ZA_MASK) {
- memset(env->zarray, 0, sizeof(env->zarray));
+ memset(&env->za_state, 0, sizeof(env->za_state));
}
if (tcg_enabled()) {
diff --git a/target/arm/machine.c b/target/arm/machine.c
index e442d48524..6e73368ef9 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -315,7 +315,7 @@ static const VMStateDescription vmstate_za = {
.minimum_version_id = 1,
.needed = za_needed,
.fields = (const VMStateField[]) {
- VMSTATE_STRUCT_ARRAY(env.zarray, ARMCPU, ARM_MAX_VQ * 16, 0,
+ VMSTATE_STRUCT_ARRAY(env.za_state.za, ARMCPU, ARM_MAX_VQ * 16, 0,
vmstate_vreg, ARMVectorReg),
VMSTATE_END_OF_LIST()
}
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 9942d717aa..7b0bc1b17c 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -39,12 +39,12 @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl)
uint32_t i;
/*
- * Special case clearing the entire ZA space.
+ * Special case clearing the entire ZArray.
* This falls into the CONSTRAINED UNPREDICTABLE zeroing of any
* parts of the ZA storage outside of SVL.
*/
if (imm == 0xff) {
- memset(env->zarray, 0, sizeof(env->zarray));
+ memset(env->za_state.za, 0, sizeof(env->za_state.za));
return;
}
@@ -54,7 +54,7 @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl)
*/
for (i = 0; i < svl; i++) {
if (imm & (1 << (i % 8))) {
- memset(&env->zarray[i], 0, svl);
+ memset(&env->za_state.za[i], 0, svl);
}
}
}
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 51175c923e..e8b3578174 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -92,7 +92,7 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
offset = tile * sizeof(ARMVectorReg);
/* Include the byte offset of zarray to make this relative to env. */
- offset += offsetof(CPUARMState, zarray);
+ offset += offsetof(CPUARMState, za_state.za);
tcg_gen_addi_i32(tmp, tmp, offset);
/* Add the byte offset to env to produce the final pointer. */
@@ -112,7 +112,7 @@ static TCGv_ptr get_tile(DisasContext *s, int esz, int tile)
TCGv_ptr addr = tcg_temp_new_ptr();
int offset;
- offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, zarray);
+ offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, za_state.za);
tcg_gen_addi_ptr(addr, tcg_env, offset);
return addr;
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 04/97] target/arm: Add isar feature tests for SME2p1, SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (2 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 03/97] target/arm: Rename zarray to za_state.za Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 05/97] target/arm: Add ZT0 Richard Henderson
` (92 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/cpu-features.h | 63 +++++++++++++++++++++++++++++++++++++++
target/arm/cpu.h | 1 +
2 files changed, 64 insertions(+)
diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index 4452e7c21e..f1afb9093b 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -603,6 +603,11 @@ static inline bool isar_feature_aa64_rpres(const ARMISARegisters *id)
return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, RPRES);
}
+static inline bool isar_feature_aa64_lut(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, LUT) != 0;
+}
+
static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id)
{
/* We always set the AdvSIMD and FP fields identically. */
@@ -931,6 +936,11 @@ static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id)
return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0;
}
+static inline bool isar_feature_aa64_sve2p1(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) >= 2;
+}
+
static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id)
{
return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0;
@@ -976,6 +986,21 @@ static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id)
return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0;
}
+static inline bool isar_feature_aa64_sve_b16b16(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, B16B16) != 0;
+}
+
+static inline bool isar_feature_aa64_sme_b16b16(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, B16B16) != 0;
+}
+
+static inline bool isar_feature_aa64_sme_f16f16(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, F16F16) != 0;
+}
+
static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id)
{
return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, F64F64);
@@ -991,6 +1016,44 @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id)
return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64);
}
+static inline bool isar_feature_aa64_sme2(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, SMEVER) != 0;
+}
+
+static inline bool isar_feature_aa64_sme2p1(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, SMEVER) >= 2;
+}
+
+/*
+ * Combinations of feature tests, for ease of use with TRANS_FEAT.
+ */
+static inline bool isar_feature_aa64_sme_or_sve2p1(const ARMISARegisters *id)
+{
+ return isar_feature_aa64_sme(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2_or_sve2p1(const ARMISARegisters *id)
+{
+ return isar_feature_aa64_sme2(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2p1_or_sve2p1(const ARMISARegisters *id)
+{
+ return isar_feature_aa64_sme2p1(id) || isar_feature_aa64_sve2p1(id);
+}
+
+static inline bool isar_feature_aa64_sme2_i16i64(const ARMISARegisters *id)
+{
+ return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_i16i64(id);
+}
+
+static inline bool isar_feature_aa64_sme2_f64f64(const ARMISARegisters *id)
+{
+ return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_f64f64(id);
+}
+
/*
* Feature tests for "does this exist in either 32-bit or 64-bit?"
*/
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 052ca20283..a6a54a605a 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -2195,6 +2195,7 @@ FIELD(ID_AA64ISAR2, SYSINSTR_128, 36, 4)
FIELD(ID_AA64ISAR2, PRFMSLC, 40, 4)
FIELD(ID_AA64ISAR2, RPRFM, 48, 4)
FIELD(ID_AA64ISAR2, CSSC, 52, 4)
+FIELD(ID_AA64ISAR2, LUT, 56, 4)
FIELD(ID_AA64ISAR2, ATS1A, 60, 4)
FIELD(ID_AA64PFR0, EL0, 0, 4)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 05/97] target/arm: Add ZT0
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (3 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 04/97] target/arm: Add isar feature tests for SME2p1, SVE2p1 Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 06/97] target/arm: Add zt0_excp_el to DisasContext Richard Henderson
` (91 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
This is a 512-bit array introduced with SME2.
Save it only when ZA is in use.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/cpu.h | 3 +++
target/arm/machine.c | 20 ++++++++++++++++++++
2 files changed, 23 insertions(+)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index a6a54a605a..f3c83702f4 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -715,6 +715,9 @@ typedef struct CPUArchState {
uint64_t scxtnum_el[4];
struct {
+ /* SME2 ZT0 -- 512 bit array, with data ordered like ARMVectorReg. */
+ uint64_t zt0[512 / 64] QEMU_ALIGNED(16);
+
/*
* SME ZA storage -- 256 x 256 byte array, with bytes in host
* word order, as we do with vfp.zregs[]. This corresponds to
diff --git a/target/arm/machine.c b/target/arm/machine.c
index 6e73368ef9..6986915bee 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -321,6 +321,25 @@ static const VMStateDescription vmstate_za = {
}
};
+static bool zt0_needed(void *opaque)
+{
+ ARMCPU *cpu = opaque;
+
+ return za_needed(cpu) && cpu_isar_feature(aa64_sme2, cpu);
+}
+
+static const VMStateDescription vmstate_zt0 = {
+ .name = "cpu/zt0",
+ .version_id = 1,
+ .minimum_version_id = 1,
+ .needed = zt0_needed,
+ .fields = (VMStateField[]) {
+ VMSTATE_UINT64_ARRAY(env.za_state.zt0, ARMCPU,
+ ARRAY_SIZE(((CPUARMState *)0)->za_state.zt0)),
+ VMSTATE_END_OF_LIST()
+ }
+};
+
static bool serror_needed(void *opaque)
{
ARMCPU *cpu = opaque;
@@ -1096,6 +1115,7 @@ const VMStateDescription vmstate_arm_cpu = {
&vmstate_m_security,
&vmstate_sve,
&vmstate_za,
+ &vmstate_zt0,
&vmstate_serror,
&vmstate_irq_line_state,
&vmstate_wfxt_timer,
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 06/97] target/arm: Add zt0_excp_el to DisasContext
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (4 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 05/97] target/arm: Add ZT0 Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-03 9:32 ` Peter Maydell
2025-07-02 12:32 ` [PATCH v3 07/97] target/arm: Implement SME2 ZERO ZT0 Richard Henderson
` (90 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Pipe the value through from SMCR_ELx through hflags and into
the disassembly context. Enable EZT0 in smcr_write.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/cpu.h | 2 ++
target/arm/tcg/translate.h | 1 +
target/arm/cpu.c | 3 +++
target/arm/helper.c | 6 +++++-
target/arm/tcg/hflags.c | 34 +++++++++++++++++++++++++++++++++-
target/arm/tcg/translate-a64.c | 1 +
6 files changed, 45 insertions(+), 2 deletions(-)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index f3c83702f4..2f2c131613 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1497,6 +1497,7 @@ FIELD(SVCR, ZA, 1, 1)
/* Fields for SMCR_ELx. */
FIELD(SMCR, LEN, 0, 4)
+FIELD(SMCR, EZT0, 30, 1)
FIELD(SMCR, FA64, 31, 1)
/* Write a new value to v7m.exception, thus transitioning into or out
@@ -3068,6 +3069,7 @@ FIELD(TBFLAG_A64, NV2_MEM_E20, 35, 1)
FIELD(TBFLAG_A64, NV2_MEM_BE, 36, 1)
FIELD(TBFLAG_A64, AH, 37, 1) /* FPCR.AH */
FIELD(TBFLAG_A64, NEP, 38, 1) /* FPCR.NEP */
+FIELD(TBFLAG_A64, ZT0EXC_EL, 39, 2)
/*
* Helpers for using the above. Note that only the A64 accessors use
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 1bfdb0fb9b..5153824a49 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -70,6 +70,7 @@ typedef struct DisasContext {
int fp_excp_el; /* FP exception EL or 0 if enabled */
int sve_excp_el; /* SVE exception EL or 0 if enabled */
int sme_excp_el; /* SME exception EL or 0 if enabled */
+ int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */
int vl; /* current vector length in bytes */
int svl; /* current streaming vector length in bytes */
bool vfp_enabled; /* FP enabled via FPSCR.EN */
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index f7cbdd6814..3ceb8d87f4 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -635,6 +635,9 @@ void arm_emulate_firmware_reset(CPUState *cpustate, int target_el)
env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK;
env->cp15.scr_el3 |= SCR_ENTP2;
env->vfp.smcr_el[3] = 0xf;
+ if (cpu_isar_feature(aa64_sme2, cpu)) {
+ env->vfp.smcr_el[3] |= R_SMCR_EZT0_MASK;
+ }
}
if (cpu_isar_feature(aa64_hcx, cpu)) {
env->cp15.scr_el3 |= SCR_HXEN;
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 617097a9e7..2edd43bb2f 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -6682,10 +6682,14 @@ static void smcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
{
int cur_el = arm_current_el(env);
int old_len = sve_vqm1_for_el(env, cur_el);
+ uint64_t valid_mask = R_SMCR_LEN_MASK | R_SMCR_FA64_MASK;
int new_len;
QEMU_BUILD_BUG_ON(ARM_MAX_VQ > R_SMCR_LEN_MASK + 1);
- value &= R_SMCR_LEN_MASK | R_SMCR_FA64_MASK;
+ if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) {
+ valid_mask |= R_SMCR_EZT0_MASK;
+ }
+ value &= valid_mask;
raw_write(env, ri, value);
/*
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index 1ccec63bbd..59ab526375 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -214,6 +214,31 @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el,
return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
}
+/*
+ * Return the exception level to which exceptions should be taken for ZT0.
+ * C.f. the ARM pseudocode function CheckSMEZT0Enabled, after the ZA check.
+ */
+static int zt0_exception_el(CPUARMState *env, int el)
+{
+#ifndef CONFIG_USER_ONLY
+ if (el <= 1
+ && !el_is_in_host(env, el)
+ && !FIELD_EX64(env->vfp.smcr_el[1], SMCR, EZT0)) {
+ return 1;
+ }
+ if (el <= 2
+ && arm_is_el2_enabled(env)
+ && !FIELD_EX64(env->vfp.smcr_el[2], SMCR, EZT0)) {
+ return 2;
+ }
+ if (arm_feature(env, ARM_FEATURE_EL3)
+ && !FIELD_EX64(env->vfp.smcr_el[3], SMCR, EZT0)) {
+ return 3;
+ }
+#endif
+ return 0;
+}
+
static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
ARMMMUIdx mmu_idx)
{
@@ -269,7 +294,14 @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el,
DP_TBFLAG_A64(flags, PSTATE_SM, 1);
DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el));
}
- DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA));
+
+ if (FIELD_EX64(env->svcr, SVCR, ZA)) {
+ DP_TBFLAG_A64(flags, PSTATE_ZA, 1);
+ if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) {
+ int zt0_el = zt0_exception_el(env, el);
+ DP_TBFLAG_A64(flags, ZT0EXC_EL, zt0_el);
+ }
+ }
}
sctlr = regime_sctlr(env, stage1);
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 7f8671e2e8..4ad2a9d1bf 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10141,6 +10141,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
dc->trap_eret = EX_TBFLAG_A64(tb_flags, TRAP_ERET);
dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL);
dc->sme_excp_el = EX_TBFLAG_A64(tb_flags, SMEEXC_EL);
+ dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL);
dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16;
dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16;
dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE);
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 07/97] target/arm: Implement SME2 ZERO ZT0
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (5 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 06/97] target/arm: Add zt0_excp_el to DisasContext Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 08/97] target/arm: Add alignment argument to gen_sve_{ldr, str} Richard Henderson
` (89 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/syndrome.h | 1 +
target/arm/tcg/translate-sme.c | 26 ++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 1 +
3 files changed, 28 insertions(+)
diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h
index 3244e0740d..c48d3b8587 100644
--- a/target/arm/syndrome.h
+++ b/target/arm/syndrome.h
@@ -80,6 +80,7 @@ typedef enum {
SME_ET_Streaming,
SME_ET_NotStreaming,
SME_ET_InactiveZA,
+ SME_ET_InaccessibleZT0,
} SMEExceptionType;
#define ARM_EL_EC_LENGTH 6
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index e8b3578174..246f191eca 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -27,6 +27,19 @@
#include "decode-sme.c.inc"
+static bool sme2_zt0_enabled_check(DisasContext *s)
+{
+ if (!sme_za_enabled_check(s)) {
+ return false;
+ }
+ if (s->zt0_excp_el) {
+ gen_exception_insn_el(s, 0, EXCP_UDEF,
+ syn_smetrap(SME_ET_InaccessibleZT0, false),
+ s->zt0_excp_el);
+ return false;
+ }
+ return true;
+}
/*
* Resolve tile.size[index] to a host pointer, where tile and index
@@ -130,6 +143,19 @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a)
return true;
}
+static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
+{
+ if (!dc_isar_feature(aa64_sme2, s)) {
+ return false;
+ }
+ if (sme_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+ tcg_gen_gvec_dup_imm(MO_64, offsetof(CPUARMState, za_state.zt0),
+ sizeof_field(CPUARMState, za_state.zt0),
+ sizeof_field(CPUARMState, za_state.zt0), 0);
+ }
+ return true;
+}
+
static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
{
static gen_helper_gvec_4 * const h_fns[5] = {
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 628804e37a..dd1f983941 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -22,6 +22,7 @@
### SME Misc
ZERO 11000000 00 001 00000000000 imm:8
+ZERO_zt0 11000000 01 001 00000000000 00000001
### SME Move into/from Array
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 08/97] target/arm: Add alignment argument to gen_sve_{ldr, str}
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (6 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 07/97] target/arm: Implement SME2 ZERO ZT0 Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-03 9:33 ` Peter Maydell
2025-07-02 12:32 ` [PATCH v3 09/97] target/arm: Implement SME2 LDR/STR ZT0 Richard Henderson
` (88 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Honor AlignmentEnforced() for LDR/STR (vector),
(predicate), and (array vector).
Within the expansion functions, clear @align when we're
done emitting loads at the largest size.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-a64.h | 6 ++--
target/arm/tcg/translate-sme.c | 5 ++--
target/arm/tcg/translate-sve.c | 50 ++++++++++++++++++++++++----------
3 files changed, 42 insertions(+), 19 deletions(-)
diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h
index b2420f59eb..8a9f4b2053 100644
--- a/target/arm/tcg/translate-a64.h
+++ b/target/arm/tcg/translate-a64.h
@@ -225,7 +225,9 @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs,
uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t opr_sz, uint32_t max_sz);
-void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
-void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
+void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs,
+ int len, int rn, int imm, MemOp align);
+void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs,
+ int len, int rn, int imm, MemOp align);
#endif /* TARGET_ARM_TRANSLATE_A64_H */
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 246f191eca..1dbd0199af 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -269,7 +269,7 @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
return true;
}
-typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int);
+typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp);
static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
{
@@ -284,7 +284,8 @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
/* ZA[n] equates to ZA0H.B[n]. */
base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
- fn(s, base, 0, svl, a->rn, imm * svl);
+ fn(s, base, 0, svl, a->rn, imm * svl,
+ s->align_mem ? MO_ALIGN_16 : MO_UNALN);
return true;
}
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 8403034a0e..d2cd298b5b 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -4160,7 +4160,7 @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz,
*/
void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
- int len, int rn, int imm)
+ int len, int rn, int imm, MemOp align)
{
int len_align = QEMU_ALIGN_DOWN(len, 16);
int len_remain = len % 16;
@@ -4189,12 +4189,15 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
for (i = 0; i < len_align; i += 16) {
tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
- MO_LE | MO_128 | MO_ATOM_NONE);
+ MO_LE | MO_128 | MO_ATOM_NONE | align);
tcg_gen_extr_i128_i64(t0, t1, t16);
tcg_gen_st_i64(t0, base, vofs + i);
tcg_gen_st_i64(t1, base, vofs + i + 8);
tcg_gen_addi_i64(clean_addr, clean_addr, 16);
}
+ if (len_align) {
+ align = MO_UNALN;
+ }
} else {
TCGLabel *loop = gen_new_label();
TCGv_ptr tp, i = tcg_temp_new_ptr();
@@ -4204,7 +4207,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
t16 = tcg_temp_new_i128();
tcg_gen_qemu_ld_i128(t16, clean_addr, midx,
- MO_LE | MO_128 | MO_ATOM_NONE);
+ MO_LE | MO_128 | MO_ATOM_NONE | align);
tcg_gen_addi_i64(clean_addr, clean_addr, 16);
tp = tcg_temp_new_ptr();
@@ -4219,6 +4222,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
tcg_gen_st_i64(t1, tp, vofs + 8);
tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
+ align = MO_UNALN;
}
/*
@@ -4227,7 +4231,9 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
*/
if (len_remain >= 8) {
t0 = tcg_temp_new_i64();
- tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+ tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
+ MO_LEUQ | MO_ATOM_NONE | align);
+ align = MO_UNALN;
tcg_gen_st_i64(t0, base, vofs + len_align);
len_remain -= 8;
len_align += 8;
@@ -4242,12 +4248,14 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
case 4:
case 8:
tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
- MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
+ MO_LE | ctz32(len_remain)
+ | MO_ATOM_NONE | align);
break;
case 6:
t1 = tcg_temp_new_i64();
- tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
+ tcg_gen_qemu_ld_i64(t0, clean_addr, midx,
+ MO_LEUL | MO_ATOM_NONE | align);
tcg_gen_addi_i64(clean_addr, clean_addr, 4);
tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
tcg_gen_deposit_i64(t0, t0, t1, 32, 32);
@@ -4262,7 +4270,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
/* Similarly for stores. */
void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
- int len, int rn, int imm)
+ int len, int rn, int imm, MemOp align)
{
int len_align = QEMU_ALIGN_DOWN(len, 16);
int len_remain = len % 16;
@@ -4294,9 +4302,12 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
tcg_gen_ld_i64(t1, base, vofs + i + 8);
tcg_gen_concat_i64_i128(t16, t0, t1);
tcg_gen_qemu_st_i128(t16, clean_addr, midx,
- MO_LE | MO_128 | MO_ATOM_NONE);
+ MO_LE | MO_128 | MO_ATOM_NONE | align);
tcg_gen_addi_i64(clean_addr, clean_addr, 16);
}
+ if (len_align) {
+ align = MO_UNALN;
+ }
} else {
TCGLabel *loop = gen_new_label();
TCGv_ptr tp, i = tcg_temp_new_ptr();
@@ -4320,13 +4331,16 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
tcg_gen_addi_i64(clean_addr, clean_addr, 16);
tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
+ align = MO_UNALN;
}
/* Predicate register stores can be any multiple of 2. */
if (len_remain >= 8) {
t0 = tcg_temp_new_i64();
tcg_gen_ld_i64(t0, base, vofs + len_align);
- tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE);
+ tcg_gen_qemu_st_i64(t0, clean_addr, midx,
+ MO_LEUQ | MO_ATOM_NONE | align);
+ align = MO_UNALN;
len_remain -= 8;
len_align += 8;
if (len_remain) {
@@ -4342,11 +4356,13 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
case 4:
case 8:
tcg_gen_qemu_st_i64(t0, clean_addr, midx,
- MO_LE | ctz32(len_remain) | MO_ATOM_NONE);
+ MO_LE | ctz32(len_remain)
+ | MO_ATOM_NONE | align);
break;
case 6:
- tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE);
+ tcg_gen_qemu_st_i64(t0, clean_addr, midx,
+ MO_LEUL | MO_ATOM_NONE | align);
tcg_gen_addi_i64(clean_addr, clean_addr, 4);
tcg_gen_shri_i64(t0, t0, 32);
tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE);
@@ -4366,7 +4382,8 @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = vec_full_reg_size(s);
int off = vec_full_reg_offset(s, a->rd);
- gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size);
+ gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size,
+ s->align_mem ? MO_ALIGN_16 : MO_UNALN);
}
return true;
}
@@ -4379,7 +4396,8 @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = pred_full_reg_size(s);
int off = pred_full_reg_offset(s, a->rd);
- gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size);
+ gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size,
+ s->align_mem ? MO_ALIGN_2 : MO_UNALN);
}
return true;
}
@@ -4392,7 +4410,8 @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = vec_full_reg_size(s);
int off = vec_full_reg_offset(s, a->rd);
- gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size);
+ gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size,
+ s->align_mem ? MO_ALIGN_16 : MO_UNALN);
}
return true;
}
@@ -4405,7 +4424,8 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = pred_full_reg_size(s);
int off = pred_full_reg_offset(s, a->rd);
- gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size);
+ gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size,
+ s->align_mem ? MO_ALIGN_2 : MO_UNALN);
}
return true;
}
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 08/97] target/arm: Add alignment argument to gen_sve_{ldr, str}
2025-07-02 12:32 ` [PATCH v3 08/97] target/arm: Add alignment argument to gen_sve_{ldr, str} Richard Henderson
@ 2025-07-03 9:33 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 9:33 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:34, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Honor AlignmentEnforced() for LDR/STR (vector),
> (predicate), and (array vector).
>
> Within the expansion functions, clear @align when we're
> done emitting loads at the largest size.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/translate-a64.h | 6 ++--
> target/arm/tcg/translate-sme.c | 5 ++--
> target/arm/tcg/translate-sve.c | 50 ++++++++++++++++++++++++----------
> 3 files changed, 42 insertions(+), 19 deletions(-)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 09/97] target/arm: Implement SME2 LDR/STR ZT0
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (7 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 08/97] target/arm: Add alignment argument to gen_sve_{ldr, str} Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 10/97] target/arm: Implement SME2 MOVT Richard Henderson
` (87 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 13 +++++++++++++
target/arm/tcg/sme.decode | 6 ++++++
2 files changed, 19 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 1dbd0199af..9f25273992 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -292,6 +292,19 @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr)
TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str)
+static bool do_ldst_zt0(DisasContext *s, arg_ldstzt0 *a, GenLdStR *fn)
+{
+ if (sme2_zt0_enabled_check(s)) {
+ fn(s, tcg_env, offsetof(CPUARMState, za_state.zt0),
+ sizeof_field(CPUARMState, za_state.zt0), a->rn, 0,
+ s->align_mem ? MO_ALIGN_16 : MO_UNALN);
+ }
+ return true;
+}
+
+TRANS_FEAT(LDR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_ldr)
+TRANS_FEAT(STR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_str)
+
static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz,
gen_helper_gvec_4 *fn)
{
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index dd1f983941..cef49c3b29 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -55,6 +55,12 @@ LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \
LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr
STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr
+&ldstzt0 rn
+@ldstzt0 ....... ... . ...... .. ... rn:5 ..... &ldstzt0
+
+LDR_zt0 1110000 100 0 111111 00 000 ..... 00000 @ldstzt0
+STR_zt0 1110000 100 1 111111 00 000 ..... 00000 @ldstzt0
+
### SME Add Vector to Array
&adda zad zn pm pn
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 10/97] target/arm: Implement SME2 MOVT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (8 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 09/97] target/arm: Implement SME2 LDR/STR ZT0 Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 11/97] target/arm: Split get_tile_rowcol argument tile_index Richard Henderson
` (86 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 13 +++++++++++++
target/arm/tcg/sme.decode | 5 +++++
2 files changed, 18 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 9f25273992..797035e289 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -210,6 +210,19 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
return true;
}
+static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
+ void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
+{
+ if (sme2_zt0_enabled_check(s)) {
+ func(cpu_reg(s, a->rt), tcg_env,
+ offsetof(CPUARMState, za_state.zt0) + a->off * 8);
+ }
+ return true;
+}
+
+TRANS_FEAT(MOVT_rzt, aa64_sme2, do_movt, a, tcg_gen_ld_i64)
+TRANS_FEAT(MOVT_ztr, aa64_sme2, do_movt, a, tcg_gen_st_i64)
+
static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
{
typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32);
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index cef49c3b29..83ca6a9104 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -39,6 +39,11 @@ MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \
MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \
&mova to_vec=1 rs=%mova_rs esz=4
+### SME Move into/from ZT0
+
+MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5
+MOVT_ztr 1100 0000 0100 1110 0 off:3 00 11111 rt:5
+
### SME Memory
&ldst esz rs pg rn rm za_imm v:bool st:bool
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 11/97] target/arm: Split get_tile_rowcol argument tile_index
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (9 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 10/97] target/arm: Implement SME2 MOVT Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 12/97] target/arm: Rename MOVA for translate Richard Henderson
` (85 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Decode tile number and index offset beforehand and separately.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 17 +++++--------
target/arm/tcg/sme.decode | 46 +++++++++++++++++++++++-----------
2 files changed, 38 insertions(+), 25 deletions(-)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 797035e289..e22ec393fd 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -41,15 +41,10 @@ static bool sme2_zt0_enabled_check(DisasContext *s)
return true;
}
-/*
- * Resolve tile.size[index] to a host pointer, where tile and index
- * are always decoded together, dependent on the element size.
- */
+/* Resolve tile.size[rs+imm] to a host pointer. */
static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
- int tile_index, bool vertical)
+ int tile, int imm, bool vertical)
{
- int tile = tile_index >> (4 - esz);
- int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz);
int pos, len, offset;
TCGv_i32 tmp;
TCGv_ptr addr;
@@ -57,7 +52,7 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
/* Compute the final index, which is Rs+imm. */
tmp = tcg_temp_new_i32();
tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
- tcg_gen_addi_i32(tmp, tmp, index);
+ tcg_gen_addi_i32(tmp, tmp, imm);
/* Prepare a power-of-two modulo via extraction of @len bits. */
len = ctz32(streaming_vec_reg_size(s)) - esz;
@@ -185,7 +180,7 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
return true;
}
- t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
t_zr = vec_full_reg_ptr(s, a->zr);
t_pg = pred_full_reg_ptr(s, a->pg);
@@ -264,7 +259,7 @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
return true;
}
- t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
t_pg = pred_full_reg_ptr(s, a->pg);
addr = tcg_temp_new_i64();
@@ -295,7 +290,7 @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
}
/* ZA[n] equates to ZA0H.B[n]. */
- base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
+ base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
fn(s, base, 0, svl, a->rn, imm * svl,
s->align_mem ? MO_ALIGN_16 : MO_UNALN);
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 83ca6a9104..efe369e079 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -27,17 +27,29 @@ ZERO_zt0 11000000 01 001 00000000000 00000001
### SME Move into/from Array
%mova_rs 13:2 !function=plus_12
-&mova esz rs pg zr za_imm v:bool to_vec:bool
+&mova esz rs pg zr za off v:bool to_vec:bool
-MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \
- &mova to_vec=0 rs=%mova_rs
-MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \
- &mova to_vec=0 rs=%mova_rs esz=4
+MOVA 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \
+ &mova to_vec=0 rs=%mova_rs esz=0 za=0
+MOVA 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \
+ &mova to_vec=0 rs=%mova_rs esz=1
+MOVA 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \
+ &mova to_vec=0 rs=%mova_rs esz=2
+MOVA 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \
+ &mova to_vec=0 rs=%mova_rs esz=3
+MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \
+ &mova to_vec=0 rs=%mova_rs esz=4 off=0
-MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \
- &mova to_vec=1 rs=%mova_rs
-MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=4
+MOVA 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=0 za=0
+MOVA 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=1
+MOVA 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=2
+MOVA 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=3
+MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=4 off=0
### SME Move into/from ZT0
@@ -46,12 +58,18 @@ MOVT_ztr 1100 0000 0100 1110 0 off:3 00 11111 rt:5
### SME Memory
-&ldst esz rs pg rn rm za_imm v:bool st:bool
+&ldst esz rs pg rn rm za off v:bool st:bool
-LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \
- &ldst rs=%mova_rs
-LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \
- &ldst esz=4 rs=%mova_rs
+LDST1 1110000 0 00 st:1 rm:5 v:1 .. pg:3 rn:5 0 off:4 \
+ &ldst rs=%mova_rs esz=0 za=0
+LDST1 1110000 0 01 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:1 off:3 \
+ &ldst rs=%mova_rs esz=1
+LDST1 1110000 0 10 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:2 off:2 \
+ &ldst rs=%mova_rs esz=2
+LDST1 1110000 0 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:3 off:1 \
+ &ldst rs=%mova_rs esz=3
+LDST1 1110000 1 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:4 \
+ &ldst rs=%mova_rs esz=4 off=0
&ldstr rv rn imm
@ldstr ....... ... . ...... .. ... rn:5 . imm:4 \
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 12/97] target/arm: Rename MOVA for translate
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (10 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 11/97] target/arm: Split get_tile_rowcol argument tile_index Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 13/97] target/arm: Split out get_zarray Richard Henderson
` (84 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Prepare for more kinds of MOVA from SME2 by renaming the
existing SME1 MOVA to indicate tile to/from vector.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 12 +++++-----
target/arm/tcg/sme.decode | 42 +++++++++++++++++-----------------
2 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index e22ec393fd..2c8cb24b7c 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -151,7 +151,7 @@ static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
return true;
}
-static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
+static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
{
static gen_helper_gvec_4 * const h_fns[5] = {
gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h,
@@ -173,9 +173,6 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
TCGv_i32 t_desc;
int svl;
- if (!dc_isar_feature(aa64_sme, s)) {
- return false;
- }
if (!sme_smza_enabled_check(s)) {
return true;
}
@@ -189,14 +186,14 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
if (a->v) {
/* Vertical slice -- use sme mova helpers. */
- if (a->to_vec) {
+ if (to_vec) {
zc_fns[a->esz](t_zr, t_za, t_pg, t_desc);
} else {
cz_fns[a->esz](t_za, t_zr, t_pg, t_desc);
}
} else {
/* Horizontal slice -- reuse sve sel helpers. */
- if (a->to_vec) {
+ if (to_vec) {
h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc);
} else {
h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc);
@@ -205,6 +202,9 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
return true;
}
+TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false)
+TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true)
+
static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
{
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index efe369e079..459b96805f 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -27,29 +27,29 @@ ZERO_zt0 11000000 01 001 00000000000 00000001
### SME Move into/from Array
%mova_rs 13:2 !function=plus_12
-&mova esz rs pg zr za off v:bool to_vec:bool
+&mova_p esz rs pg zr za off v:bool
-MOVA 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \
- &mova to_vec=0 rs=%mova_rs esz=0 za=0
-MOVA 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \
- &mova to_vec=0 rs=%mova_rs esz=1
-MOVA 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \
- &mova to_vec=0 rs=%mova_rs esz=2
-MOVA 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \
- &mova to_vec=0 rs=%mova_rs esz=3
-MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \
- &mova to_vec=0 rs=%mova_rs esz=4 off=0
+MOVA_tz 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \
+ &mova_p rs=%mova_rs esz=0 za=0
+MOVA_tz 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \
+ &mova_p rs=%mova_rs esz=1
+MOVA_tz 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \
+ &mova_p rs=%mova_rs esz=2
+MOVA_tz 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \
+ &mova_p rs=%mova_rs esz=3
+MOVA_tz 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \
+ &mova_p rs=%mova_rs esz=4 off=0
-MOVA 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=0 za=0
-MOVA 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=1
-MOVA 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=2
-MOVA 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=3
-MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=4 off=0
+MOVA_zt 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \
+ &mova_p rs=%mova_rs esz=0 za=0
+MOVA_zt 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \
+ &mova_p rs=%mova_rs esz=1
+MOVA_zt 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \
+ &mova_p rs=%mova_rs esz=2
+MOVA_zt 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \
+ &mova_p rs=%mova_rs esz=3
+MOVA_zt 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \
+ &mova_p rs=%mova_rs esz=4 off=0
### SME Move into/from ZT0
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 13/97] target/arm: Split out get_zarray
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (11 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 12/97] target/arm: Rename MOVA for translate Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 14/97] target/arm: Introduce ARMCPU.sme_max_vq Richard Henderson
` (83 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Prepare for MOVA array to/from vector with multiple registers
by adding a div_len parameter, herein always 1, and a vec_mod
parameter, herein always 0.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 47 +++++++++++++++++++++++-----------
1 file changed, 32 insertions(+), 15 deletions(-)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 2c8cb24b7c..ea0e5a7cb5 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -43,7 +43,8 @@ static bool sme2_zt0_enabled_check(DisasContext *s)
/* Resolve tile.size[rs+imm] to a host pointer. */
static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
- int tile, int imm, bool vertical)
+ int tile, int imm, int div_len,
+ int vec_mod, bool vertical)
{
int pos, len, offset;
TCGv_i32 tmp;
@@ -52,10 +53,23 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
/* Compute the final index, which is Rs+imm. */
tmp = tcg_temp_new_i32();
tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
+ /*
+ * Round the vector index down to a multiple of vec_mod if necessary.
+ * We do this before adding the offset, to handle cases like
+ * MOVA (tile to vector, 2 registers) where we want to call this
+ * several times in a loop with an increasing offset. We rely on
+ * the instruction encodings always forcing the initial offset in
+ * [rs + offset] to be a multiple of vec_mod. The pseudocode usually
+ * does the round-down after adding the offset rather than before,
+ * but MOVA is an exception.
+ */
+ if (vec_mod > 1) {
+ tcg_gen_andc_i32(tmp, tmp, tcg_constant_i32(vec_mod - 1));
+ }
tcg_gen_addi_i32(tmp, tmp, imm);
/* Prepare a power-of-two modulo via extraction of @len bits. */
- len = ctz32(streaming_vec_reg_size(s)) - esz;
+ len = ctz32(streaming_vec_reg_size(s) / div_len) - esz;
if (!len) {
/*
@@ -111,6 +125,14 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
return addr;
}
+/* Resolve ZArray[rs+imm] to a host pointer. */
+static TCGv_ptr get_zarray(DisasContext *s, int rs, int imm,
+ int div_len, int vec_mod)
+{
+ /* ZA[n] equates to ZA0H.B[n]. */
+ return get_tile_rowcol(s, MO_8, rs, 0, imm, div_len, vec_mod, false);
+}
+
/*
* Resolve tile.size[0] to a host pointer.
* Used by e.g. outer product insns where we require the entire tile.
@@ -177,7 +199,7 @@ static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
return true;
}
- t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v);
t_zr = vec_full_reg_ptr(s, a->zr);
t_pg = pred_full_reg_ptr(s, a->pg);
@@ -259,7 +281,7 @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
return true;
}
- t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v);
t_pg = pred_full_reg_ptr(s, a->pg);
addr = tcg_temp_new_i64();
@@ -281,19 +303,14 @@ typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp);
static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn)
{
- int svl = streaming_vec_reg_size(s);
- int imm = a->imm;
- TCGv_ptr base;
+ if (sme_za_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int imm = a->imm;
+ TCGv_ptr base = get_zarray(s, a->rv, imm, 1, 0);
- if (!sme_za_enabled_check(s)) {
- return true;
+ fn(s, base, 0, svl, a->rn, imm * svl,
+ s->align_mem ? MO_ALIGN_16 : MO_UNALN);
}
-
- /* ZA[n] equates to ZA0H.B[n]. */
- base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
-
- fn(s, base, 0, svl, a->rn, imm * svl,
- s->align_mem ? MO_ALIGN_16 : MO_UNALN);
return true;
}
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 14/97] target/arm: Introduce ARMCPU.sme_max_vq
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (12 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 13/97] target/arm: Split out get_zarray Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-03 9:33 ` Peter Maydell
2025-07-02 12:32 ` [PATCH v3 15/97] target/arm: Implement SME2 MOVA to/from tile, multiple registers Richard Henderson
` (82 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/cpu.h | 1 +
target/arm/cpu64.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 2f2c131613..b5c4fa1e80 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1118,6 +1118,7 @@ struct ArchCPU {
/* Used to set the maximum vector length the cpu will support. */
uint32_t sve_max_vq;
+ uint32_t sme_max_vq;
#ifdef CONFIG_USER_ONLY
/* Used to set the default vector length at process start. */
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index c5c289eadf..8400c7b567 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -343,6 +343,7 @@ void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp)
}
cpu->sme_vq.map = vq_map;
+ cpu->sme_max_vq = 32 - clz32(vq_map);
}
static bool cpu_arm_get_sme(Object *obj, Error **errp)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 14/97] target/arm: Introduce ARMCPU.sme_max_vq
2025-07-02 12:32 ` [PATCH v3 14/97] target/arm: Introduce ARMCPU.sme_max_vq Richard Henderson
@ 2025-07-03 9:33 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 9:33 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:34, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/cpu.h | 1 +
> target/arm/cpu64.c | 1 +
> 2 files changed, 2 insertions(+)
>
> diff --git a/target/arm/cpu.h b/target/arm/cpu.h
> index 2f2c131613..b5c4fa1e80 100644
> --- a/target/arm/cpu.h
> +++ b/target/arm/cpu.h
> @@ -1118,6 +1118,7 @@ struct ArchCPU {
>
> /* Used to set the maximum vector length the cpu will support. */
> uint32_t sve_max_vq;
> + uint32_t sme_max_vq;
>
> #ifdef CONFIG_USER_ONLY
> /* Used to set the default vector length at process start. */
> diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
> index c5c289eadf..8400c7b567 100644
> --- a/target/arm/cpu64.c
> +++ b/target/arm/cpu64.c
> @@ -343,6 +343,7 @@ void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp)
> }
>
> cpu->sme_vq.map = vq_map;
> + cpu->sme_max_vq = 32 - clz32(vq_map);
> }
>
> static bool cpu_arm_get_sme(Object *obj, Error **errp)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 15/97] target/arm: Implement SME2 MOVA to/from tile, multiple registers
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (13 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 14/97] target/arm: Introduce ARMCPU.sme_max_vq Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-03 9:33 ` Peter Maydell
2025-07-02 12:32 ` [PATCH v3 16/97] target/arm: Implement SME2 MOVA to/from array, " Richard Henderson
` (81 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 9 +++++
target/arm/tcg/translate.h | 1 +
target/arm/tcg/sme_helper.c | 64 ++++++++++++++++++++++++++++++
target/arm/tcg/translate-a64.c | 1 +
target/arm/tcg/translate-sme.c | 71 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 37 ++++++++++++++++++
6 files changed, 183 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 858d69188f..8246ce774c 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -33,6 +33,15 @@ DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_cz_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_cz_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_cz_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 5153824a49..4dbc30a376 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -73,6 +73,7 @@ typedef struct DisasContext {
int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */
int vl; /* current vector length in bytes */
int svl; /* current streaming vector length in bytes */
+ int max_svl; /* maximum implemented streaming vector length */
bool vfp_enabled; /* FP enabled via FPSCR.EN */
int vec_len;
int vec_stride;
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 7b0bc1b17c..baeaa3e069 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -206,6 +206,50 @@ void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc)
#undef DO_MOVA_Z
+void HELPER(sme2_mova_zc_b)(void *vdst, void *vsrc, uint32_t desc)
+{
+ const uint8_t *src = vsrc;
+ uint8_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc);
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ }
+}
+
+void HELPER(sme2_mova_zc_h)(void *vdst, void *vsrc, uint32_t desc)
+{
+ const uint16_t *src = vsrc;
+ uint16_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 2;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ }
+}
+
+void HELPER(sme2_mova_zc_s)(void *vdst, void *vsrc, uint32_t desc)
+{
+ const uint32_t *src = vsrc;
+ uint32_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 4;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ }
+}
+
+void HELPER(sme2_mova_zc_d)(void *vdst, void *vsrc, uint32_t desc)
+{
+ const uint64_t *src = vsrc;
+ uint64_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 8;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ }
+}
+
/*
* Clear elements in a tile slice comprising len bytes.
*/
@@ -314,6 +358,26 @@ static void copy_vertical_q(void *vdst, const void *vsrc, size_t len)
}
}
+void HELPER(sme2_mova_cz_b)(void *vdst, void *vsrc, uint32_t desc)
+{
+ copy_vertical_b(vdst, vsrc, simd_oprsz(desc));
+}
+
+void HELPER(sme2_mova_cz_h)(void *vdst, void *vsrc, uint32_t desc)
+{
+ copy_vertical_h(vdst, vsrc, simd_oprsz(desc));
+}
+
+void HELPER(sme2_mova_cz_s)(void *vdst, void *vsrc, uint32_t desc)
+{
+ copy_vertical_s(vdst, vsrc, simd_oprsz(desc));
+}
+
+void HELPER(sme2_mova_cz_d)(void *vdst, void *vsrc, uint32_t desc)
+{
+ copy_vertical_d(vdst, vsrc, simd_oprsz(desc));
+}
+
/*
* Host and TLB primitives for vertical tile slice addressing.
*/
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 4ad2a9d1bf..11abddee52 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10144,6 +10144,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL);
dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16;
dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16;
+ dc->max_svl = arm_cpu->sme_max_vq * 16;
dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE);
dc->bt = EX_TBFLAG_A64(tb_flags, BT);
dc->btype = EX_TBFLAG_A64(tb_flags, BTYPE);
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index ea0e5a7cb5..7d4c7d7e85 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -227,6 +227,77 @@ static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false)
TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true)
+static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
+{
+ static gen_helper_gvec_2 * const cz_fns[] = {
+ gen_helper_sme2_mova_cz_b, gen_helper_sme2_mova_cz_h,
+ gen_helper_sme2_mova_cz_s, gen_helper_sme2_mova_cz_d,
+ };
+ static gen_helper_gvec_2 * const zc_fns[] = {
+ gen_helper_sme2_mova_zc_b, gen_helper_sme2_mova_zc_h,
+ gen_helper_sme2_mova_zc_s, gen_helper_sme2_mova_zc_d,
+ };
+ TCGv_ptr t_za;
+ int svl, bytes_per_op = n << a->esz;
+
+ /*
+ * The MaxImplementedSVL check happens in the decode pseudocode,
+ * before the SM+ZA enabled check in the operation pseudocode.
+ * This will (currently) only fail for NREG=4, ESZ=MO_64.
+ */
+ if (s->max_svl < bytes_per_op) {
+ unallocated_encoding(s);
+ return true;
+ }
+
+ if (!sme_smza_enabled_check(s)) {
+ return true;
+ }
+
+ svl = streaming_vec_reg_size(s);
+
+ /*
+ * The CurrentVL check happens in the operation pseudocode,
+ * after the SM+ZA enabled check.
+ */
+ if (svl < bytes_per_op) {
+ unallocated_encoding(s);
+ return true;
+ }
+
+ if (a->v) {
+ TCGv_i32 t_desc = tcg_constant_i32(simd_desc(svl, svl, 0));
+
+ for (int i = 0; i < n; ++i) {
+ TCGv_ptr t_zr = vec_full_reg_ptr(s, a->zr * n + i);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za,
+ a->off * n + i, 1, n, a->v);
+ if (to_vec) {
+ zc_fns[a->esz](t_zr, t_za, t_desc);
+ } else {
+ cz_fns[a->esz](t_za, t_zr, t_desc);
+ }
+ }
+ } else {
+ for (int i = 0; i < n; ++i) {
+ int o_zr = vec_full_reg_offset(s, a->zr * n + i);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za,
+ a->off * n + i, 1, n, a->v);
+ if (to_vec) {
+ tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, 0, svl, svl);
+ } else {
+ tcg_gen_gvec_mov_var(MO_8, t_za, 0, tcg_env, o_zr, svl, svl);
+ }
+ }
+ }
+ return true;
+}
+
+TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false)
+TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false)
+TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true)
+TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true)
+
static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
{
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 459b96805f..5eca5f4acf 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -28,6 +28,7 @@ ZERO_zt0 11000000 01 001 00000000000 00000001
%mova_rs 13:2 !function=plus_12
&mova_p esz rs pg zr za off v:bool
+&mova_t esz rs zr za off v:bool
MOVA_tz 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \
&mova_p rs=%mova_rs esz=0 za=0
@@ -51,6 +52,42 @@ MOVA_zt 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \
MOVA_zt 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \
&mova_p rs=%mova_rs esz=4 off=0
+MOVA_tz2 11000000 00 00010 0 v:1 .. 000 zr:4 0 00 off:3 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVA_tz2 11000000 01 00010 0 v:1 .. 000 zr:4 0 00 za:1 off:2 \
+ &mova_t rs=%mova_rs esz=1
+MOVA_tz2 11000000 10 00010 0 v:1 .. 000 zr:4 0 00 za:2 off:1 \
+ &mova_t rs=%mova_rs esz=2
+MOVA_tz2 11000000 11 00010 0 v:1 .. 000 zr:4 0 00 za:3 \
+ &mova_t rs=%mova_rs esz=3 off=0
+
+MOVA_zt2 11000000 00 00011 0 v:1 .. 000 00 off:3 zr:4 0 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVA_zt2 11000000 01 00011 0 v:1 .. 000 00 za:1 off:2 zr:4 0 \
+ &mova_t rs=%mova_rs esz=1
+MOVA_zt2 11000000 10 00011 0 v:1 .. 000 00 za:2 off:1 zr:4 0 \
+ &mova_t rs=%mova_rs esz=2
+MOVA_zt2 11000000 11 00011 0 v:1 .. 000 00 za:3 zr:4 0 \
+ &mova_t rs=%mova_rs esz=3 off=0
+
+MOVA_tz4 11000000 00 00010 0 v:1 .. 001 zr:3 00 000 off:2 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVA_tz4 11000000 01 00010 0 v:1 .. 001 zr:3 00 000 za:1 off:1 \
+ &mova_t rs=%mova_rs esz=1
+MOVA_tz4 11000000 10 00010 0 v:1 .. 001 zr:3 00 000 za:2 \
+ &mova_t rs=%mova_rs esz=2 off=0
+MOVA_tz4 11000000 11 00010 0 v:1 .. 001 zr:3 00 00 za:3 \
+ &mova_t rs=%mova_rs esz=3 off=0
+
+MOVA_zt4 11000000 00 00011 0 v:1 .. 001 000 off:2 zr:3 00 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVA_zt4 11000000 01 00011 0 v:1 .. 001 000 za:1 off:1 zr:3 00 \
+ &mova_t rs=%mova_rs esz=1
+MOVA_zt4 11000000 10 00011 0 v:1 .. 001 000 za:2 zr:3 00 \
+ &mova_t rs=%mova_rs esz=2 off=0
+MOVA_zt4 11000000 11 00011 0 v:1 .. 001 00 za:3 zr:3 00 \
+ &mova_t rs=%mova_rs esz=3 off=0
+
### SME Move into/from ZT0
MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 16/97] target/arm: Implement SME2 MOVA to/from array, multiple registers
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (14 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 15/97] target/arm: Implement SME2 MOVA to/from tile, multiple registers Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 17/97] target/arm: Implement SME2 BMOPA Richard Henderson
` (80 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate.h | 5 +++++
target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 12 ++++++++++++
3 files changed, 47 insertions(+)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 4dbc30a376..1b29b958f3 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -210,6 +210,11 @@ static inline int plus_2(DisasContext *s, int x)
return x + 2;
}
+static inline int plus_8(DisasContext *s, int x)
+{
+ return x + 8;
+}
+
static inline int plus_12(DisasContext *s, int x)
{
return x + 12;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 7d4c7d7e85..7b275dd2b8 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -298,6 +298,36 @@ TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false)
TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true)
TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true)
+static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
+{
+ TCGv_ptr t_za;
+ int svl;
+
+ if (!sme_smza_enabled_check(s)) {
+ return true;
+ }
+
+ svl = streaming_vec_reg_size(s);
+ t_za = get_zarray(s, a->rv, a->off, n, 0);
+
+ for (int i = 0; i < n; ++i) {
+ int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+ int o_zr = vec_full_reg_offset(s, a->zr * n + i);
+
+ if (to_vec) {
+ tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl);
+ } else {
+ tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl);
+ }
+ }
+ return true;
+}
+
+TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false)
+TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false)
+TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true)
+TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true)
+
static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
{
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 5eca5f4acf..37bd0c6198 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -27,6 +27,8 @@ ZERO_zt0 11000000 01 001 00000000000 00000001
### SME Move into/from Array
%mova_rs 13:2 !function=plus_12
+%mova_rv 13:2 !function=plus_8
+&mova_a rv zr off
&mova_p esz rs pg zr za off v:bool
&mova_t esz rs zr za off v:bool
@@ -88,6 +90,16 @@ MOVA_zt4 11000000 10 00011 0 v:1 .. 001 000 za:2 zr:3 00 \
MOVA_zt4 11000000 11 00011 0 v:1 .. 001 00 za:3 zr:3 00 \
&mova_t rs=%mova_rs esz=3 off=0
+MOVA_az2 11000000 00 00010 00 .. 010 zr:4 000 off:3 \
+ &mova_a rv=%mova_rv
+MOVA_az4 11000000 00 00010 00 .. 011 zr:3 0000 off:3 \
+ &mova_a rv=%mova_rv
+
+MOVA_za2 11000000 00 00011 00 .. 010 00 off:3 zr:4 0 \
+ &mova_a rv=%mova_rv
+MOVA_za4 11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \
+ &mova_a rv=%mova_rv
+
### SME Move into/from ZT0
MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 17/97] target/arm: Implement SME2 BMOPA
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (15 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 16/97] target/arm: Implement SME2 MOVA to/from array, " Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 18/97] target/arm: Implement SME2 SMOPS, UMOPS (2-way) Richard Henderson
` (79 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 3 +++
target/arm/tcg/sme_helper.c | 34 ++++++++++++++++++++++++----------
target/arm/tcg/translate-sme.c | 2 ++
target/arm/tcg/sme.decode | 2 ++
4 files changed, 31 insertions(+), 10 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 8246ce774c..17d1a7c102 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -153,3 +153,6 @@ DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index baeaa3e069..6122a5b5d9 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1297,17 +1297,31 @@ DEF_IMOP_64(umopa_d, uint16_t, uint16_t)
DEF_IMOP_64(sumopa_d, int16_t, uint16_t)
DEF_IMOP_64(usmopa_d, uint16_t, int16_t)
-#define DEF_IMOPH(NAME, S) \
- void HELPER(sme_##NAME##_##S)(void *vza, void *vzn, void *vzm, \
+#define DEF_IMOPH(P, NAME, S) \
+ void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm, \
void *vpn, void *vpm, uint32_t desc) \
{ do_imopa_##S(vza, vzn, vzm, vpn, vpm, desc, NAME##_##S); }
-DEF_IMOPH(smopa, s)
-DEF_IMOPH(umopa, s)
-DEF_IMOPH(sumopa, s)
-DEF_IMOPH(usmopa, s)
+DEF_IMOPH(sme, smopa, s)
+DEF_IMOPH(sme, umopa, s)
+DEF_IMOPH(sme, sumopa, s)
+DEF_IMOPH(sme, usmopa, s)
-DEF_IMOPH(smopa, d)
-DEF_IMOPH(umopa, d)
-DEF_IMOPH(sumopa, d)
-DEF_IMOPH(usmopa, d)
+DEF_IMOPH(sme, smopa, d)
+DEF_IMOPH(sme, umopa, d)
+DEF_IMOPH(sme, sumopa, d)
+DEF_IMOPH(sme, usmopa, d)
+
+static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg)
+{
+ uint32_t sum = ctpop32(~(n ^ m));
+ if (neg) {
+ sum = -sum;
+ }
+ if (!(p & 1)) {
+ sum = 0;
+ }
+ return a + sum;
+}
+
+DEF_IMOPH(sme2, bmopa, s)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 7b275dd2b8..c2615f06ae 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -539,3 +539,5 @@ TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_smopa_
TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d)
TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d)
TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d)
+
+TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 37bd0c6198..de8d04cb87 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -165,3 +165,5 @@ SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64
SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64
USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64
UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64
+
+BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 18/97] target/arm: Implement SME2 SMOPS, UMOPS (2-way)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (16 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 17/97] target/arm: Implement SME2 BMOPA Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 19/97] target/arm: Introduce gen_gvec_sve2_sqdmulh Richard Henderson
` (78 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 4 ++++
target/arm/tcg/sme_helper.c | 37 +++++++++++++++++++++++++---------
target/arm/tcg/translate-sme.c | 2 ++
target/arm/tcg/sme.decode | 2 ++
4 files changed, 35 insertions(+), 10 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 17d1a7c102..ecd06f2cd1 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -156,3 +156,7 @@ DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme2_smopa2_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sme2_umopa2_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 6122a5b5d9..8ce50653b4 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1261,7 +1261,7 @@ static inline void do_imopa_d(uint64_t *za, uint64_t *zn, uint64_t *zm,
}
}
-#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \
+#define DEF_IMOP_8x4_32(NAME, NTYPE, MTYPE) \
static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \
{ \
uint32_t sum = 0; \
@@ -1274,7 +1274,7 @@ static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \
return neg ? a - sum : a + sum; \
}
-#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \
+#define DEF_IMOP_16x4_64(NAME, NTYPE, MTYPE) \
static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \
{ \
uint64_t sum = 0; \
@@ -1287,15 +1287,15 @@ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \
return neg ? a - sum : a + sum; \
}
-DEF_IMOP_32(smopa_s, int8_t, int8_t)
-DEF_IMOP_32(umopa_s, uint8_t, uint8_t)
-DEF_IMOP_32(sumopa_s, int8_t, uint8_t)
-DEF_IMOP_32(usmopa_s, uint8_t, int8_t)
+DEF_IMOP_8x4_32(smopa_s, int8_t, int8_t)
+DEF_IMOP_8x4_32(umopa_s, uint8_t, uint8_t)
+DEF_IMOP_8x4_32(sumopa_s, int8_t, uint8_t)
+DEF_IMOP_8x4_32(usmopa_s, uint8_t, int8_t)
-DEF_IMOP_64(smopa_d, int16_t, int16_t)
-DEF_IMOP_64(umopa_d, uint16_t, uint16_t)
-DEF_IMOP_64(sumopa_d, int16_t, uint16_t)
-DEF_IMOP_64(usmopa_d, uint16_t, int16_t)
+DEF_IMOP_16x4_64(smopa_d, int16_t, int16_t)
+DEF_IMOP_16x4_64(umopa_d, uint16_t, uint16_t)
+DEF_IMOP_16x4_64(sumopa_d, int16_t, uint16_t)
+DEF_IMOP_16x4_64(usmopa_d, uint16_t, int16_t)
#define DEF_IMOPH(P, NAME, S) \
void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm, \
@@ -1325,3 +1325,20 @@ static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg)
}
DEF_IMOPH(sme2, bmopa, s)
+
+#define DEF_IMOP_16x2_32(NAME, NTYPE, MTYPE) \
+static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \
+{ \
+ uint32_t sum = 0; \
+ /* Apply P to N as a mask, making the inactive elements 0. */ \
+ n &= expand_pred_h(p); \
+ sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \
+ sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \
+ return neg ? a - sum : a + sum; \
+}
+
+DEF_IMOP_16x2_32(smopa2_s, int16_t, int16_t)
+DEF_IMOP_16x2_32(umopa2_s, uint16_t, uint16_t)
+
+DEF_IMOPH(sme2, smopa2, s)
+DEF_IMOPH(sme2, umopa2, s)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index c2615f06ae..0a863a50bf 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -541,3 +541,5 @@ TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumop
TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d)
TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s)
+TRANS_FEAT(SMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_smopa2_s)
+TRANS_FEAT(UMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_umopa2_s)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index de8d04cb87..36f369d02a 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -167,3 +167,5 @@ USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64
UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64
BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32
+SMOPA2_s 1010000 0 10 0 ..... ... ... ..... . 10 .. @op_32
+UMOPA2_s 1010000 1 10 0 ..... ... ... ..... . 10 .. @op_32
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 19/97] target/arm: Introduce gen_gvec_sve2_sqdmulh
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (17 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 18/97] target/arm: Implement SME2 SMOPS, UMOPS (2-way) Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 20/97] target/arm: Implement SME2 Multiple and Single SVE Destructive Richard Henderson
` (77 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
To be used by both SVE2 and SME2.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-a64.h | 4 ++++
target/arm/tcg/gengvec64.c | 11 +++++++++++
target/arm/tcg/translate-sve.c | 8 +-------
3 files changed, 16 insertions(+), 7 deletions(-)
diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h
index 8a9f4b2053..993dde61a4 100644
--- a/target/arm/tcg/translate-a64.h
+++ b/target/arm/tcg/translate-a64.h
@@ -225,6 +225,10 @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs,
uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t opr_sz, uint32_t max_sz);
+void gen_gvec_sve2_sqdmulh(unsigned vece, uint32_t rd_ofs,
+ uint32_t rn_ofs, uint32_t rm_ofs,
+ uint32_t opr_sz, uint32_t max_sz);
+
void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs,
int len, int rn, int imm, MemOp align);
void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs,
diff --git a/target/arm/tcg/gengvec64.c b/target/arm/tcg/gengvec64.c
index 2617cde0a5..2429cab1b8 100644
--- a/target/arm/tcg/gengvec64.c
+++ b/target/arm/tcg/gengvec64.c
@@ -369,3 +369,14 @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs,
tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
}
+
+void gen_gvec_sve2_sqdmulh(unsigned vece, uint32_t rd_ofs,
+ uint32_t rn_ofs, uint32_t rm_ofs,
+ uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3 * const fns[4] = {
+ gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h,
+ gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d,
+ };
+ tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]);
+}
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index d2cd298b5b..7e304245c6 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -5948,6 +5948,7 @@ TRANS_FEAT(MOVPRFX_z, aa64_sve, do_movz_zpz, a->rd, a->rn, a->pg, a->esz, false)
*/
TRANS_FEAT(MUL_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, tcg_gen_gvec_mul, a)
+TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_sve2_sqdmulh, a)
static gen_helper_gvec_3 * const smulh_zzz_fns[4] = {
gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h,
@@ -5966,13 +5967,6 @@ TRANS_FEAT(UMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz,
TRANS_FEAT(PMUL_zzz, aa64_sve2, gen_gvec_ool_arg_zzz,
gen_helper_gvec_pmul_b, a, 0)
-static gen_helper_gvec_3 * const sqdmulh_zzz_fns[4] = {
- gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h,
- gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d,
-};
-TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz,
- sqdmulh_zzz_fns[a->esz], a, 0)
-
static gen_helper_gvec_3 * const sqrdmulh_zzz_fns[4] = {
gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h,
gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d,
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 20/97] target/arm: Implement SME2 Multiple and Single SVE Destructive
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (18 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 19/97] target/arm: Introduce gen_gvec_sve2_sqdmulh Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 21/97] target/arm: Implement SME2 Multiple Vectors " Richard Henderson
` (76 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 13 ++++
target/arm/tcg/helper.h | 8 ++
target/arm/tcg/vec_internal.h | 4 +
target/arm/tcg/helper-a64.c | 2 +
target/arm/tcg/neon_helper.c | 30 ++++++++
target/arm/tcg/translate-sme.c | 137 +++++++++++++++++++++++++++++++++
target/arm/tcg/vec_helper.c | 7 ++
target/arm/tcg/sme.decode | 40 ++++++++++
8 files changed, 241 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index ecd06f2cd1..cdd7058aed 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -160,3 +160,16 @@ DEF_HELPER_FLAGS_6(sme2_smopa2_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sme2_umopa2_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(gvec_fmax_b16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fmin_b16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_ah_fmax_b16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_ah_fmin_b16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fmaxnum_b16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fminnum_b16, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index 80db7c2c37..8c4705fc53 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -353,6 +353,14 @@ DEF_HELPER_FLAGS_4(gvec_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(gvec_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_srshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_srshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_2(neon_add_u8, i32, i32, i32)
DEF_HELPER_2(neon_add_u16, i32, i32, i32)
DEF_HELPER_2(neon_sub_u8, i32, i32, i32)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index c02f9c37f8..64a7249d01 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -302,4 +302,8 @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah)
return fpcr_ah && float64_is_any_nan(a) ? a : float64_chs(a);
}
+/* Not actually called directly as a helper, but uses similar machinery. */
+bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst);
+bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
+
#endif /* TARGET_ARM_VEC_INTERNAL_H */
diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c
index 4f618ae390..c66d521278 100644
--- a/target/arm/tcg/helper-a64.c
+++ b/target/arm/tcg/helper-a64.c
@@ -402,6 +402,8 @@ AH_MINMAX_HELPER(vfp_ah_mind, float64, float64, min)
AH_MINMAX_HELPER(vfp_ah_maxh, dh_ctype_f16, float16, max)
AH_MINMAX_HELPER(vfp_ah_maxs, float32, float32, max)
AH_MINMAX_HELPER(vfp_ah_maxd, float64, float64, max)
+AH_MINMAX_HELPER(sme2_ah_fmax_b16, bfloat16, bfloat16, max)
+AH_MINMAX_HELPER(sme2_ah_fmin_b16, bfloat16, bfloat16, min)
/* 64-bit versions of the CRC helpers. Note that although the operation
* (and the prototypes of crc32c() and crc32() mean that only the bottom
diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c
index 2cc8241f1e..8d288f3a70 100644
--- a/target/arm/tcg/neon_helper.c
+++ b/target/arm/tcg/neon_helper.c
@@ -228,16 +228,31 @@ NEON_VOP(rshl_s16, neon_s16, 2)
NEON_GVEC_VOP2(gvec_srshl_h, int16_t)
#undef NEON_FN
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_sqrshl_bhs(src1, src2, 16, true, NULL))
+NEON_GVEC_VOP2(sme2_srshl_h, int16_t)
+#undef NEON_FN
+
#define NEON_FN(dest, src1, src2) \
(dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, NULL))
NEON_GVEC_VOP2(gvec_srshl_s, int32_t)
#undef NEON_FN
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_sqrshl_bhs(src1, src2, 32, true, NULL))
+NEON_GVEC_VOP2(sme2_srshl_s, int32_t)
+#undef NEON_FN
+
#define NEON_FN(dest, src1, src2) \
(dest = do_sqrshl_d(src1, (int8_t)src2, true, NULL))
NEON_GVEC_VOP2(gvec_srshl_d, int64_t)
#undef NEON_FN
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_sqrshl_d(src1, src2, true, NULL))
+NEON_GVEC_VOP2(sme2_srshl_d, int64_t)
+#undef NEON_FN
+
uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift)
{
return do_sqrshl_bhs(val, (int8_t)shift, 32, true, NULL);
@@ -260,16 +275,31 @@ NEON_VOP(rshl_u16, neon_u16, 2)
NEON_GVEC_VOP2(gvec_urshl_h, uint16_t)
#undef NEON_FN
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_uqrshl_bhs(src1, (int16_t)src2, 16, true, NULL))
+NEON_GVEC_VOP2(sme2_urshl_h, uint16_t)
+#undef NEON_FN
+
#define NEON_FN(dest, src1, src2) \
(dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, NULL))
NEON_GVEC_VOP2(gvec_urshl_s, int32_t)
#undef NEON_FN
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_uqrshl_bhs(src1, src2, 32, true, NULL))
+NEON_GVEC_VOP2(sme2_urshl_s, int32_t)
+#undef NEON_FN
+
#define NEON_FN(dest, src1, src2) \
(dest = do_uqrshl_d(src1, (int8_t)src2, true, NULL))
NEON_GVEC_VOP2(gvec_urshl_d, int64_t)
#undef NEON_FN
+#define NEON_FN(dest, src1, src2) \
+ (dest = do_uqrshl_d(src1, src2, true, NULL))
+NEON_GVEC_VOP2(sme2_urshl_d, int64_t)
+#undef NEON_FN
+
uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift)
{
return do_uqrshl_bhs(val, (int8_t)shift, 32, true, NULL);
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 0a863a50bf..954da18ff0 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -543,3 +543,140 @@ TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmop
TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s)
TRANS_FEAT(SMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_smopa2_s)
TRANS_FEAT(UMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_umopa2_s)
+
+static bool do_z2z_n1(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn)
+{
+ int esz, dn, vsz, mofs, n;
+ bool overlap = false;
+
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+
+ esz = a->esz;
+ n = a->n;
+ dn = a->zdn;
+ mofs = vec_full_reg_offset(s, a->zm);
+ vsz = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; i++) {
+ int dofs = vec_full_reg_offset(s, dn + i);
+ if (dofs == mofs) {
+ overlap = true;
+ } else {
+ fn(esz, dofs, dofs, mofs, vsz, vsz);
+ }
+ }
+ if (overlap) {
+ fn(esz, mofs, mofs, mofs, vsz, vsz);
+ }
+ return true;
+}
+
+static void gen_sme2_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3 * const fns[] = {
+ gen_helper_gvec_srshl_b, gen_helper_sme2_srshl_h,
+ gen_helper_sme2_srshl_s, gen_helper_sme2_srshl_d,
+ };
+ tcg_debug_assert(vece <= MO_64);
+ tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]);
+}
+
+static void gen_sme2_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
+ uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz)
+{
+ static gen_helper_gvec_3 * const fns[] = {
+ gen_helper_gvec_urshl_b, gen_helper_sme2_urshl_h,
+ gen_helper_sme2_urshl_s, gen_helper_sme2_urshl_d,
+ };
+ tcg_debug_assert(vece <= MO_64);
+ tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]);
+}
+
+TRANS_FEAT(ADD_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_add)
+TRANS_FEAT(SMAX_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_smax)
+TRANS_FEAT(SMIN_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_smin)
+TRANS_FEAT(UMAX_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_umax)
+TRANS_FEAT(UMIN_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_umin)
+TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl)
+TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl)
+TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh)
+
+static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
+ gen_helper_gvec_3_ptr * const fns[4])
+{
+ int esz = a->esz, n, dn, vsz, mofs;
+ bool overlap = false;
+ gen_helper_gvec_3_ptr *fn;
+ TCGv_ptr fpst;
+
+ /* These insns use MO_8 to encode BFloat16. */
+ if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) {
+ return false;
+ }
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+
+ fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+ fn = fns[esz];
+ n = a->n;
+ dn = a->zdn;
+ mofs = vec_full_reg_offset(s, a->zm);
+ vsz = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; i++) {
+ int dofs = vec_full_reg_offset(s, dn + i);
+ if (dofs == mofs) {
+ overlap = true;
+ } else {
+ tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn);
+ }
+ }
+ if (overlap) {
+ tcg_gen_gvec_3_ptr(mofs, mofs, mofs, fpst, vsz, vsz, 0, fn);
+ }
+ return true;
+}
+
+static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
+ { gen_helper_gvec_fmax_b16,
+ gen_helper_gvec_fmax_h,
+ gen_helper_gvec_fmax_s,
+ gen_helper_gvec_fmax_d },
+ { gen_helper_gvec_ah_fmax_b16,
+ gen_helper_gvec_ah_fmax_h,
+ gen_helper_gvec_ah_fmax_s,
+ gen_helper_gvec_ah_fmax_d },
+};
+TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah])
+
+static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
+ { gen_helper_gvec_fmin_b16,
+ gen_helper_gvec_fmin_h,
+ gen_helper_gvec_fmin_s,
+ gen_helper_gvec_fmin_d },
+ { gen_helper_gvec_ah_fmin_b16,
+ gen_helper_gvec_ah_fmin_h,
+ gen_helper_gvec_ah_fmin_s,
+ gen_helper_gvec_ah_fmin_d },
+};
+TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah])
+
+static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
+ gen_helper_gvec_fmaxnum_b16,
+ gen_helper_gvec_fmaxnum_h,
+ gen_helper_gvec_fmaxnum_s,
+ gen_helper_gvec_fmaxnum_d,
+};
+TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm)
+
+static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
+ gen_helper_gvec_fminnum_b16,
+ gen_helper_gvec_fminnum_h,
+ gen_helper_gvec_fminnum_s,
+ gen_helper_gvec_fminnum_d,
+};
+TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 21c6175d2e..40ce0cbc8b 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -1515,6 +1515,13 @@ DO_3OP(gvec_ah_fmin_h, helper_vfp_ah_minh, float16)
DO_3OP(gvec_ah_fmin_s, helper_vfp_ah_mins, float32)
DO_3OP(gvec_ah_fmin_d, helper_vfp_ah_mind, float64)
+DO_3OP(gvec_fmax_b16, bfloat16_max, bfloat16)
+DO_3OP(gvec_fmin_b16, bfloat16_min, bfloat16)
+DO_3OP(gvec_fmaxnum_b16, bfloat16_maxnum, bfloat16)
+DO_3OP(gvec_fminnum_b16, bfloat16_minnum, bfloat16)
+DO_3OP(gvec_ah_fmax_b16, helper_sme2_ah_fmax_b16, bfloat16)
+DO_3OP(gvec_ah_fmin_b16, helper_sme2_ah_fmin_b16, bfloat16)
+
#endif
#undef DO_3OP
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 36f369d02a..005f87777b 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -169,3 +169,43 @@ UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64
BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32
SMOPA2_s 1010000 0 10 0 ..... ... ... ..... . 10 .. @op_32
UMOPA2_s 1010000 1 10 0 ..... ... ... ..... . 10 .. @op_32
+
+### SME2 Multi-vector Multiple and Single SVE Destructive
+
+%zd_ax2 1:4 !function=times_2
+%zd_ax4 2:3 !function=times_4
+
+&z2z_en zdn zm esz n
+@z2z_2x1 ....... . esz:2 .. zm:4 ....0. ..... .... . \
+ &z2z_en n=2 zdn=%zd_ax2
+@z2z_4x1 ....... . esz:2 .. zm:4 ....1. ..... ...0 . \
+ &z2z_en n=4 zdn=%zd_ax4
+
+SMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 0 @z2z_2x1
+SMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 0 @z2z_4x1
+UMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 1 @z2z_2x1
+UMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 1 @z2z_4x1
+SMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 0 @z2z_2x1
+SMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 0 @z2z_4x1
+UMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 1 @z2z_2x1
+UMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 1 @z2z_4x1
+
+FMAX_n1 1100000 1 .. 10 .... 1010.0 01000 .... 0 @z2z_2x1
+FMAX_n1 1100000 1 .. 10 .... 1010.0 01000 .... 0 @z2z_4x1
+FMIN_n1 1100000 1 .. 10 .... 1010.0 01000 .... 1 @z2z_2x1
+FMIN_n1 1100000 1 .. 10 .... 1010.0 01000 .... 1 @z2z_4x1
+FMAXNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 0 @z2z_2x1
+FMAXNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 0 @z2z_4x1
+FMINNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 1 @z2z_2x1
+FMINNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 1 @z2z_4x1
+
+SRSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 0 @z2z_2x1
+SRSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 0 @z2z_4x1
+URSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 1 @z2z_2x1
+URSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 1 @z2z_4x1
+
+ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_2x1
+ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_4x1
+
+SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_2x1
+SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_4x1
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 21/97] target/arm: Implement SME2 Multiple Vectors SVE Destructive
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (19 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 20/97] target/arm: Implement SME2 Multiple and Single SVE Destructive Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 22/97] target/arm: Implement SME2 ADD/SUB (array results, multiple and single vector) Richard Henderson
` (75 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 65 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 36 +++++++++++++++++++
2 files changed, 101 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 954da18ff0..0a6a10b63d 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -604,6 +604,37 @@ TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl)
TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl)
TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh)
+static bool do_z2z_nn(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn)
+{
+ int esz, dn, dm, vsz, n;
+
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+
+ esz = a->esz;
+ n = a->n;
+ dn = a->zdn;
+ dm = a->zm;
+ vsz = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; i++) {
+ int dofs = vec_full_reg_offset(s, dn + i);
+ int mofs = vec_full_reg_offset(s, dm + i);
+
+ fn(esz, dofs, dofs, mofs, vsz, vsz);
+ }
+ return true;
+}
+
+TRANS_FEAT(SMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smax)
+TRANS_FEAT(SMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smin)
+TRANS_FEAT(UMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umax)
+TRANS_FEAT(UMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umin)
+TRANS_FEAT(SRSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_srshl)
+TRANS_FEAT(URSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_urshl)
+TRANS_FEAT(SQDMULH_nn, aa64_sme2, do_z2z_nn, a, gen_gvec_sve2_sqdmulh)
+
static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
gen_helper_gvec_3_ptr * const fns[4])
{
@@ -641,6 +672,36 @@ static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a,
return true;
}
+static bool do_z2z_nn_fpst(DisasContext *s, arg_z2z_en *a,
+ gen_helper_gvec_3_ptr * const fns[4])
+{
+ int esz = a->esz, n, dn, dm, vsz;
+ gen_helper_gvec_3_ptr *fn;
+ TCGv_ptr fpst;
+
+ if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) {
+ return false;
+ }
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+
+ fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+ fn = fns[esz];
+ n = a->n;
+ dn = a->zdn;
+ dm = a->zm;
+ vsz = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; i++) {
+ int dofs = vec_full_reg_offset(s, dn + i);
+ int mofs = vec_full_reg_offset(s, dm + i);
+
+ tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn);
+ }
+ return true;
+}
+
static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
{ gen_helper_gvec_fmax_b16,
gen_helper_gvec_fmax_h,
@@ -652,6 +713,7 @@ static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = {
gen_helper_gvec_ah_fmax_d },
};
TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah])
+TRANS_FEAT(FMAX_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmax[s->fpcr_ah])
static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
{ gen_helper_gvec_fmin_b16,
@@ -664,6 +726,7 @@ static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = {
gen_helper_gvec_ah_fmin_d },
};
TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah])
+TRANS_FEAT(FMIN_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmin[s->fpcr_ah])
static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
gen_helper_gvec_fmaxnum_b16,
@@ -672,6 +735,7 @@ static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = {
gen_helper_gvec_fmaxnum_d,
};
TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm)
+TRANS_FEAT(FMAXNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmaxnm)
static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
gen_helper_gvec_fminnum_b16,
@@ -680,3 +744,4 @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
gen_helper_gvec_fminnum_d,
};
TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
+TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 005f87777b..470592f4c0 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -209,3 +209,39 @@ ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_4x1
SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_2x1
SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_4x1
+
+### SME2 Multi-vector Multiple Vectors SVE Destructive
+
+%zm_ax2 17:4 !function=times_2
+%zm_ax4 18:3 !function=times_4
+
+@z2z_2x2 ....... . esz:2 . ....0 ....0. ..... .... . \
+ &z2z_en n=2 zdn=%zd_ax2 zm=%zm_ax2
+@z2z_4x4 ....... . esz:2 . ...00 ....1. ..... ...0 . \
+ &z2z_en n=4 zdn=%zd_ax4 zm=%zm_ax4
+
+SMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 0 @z2z_2x2
+SMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 0 @z2z_4x4
+UMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 1 @z2z_2x2
+UMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 1 @z2z_4x4
+SMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 0 @z2z_2x2
+SMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 0 @z2z_4x4
+UMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 1 @z2z_2x2
+UMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 1 @z2z_4x4
+
+FMAX_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 0 @z2z_2x2
+FMAX_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 0 @z2z_4x4
+FMIN_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 1 @z2z_2x2
+FMIN_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 1 @z2z_4x4
+FMAXNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 0 @z2z_2x2
+FMAXNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 0 @z2z_4x4
+FMINNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 1 @z2z_2x2
+FMINNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 1 @z2z_4x4
+
+SRSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 0 @z2z_2x2
+SRSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 0 @z2z_4x4
+URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_2x2
+URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_4x4
+
+SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_2x2
+SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_4x4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 22/97] target/arm: Implement SME2 ADD/SUB (array results, multiple and single vector)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (20 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 21/97] target/arm: Implement SME2 Multiple Vectors " Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 23/97] target/arm: Implement SME2 ADD/SUB (array results, multiple vectors) Richard Henderson
` (74 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate.h | 2 ++
target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 15 +++++++++++++++
3 files changed, 47 insertions(+)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 1b29b958f3..acfc00be78 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -642,6 +642,8 @@ typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
uint32_t, uint32_t, uint32_t);
typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
uint32_t, uint32_t, uint32_t);
+typedef void GVecGen3FnVar(unsigned, TCGv_ptr, uint32_t, TCGv_ptr, uint32_t,
+ TCGv_ptr, uint32_t, uint32_t, uint32_t);
/* Function prototype for gen_ functions for calling Neon helpers */
typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32);
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 0a6a10b63d..4bb880d9ef 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -745,3 +745,33 @@ static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = {
};
TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm)
TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm)
+
+/* Add/Sub vector Z[m] to each Z[n*N] with result in ZA[d*N]. */
+static bool do_azz_n1(DisasContext *s, arg_azz_n *a, int esz,
+ GVecGen3FnVar *fn)
+{
+ TCGv_ptr t_za;
+ int svl, n, o_zm;
+
+ if (!sme_smza_enabled_check(s)) {
+ return true;
+ }
+
+ n = a->n;
+ t_za = get_zarray(s, a->rv, a->off, n, 0);
+ o_zm = vec_full_reg_offset(s, a->zm);
+ svl = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; ++i) {
+ int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+ int o_zn = vec_full_reg_offset(s, (a->zn + i) % 32);
+
+ fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl);
+ }
+ return true;
+}
+
+TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var)
+TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 470592f4c0..8b81c0a0ce 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -245,3 +245,18 @@ URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_4x4
SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_2x2
SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_4x4
+
+### SME2 Multi-vector Multiple and Single Array Vectors
+
+&azz_n n off rv zn zm
+@azz_nx1_o3 ........ .... zm:4 ...... zn:5 .. off:3 &azz_n rv=%mova_rv
+
+ADD_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=2
+ADD_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=4
+ADD_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=2
+ADD_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=4
+
+SUB_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2
+SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4
+SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2
+SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 23/97] target/arm: Implement SME2 ADD/SUB (array results, multiple vectors)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (21 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 22/97] target/arm: Implement SME2 ADD/SUB (array results, multiple and single vector) Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 24/97] target/arm: Pass ZA to helper_sve2_fmlal_zz[zx]w_s Richard Henderson
` (73 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 30 ++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 20 ++++++++++++++++++++
2 files changed, 50 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 4bb880d9ef..aabdb96675 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -775,3 +775,33 @@ TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var)
TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var)
TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var)
TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var)
+
+/* Add/Sub each vector Z[m*N] to each Z[n*N] with result in ZA[d*N]. */
+static bool do_azz_nn(DisasContext *s, arg_azz_n *a, int esz,
+ GVecGen3FnVar *fn)
+{
+ TCGv_ptr t_za;
+ int svl, n;
+
+ if (!sme_smza_enabled_check(s)) {
+ return true;
+ }
+
+ n = a->n;
+ t_za = get_zarray(s, a->rv, a->off, n, 1);
+ svl = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; ++i) {
+ int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+ int o_zn = vec_full_reg_offset(s, a->zn + i);
+ int o_zm = vec_full_reg_offset(s, a->zm + i);
+
+ fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl);
+ }
+ return true;
+}
+
+TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var)
+TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 8b81c0a0ce..a6dee08661 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -260,3 +260,23 @@ SUB_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2
SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4
SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2
SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4
+
+### SME2 Multi-vector Multiple Array Vectors
+
+%zn_ax2 6:4 !function=times_2
+%zn_ax4 7:3 !function=times_4
+
+@azz_2x2_o3 ........ ... ..... . .. ... ..... .. off:3 \
+ &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2
+@azz_4x4_o3 ........ ... ..... . .. ... ..... .. off:3 \
+ &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4
+
+ADD_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 10 ... @azz_2x2_o3
+ADD_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 10 ... @azz_4x4_o3
+ADD_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 10 ... @azz_2x2_o3
+ADD_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 10 ... @azz_4x4_o3
+
+SUB_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3
+SUB_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3
+SUB_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3
+SUB_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 24/97] target/arm: Pass ZA to helper_sve2_fmlal_zz[zx]w_s
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (22 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 23/97] target/arm: Implement SME2 ADD/SUB (array results, multiple vectors) Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:32 ` [PATCH v3 25/97] target/arm: Add helper_gvec{_ah}_bfmlsl{_nx} Richard Henderson
` (72 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Indicate whether to use FPST_FPCR or FPST_ZA via bit 2 of
simd_data(desc). For SVE, this bit remains zero.
For do_FMLAL_zzzw, this requires no change.
For do_FMLAL_zzxw, move the index up one bit.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 2 +-
target/arm/tcg/vec_helper.c | 8 +++++---
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 7e304245c6..b85bd885f9 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7214,7 +7214,7 @@ static bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel)
{
return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzxw_s,
a->rd, a->rn, a->rm, a->ra,
- (a->index << 2) | (sel << 1) | sub, tcg_env);
+ (a->index << 3) | (sel << 1) | sub, tcg_env);
}
TRANS_FEAT(FMLALB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, false)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 40ce0cbc8b..f3de26ca54 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -2191,7 +2191,8 @@ void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va,
intptr_t i, oprsz = simd_oprsz(desc);
bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
- float_status *status = &env->vfp.fp_status[FPST_A64];
+ bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+ float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
bool fz16 = env->vfp.fpcr & FPCR_FZ16;
int negx = 0, negf = 0;
@@ -2274,8 +2275,9 @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va,
intptr_t i, j, oprsz = simd_oprsz(desc);
bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1);
intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16);
- intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16);
- float_status *status = &env->vfp.fp_status[FPST_A64];
+ bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 3, 3) * sizeof(float16);
+ float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
bool fz16 = env->vfp.fpcr & FPCR_FZ16;
int negx = 0, negf = 0;
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 25/97] target/arm: Add helper_gvec{_ah}_bfmlsl{_nx}
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (23 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 24/97] target/arm: Pass ZA to helper_sve2_fmlal_zz[zx]w_s Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-03 9:34 ` Peter Maydell
2025-07-02 12:32 ` [PATCH v3 26/97] target/arm: Implement SME2 FMLAL, BFMLAL Richard Henderson
` (71 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 8 +++++
target/arm/tcg/vec_helper.c | 58 ++++++++++++++++++++++++++++---------
2 files changed, 53 insertions(+), 13 deletions(-)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index 8c4705fc53..a05b63380c 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -1095,8 +1095,16 @@ DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmlsl, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmlsl_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index f3de26ca54..3ebee97e68 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3186,44 +3186,76 @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va,
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
- float_status *stat, uint32_t desc)
+static void do_bfmlal(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a,
+ float_status *stat, uint32_t desc, int negx, int negf)
{
intptr_t i, opr_sz = simd_oprsz(desc);
- intptr_t sel = simd_data(desc);
- float32 *d = vd, *a = va;
- bfloat16 *n = vn, *m = vm;
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1);
for (i = 0; i < opr_sz / 4; ++i) {
- float32 nn = n[H2(i * 2 + sel)] << 16;
+ float32 nn = (negx ^ n[H2(i * 2 + sel)]) << 16;
float32 mm = m[H2(i * 2 + sel)] << 16;
- d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat);
+ d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], negf, stat);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm,
- void *va, float_status *stat, uint32_t desc)
+void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va,
+ float_status *stat, uint32_t desc)
+{
+ do_bfmlal(vd, vn, vm, va, stat, desc, 0, 0);
+}
+
+void HELPER(gvec_bfmlsl)(void *vd, void *vn, void *vm, void *va,
+ float_status *stat, uint32_t desc)
+{
+ do_bfmlal(vd, vn, vm, va, stat, desc, 0x8000, 0);
+}
+
+void HELPER(gvec_ah_bfmlsl)(void *vd, void *vn, void *vm, void *va,
+ float_status *stat, uint32_t desc)
+{
+ do_bfmlal(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product);
+}
+
+static void do_bfmlal_idx(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a,
+ float_status *stat, uint32_t desc, int negx, int negf)
{
intptr_t i, j, opr_sz = simd_oprsz(desc);
intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1);
intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 1, 3);
intptr_t elements = opr_sz / 4;
intptr_t eltspersegment = MIN(16 / 4, elements);
- float32 *d = vd, *a = va;
- bfloat16 *n = vn, *m = vm;
for (i = 0; i < elements; i += eltspersegment) {
float32 m_idx = m[H2(2 * i + index)] << 16;
for (j = i; j < i + eltspersegment; j++) {
- float32 n_j = n[H2(2 * j + sel)] << 16;
- d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], 0, stat);
+ float32 n_j = (negx ^ n[H2(2 * j + sel)]) << 16;
+ d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], negf, stat);
}
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
+void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, void *va,
+ float_status *stat, uint32_t desc)
+{
+ do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, 0);
+}
+
+void HELPER(gvec_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va,
+ float_status *stat, uint32_t desc)
+{
+ do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0x8000, 0);
+}
+
+void HELPER(gvec_ah_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va,
+ float_status *stat, uint32_t desc)
+{
+ do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product);
+}
+
#define DO_CLAMP(NAME, TYPE) \
void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \
{ \
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 26/97] target/arm: Implement SME2 FMLAL, BFMLAL
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (24 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 25/97] target/arm: Add helper_gvec{_ah}_bfmlsl{_nx} Richard Henderson
@ 2025-07-02 12:32 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 27/97] target/arm: Implement SME2 FDOT Richard Henderson
` (70 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:32 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 98 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 71 ++++++++++++++++++++++++
2 files changed, 169 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index aabdb96675..9ec02d960d 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -805,3 +805,101 @@ TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var)
TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var)
TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var)
TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var)
+
+/*
+ * Expand array multi-vector single (n1), array multi-vector (nn),
+ * and array multi-vector indexed (nx), for floating-point accumulate.
+ * multi: true for nn, false for n1.
+ * fpst: >= 0 to set ptr argument for FPST_*, < 0 for ENV.
+ * data: stuff for simd_data, including any index.
+ */
+#define FPST_ENV -1
+
+static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel,
+ int rv, int off, int zn, int zm,
+ int data, int shsel, bool multi, int fpst,
+ gen_helper_gvec_4_ptr *fn)
+{
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int vstride = svl / nreg;
+ TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+ TCGv_ptr t, ptr;
+
+ if (fpst >= 0) {
+ ptr = fpstatus_ptr(fpst);
+ } else {
+ ptr = tcg_env;
+ }
+ t = tcg_temp_new_ptr();
+
+ for (int r = 0; r < nreg; ++r) {
+ TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+ TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+ for (int i = 0; i < nsel; ++i) {
+ int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+ int desc = simd_desc(svl, svl, data | (i << shsel));
+
+ tcg_gen_addi_ptr(t, t_za, o_za);
+ fn(t, t_zn, t_zm, t, ptr, tcg_constant_i32(desc));
+ }
+
+ /*
+ * For multiple-and-single vectors, Zn may wrap.
+ * For multiple vectors, both Zn and Zm are aligned.
+ */
+ zn = (zn + 1) % 32;
+ zm += multi;
+ }
+ }
+ return true;
+}
+
+static bool do_fmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi)
+{
+ return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+ (1 << 2) | sub, 1,
+ multi, FPST_ENV, gen_helper_sve2_fmlal_zzzw_s);
+}
+
+TRANS_FEAT(FMLAL_n1, aa64_sme2, do_fmlal, a, false, false)
+TRANS_FEAT(FMLSL_n1, aa64_sme2, do_fmlal, a, true, false)
+TRANS_FEAT(FMLAL_nn, aa64_sme2, do_fmlal, a, false, true)
+TRANS_FEAT(FMLSL_nn, aa64_sme2, do_fmlal, a, true, true)
+
+static bool do_fmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
+{
+ return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+ (a->idx << 3) | (1 << 2) | sub, 1,
+ false, FPST_ENV, gen_helper_sve2_fmlal_zzxw_s);
+}
+
+TRANS_FEAT(FMLAL_nx, aa64_sme2, do_fmlal_nx, a, false)
+TRANS_FEAT(FMLSL_nx, aa64_sme2, do_fmlal_nx, a, true)
+
+static bool do_bfmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi)
+{
+ return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+ 0, 0, multi, FPST_ZA,
+ (!sub ? gen_helper_gvec_bfmlal
+ : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl
+ : gen_helper_gvec_bfmlsl));
+}
+
+TRANS_FEAT(BFMLAL_n1, aa64_sme2, do_bfmlal, a, false, false)
+TRANS_FEAT(BFMLSL_n1, aa64_sme2, do_bfmlal, a, true, false)
+TRANS_FEAT(BFMLAL_nn, aa64_sme2, do_bfmlal, a, false, true)
+TRANS_FEAT(BFMLSL_nn, aa64_sme2, do_bfmlal, a, true, true)
+
+static bool do_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
+{
+ return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+ a->idx << 1, 0, false, FPST_ZA,
+ !sub ? gen_helper_gvec_bfmlal_idx
+ : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl_idx
+ : gen_helper_gvec_bfmlsl_idx);
+}
+
+TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false)
+TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index a6dee08661..9850c19d90 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -261,6 +261,30 @@ SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4
SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2
SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4
+%off3_x2 0:3 !function=times_2
+%off2_x2 0:2 !function=times_2
+
+@azz_nx1_o3x2 ........ ... . zm:4 . .. ... zn:5 .. ... \
+ &azz_n off=%off3_x2 rv=%mova_rv
+@azz_nx1_o2x2 ........ ... . zm:4 . .. ... zn:5 ... .. \
+ &azz_n off=%off2_x2 rv=%mova_rv
+
+FMLAL_n1 11000001 001 0 .... 0 .. 011 ..... 00 ... @azz_nx1_o3x2 n=1
+FMLAL_n1 11000001 001 0 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=2
+FMLAL_n1 11000001 001 1 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=4
+
+FMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 01 ... @azz_nx1_o3x2 n=1
+FMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=2
+FMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=4
+
+BFMLAL_n1 11000001 001 0 .... 0 .. 011 ..... 10 ... @azz_nx1_o3x2 n=1
+BFMLAL_n1 11000001 001 0 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=2
+BFMLAL_n1 11000001 001 1 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=4
+
+BFMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1
+BFMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2
+BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4
+
### SME2 Multi-vector Multiple Array Vectors
%zn_ax2 6:4 !function=times_2
@@ -280,3 +304,50 @@ SUB_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3
SUB_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3
SUB_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3
SUB_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3
+
+@azz_2x2_o2x2 ........ ... ..... . .. ... ..... ... .. \
+ &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off2_x2
+@azz_4x4_o2x2 ........ ... ..... . .. ... ..... ... .. \
+ &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off2_x2
+
+FMLAL_nn 11000001 101 ....0 0 .. 010 ....0 000 .. @azz_2x2_o2x2
+FMLAL_nn 11000001 101 ...01 0 .. 010 ...00 000 .. @azz_4x4_o2x2
+
+FMLSL_nn 11000001 101 ....0 0 .. 010 ....0 010 .. @azz_2x2_o2x2
+FMLSL_nn 11000001 101 ...01 0 .. 010 ...00 010 .. @azz_4x4_o2x2
+
+BFMLAL_nn 11000001 101 ....0 0 .. 010 ....0 100 .. @azz_2x2_o2x2
+BFMLAL_nn 11000001 101 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2
+
+BFMLSL_nn 11000001 101 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2
+BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2
+
+### SME2 Multi-vector Indexed
+
+&azx_n n off rv zn zm idx
+
+%idx3_15_10 15:1 10:2
+%idx2_10_2 10:2 2:1
+
+@azx_1x1_o3x2 ........ .... zm:4 . .. . .. zn:5 .. ... \
+ &azx_n n=1 rv=%mova_rv off=%off3_x2 idx=%idx3_15_10
+@azx_2x1_o2x2 ........ .... zm:4 . .. . .. ..... .. ... \
+ &azx_n n=2 rv=%mova_rv off=%off2_x2 zn=%zn_ax2 idx=%idx2_10_2
+@azx_4x1_o2x2 ........ .... zm:4 . .. . .. ..... .. ... \
+ &azx_n n=4 rv=%mova_rv off=%off2_x2 zn=%zn_ax4 idx=%idx2_10_2
+
+FMLAL_nx 11000001 1000 .... . .. 1 .. ..... 00 ... @azx_1x1_o3x2
+FMLAL_nx 11000001 1001 .... 0 .. 1 .. ....0 00 ... @azx_2x1_o2x2
+FMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 00 ... @azx_4x1_o2x2
+
+FMLSL_nx 11000001 1000 .... . .. 1 .. ..... 01 ... @azx_1x1_o3x2
+FMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 01 ... @azx_2x1_o2x2
+FMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 01 ... @azx_4x1_o2x2
+
+BFMLAL_nx 11000001 1000 .... . .. 1 .. ..... 10 ... @azx_1x1_o3x2
+BFMLAL_nx 11000001 1001 .... 0 .. 1 .. ....0 10 ... @azx_2x1_o2x2
+BFMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2
+
+BFMLSL_nx 11000001 1000 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2
+BFMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2
+BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 27/97] target/arm: Implement SME2 FDOT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (25 preceding siblings ...)
2025-07-02 12:32 ` [PATCH v3 26/97] target/arm: Implement SME2 FMLAL, BFMLAL Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 28/97] target/arm: Implement SME2 BFDOT Richard Henderson
` (69 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 5 ++++
target/arm/tcg/sme_helper.c | 44 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 18 ++++++++++++++
target/arm/tcg/translate-sve.c | 5 ++++
target/arm/tcg/sme.decode | 14 +++++++++++
target/arm/tcg/sve.decode | 7 ++++--
6 files changed, 91 insertions(+), 2 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index cdd7058aed..ec93ff57ff 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -173,3 +173,8 @@ DEF_HELPER_FLAGS_5(gvec_fmaxnum_b16, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fminnum_b16, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_6(sme2_fdot_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 8ce50653b4..60322be3d0 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1152,6 +1152,50 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
}
}
+void HELPER(sme2_fdot_h)(void *vd, void *vn, void *vm, void *va,
+ CPUARMState *env, uint32_t desc)
+{
+ intptr_t i, oprsz = simd_maxsz(desc);
+ bool za = extract32(desc, SIMD_DATA_SHIFT, 1);
+ float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
+ float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16];
+ float_status fpst_odd = *fpst_std;
+ float32 *d = vd, *a = va;
+ uint32_t *n = vn, *m = vm;
+
+ set_float_rounding_mode(float_round_to_odd, &fpst_odd);
+
+ for (i = 0; i < oprsz / sizeof(float32); ++i) {
+ d[H4(i)] = f16_dotadd(a[H4(i)], n[H4(i)], m[H4(i)],
+ fpst_f16, fpst_std, &fpst_odd);
+ }
+}
+
+void HELPER(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va,
+ CPUARMState *env, uint32_t desc)
+{
+ intptr_t i, j, oprsz = simd_maxsz(desc);
+ intptr_t elements = oprsz / sizeof(float32);
+ intptr_t eltspersegment = MIN(4, elements);
+ int idx = extract32(desc, SIMD_DATA_SHIFT, 2);
+ bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+ float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64];
+ float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16];
+ float_status fpst_odd = *fpst_std;
+ float32 *d = vd, *a = va;
+ uint32_t *n = vn, *m = (uint32_t *)vm + H4(idx);
+
+ set_float_rounding_mode(float_round_to_odd, &fpst_odd);
+
+ for (i = 0; i < elements; i += eltspersegment) {
+ uint32_t mm = m[i];
+ for (j = 0; j < eltspersegment; ++j) {
+ d[H4(i + j)] = f16_dotadd(a[H4(i + j)], n[H4(i + j)], mm,
+ fpst_f16, fpst_std, &fpst_odd);
+ }
+ }
+}
+
void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm,
void *vpn, void *vpm, CPUARMState *env, uint32_t desc)
{
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 9ec02d960d..761584c90b 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -903,3 +903,21 @@ static bool do_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub)
TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false)
TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true)
+
+static bool do_fdot(DisasContext *s, arg_azz_n *a, bool multi)
+{
+ return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, 1, 0,
+ multi, FPST_ENV, gen_helper_sme2_fdot_h);
+}
+
+TRANS_FEAT(FDOT_n1, aa64_sme2, do_fdot, a, false)
+TRANS_FEAT(FDOT_nn, aa64_sme2, do_fdot, a, true)
+
+static bool do_fdot_nx(DisasContext *s, arg_azx_n *a)
+{
+ return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+ a->idx | (1 << 2), 0, false, FPST_ENV,
+ gen_helper_sme2_fdot_idx_h);
+}
+
+TRANS_FEAT(FDOT_nx, aa64_sme2, do_fdot_nx, a)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index b85bd885f9..4acd22f55e 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7229,6 +7229,11 @@ TRANS_FEAT_NONSTREAMING(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
TRANS_FEAT_NONSTREAMING(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
gen_helper_gvec_ummla_b, a, 0)
+TRANS_FEAT(FDOT_zzzz, aa64_sme2_or_sve2p1, gen_gvec_env_arg_zzzz,
+ gen_helper_sme2_fdot_h, a, 0)
+TRANS_FEAT(FDOT_zzxz, aa64_sme2_or_sve2p1, gen_gvec_env_arg_zzxz,
+ gen_helper_sme2_fdot_idx_h, a)
+
TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_env_arg_zzzz,
gen_helper_gvec_bfdot, a, 0)
TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_env_arg_zzxz,
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 9850c19d90..a2b93519c4 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -285,6 +285,9 @@ BFMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1
BFMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2
BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4
+FDOT_n1 11000001 001 0 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=2
+FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4
+
### SME2 Multi-vector Multiple Array Vectors
%zn_ax2 6:4 !function=times_2
@@ -322,6 +325,9 @@ BFMLAL_nn 11000001 101 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2
BFMLSL_nn 11000001 101 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2
BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2
+FDOT_nn 11000001 101 ....0 0 .. 100 ....0 00 ... @azz_2x2_o3
+FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3
+
### SME2 Multi-vector Indexed
&azx_n n off rv zn zm idx
@@ -351,3 +357,11 @@ BFMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2
BFMLSL_nx 11000001 1000 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2
BFMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2
BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2
+
+@azx_2x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \
+ &azx_n n=2 rv=%mova_rv zn=%zn_ax2
+@azx_4x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \
+ &azx_n n=2 rv=%mova_rv zn=%zn_ax4
+
+FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3
+FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 3a99eb7299..5970ed9ac4 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1662,7 +1662,8 @@ FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2
BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2
BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2
-### SVE2 floating-point bfloat16 dot-product
+### SVE2 floating-point dot-product
+FDOT_zzzz 01100100 00 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2
BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2
### SVE2 floating-point multiply-add long (indexed)
@@ -1673,7 +1674,9 @@ FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2
BFMLALB_zzxw 01100100 11 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2
BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2
-### SVE2 floating-point bfloat16 dot-product (indexed)
+### SVE2 floating-point dot-product (indexed)
+
+FDOT_zzxz 01100100 00 1 ..... 010000 ..... ..... @rrxr_2 esz=2
BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2
### SVE broadcast predicate element
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 28/97] target/arm: Implement SME2 BFDOT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (26 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 27/97] target/arm: Implement SME2 FDOT Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 29/97] target/arm: Implement SME2 FVDOT, BFVDOT Richard Henderson
` (68 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 17 +++++++++++++++++
target/arm/tcg/sme.decode | 9 +++++++++
2 files changed, 26 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 761584c90b..965a49465e 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -921,3 +921,20 @@ static bool do_fdot_nx(DisasContext *s, arg_azx_n *a)
}
TRANS_FEAT(FDOT_nx, aa64_sme2, do_fdot_nx, a)
+
+static bool do_bfdot(DisasContext *s, arg_azz_n *a, bool multi)
+{
+ return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, 0, 0,
+ multi, FPST_ENV, gen_helper_gvec_bfdot);
+}
+
+TRANS_FEAT(BFDOT_n1, aa64_sme2, do_bfdot, a, false)
+TRANS_FEAT(BFDOT_nn, aa64_sme2, do_bfdot, a, true)
+
+static bool do_bfdot_nx(DisasContext *s, arg_azx_n *a)
+{
+ return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, a->idx, 0,
+ false, FPST_ENV, gen_helper_gvec_bfdot_idx);
+}
+
+TRANS_FEAT(BFDOT_nx, aa64_sme2, do_bfdot_nx, a)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index a2b93519c4..18e625605f 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -288,6 +288,9 @@ BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4
FDOT_n1 11000001 001 0 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=2
FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4
+BFDOT_n1 11000001 001 0 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=2
+BFDOT_n1 11000001 001 1 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=4
+
### SME2 Multi-vector Multiple Array Vectors
%zn_ax2 6:4 !function=times_2
@@ -328,6 +331,9 @@ BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2
FDOT_nn 11000001 101 ....0 0 .. 100 ....0 00 ... @azz_2x2_o3
FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3
+BFDOT_nn 11000001 101 ....0 0 .. 100 ....0 10 ... @azz_2x2_o3
+BFDOT_nn 11000001 101 ...01 0 .. 100 ...00 10 ... @azz_4x4_o3
+
### SME2 Multi-vector Indexed
&azx_n n off rv zn zm idx
@@ -365,3 +371,6 @@ BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2
FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3
FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3
+
+BFDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_i2_o3
+BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 29/97] target/arm: Implement SME2 FVDOT, BFVDOT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (27 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 28/97] target/arm: Implement SME2 BFDOT Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 30/97] target/arm: Rename helper_gvec_*dot_[bh] to *_4[bh] Richard Henderson
` (67 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 2 ++
target/arm/tcg/helper.h | 2 ++
target/arm/tcg/sme_helper.c | 30 ++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 24 +++++++++++++++++++++
target/arm/tcg/vec_helper.c | 39 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 3 +++
6 files changed, 100 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index ec93ff57ff..8f5a1b3c90 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -178,3 +178,5 @@ DEF_HELPER_FLAGS_6(sme2_fdot_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_6(sme2_fvdot_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index a05b63380c..d8d389af2b 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -1089,6 +1089,8 @@ DEF_HELPER_FLAGS_6(gvec_bfdot, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_FLAGS_6(gvec_bfdot_idx, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_6(sme2_bfvdot_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 60322be3d0..8b45865461 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1196,6 +1196,36 @@ void HELPER(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va,
}
}
+void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va,
+ CPUARMState *env, uint32_t desc)
+{
+ intptr_t i, j, oprsz = simd_maxsz(desc);
+ intptr_t elements = oprsz / sizeof(float32);
+ intptr_t eltspersegment = MIN(4, elements);
+ int idx = extract32(desc, SIMD_DATA_SHIFT, 2);
+ int sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+ float_status fpst_odd, *fpst_std, *fpst_f16;
+ float32 *d = vd, *a = va;
+ uint16_t *n0 = vn;
+ uint16_t *n1 = vn + sizeof(ARMVectorReg);
+ uint32_t *m = (uint32_t *)vm + H4(idx);
+
+ fpst_std = &env->vfp.fp_status[FPST_ZA];
+ fpst_f16 = &env->vfp.fp_status[FPST_ZA_F16];
+ fpst_odd = *fpst_std;
+ set_float_rounding_mode(float_round_to_odd, &fpst_odd);
+
+ for (i = 0; i < elements; i += eltspersegment) {
+ uint32_t mm = m[i];
+ for (j = 0; j < eltspersegment; ++j) {
+ uint32_t nn = (n0[H2(2 * (i + j) + sel)])
+ | (n1[H2(2 * (i + j) + sel)] << 16);
+ d[i + H4(j)] = f16_dotadd(a[i + H4(j)], nn, mm,
+ fpst_f16, fpst_std, &fpst_odd);
+ }
+ }
+}
+
void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm,
void *vpn, void *vpm, CPUARMState *env, uint32_t desc)
{
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 965a49465e..410a8d037c 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -938,3 +938,27 @@ static bool do_bfdot_nx(DisasContext *s, arg_azx_n *a)
}
TRANS_FEAT(BFDOT_nx, aa64_sme2, do_bfdot_nx, a)
+
+static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
+{
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int vstride = svl / 2;
+ TCGv_ptr t_za = get_zarray(s, a->rv, a->off, 2, 1);
+ TCGv_ptr t_zn = vec_full_reg_ptr(s, a->zn);
+ TCGv_ptr t_zm = vec_full_reg_ptr(s, a->zm);
+ TCGv_ptr t = tcg_temp_new_ptr();
+
+ for (int i = 0; i < 2; ++i) {
+ int o_za = i * vstride * sizeof(ARMVectorReg);
+ int desc = simd_desc(svl, svl, a->idx | (i << 2));
+
+ tcg_gen_addi_ptr(t, t_za, o_za);
+ fn(t, t_zn, t_zm, t, tcg_env, tcg_constant_i32(desc));
+ }
+ }
+ return true;
+}
+
+TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
+TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 3ebee97e68..130f040f7b 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3110,6 +3110,45 @@ void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm,
clear_tail(d, opr_sz, simd_maxsz(desc));
}
+void HELPER(sme2_bfvdot_idx)(void *vd, void *vn, void *vm,
+ void *va, CPUARMState *env, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2);
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1);
+ intptr_t elements = opr_sz / 4;
+ intptr_t eltspersegment = MIN(16 / 4, elements);
+ float32 *d = vd, *a = va;
+ uint16_t *n0 = vn;
+ uint16_t *n1 = vn + sizeof(ARMVectorReg);
+ uint32_t *m = vm;
+ float_status fpst, fpst_odd;
+
+ if (is_ebf(env, &fpst, &fpst_odd)) {
+ for (i = 0; i < elements; i += eltspersegment) {
+ uint32_t m_idx = m[i + H4(idx)];
+
+ for (j = 0; j < eltspersegment; j++) {
+ uint32_t nn = (n0[H2(2 * (i + j) + sel)])
+ | (n1[H2(2 * (i + j) + sel)] << 16);
+ d[i + H4(j)] = bfdotadd_ebf(a[i + H4(j)], nn, m_idx,
+ &fpst, &fpst_odd);
+ }
+ }
+ } else {
+ for (i = 0; i < elements; i += eltspersegment) {
+ uint32_t m_idx = m[i + H4(idx)];
+
+ for (j = 0; j < eltspersegment; j++) {
+ uint32_t nn = (n0[H2(2 * (i + j) + sel)])
+ | (n1[H2(2 * (i + j) + sel)] << 16);
+ d[i + H4(j)] = bfdotadd(a[i + H4(j)], nn, m_idx, &fpst);
+ }
+ }
+ }
+ clear_tail(d, opr_sz, simd_maxsz(desc));
+}
+
void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va,
CPUARMState *env, uint32_t desc)
{
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 18e625605f..7c057bcad2 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -374,3 +374,6 @@ FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3
BFDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_i2_o3
BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3
+
+FVDOT 11000001 0101 .... 0 .. 0 .. ....0 01 ... @azx_2x1_i2_o3
+BFVDOT 11000001 0101 .... 0 .. 0 .. ....0 11 ... @azx_2x1_i2_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 30/97] target/arm: Rename helper_gvec_*dot_[bh] to *_4[bh]
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (28 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 29/97] target/arm: Implement SME2 FVDOT, BFVDOT Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 31/97] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT Richard Henderson
` (66 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Emphasize that these are 4-way dot products.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 22 +++++++++++-----------
target/arm/tcg/translate-a64.c | 14 +++++++-------
target/arm/tcg/translate-neon.c | 14 +++++++-------
target/arm/tcg/translate-sve.c | 18 +++++++++---------
target/arm/tcg/vec_helper.c | 22 +++++++++++-----------
5 files changed, 45 insertions(+), 45 deletions(-)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index d8d389af2b..a19955b872 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -616,23 +616,23 @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_4h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_udot_idx_4h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 11abddee52..bf2272e449 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -6116,9 +6116,9 @@ static bool do_dot_vector_env(DisasContext *s, arg_qrrr_e *a,
return true;
}
-TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b)
-TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b)
-TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b)
+TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_4b)
+TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_4b)
TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfdot)
TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfmmla)
TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b)
@@ -6878,12 +6878,12 @@ static bool do_dot_vector_idx_env(DisasContext *s, arg_qrrx_e *a,
return true;
}
-TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b)
-TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b)
+TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_4b)
TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
- gen_helper_gvec_sudot_idx_b)
+ gen_helper_gvec_sudot_idx_4b)
TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
- gen_helper_gvec_usdot_idx_b)
+ gen_helper_gvec_usdot_idx_4b)
TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx_env, a,
gen_helper_gvec_bfdot_idx)
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index c4fecb8fd6..ea04336797 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -271,7 +271,7 @@ static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a)
return false;
}
return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
- gen_helper_gvec_sdot_b);
+ gen_helper_gvec_sdot_4b);
}
static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
@@ -280,7 +280,7 @@ static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a)
return false;
}
return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
- gen_helper_gvec_udot_b);
+ gen_helper_gvec_udot_4b);
}
static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
@@ -289,7 +289,7 @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a)
return false;
}
return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0,
- gen_helper_gvec_usdot_b);
+ gen_helper_gvec_usdot_4b);
}
static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a)
@@ -356,7 +356,7 @@ static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a)
return false;
}
return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
- gen_helper_gvec_sdot_idx_b);
+ gen_helper_gvec_sdot_idx_4b);
}
static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
@@ -365,7 +365,7 @@ static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a)
return false;
}
return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
- gen_helper_gvec_udot_idx_b);
+ gen_helper_gvec_udot_idx_4b);
}
static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
@@ -374,7 +374,7 @@ static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a)
return false;
}
return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
- gen_helper_gvec_usdot_idx_b);
+ gen_helper_gvec_usdot_idx_4b);
}
static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
@@ -383,7 +383,7 @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a)
return false;
}
return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index,
- gen_helper_gvec_sudot_idx_b);
+ gen_helper_gvec_sudot_idx_4b);
}
static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 4acd22f55e..1564ee2558 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3402,8 +3402,8 @@ DO_ZZI(UMIN, umin)
#undef DO_ZZI
static gen_helper_gvec_4 * const dot_fns[2][2] = {
- { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h },
- { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h }
+ { gen_helper_gvec_sdot_4b, gen_helper_gvec_sdot_4h },
+ { gen_helper_gvec_udot_4b, gen_helper_gvec_udot_4h }
};
TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
dot_fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0)
@@ -3413,18 +3413,18 @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
*/
TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
- gen_helper_gvec_sdot_idx_b, a)
+ gen_helper_gvec_sdot_idx_4b, a)
TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
- gen_helper_gvec_sdot_idx_h, a)
+ gen_helper_gvec_sdot_idx_4h, a)
TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
- gen_helper_gvec_udot_idx_b, a)
+ gen_helper_gvec_udot_idx_4b, a)
TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
- gen_helper_gvec_udot_idx_h, a)
+ gen_helper_gvec_udot_idx_4h, a)
TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
- gen_helper_gvec_sudot_idx_b, a)
+ gen_helper_gvec_sudot_idx_4b, a)
TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
- gen_helper_gvec_usdot_idx_b, a)
+ gen_helper_gvec_usdot_idx_4b, a)
#define DO_SVE2_RRX(NAME, FUNC) \
TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \
@@ -7152,7 +7152,7 @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot)
TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
- a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0)
+ a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0)
TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
gen_helper_crypto_aesmc, a->rd, a->rd, 0)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 130f040f7b..4fedaa7293 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -825,11 +825,11 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
clear_tail(d, opr_sz, simd_maxsz(desc)); \
}
-DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t)
-DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t)
-DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t)
-DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t)
-DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t)
+DO_DOT(gvec_sdot_4b, int32_t, int8_t, int8_t)
+DO_DOT(gvec_udot_4b, uint32_t, uint8_t, uint8_t)
+DO_DOT(gvec_usdot_4b, uint32_t, uint8_t, int8_t)
+DO_DOT(gvec_sdot_4h, int64_t, int16_t, int16_t)
+DO_DOT(gvec_udot_4h, uint64_t, uint16_t, uint16_t)
#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
@@ -865,12 +865,12 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
clear_tail(d, opr_sz, simd_maxsz(desc)); \
}
-DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4)
-DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4)
-DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4)
-DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4)
-DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, H8)
-DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, H8)
+DO_DOT_IDX(gvec_sdot_idx_4b, int32_t, int8_t, int8_t, H4)
+DO_DOT_IDX(gvec_udot_idx_4b, uint32_t, uint8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_sudot_idx_4b, int32_t, int8_t, uint8_t, H4)
+DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4)
+DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8)
+DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8)
void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
float_status *fpst, uint32_t desc)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 31/97] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (29 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 30/97] target/arm: Rename helper_gvec_*dot_[bh] to *_4[bh] Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:45 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 32/97] target/arm: Rename SVE SDOT and UDOT patterns Richard Henderson
` (65 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 8 ++++
target/arm/tcg/translate-sme.c | 85 ++++++++++++++++++++++++++++++++++
target/arm/tcg/vec_helper.c | 51 ++++++++++++++++++++
target/arm/tcg/sme.decode | 63 ++++++++++++++++++++++++-
4 files changed, 206 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index a19955b872..c4a208e3ba 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -622,6 +622,9 @@ DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG,
@@ -635,6 +638,11 @@ DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_sdot_idx_2h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(gvec_udot_idx_2h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 410a8d037c..341f4495e9 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -962,3 +962,88 @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
+
+/*
+ * Expand array multi-vector single (n1), array multi-vector (nn),
+ * and array multi-vector indexed (nx), for integer accumulate.
+ * multi: true for nn, false for n1.
+ * data: stuff for simd_data, including any index.
+ */
+static bool do_azz_acc(DisasContext *s, int nreg, int nsel,
+ int rv, int off, int zn, int zm,
+ int data, int shsel, bool multi,
+ gen_helper_gvec_4 *fn)
+{
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int vstride = svl / nreg;
+ TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+ TCGv_ptr t = tcg_temp_new_ptr();
+
+ for (int r = 0; r < nreg; ++r) {
+ TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+ TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+ for (int i = 0; i < nsel; ++i) {
+ int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+ int desc = simd_desc(svl, svl, data | (i << shsel));
+
+ tcg_gen_addi_ptr(t, t_za, o_za);
+ fn(t, t_zn, t_zm, t, tcg_constant_i32(desc));
+ }
+
+ /*
+ * For multiple-and-single vectors, Zn may wrap.
+ * For multiple vectors, both Zn and Zm are aligned.
+ */
+ zn = (zn + 1) % 32;
+ zm += multi;
+ }
+ }
+ return true;
+}
+
+static bool do_dot(DisasContext *s, arg_azz_n *a, bool multi,
+ gen_helper_gvec_4 *fn)
+{
+ return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+ 0, 0, multi, fn);
+}
+
+static void gen_helper_gvec_sudot_4b(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m,
+ TCGv_ptr a, TCGv_i32 desc)
+{
+ gen_helper_gvec_usdot_4b(d, m, n, a, desc);
+}
+
+TRANS_FEAT(USDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_usdot_4b)
+TRANS_FEAT(SUDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_sudot_4b)
+TRANS_FEAT(SDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_2h)
+TRANS_FEAT(UDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_2h)
+TRANS_FEAT(SDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_4b)
+TRANS_FEAT(SDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_sdot_4h)
+TRANS_FEAT(UDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_udot_4h)
+
+TRANS_FEAT(USDOT_nn, aa64_sme2, do_dot, a, true, gen_helper_gvec_usdot_4b)
+TRANS_FEAT(SDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_2h)
+TRANS_FEAT(UDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_2h)
+TRANS_FEAT(SDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_4b)
+TRANS_FEAT(SDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_sdot_4h)
+TRANS_FEAT(UDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_udot_4h)
+
+static bool do_dot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4 *fn)
+{
+ return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+ a->idx, 0, false, fn);
+}
+
+TRANS_FEAT(USDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_usdot_idx_4b)
+TRANS_FEAT(SUDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sudot_idx_4b)
+TRANS_FEAT(SDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_2h)
+TRANS_FEAT(UDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_2h)
+TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b)
+TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h)
+TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 4fedaa7293..c9d1b09268 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -872,6 +872,57 @@ DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4)
DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8)
DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8)
+#undef DO_DOT
+#undef DO_DOT_IDX
+
+/* Similar for 2-way dot product */
+#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ TYPED *d = vd, *a = va; \
+ TYPEN *n = vn; \
+ TYPEM *m = vm; \
+ for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \
+ d[i] = (a[i] + \
+ (TYPED)n[i * 2 + 0] * m[i * 2 + 0] + \
+ (TYPED)n[i * 2 + 1] * m[i * 2 + 1]); \
+ } \
+ clear_tail(d, opr_sz, simd_maxsz(desc)); \
+}
+
+#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{ \
+ intptr_t i = 0, opr_sz = simd_oprsz(desc); \
+ intptr_t opr_sz_n = opr_sz / sizeof(TYPED); \
+ intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n); \
+ intptr_t index = simd_data(desc); \
+ TYPED *d = vd, *a = va; \
+ TYPEN *n = vn; \
+ TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 2; \
+ do { \
+ TYPED m0 = m_indexed[i * 2 + 0]; \
+ TYPED m1 = m_indexed[i * 2 + 1]; \
+ do { \
+ d[i] = (a[i] + \
+ n[i * 2 + 0] * m0 + \
+ n[i * 2 + 1] * m1); \
+ } while (++i < segend); \
+ segend = i + (16 / sizeof(TYPED)); \
+ } while (i < opr_sz_n); \
+ clear_tail(d, opr_sz, simd_maxsz(desc)); \
+}
+
+DO_DOT(gvec_sdot_2h, int32_t, int16_t, int16_t)
+DO_DOT(gvec_udot_2h, uint32_t, uint16_t, uint16_t)
+
+DO_DOT_IDX(gvec_sdot_idx_2h, int32_t, int16_t, int16_t, H4)
+DO_DOT_IDX(gvec_udot_idx_2h, uint32_t, uint16_t, uint16_t, H4)
+
+#undef DO_DOT
+#undef DO_DOT_IDX
+
void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm,
float_status *fpst, uint32_t desc)
{
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 7c057bcad2..338637decd 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -291,6 +291,26 @@ FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4
BFDOT_n1 11000001 001 0 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=2
BFDOT_n1 11000001 001 1 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=4
+USDOT_n1 11000001 001 0 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=2
+USDOT_n1 11000001 001 1 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=4
+
+SUDOT_n1 11000001 001 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2
+SUDOT_n1 11000001 001 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4
+
+SDOT_n1_4b 11000001 001 0 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=2
+SDOT_n1_4b 11000001 001 1 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=4
+SDOT_n1_4h 11000001 011 0 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=2
+SDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=4
+SDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=2
+SDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=4
+
+UDOT_n1_4b 11000001 001 0 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=2
+UDOT_n1_4b 11000001 001 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4
+UDOT_n1_4h 11000001 011 0 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=2
+UDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4
+UDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2
+UDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4
+
### SME2 Multi-vector Multiple Array Vectors
%zn_ax2 6:4 !function=times_2
@@ -334,6 +354,23 @@ FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3
BFDOT_nn 11000001 101 ....0 0 .. 100 ....0 10 ... @azz_2x2_o3
BFDOT_nn 11000001 101 ...01 0 .. 100 ...00 10 ... @azz_4x4_o3
+USDOT_nn 11000001 101 ....0 0 .. 101 ....0 01 ... @azz_2x2_o3
+USDOT_nn 11000001 101 ...01 0 .. 101 ...00 01 ... @azz_4x4_o3
+
+SDOT_nn_4b 11000001 101 ....0 0 .. 101 ....0 00 ... @azz_2x2_o3
+SDOT_nn_4b 11000001 101 ...01 0 .. 101 ...00 00 ... @azz_4x4_o3
+SDOT_nn_4h 11000001 111 ....0 0 .. 101 ....0 00 ... @azz_2x2_o3
+SDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 00 ... @azz_4x4_o3
+SDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 01 ... @azz_2x2_o3
+SDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 01 ... @azz_4x4_o3
+
+UDOT_nn_4b 11000001 101 ....0 0 .. 101 ....0 10 ... @azz_2x2_o3
+UDOT_nn_4b 11000001 101 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3
+UDOT_nn_4h 11000001 111 ....0 0 .. 101 ....0 10 ... @azz_2x2_o3
+UDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3
+UDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 11 ... @azz_2x2_o3
+UDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 11 ... @azz_4x4_o3
+
### SME2 Multi-vector Indexed
&azx_n n off rv zn zm idx
@@ -367,7 +404,11 @@ BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2
@azx_2x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \
&azx_n n=2 rv=%mova_rv zn=%zn_ax2
@azx_4x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \
- &azx_n n=2 rv=%mova_rv zn=%zn_ax4
+ &azx_n n=4 rv=%mova_rv zn=%zn_ax4
+@azx_2x1_i1_o3 ........ .... zm:4 . .. .. idx:1 .... ... off:3 \
+ &azx_n n=2 rv=%mova_rv zn=%zn_ax2
+@azx_4x1_i1_o3 ........ .... zm:4 . .. .. idx:1 .... ... off:3 \
+ &azx_n n=4 rv=%mova_rv zn=%zn_ax4
FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3
FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3
@@ -377,3 +418,23 @@ BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3
FVDOT 11000001 0101 .... 0 .. 0 .. ....0 01 ... @azx_2x1_i2_o3
BFVDOT 11000001 0101 .... 0 .. 0 .. ....0 11 ... @azx_2x1_i2_o3
+
+SDOT_nx_2h 11000001 0101 .... 0 .. 1 .. ....0 00 ... @azx_2x1_i2_o3
+SDOT_nx_2h 11000001 0101 .... 1 .. 1 .. ...00 00 ... @azx_4x1_i2_o3
+SDOT_nx_4b 11000001 0101 .... 0 .. 1 .. ....1 00 ... @azx_2x1_i2_o3
+SDOT_nx_4b 11000001 0101 .... 1 .. 1 .. ...01 00 ... @azx_4x1_i2_o3
+SDOT_nx_4h 11000001 1101 .... 0 .. 00 . ....0 01 ... @azx_2x1_i1_o3
+SDOT_nx_4h 11000001 1101 .... 1 .. 00 . ...00 01 ... @azx_4x1_i1_o3
+
+UDOT_nx_2h 11000001 0101 .... 0 .. 1 .. ....0 10 ... @azx_2x1_i2_o3
+UDOT_nx_2h 11000001 0101 .... 1 .. 1 .. ...00 10 ... @azx_4x1_i2_o3
+UDOT_nx_4b 11000001 0101 .... 0 .. 1 .. ....1 10 ... @azx_2x1_i2_o3
+UDOT_nx_4b 11000001 0101 .... 1 .. 1 .. ...01 10 ... @azx_4x1_i2_o3
+UDOT_nx_4h 11000001 1101 .... 0 .. 00 . ....0 11 ... @azx_2x1_i1_o3
+UDOT_nx_4h 11000001 1101 .... 1 .. 00 . ...00 11 ... @azx_4x1_i1_o3
+
+USDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 01 ... @azx_2x1_i2_o3
+USDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 01 ... @azx_4x1_i2_o3
+
+SUDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 11 ... @azx_2x1_i2_o3
+SUDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 11 ... @azx_4x1_i2_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 31/97] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT
2025-07-02 12:33 ` [PATCH v3 31/97] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT Richard Henderson
@ 2025-07-03 9:45 ` Peter Maydell
2025-07-03 16:25 ` Richard Henderson
0 siblings, 1 reply; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 9:45 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:34, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> +/* Similar for 2-way dot product */
> +#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \
> +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
> +{ \
> + intptr_t i, opr_sz = simd_oprsz(desc); \
> + TYPED *d = vd, *a = va; \
> + TYPEN *n = vn; \
> + TYPEM *m = vm; \
> + for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \
> + d[i] = (a[i] + \
> + (TYPED)n[i * 2 + 0] * m[i * 2 + 0] + \
> + (TYPED)n[i * 2 + 1] * m[i * 2 + 1]); \
Don't we need some H macros here for the big-endian host case?
(For that matter, the existing 4-way dot product helpers also
look like they won't work on big-endian...)
> + } \
> + clear_tail(d, opr_sz, simd_maxsz(desc)); \
> +}
> +
> +#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \
> +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
> +{ \
> + intptr_t i = 0, opr_sz = simd_oprsz(desc); \
> + intptr_t opr_sz_n = opr_sz / sizeof(TYPED); \
> + intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n); \
> + intptr_t index = simd_data(desc); \
> + TYPED *d = vd, *a = va; \
> + TYPEN *n = vn; \
> + TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 2; \
> + do { \
> + TYPED m0 = m_indexed[i * 2 + 0]; \
> + TYPED m1 = m_indexed[i * 2 + 1]; \
> + do { \
> + d[i] = (a[i] + \
> + n[i * 2 + 0] * m0 + \
> + n[i * 2 + 1] * m1); \
Similarly here.
> + } while (++i < segend); \
> + segend = i + (16 / sizeof(TYPED)); \
> + } while (i < opr_sz_n); \
> + clear_tail(d, opr_sz, simd_maxsz(desc)); \
> +}
Otherwise
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread* Re: [PATCH v3 31/97] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT
2025-07-03 9:45 ` Peter Maydell
@ 2025-07-03 16:25 ` Richard Henderson
0 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-03 16:25 UTC (permalink / raw)
To: Peter Maydell; +Cc: qemu-devel, qemu-arm
On 7/3/25 03:45, Peter Maydell wrote:
> On Wed, 2 Jul 2025 at 13:34, Richard Henderson
> <richard.henderson@linaro.org> wrote:
>>
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>
>
>
>> +/* Similar for 2-way dot product */
>> +#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \
>> +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
>> +{ \
>> + intptr_t i, opr_sz = simd_oprsz(desc); \
>> + TYPED *d = vd, *a = va; \
>> + TYPEN *n = vn; \
>> + TYPEM *m = vm; \
>> + for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \
>> + d[i] = (a[i] + \
>> + (TYPED)n[i * 2 + 0] * m[i * 2 + 0] + \
>> + (TYPED)n[i * 2 + 1] * m[i * 2 + 1]); \
>
> Don't we need some H macros here for the big-endian host case?
> (For that matter, the existing 4-way dot product helpers also
> look like they won't work on big-endian...)
The logic here is that all columns are treated identically.
...a0... ...a1...
.n0..n1. .n2..n3.
.m0..m1. .m2..m3.
vs
...a1... ...a0...
.n3..n2. .n1..n0.
.m3..m2. .m1..m0.
d0 = a0 + n0 * m0 + n1 * m1 -- it doesn't matter if n0 or n1 is at the lowest or highest
address, because it still gets multiplied by the corresponding element in m, and then the
two products are added to the sum that is addressed the same way.
The existing 4-way dot product uses the same endian independent logic, fwiw.
r~
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 32/97] target/arm: Rename SVE SDOT and UDOT patterns
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (30 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 31/97] target/arm: Implemement SME2 SDOT, UDOT, USDOT, SUDOT Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:49 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 33/97] target/arm: Tighten USDOT (vectors) decode Richard Henderson
` (64 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Emphasize the 4-way nature of these dot products.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 12 ++++++------
target/arm/tcg/sve.decode | 12 ++++++------
2 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 1564ee2558..56353b3bb4 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3412,18 +3412,18 @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz,
* SVE Multiply - Indexed
*/
-TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_sdot_idx_4b, a)
-TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_sdot_idx_4h, a)
-TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(UDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_udot_idx_4b, a)
-TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(UDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_udot_idx_4h, a)
-TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_sudot_idx_4b, a)
-TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
+TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_usdot_idx_4b, a)
#define DO_SVE2_RRX(NAME, FUNC) \
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 5970ed9ac4..51847ea56e 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -851,10 +851,10 @@ CDOT_zzzz 01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5 ra=%reg_movprfx
#### SVE Multiply - Indexed
# SVE integer dot product (indexed)
-SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2
-SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3
-UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2
-UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3
+SDOT_zzxw_4s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2
+SDOT_zzxw_4d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3
+UDOT_zzxw_4s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2
+UDOT_zzxw_4d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3
# SVE2 integer multiply-add (indexed)
MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1
@@ -873,8 +873,8 @@ SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2
SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3
# SVE mixed sign dot product (indexed)
-USDOT_zzxw_s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2
-SUDOT_zzxw_s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2
+USDOT_zzxw_4s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2
+SUDOT_zzxw_4s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2
# SVE2 saturating multiply-add (indexed)
SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 33/97] target/arm: Tighten USDOT (vectors) decode
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (31 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 32/97] target/arm: Rename SVE SDOT and UDOT patterns Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:49 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 34/97] target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1 Richard Henderson
` (63 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Rename to USDOT_zzzz_4s and force size=2 during decode.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 4 ++--
target/arm/tcg/sve.decode | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 56353b3bb4..c82a0f771d 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7151,8 +7151,8 @@ static gen_helper_gvec_4 * const sqrdcmlah_fns[] = {
TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot)
-TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
- a->esz == 2 ? gen_helper_gvec_usdot_4b : NULL, a, 0)
+TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
+ gen_helper_gvec_usdot_4b, a, 0)
TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
gen_helper_crypto_aesmc, a->rd, a->rd, 0)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 51847ea56e..401c025852 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1599,7 +1599,7 @@ SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx
## SVE mixed sign dot product
-USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm
+USDOT_zzzz_4s 01000100 10 0 ..... 011 110 ..... ..... @rda_rn_rm_ex esz=2
### SVE2 floating point matrix multiply accumulate
BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=1
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 34/97] target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (32 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 33/97] target/arm: Tighten USDOT (vectors) decode Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:49 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 35/97] target/arm: Implement SME2 SVDOT, UVDOT, SUVDOT, USVDOT Richard Henderson
` (62 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 10 ++++++++++
target/arm/tcg/sve.decode | 8 +++++++-
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index c82a0f771d..10261e25f9 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3426,6 +3426,11 @@ TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz,
gen_helper_gvec_usdot_idx_4b, a)
+TRANS_FEAT(SDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz,
+ gen_helper_gvec_sdot_idx_2h, a)
+TRANS_FEAT(UDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz,
+ gen_helper_gvec_udot_idx_2h, a)
+
#define DO_SVE2_RRX(NAME, FUNC) \
TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \
a->rd, a->rn, a->rm, a->index)
@@ -7154,6 +7159,11 @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz,
TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz,
gen_helper_gvec_usdot_4b, a, 0)
+TRANS_FEAT(SDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz,
+ gen_helper_gvec_sdot_2h, a, 0)
+TRANS_FEAT(UDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz,
+ gen_helper_gvec_udot_2h, a, 0)
+
TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz,
gen_helper_crypto_aesmc, a->rd, a->rd, 0)
TRANS_FEAT_NONSTREAMING(AESIMC, aa64_sve2_aes, gen_gvec_ool_zz,
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 401c025852..83c259def6 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -856,6 +856,9 @@ SDOT_zzxw_4d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3
UDOT_zzxw_4s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2
UDOT_zzxw_4d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3
+SDOT_zzxw_2s 01000100 10 0 ..... 110010 ..... ..... @rrxr_2 esz=2
+UDOT_zzxw_2s 01000100 10 0 ..... 110011 ..... ..... @rrxr_2 esz=2
+
# SVE2 integer multiply-add (indexed)
MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1
MLA_zzxz_s 01000100 10 1 ..... 000010 ..... ..... @rrxr_2 esz=2
@@ -1597,7 +1600,10 @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm
CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx
SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx
-## SVE mixed sign dot product
+## SVE dot product
+
+SDOT_zzzz_2s 01000100 00 0 ..... 110 010 ..... ..... @rda_rn_rm_ex esz=2
+UDOT_zzzz_2s 01000100 00 0 ..... 110 011 ..... ..... @rda_rn_rm_ex esz=2
USDOT_zzzz_4s 01000100 10 0 ..... 011 110 ..... ..... @rda_rn_rm_ex esz=2
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 35/97] target/arm: Implement SME2 SVDOT, UVDOT, SUVDOT, USVDOT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (33 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 34/97] target/arm: Implement SDOT, UDOT (2-way) for SME2/SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 36/97] target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL Richard Henderson
` (61 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 11 +++++++++
target/arm/tcg/sme_helper.c | 42 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 23 +++++++++++++++++++
target/arm/tcg/sme.decode | 11 +++++++++
4 files changed, 87 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 8f5a1b3c90..464877516b 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -180,3 +180,14 @@ DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_FLAGS_6(sme2_fvdot_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_svdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_suvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_usvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_svdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 8b45865461..f5242d99be 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1416,3 +1416,45 @@ DEF_IMOP_16x2_32(umopa2_s, uint16_t, uint16_t)
DEF_IMOPH(sme2, smopa2, s)
DEF_IMOPH(sme2, umopa2, s)
+
+#define DO_VDOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD, HN) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t svl = simd_oprsz(desc); \
+ intptr_t elements = svl / sizeof(TYPED); \
+ intptr_t eltperseg = 16 / sizeof(TYPED); \
+ intptr_t nreg = sizeof(TYPED) / sizeof(TYPEN); \
+ intptr_t vstride = (svl / nreg) * sizeof(ARMVectorReg); \
+ intptr_t zstride = sizeof(ARMVectorReg) / sizeof(TYPEN); \
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2); \
+ TYPEN *n = vn; \
+ TYPEM *m = vm; \
+ for (intptr_t r = 0; r < nreg; r++) { \
+ TYPED *d = vd + r * vstride; \
+ for (intptr_t seg = 0; seg < elements; seg += eltperseg) { \
+ intptr_t s = seg + idx; \
+ for (intptr_t e = seg; e < seg + eltperseg; e++) { \
+ TYPED sum = d[HD(e)]; \
+ for (intptr_t i = 0; i < nreg; i++) { \
+ TYPED nn = n[i * zstride + HN(nreg * e + r)]; \
+ TYPED mm = m[HN(nreg * s + i)]; \
+ sum += nn * mm; \
+ } \
+ d[HD(e)] = sum; \
+ } \
+ } \
+ } \
+}
+
+DO_VDOT_IDX(sme2_svdot_idx_4b, int32_t, int8_t, int8_t, H4, H1)
+DO_VDOT_IDX(sme2_uvdot_idx_4b, uint32_t, uint8_t, uint8_t, H4, H1)
+DO_VDOT_IDX(sme2_suvdot_idx_4b, int32_t, int8_t, uint8_t, H4, H1)
+DO_VDOT_IDX(sme2_usvdot_idx_4b, int32_t, uint8_t, int8_t, H4, H1)
+
+DO_VDOT_IDX(sme2_svdot_idx_4h, int64_t, int16_t, int16_t, H8, H2)
+DO_VDOT_IDX(sme2_uvdot_idx_4h, uint64_t, uint16_t, uint16_t, H8, H2)
+
+DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2)
+DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2)
+
+#undef DO_VDOT_IDX
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 341f4495e9..b88f439ef9 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1047,3 +1047,26 @@ TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b)
TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b)
TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h)
TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h)
+
+static bool do_vdot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_3 *fn)
+{
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ fn(get_zarray(s, a->rv, a->off, a->n, 0),
+ vec_full_reg_ptr(s, a->zn),
+ vec_full_reg_ptr(s, a->zm),
+ tcg_constant_i32(simd_desc(svl, svl, a->idx)));
+ }
+ return true;
+}
+
+TRANS_FEAT(SVDOT_nx_2h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_2h)
+TRANS_FEAT(SVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_4b)
+TRANS_FEAT(SVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_4h)
+
+TRANS_FEAT(UVDOT_nx_2h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_2h)
+TRANS_FEAT(UVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4b)
+TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h)
+
+TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b)
+TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 338637decd..4146744a46 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -438,3 +438,14 @@ USDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 01 ... @azx_4x1_i2_o3
SUDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 11 ... @azx_2x1_i2_o3
SUDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 11 ... @azx_4x1_i2_o3
+
+SVDOT_nx_2h 11000001 0101 .... 0 .. 0 .. ....1 00 ... @azx_2x1_i2_o3
+SVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 00 ... @azx_4x1_i2_o3
+SVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 01 ... @azx_4x1_i1_o3
+
+UVDOT_nx_2h 11000001 0101 .... 0 .. 0 .. ....1 10 ... @azx_2x1_i2_o3
+UVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 10 ... @azx_4x1_i2_o3
+UVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 11 ... @azx_4x1_i1_o3
+
+SUVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 11 ... @azx_4x1_i2_o3
+USVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 01 ... @azx_4x1_i2_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 36/97] target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (34 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 35/97] target/arm: Implement SME2 SVDOT, UVDOT, SUVDOT, USVDOT Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:50 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 37/97] target/arm: Rename gvec_fml[as]_[hs] with _nf_ infix Richard Henderson
` (60 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 21 +++++
target/arm/tcg/sme_helper.c | 59 ++++++++++++
target/arm/tcg/translate-sme.c | 84 +++++++++++++++++
target/arm/tcg/sme.decode | 168 +++++++++++++++++++++++++++++++++
4 files changed, 332 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 464877516b..0bb8af194b 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -191,3 +191,24 @@ DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_smlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_usmlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_smlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_smlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index f5242d99be..0f79d7cb6e 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1458,3 +1458,62 @@ DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2)
DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2)
#undef DO_VDOT_IDX
+
+#define DO_MLALL(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{ \
+ intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW); \
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2); \
+ TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm; \
+ for (intptr_t i = 0; i < elements; ++i) { \
+ TYPEW nn = n[HN(i * 4 + sel)]; \
+ TYPEM mm = m[HN(i * 4 + sel)]; \
+ d[HW(i)] = a[HW(i)] OP (nn * mm); \
+ } \
+}
+
+DO_MLALL(sme2_smlall_s, int32_t, int8_t, int8_t, H4, H1, +)
+DO_MLALL(sme2_smlall_d, int64_t, int16_t, int16_t, H8, H2, +)
+DO_MLALL(sme2_smlsll_s, int32_t, int8_t, int8_t, H4, H1, -)
+DO_MLALL(sme2_smlsll_d, int64_t, int16_t, int16_t, H8, H2, -)
+
+DO_MLALL(sme2_umlall_s, uint32_t, uint8_t, uint8_t, H4, H1, +)
+DO_MLALL(sme2_umlall_d, uint64_t, uint16_t, uint16_t, H8, H2, +)
+DO_MLALL(sme2_umlsll_s, uint32_t, uint8_t, uint8_t, H4, H1, -)
+DO_MLALL(sme2_umlsll_d, uint64_t, uint16_t, uint16_t, H8, H2, -)
+
+DO_MLALL(sme2_usmlall_s, uint32_t, uint8_t, int8_t, H4, H1, +)
+
+#undef DO_MLALL
+
+#define DO_MLALL_IDX(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{ \
+ intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW); \
+ intptr_t eltspersegment = 16 / sizeof(TYPEW); \
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2); \
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 4); \
+ TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm; \
+ for (intptr_t i = 0; i < elements; i += eltspersegment) { \
+ TYPEW mm = m[HN(i * 4 + idx)]; \
+ for (intptr_t j = 0; j < eltspersegment; ++j) { \
+ TYPEN nn = n[HN((i + j) * 4 + sel)]; \
+ d[HW(i + j)] = a[HW(i + j)] OP (nn * mm); \
+ } \
+ } \
+}
+
+DO_MLALL_IDX(sme2_smlall_idx_s, int32_t, int8_t, int8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_smlall_idx_d, int64_t, int16_t, int16_t, H8, H2, +)
+DO_MLALL_IDX(sme2_smlsll_idx_s, int32_t, int8_t, int8_t, H4, H1, -)
+DO_MLALL_IDX(sme2_smlsll_idx_d, int64_t, int16_t, int16_t, H8, H2, -)
+
+DO_MLALL_IDX(sme2_umlall_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_umlall_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, +)
+DO_MLALL_IDX(sme2_umlsll_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, -)
+DO_MLALL_IDX(sme2_umlsll_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, -)
+
+DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +)
+DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +)
+
+#undef DO_MLALL_IDX
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index b88f439ef9..070cebc573 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1070,3 +1070,87 @@ TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h)
TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b)
TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b)
+
+static bool do_smlal(DisasContext *s, arg_azz_n *a, bool multi,
+ gen_helper_gvec_4 *fn)
+{
+ return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+ 0, 0, multi, fn);
+}
+
+TRANS_FEAT(SMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlal_zzzw_s)
+TRANS_FEAT(SMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlsl_zzzw_s)
+TRANS_FEAT(UMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlal_zzzw_s)
+TRANS_FEAT(UMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlsl_zzzw_s)
+
+TRANS_FEAT(SMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlal_zzzw_s)
+TRANS_FEAT(SMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlsl_zzzw_s)
+TRANS_FEAT(UMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlal_zzzw_s)
+TRANS_FEAT(UMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlsl_zzzw_s)
+
+static bool do_smlal_nx(DisasContext *s, arg_azx_n *a,
+ gen_helper_gvec_4 *fn)
+{
+ return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm,
+ a->idx << 1, 0, false, fn);
+}
+
+TRANS_FEAT(SMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlal_idx_s)
+TRANS_FEAT(SMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlsl_idx_s)
+TRANS_FEAT(UMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlal_idx_s)
+TRANS_FEAT(UMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlsl_idx_s)
+
+static bool do_smlall(DisasContext *s, arg_azz_n *a, bool multi,
+ gen_helper_gvec_4 *fn)
+{
+ return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm,
+ 0, 0, multi, fn);
+}
+
+static void gen_helper_sme2_sumlall_s(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m,
+ TCGv_ptr a, TCGv_i32 desc)
+{
+ gen_helper_sme2_usmlall_s(d, m, n, a, desc);
+}
+
+TRANS_FEAT(SMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlall_s)
+TRANS_FEAT(SMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlsll_s)
+TRANS_FEAT(UMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlall_s)
+TRANS_FEAT(UMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlsll_s)
+TRANS_FEAT(USMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_usmlall_s)
+TRANS_FEAT(SUMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_sumlall_s)
+
+TRANS_FEAT(SMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlall_d)
+TRANS_FEAT(SMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlsll_d)
+TRANS_FEAT(UMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlall_d)
+TRANS_FEAT(UMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlsll_d)
+
+TRANS_FEAT(SMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlall_s)
+TRANS_FEAT(SMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlsll_s)
+TRANS_FEAT(UMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlall_s)
+TRANS_FEAT(UMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlsll_s)
+TRANS_FEAT(USMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_usmlall_s)
+
+TRANS_FEAT(SMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlall_d)
+TRANS_FEAT(SMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlsll_d)
+TRANS_FEAT(UMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlall_d)
+TRANS_FEAT(UMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlsll_d)
+
+static bool do_smlall_nx(DisasContext *s, arg_azx_n *a,
+ gen_helper_gvec_4 *fn)
+{
+ return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm,
+ a->idx << 2, 0, false, fn);
+}
+
+TRANS_FEAT(SMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlall_idx_s)
+TRANS_FEAT(SMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_s)
+TRANS_FEAT(UMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlall_idx_s)
+TRANS_FEAT(UMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_s)
+TRANS_FEAT(USMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_usmlall_idx_s)
+TRANS_FEAT(SUMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_sumlall_idx_s)
+
+TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlall_idx_d)
+TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d)
+TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d)
+TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 4146744a46..934e4a802e 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -311,6 +311,65 @@ UDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4
UDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2
UDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4
+SMLAL_n1 11000001 011 0 .... 0 .. 011 ..... 00 ... @azz_nx1_o3x2 n=1
+SMLAL_n1 11000001 011 0 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=2
+SMLAL_n1 11000001 011 1 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=4
+
+SMLSL_n1 11000001 011 0 .... 0 .. 011 ..... 01 ... @azz_nx1_o3x2 n=1
+SMLSL_n1 11000001 011 0 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=2
+SMLSL_n1 11000001 011 1 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=4
+
+UMLAL_n1 11000001 011 0 .... 0 .. 011 ..... 10 ... @azz_nx1_o3x2 n=1
+UMLAL_n1 11000001 011 0 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=2
+UMLAL_n1 11000001 011 1 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=4
+
+UMLSL_n1 11000001 011 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1
+UMLSL_n1 11000001 011 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2
+UMLSL_n1 11000001 011 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4
+
+%off2_x4 0:2 !function=times_4
+%off1_x4 0:1 !function=times_4
+
+@azz_nx1_o2x4 ........ ... . zm:4 . .. ... zn:5 ... .. \
+ &azz_n off=%off2_x4 rv=%mova_rv
+@azz_nx1_o1x4 ........ ... . zm:4 . .. ... zn:5 .... . \
+ &azz_n off=%off1_x4 rv=%mova_rv
+
+SMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 000 .. @azz_nx1_o2x4 n=1
+SMLALL_n1_d 11000001 011 0 .... 0 .. 001 ..... 000 .. @azz_nx1_o2x4 n=1
+SMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=2
+SMLALL_n1_d 11000001 011 0 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=2
+SMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=4
+SMLALL_n1_d 11000001 011 1 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=4
+
+SMLSLL_n1_s 11000001 001 0 .... 0 .. 001 ..... 010 .. @azz_nx1_o2x4 n=1
+SMLSLL_n1_d 11000001 011 0 .... 0 .. 001 ..... 010 .. @azz_nx1_o2x4 n=1
+SMLSLL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=2
+SMLSLL_n1_d 11000001 011 0 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=2
+SMLSLL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=4
+SMLSLL_n1_d 11000001 011 1 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=4
+
+UMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 100 .. @azz_nx1_o2x4 n=1
+UMLALL_n1_d 11000001 011 0 .... 0 .. 001 ..... 100 .. @azz_nx1_o2x4 n=1
+UMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=2
+UMLALL_n1_d 11000001 011 0 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=2
+UMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=4
+UMLALL_n1_d 11000001 011 1 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=4
+
+UMLSLL_n1_s 11000001 001 0 .... 0 .. 001 ..... 110 .. @azz_nx1_o2x4 n=1
+UMLSLL_n1_d 11000001 011 0 .... 0 .. 001 ..... 110 .. @azz_nx1_o2x4 n=1
+UMLSLL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=2
+UMLSLL_n1_d 11000001 011 0 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=2
+UMLSLL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=4
+UMLSLL_n1_d 11000001 011 1 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=4
+
+USMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 001 .. @azz_nx1_o2x4 n=1
+USMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=2
+USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4
+
+SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2
+SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4
+
### SME2 Multi-vector Multiple Array Vectors
%zn_ax2 6:4 !function=times_2
@@ -371,6 +430,46 @@ UDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3
UDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 11 ... @azz_2x2_o3
UDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 11 ... @azz_4x4_o3
+SMLAL_nn 11000001 111 ....0 0 .. 010 ....0 000 .. @azz_2x2_o2x2
+SMLAL_nn 11000001 111 ...01 0 .. 010 ...00 000 .. @azz_4x4_o2x2
+
+SMLSL_nn 11000001 111 ....0 0 .. 010 ....0 010 .. @azz_2x2_o2x2
+SMLSL_nn 11000001 111 ...01 0 .. 010 ...00 010 .. @azz_4x4_o2x2
+
+UMLAL_nn 11000001 111 ....0 0 .. 010 ....0 100 .. @azz_2x2_o2x2
+UMLAL_nn 11000001 111 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2
+
+UMLSL_nn 11000001 111 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2
+UMLSL_nn 11000001 111 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2
+
+@azz_2x2_o1x4 ........ ... ..... . .. ... ..... ... .. \
+ &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off1_x4
+@azz_4x4_o1x4 ........ ... ..... . .. ... ..... ... .. \
+ &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off1_x4
+
+SMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0000 . @azz_2x2_o1x4
+SMLALL_nn_d 11000001 111 ....0 0 .. 000 ....0 0000 . @azz_2x2_o1x4
+SMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0000 . @azz_4x4_o1x4
+SMLALL_nn_d 11000001 111 ...01 0 .. 000 ...00 0000 . @azz_4x4_o1x4
+
+SMLSLL_nn_s 11000001 101 ....0 0 .. 000 ....0 0100 . @azz_2x2_o1x4
+SMLSLL_nn_d 11000001 111 ....0 0 .. 000 ....0 0100 . @azz_2x2_o1x4
+SMLSLL_nn_s 11000001 101 ...01 0 .. 000 ...00 0100 . @azz_4x4_o1x4
+SMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 0100 . @azz_4x4_o1x4
+
+UMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 1000 . @azz_2x2_o1x4
+UMLALL_nn_d 11000001 111 ....0 0 .. 000 ....0 1000 . @azz_2x2_o1x4
+UMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 1000 . @azz_4x4_o1x4
+UMLALL_nn_d 11000001 111 ...01 0 .. 000 ...00 1000 . @azz_4x4_o1x4
+
+UMLSLL_nn_s 11000001 101 ....0 0 .. 000 ....0 1100 . @azz_2x2_o1x4
+UMLSLL_nn_d 11000001 111 ....0 0 .. 000 ....0 1100 . @azz_2x2_o1x4
+UMLSLL_nn_s 11000001 101 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4
+UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4
+
+USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4
+USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4
+
### SME2 Multi-vector Indexed
&azx_n n off rv zn zm idx
@@ -449,3 +548,72 @@ UVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 11 ... @azx_4x1_i1_o3
SUVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 11 ... @azx_4x1_i2_o3
USVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 01 ... @azx_4x1_i2_o3
+
+SMLAL_nx 11000001 1100 .... . .. 1 .. ..... 00 ... @azx_1x1_o3x2
+SMLAL_nx 11000001 1101 .... 0 .. 1 .. ....0 00 ... @azx_2x1_o2x2
+SMLAL_nx 11000001 1101 .... 1 .. 1 .. ...00 00 ... @azx_4x1_o2x2
+
+SMLSL_nx 11000001 1100 .... . .. 1 .. ..... 01 ... @azx_1x1_o3x2
+SMLSL_nx 11000001 1101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_o2x2
+SMLSL_nx 11000001 1101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_o2x2
+
+UMLAL_nx 11000001 1100 .... . .. 1 .. ..... 10 ... @azx_1x1_o3x2
+UMLAL_nx 11000001 1101 .... 0 .. 1 .. ....0 10 ... @azx_2x1_o2x2
+UMLAL_nx 11000001 1101 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2
+
+UMLSL_nx 11000001 1100 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2
+UMLSL_nx 11000001 1101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2
+UMLSL_nx 11000001 1101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2
+
+%idx4_15_10 15:1 10:3
+%idx4_10_1 10:2 1:2
+%idx3_10_1 10:1 1:2
+
+@azx_1x1_i4_o2 ........ .... zm:4 . .. ... zn:5 ... .. \
+ &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx4_15_10
+@azx_1x1_i3_o2 ........ .... zm:4 . .. ... zn:5 ... .. \
+ &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx3_15_10
+@azx_2x1_i4_o1 ........ .... zm:4 . .. ... ..... ... .. \
+ &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx4_10_1
+@azx_2x1_i3_o1 ........ .... zm:4 . .. ... ..... ... .. \
+ &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx3_10_1
+@azx_4x1_i4_o1 ........ .... zm:4 . .. ... ..... ... .. \
+ &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx4_10_1
+@azx_4x1_i3_o1 ........ .... zm:4 . .. ... ..... ... .. \
+ &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx3_10_1
+
+SMLALL_nx_s 11000001 0000 .... . .. ... ..... 000 .. @azx_1x1_i4_o2
+SMLALL_nx_d 11000001 1000 .... . .. 0.. ..... 000 .. @azx_1x1_i3_o2
+SMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....0 00 ... @azx_2x1_i4_o1
+SMLALL_nx_d 11000001 1001 .... 0 .. 00. ....0 00 ... @azx_2x1_i3_o1
+SMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...00 00 ... @azx_4x1_i4_o1
+SMLALL_nx_d 11000001 1001 .... 1 .. 00. ...00 00 ... @azx_4x1_i3_o1
+
+SMLSLL_nx_s 11000001 0000 .... . .. ... ..... 010 .. @azx_1x1_i4_o2
+SMLSLL_nx_d 11000001 1000 .... . .. 0.. ..... 010 .. @azx_1x1_i3_o2
+SMLSLL_nx_s 11000001 0001 .... 0 .. 0.. ....0 01 ... @azx_2x1_i4_o1
+SMLSLL_nx_d 11000001 1001 .... 0 .. 00. ....0 01 ... @azx_2x1_i3_o1
+SMLSLL_nx_s 11000001 0001 .... 1 .. 0.. ...00 01 ... @azx_4x1_i4_o1
+SMLSLL_nx_d 11000001 1001 .... 1 .. 00. ...00 01 ... @azx_4x1_i3_o1
+
+UMLALL_nx_s 11000001 0000 .... . .. ... ..... 100 .. @azx_1x1_i4_o2
+UMLALL_nx_d 11000001 1000 .... . .. 0.. ..... 100 .. @azx_1x1_i3_o2
+UMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....0 10 ... @azx_2x1_i4_o1
+UMLALL_nx_d 11000001 1001 .... 0 .. 00. ....0 10 ... @azx_2x1_i3_o1
+UMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...00 10 ... @azx_4x1_i4_o1
+UMLALL_nx_d 11000001 1001 .... 1 .. 00. ...00 10 ... @azx_4x1_i3_o1
+
+UMLSLL_nx_s 11000001 0000 .... . .. ... ..... 110 .. @azx_1x1_i4_o2
+UMLSLL_nx_d 11000001 1000 .... . .. 0.. ..... 110 .. @azx_1x1_i3_o2
+UMLSLL_nx_s 11000001 0001 .... 0 .. 0.. ....0 11 ... @azx_2x1_i4_o1
+UMLSLL_nx_d 11000001 1001 .... 0 .. 00. ....0 11 ... @azx_2x1_i3_o1
+UMLSLL_nx_s 11000001 0001 .... 1 .. 0.. ...00 11 ... @azx_4x1_i4_o1
+UMLSLL_nx_d 11000001 1001 .... 1 .. 00. ...00 11 ... @azx_4x1_i3_o1
+
+USMLALL_nx_s 11000001 0000 .... . .. ... ..... 001 .. @azx_1x1_i4_o2
+USMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 00 ... @azx_2x1_i4_o1
+USMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 00 ... @azx_4x1_i4_o1
+
+SUMLALL_nx_s 11000001 0000 .... . .. ... ..... 101 .. @azx_1x1_i4_o2
+SUMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 10 ... @azx_2x1_i4_o1
+SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 36/97] target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL
2025-07-02 12:33 ` [PATCH v3 36/97] target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL Richard Henderson
@ 2025-07-03 9:50 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 9:50 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:34, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 21 +++++
> target/arm/tcg/sme_helper.c | 59 ++++++++++++
> target/arm/tcg/translate-sme.c | 84 +++++++++++++++++
> target/arm/tcg/sme.decode | 168 +++++++++++++++++++++++++++++++++
> 4 files changed, 332 insertions(+)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 37/97] target/arm: Rename gvec_fml[as]_[hs] with _nf_ infix
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (35 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 36/97] target/arm: Implement SME2 SMLAL, SMLSL, UMLAL, UMLSL Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:50 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 38/97] target/arm: Implement SME2 FMLA, FMLS Richard Henderson
` (59 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Emphasize the non-fused nature of these multiply-add.
Matches other helpers such as gvec_rsqrts_nf_[hs].
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 8 ++++----
target/arm/tcg/translate-neon.c | 4 ++--
target/arm/tcg/vec_helper.c | 8 ++++----
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index c4a208e3ba..b741470b51 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -790,11 +790,11 @@ DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst,
DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
-DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
-DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fmla_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fmla_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
-DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
-DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fmls_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c
index ea04336797..844d2e29e4 100644
--- a/target/arm/tcg/translate-neon.c
+++ b/target/arm/tcg/translate-neon.c
@@ -1010,8 +1010,8 @@ DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h)
DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h)
DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h)
DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h)
-DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h)
-DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h)
+DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_nf_s, gen_helper_gvec_fmla_nf_h)
+DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_nf_s, gen_helper_gvec_fmls_nf_h)
DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h)
DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h)
DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index c9d1b09268..e03db47ef7 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -1668,11 +1668,11 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, \
clear_tail(d, oprsz, simd_maxsz(desc)); \
}
-DO_MULADD(gvec_fmla_h, float16_muladd_nf, float16)
-DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32)
+DO_MULADD(gvec_fmla_nf_h, float16_muladd_nf, float16)
+DO_MULADD(gvec_fmla_nf_s, float32_muladd_nf, float32)
-DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16)
-DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32)
+DO_MULADD(gvec_fmls_nf_h, float16_mulsub_nf, float16)
+DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32)
DO_MULADD(gvec_vfma_h, float16_muladd_f, float16)
DO_MULADD(gvec_vfma_s, float32_muladd_f, float32)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 38/97] target/arm: Implement SME2 FMLA, FMLS
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (36 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 37/97] target/arm: Rename gvec_fml[as]_[hs] with _nf_ infix Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:50 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 39/97] target/arm: Implement SME2 BFMLA, BFMLS Richard Henderson
` (58 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 95 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 48 +++++++++++++++++
2 files changed, 143 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 070cebc573..5f51369609 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -815,6 +815,47 @@ TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub
*/
#define FPST_ENV -1
+static bool do_azz_fp(DisasContext *s, int nreg, int nsel,
+ int rv, int off, int zn, int zm,
+ int data, int shsel, bool multi, int fpst,
+ gen_helper_gvec_3_ptr *fn)
+{
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int vstride = svl / nreg;
+ TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel);
+ TCGv_ptr t, ptr;
+
+ if (fpst >= 0) {
+ ptr = fpstatus_ptr(fpst);
+ } else {
+ ptr = tcg_env;
+ }
+ t = tcg_temp_new_ptr();
+
+ for (int r = 0; r < nreg; ++r) {
+ TCGv_ptr t_zn = vec_full_reg_ptr(s, zn);
+ TCGv_ptr t_zm = vec_full_reg_ptr(s, zm);
+
+ for (int i = 0; i < nsel; ++i) {
+ int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+ int desc = simd_desc(svl, svl, data | (i << shsel));
+
+ tcg_gen_addi_ptr(t, t_za, o_za);
+ fn(t, t_zn, t_zm, ptr, tcg_constant_i32(desc));
+ }
+
+ /*
+ * For multiple-and-single vectors, Zn may wrap.
+ * For multiple vectors, both Zn and Zm are aligned.
+ */
+ zn = (zn + 1) % 32;
+ zm += multi;
+ }
+ }
+ return true;
+}
+
static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel,
int rv, int off, int zn, int zm,
int data, int shsel, bool multi, int fpst,
@@ -963,6 +1004,60 @@ static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn)
TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h)
TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx)
+static bool do_fmla(DisasContext *s, arg_azz_n *a, bool multi,
+ ARMFPStatusFlavour fpst, gen_helper_gvec_3_ptr *fn)
+{
+ return do_azz_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+ 0, 0, multi, fpst, fn);
+}
+
+TRANS_FEAT(FMLA_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16,
+ gen_helper_gvec_vfma_h)
+TRANS_FEAT(FMLS_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16,
+ s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h)
+TRANS_FEAT(FMLA_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16,
+ gen_helper_gvec_vfma_h)
+TRANS_FEAT(FMLS_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16,
+ s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h)
+
+TRANS_FEAT(FMLA_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA,
+ gen_helper_gvec_vfma_s)
+TRANS_FEAT(FMLS_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s)
+TRANS_FEAT(FMLA_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA,
+ gen_helper_gvec_vfma_s)
+TRANS_FEAT(FMLS_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s)
+
+TRANS_FEAT(FMLA_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA,
+ gen_helper_gvec_vfma_d)
+TRANS_FEAT(FMLS_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
+ gen_helper_gvec_vfma_d)
+TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+
+static bool do_fmla_nx(DisasContext *s, arg_azx_n *a,
+ ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn)
+{
+ return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm,
+ a->idx, 0, false, fpst, fn);
+}
+
+TRANS_FEAT(FMLA_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16,
+ gen_helper_gvec_fmla_idx_h)
+TRANS_FEAT(FMLS_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16,
+ s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_h : gen_helper_gvec_fmls_idx_h)
+TRANS_FEAT(FMLA_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA,
+ gen_helper_gvec_fmla_idx_s)
+TRANS_FEAT(FMLS_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_s : gen_helper_gvec_fmls_idx_s)
+TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
+ gen_helper_gvec_fmla_idx_d)
+TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d)
+
/*
* Expand array multi-vector single (n1), array multi-vector (nn),
* and array multi-vector indexed (nx), for integer accumulate.
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 934e4a802e..962ffae3d6 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -370,6 +370,20 @@ USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4
SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2
SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4
+FMLA_n1_h 11000001 001 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2
+FMLA_n1_s 11000001 001 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2
+FMLA_n1_d 11000001 011 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2
+FMLA_n1_h 11000001 001 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4
+FMLA_n1_s 11000001 001 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4
+FMLA_n1_d 11000001 011 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4
+
+FMLS_n1_h 11000001 001 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2
+FMLS_n1_s 11000001 001 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2
+FMLS_n1_d 11000001 011 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2
+FMLS_n1_h 11000001 001 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4
+FMLS_n1_s 11000001 001 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4
+FMLS_n1_d 11000001 011 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4
+
### SME2 Multi-vector Multiple Array Vectors
%zn_ax2 6:4 !function=times_2
@@ -470,6 +484,20 @@ UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4
USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4
USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4
+FMLA_nn_h 11000001 101 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3
+FMLA_nn_s 11000001 101 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3
+FMLA_nn_d 11000001 111 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3
+FMLA_nn_h 11000001 101 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3
+FMLA_nn_s 11000001 101 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3
+FMLA_nn_d 11000001 111 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3
+
+FMLS_nn_h 11000001 101 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3
+FMLS_nn_s 11000001 101 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3
+FMLS_nn_d 11000001 111 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3
+FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3
+FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3
+FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3
+
### SME2 Multi-vector Indexed
&azx_n n off rv zn zm idx
@@ -617,3 +645,23 @@ USMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 00 ... @azx_4x1_i4_o1
SUMLALL_nx_s 11000001 0000 .... . .. ... ..... 101 .. @azx_1x1_i4_o2
SUMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 10 ... @azx_2x1_i4_o1
SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1
+
+%idx3_10_3 10:2 3:1
+@azx_2x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \
+ &azx_n n=2 rv=%mova_rv zn=%zn_ax2 idx=%idx3_10_3
+@azx_4x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \
+ &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3
+
+FMLA_nx_h 11000001 0001 .... 0 .. 1.. ....0 0 .... @azx_2x1_i3_o3
+FMLA_nx_s 11000001 0101 .... 0 .. 0.. ....0 00 ... @azx_2x1_i2_o3
+FMLA_nx_d 11000001 1101 .... 0 .. 00. ....0 00 ... @azx_2x1_i1_o3
+FMLA_nx_h 11000001 0001 .... 1 .. 1.. ...00 0 .... @azx_4x1_i3_o3
+FMLA_nx_s 11000001 0101 .... 1 .. 0.. ...00 00 ... @azx_4x1_i2_o3
+FMLA_nx_d 11000001 1101 .... 1 .. 00. ...00 00 ... @azx_4x1_i1_o3
+
+FMLS_nx_h 11000001 0001 .... 0 .. 1.. ....0 1 .... @azx_2x1_i3_o3
+FMLS_nx_s 11000001 0101 .... 0 .. 0.. ....0 10 ... @azx_2x1_i2_o3
+FMLS_nx_d 11000001 1101 .... 0 .. 00. ....0 10 ... @azx_2x1_i1_o3
+FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3
+FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3
+FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 39/97] target/arm: Implement SME2 BFMLA, BFMLS
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (37 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 38/97] target/arm: Implement SME2 FMLA, FMLS Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:50 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 40/97] target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB Richard Henderson
` (57 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 9 +++++++++
target/arm/tcg/translate-sme.c | 14 ++++++++++++++
target/arm/tcg/vec_helper.c | 26 ++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 18 ++++++++++++++++++
4 files changed, 67 insertions(+)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index b741470b51..37dd384659 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -799,14 +799,17 @@ DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i
DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_ah_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, fpst, i32)
@@ -838,6 +841,8 @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmla_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(gvec_fmls_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
@@ -845,6 +850,8 @@ DEF_HELPER_FLAGS_6(gvec_fmls_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(gvec_fmls_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_bfmls_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
@@ -852,6 +859,8 @@ DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_6(gvec_ah_bfmls_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 5f51369609..3f9a80248a 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1038,6 +1038,15 @@ TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA,
s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d)
+TRANS_FEAT(BFMLA_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA,
+ gen_helper_gvec_bfmla)
+TRANS_FEAT(BFMLS_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls)
+TRANS_FEAT(BFMLA_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA,
+ gen_helper_gvec_bfmla)
+TRANS_FEAT(BFMLS_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls)
+
static bool do_fmla_nx(DisasContext *s, arg_azx_n *a,
ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn)
{
@@ -1058,6 +1067,11 @@ TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA,
s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d)
+TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
+ gen_helper_gvec_bfmla_idx)
+TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
+ s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx)
+
/*
* Expand array multi-vector single (n1), array multi-vector (nn),
* and array multi-vector indexed (nx), for integer accumulate.
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index e03db47ef7..f4373dd4bf 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -1608,6 +1608,12 @@ static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2,
return float16_muladd(op1, op2, dest, 0, stat);
}
+static bfloat16 bfloat16_muladd_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+ float_status *stat)
+{
+ return bfloat16_muladd(op1, op2, dest, 0, stat);
+}
+
static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
@@ -1626,6 +1632,12 @@ static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2,
return float16_muladd(float16_chs(op1), op2, dest, 0, stat);
}
+static bfloat16 bfloat16_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+ float_status *stat)
+{
+ return bfloat16_muladd(bfloat16_chs(op1), op2, dest, 0, stat);
+}
+
static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
@@ -1644,6 +1656,12 @@ static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2,
return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
}
+static bfloat16 bfloat16_ah_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2,
+ float_status *stat)
+{
+ return bfloat16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
+}
+
static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
@@ -1677,14 +1695,19 @@ DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32)
DO_MULADD(gvec_vfma_h, float16_muladd_f, float16)
DO_MULADD(gvec_vfma_s, float32_muladd_f, float32)
DO_MULADD(gvec_vfma_d, float64_muladd_f, float64)
+DO_MULADD(gvec_bfmla, bfloat16_muladd_f, bfloat16)
DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64)
+DO_MULADD(gvec_bfmls, bfloat16_mulsub_f, bfloat16)
DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16)
DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32)
DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64)
+DO_MULADD(gvec_ah_bfmls, bfloat16_ah_mulsub_f, bfloat16)
+
+#undef DO_MULADD
/* For the indexed ops, SVE applies the index per 128-bit vector segment.
* For AdvSIMD, there is of course only one such vector segment.
@@ -1803,14 +1826,17 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \
DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2, 0, 0)
DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4, 0, 0)
DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8, 0, 0)
+DO_FMLA_IDX(gvec_bfmla_idx, bfloat16, H2, 0, 0)
DO_FMLA_IDX(gvec_fmls_idx_h, float16, H2, INT16_MIN, 0)
DO_FMLA_IDX(gvec_fmls_idx_s, float32, H4, INT32_MIN, 0)
DO_FMLA_IDX(gvec_fmls_idx_d, float64, H8, INT64_MIN, 0)
+DO_FMLA_IDX(gvec_bfmls_idx, bfloat16, H2, INT16_MIN, 0)
DO_FMLA_IDX(gvec_ah_fmls_idx_h, float16, H2, 0, float_muladd_negate_product)
DO_FMLA_IDX(gvec_ah_fmls_idx_s, float32, H4, 0, float_muladd_negate_product)
DO_FMLA_IDX(gvec_ah_fmls_idx_d, float64, H8, 0, float_muladd_negate_product)
+DO_FMLA_IDX(gvec_ah_bfmls_idx, bfloat16, H2, 0, float_muladd_negate_product)
#undef DO_FMLA_IDX
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 962ffae3d6..b3dd3bffc3 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -370,16 +370,22 @@ USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4
SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2
SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4
+BFMLA_n1 11000001 011 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2
FMLA_n1_h 11000001 001 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2
FMLA_n1_s 11000001 001 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2
FMLA_n1_d 11000001 011 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2
+
+BFMLA_n1 11000001 011 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4
FMLA_n1_h 11000001 001 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4
FMLA_n1_s 11000001 001 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4
FMLA_n1_d 11000001 011 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4
+BFMLS_n1 11000001 011 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2
FMLS_n1_h 11000001 001 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2
FMLS_n1_s 11000001 001 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2
FMLS_n1_d 11000001 011 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2
+
+BFMLS_n1 11000001 011 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4
FMLS_n1_h 11000001 001 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4
FMLS_n1_s 11000001 001 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4
FMLS_n1_d 11000001 011 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4
@@ -484,16 +490,22 @@ UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4
USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4
USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4
+BFMLA_nn 11000001 111 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3
FMLA_nn_h 11000001 101 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3
FMLA_nn_s 11000001 101 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3
FMLA_nn_d 11000001 111 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3
+
+BFMLA_nn 11000001 111 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3
FMLA_nn_h 11000001 101 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3
FMLA_nn_s 11000001 101 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3
FMLA_nn_d 11000001 111 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3
+BFMLS_nn 11000001 111 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3
FMLS_nn_h 11000001 101 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3
FMLS_nn_s 11000001 101 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3
FMLS_nn_d 11000001 111 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3
+
+BFMLS_nn 11000001 111 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3
FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3
FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3
FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3
@@ -652,16 +664,22 @@ SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1
@azx_4x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \
&azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3
+BFMLA_nx 11000001 0001 .... 0 .. 1.. ....1 0 .... @azx_2x1_i3_o3
FMLA_nx_h 11000001 0001 .... 0 .. 1.. ....0 0 .... @azx_2x1_i3_o3
FMLA_nx_s 11000001 0101 .... 0 .. 0.. ....0 00 ... @azx_2x1_i2_o3
FMLA_nx_d 11000001 1101 .... 0 .. 00. ....0 00 ... @azx_2x1_i1_o3
+
+BFMLA_nx 11000001 0001 .... 1 .. 1.. ...01 0 .... @azx_4x1_i3_o3
FMLA_nx_h 11000001 0001 .... 1 .. 1.. ...00 0 .... @azx_4x1_i3_o3
FMLA_nx_s 11000001 0101 .... 1 .. 0.. ...00 00 ... @azx_4x1_i2_o3
FMLA_nx_d 11000001 1101 .... 1 .. 00. ...00 00 ... @azx_4x1_i1_o3
+BFMLS_nx 11000001 0001 .... 0 .. 1.. ....1 1 .... @azx_2x1_i3_o3
FMLS_nx_h 11000001 0001 .... 0 .. 1.. ....0 1 .... @azx_2x1_i3_o3
FMLS_nx_s 11000001 0101 .... 0 .. 0.. ....0 10 ... @azx_2x1_i2_o3
FMLS_nx_d 11000001 1101 .... 0 .. 00. ....0 10 ... @azx_2x1_i1_o3
+
+BFMLS_nx 11000001 0001 .... 1 .. 1.. ...01 1 .... @azx_4x1_i3_o3
FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3
FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3
FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 40/97] target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (38 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 39/97] target/arm: Implement SME2 BFMLA, BFMLS Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 9:51 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 41/97] target/arm: Implement SME2 ADD/SUB (array accumulator) Richard Henderson
` (56 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 2 ++
target/arm/tcg/translate-sme.c | 44 ++++++++++++++++++++++++++++++++++
target/arm/tcg/vec_helper.c | 2 ++
target/arm/tcg/sme.decode | 25 +++++++++++++++++++
4 files changed, 73 insertions(+)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index 37dd384659..392bf7b9b5 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -731,10 +731,12 @@ DEF_HELPER_FLAGS_4(gvec_fclt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfadd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(gvec_bfsub, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 3f9a80248a..664fdd86aa 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1072,6 +1072,50 @@ TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA,
s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx)
+static bool do_faddsub(DisasContext *s, arg_az_n *a, ARMFPStatusFlavour fpst,
+ gen_helper_gvec_3_ptr *fn)
+{
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int n = a->n;
+ int zm = a->zm;
+ int vstride = svl / n;
+ TCGv_ptr t_za = get_zarray(s, a->rv, a->off, n, 0);
+ TCGv_ptr ptr = fpstatus_ptr(fpst);
+ TCGv_ptr t = tcg_temp_new_ptr();
+
+ for (int r = 0; r < n; ++r) {
+ TCGv_ptr t_zm = vec_full_reg_ptr(s, zm + r);
+ int o_za = r * vstride * sizeof(ARMVectorReg);
+ int desc = simd_desc(svl, svl, 0);
+
+ tcg_gen_addi_ptr(t, t_za, o_za);
+ fn(t, t, t_zm, ptr, tcg_constant_i32(desc));
+ }
+ }
+ return true;
+}
+
+TRANS_FEAT(FADD_nn_h, aa64_sme_f16f16, do_faddsub, a,
+ FPST_ZA_F16, gen_helper_gvec_fadd_h)
+TRANS_FEAT(FSUB_nn_h, aa64_sme_f16f16, do_faddsub, a,
+ FPST_ZA_F16, gen_helper_gvec_fsub_h)
+
+TRANS_FEAT(FADD_nn_s, aa64_sme2, do_faddsub, a,
+ FPST_ZA, gen_helper_gvec_fadd_s)
+TRANS_FEAT(FSUB_nn_s, aa64_sme2, do_faddsub, a,
+ FPST_ZA, gen_helper_gvec_fsub_s)
+
+TRANS_FEAT(FADD_nn_d, aa64_sme2_f64f64, do_faddsub, a,
+ FPST_ZA, gen_helper_gvec_fadd_d)
+TRANS_FEAT(FSUB_nn_d, aa64_sme2_f64f64, do_faddsub, a,
+ FPST_ZA, gen_helper_gvec_fsub_d)
+
+TRANS_FEAT(BFADD_nn, aa64_sme_b16b16, do_faddsub, a,
+ FPST_ZA, gen_helper_gvec_bfadd)
+TRANS_FEAT(BFSUB_nn, aa64_sme_b16b16, do_faddsub, a,
+ FPST_ZA, gen_helper_gvec_bfsub)
+
/*
* Expand array multi-vector single (n1), array multi-vector (nn),
* and array multi-vector indexed (nx), for integer accumulate.
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index f4373dd4bf..e1ded43af7 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -1470,10 +1470,12 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, \
DO_3OP(gvec_fadd_h, float16_add, float16)
DO_3OP(gvec_fadd_s, float32_add, float32)
DO_3OP(gvec_fadd_d, float64_add, float64)
+DO_3OP(gvec_bfadd, bfloat16_add, bfloat16)
DO_3OP(gvec_fsub_h, float16_sub, float16)
DO_3OP(gvec_fsub_s, float32_sub, float32)
DO_3OP(gvec_fsub_d, float64_sub, float64)
+DO_3OP(gvec_bfsub, bfloat16_sub, bfloat16)
DO_3OP(gvec_fmul_h, float16_mul, float16)
DO_3OP(gvec_fmul_s, float32_mul, float32)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index b3dd3bffc3..0badc8f9fa 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -510,6 +510,31 @@ FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3
FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3
FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3
+&az_n n off rv zm
+@az_2x2_o3 ........ ... ..... . .. ... ..... .. off:3 \
+ &az_n n=2 rv=%mova_rv zm=%zn_ax2
+@az_4x4_o3 ........ ... ..... . .. ... ..... .. off:3 \
+ &az_n n=4 rv=%mova_rv zm=%zn_ax4
+
+FADD_nn_h 11000001 101 00100 0 .. 111 ....0 00 ... @az_2x2_o3
+FADD_nn_s 11000001 101 00000 0 .. 111 ....0 00 ... @az_2x2_o3
+FADD_nn_d 11000001 111 00000 0 .. 111 ....0 00 ... @az_2x2_o3
+FADD_nn_h 11000001 101 00101 0 .. 111 ...00 00 ... @az_4x4_o3
+FADD_nn_s 11000001 101 00001 0 .. 111 ...00 00 ... @az_4x4_o3
+FADD_nn_d 11000001 111 00001 0 .. 111 ...00 00 ... @az_4x4_o3
+
+FSUB_nn_h 11000001 101 00100 0 .. 111 ....0 01 ... @az_2x2_o3
+FSUB_nn_s 11000001 101 00000 0 .. 111 ....0 01 ... @az_2x2_o3
+FSUB_nn_d 11000001 111 00000 0 .. 111 ....0 01 ... @az_2x2_o3
+FSUB_nn_h 11000001 101 00101 0 .. 111 ...00 01 ... @az_4x4_o3
+FSUB_nn_s 11000001 101 00001 0 .. 111 ...00 01 ... @az_4x4_o3
+FSUB_nn_d 11000001 111 00001 0 .. 111 ...00 01 ... @az_4x4_o3
+
+BFADD_nn 11000001 111 00100 0 .. 111 ....0 00 ... @az_2x2_o3
+BFADD_nn 11000001 111 00101 0 .. 111 ...00 00 ... @az_4x4_o3
+BFSUB_nn 11000001 111 00100 0 .. 111 ....0 01 ... @az_2x2_o3
+BFSUB_nn 11000001 111 00101 0 .. 111 ...00 01 ... @az_4x4_o3
+
### SME2 Multi-vector Indexed
&azx_n n off rv zn zm idx
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 40/97] target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB
2025-07-02 12:33 ` [PATCH v3 40/97] target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB Richard Henderson
@ 2025-07-03 9:51 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 9:51 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper.h | 2 ++
> target/arm/tcg/translate-sme.c | 44 ++++++++++++++++++++++++++++++++++
> target/arm/tcg/vec_helper.c | 2 ++
> target/arm/tcg/sme.decode | 25 +++++++++++++++++++
> 4 files changed, 73 insertions(+)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 41/97] target/arm: Implement SME2 ADD/SUB (array accumulator)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (39 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 40/97] target/arm: Implement SME2 FADD, FSUB, BFADD, BFSUB Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:13 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 42/97] target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN Richard Henderson
` (55 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 28 ++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 12 ++++++++++++
2 files changed, 40 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 664fdd86aa..4c3b9aa7d6 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -806,6 +806,34 @@ TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var)
TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var)
TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var)
+/* Add/Sub each ZA[d*N] += Z[m*N] */
+static bool do_aaz(DisasContext *s, arg_az_n *a, int esz, GVecGen3FnVar *fn)
+{
+ TCGv_ptr t_za;
+ int svl, n;
+
+ if (!sme_smza_enabled_check(s)) {
+ return true;
+ }
+
+ n = a->n;
+ t_za = get_zarray(s, a->rv, a->off, n, 0);
+ svl = streaming_vec_reg_size(s);
+
+ for (int i = 0; i < n; ++i) {
+ int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+ int o_zm = vec_full_reg_offset(s, a->zm + i);
+
+ fn(esz, t_za, o_za, t_za, o_za, tcg_env, o_zm, svl, svl);
+ }
+ return true;
+}
+
+TRANS_FEAT(ADD_aaz_s, aa64_sme2, do_aaz, a, MO_32, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_aaz_s, aa64_sme2, do_aaz, a, MO_32, tcg_gen_gvec_sub_var)
+TRANS_FEAT(ADD_aaz_d, aa64_sme2_i16i64, do_aaz, a, MO_64, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_aaz_d, aa64_sme2_i16i64, do_aaz, a, MO_64, tcg_gen_gvec_sub_var)
+
/*
* Expand array multi-vector single (n1), array multi-vector (nn),
* and array multi-vector indexed (nx), for floating-point accumulate.
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 0badc8f9fa..22e2a68b1b 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -708,3 +708,15 @@ BFMLS_nx 11000001 0001 .... 1 .. 1.. ...01 1 .... @azx_4x1_i3_o3
FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3
FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3
FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3
+
+### SME2 Add / Sub array accumulators
+
+ADD_aaz_s 11000001 101 000000 .. 111 ....0 10 ... @az_2x2_o3
+ADD_aaz_s 11000001 101 000010 .. 111 ...00 10 ... @az_4x4_o3
+ADD_aaz_d 11000001 111 000000 .. 111 ....0 10 ... @az_2x2_o3
+ADD_aaz_d 11000001 111 000010 .. 111 ...00 10 ... @az_4x4_o3
+
+SUB_aaz_s 11000001 101 000000 .. 111 ....0 11 ... @az_2x2_o3
+SUB_aaz_s 11000001 101 000010 .. 111 ...00 11 ... @az_4x4_o3
+SUB_aaz_d 11000001 111 000000 .. 111 ....0 11 ... @az_2x2_o3
+SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 42/97] target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (40 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 41/97] target/arm: Implement SME2 ADD/SUB (array accumulator) Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:13 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 43/97] target/arm: Implement SME2 FCVT (widening), FCVTL Richard Henderson
` (54 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 5 +++
target/arm/tcg/vec_internal.h | 2 +
target/arm/tcg/sme_helper.c | 74 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sve_helper.c | 2 +-
target/arm/tcg/translate-sme.c | 25 ++++++++++++
target/arm/tcg/sme.decode | 12 ++++++
6 files changed, 119 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 0bb8af194b..97e70959e8 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -212,3 +212,8 @@ DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr,
DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_bfcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index 64a7249d01..c8199a3ef8 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -306,4 +306,6 @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah)
bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst);
bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
+float16 sve_f32_to_f16(float32 f, float_status *fpst);
+
#endif /* TARGET_ARM_VEC_INTERNAL_H */
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 0f79d7cb6e..d97afdb69c 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1517,3 +1517,77 @@ DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +)
DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +)
#undef DO_MLALL_IDX
+
+/* Convert and compress */
+void HELPER(sme2_bfcvt)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ ARMVectorReg scratch;
+ size_t oprsz = simd_oprsz(desc);
+ size_t i, n = oprsz / 4;
+ float32 *s0 = vs;
+ float32 *s1 = vs + sizeof(ARMVectorReg);
+ bfloat16 *d = vd;
+
+ if (vd == s1) {
+ s1 = memcpy(&scratch, s1, oprsz);
+ }
+
+ for (i = 0; i < n; ++i) {
+ d[H2(i)] = float32_to_bfloat16(s0[H4(i)], fpst);
+ }
+ for (i = 0; i < n; ++i) {
+ d[H2(i) + n] = float32_to_bfloat16(s1[H4(i)], fpst);
+ }
+}
+
+void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ ARMVectorReg scratch;
+ size_t oprsz = simd_oprsz(desc);
+ size_t i, n = oprsz / 4;
+ float32 *s0 = vs;
+ float32 *s1 = vs + sizeof(ARMVectorReg);
+ float16 *d = vd;
+
+ if (vd == s1) {
+ s1 = memcpy(&scratch, s1, oprsz);
+ }
+
+ for (i = 0; i < n; ++i) {
+ d[H2(i)] = sve_f32_to_f16(s0[H4(i)], fpst);
+ }
+ for (i = 0; i < n; ++i) {
+ d[H2(i) + n] = sve_f32_to_f16(s1[H4(i)], fpst);
+ }
+}
+
+/* Convert and interleave */
+void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ size_t i, n = simd_oprsz(desc) / 4;
+ float32 *s0 = vs;
+ float32 *s1 = vs + sizeof(ARMVectorReg);
+ bfloat16 *d = vd;
+
+ for (i = 0; i < n; ++i) {
+ bfloat16 d0 = float32_to_bfloat16(s0[H4(i)], fpst);
+ bfloat16 d1 = float32_to_bfloat16(s1[H4(i)], fpst);
+ d[H2(i * 2 + 0)] = d0;
+ d[H2(i * 2 + 1)] = d1;
+ }
+}
+
+void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ size_t i, n = simd_oprsz(desc) / 4;
+ float32 *s0 = vs;
+ float32 *s1 = vs + sizeof(ARMVectorReg);
+ bfloat16 *d = vd;
+
+ for (i = 0; i < n; ++i) {
+ bfloat16 d0 = sve_f32_to_f16(s0[H4(i)], fpst);
+ bfloat16 d1 = sve_f32_to_f16(s1[H4(i)], fpst);
+ d[H2(i * 2 + 0)] = d0;
+ d[H2(i * 2 + 1)] = d1;
+ }
+}
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index a2c363a4e1..b522ddaf7c 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4576,7 +4576,7 @@ static inline float64 sve_f16_to_f64(float16 f, float_status *fpst)
return ret;
}
-static inline float16 sve_f32_to_f16(float32 f, float_status *fpst)
+float16 sve_f32_to_f16(float32 f, float_status *fpst)
{
bool save = get_flush_to_zero(fpst);
float16 ret;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 4c3b9aa7d6..10e5b77040 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1335,3 +1335,28 @@ TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlal
TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d)
TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d)
TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d)
+
+static bool do_zz_fpst(DisasContext *s, arg_zz_n *a, int data,
+ ARMFPStatusFlavour type, gen_helper_gvec_2_ptr *fn)
+{
+ if (sme_sm_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ TCGv_ptr fpst = fpstatus_ptr(type);
+
+ for (int i = 0, n = a->n; i < n; ++i) {
+ tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd + i),
+ vec_full_reg_offset(s, a->zn + i),
+ fpst, svl, svl, data, fn);
+ }
+ }
+ return true;
+}
+
+TRANS_FEAT(BFCVT, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_sme2_bfcvt)
+TRANS_FEAT(BFCVTN, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_sme2_bfcvtn)
+TRANS_FEAT(FCVT_n, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_sme2_fcvt_n)
+TRANS_FEAT(FCVTN, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_sme2_fcvtn)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 22e2a68b1b..831179c0ee 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -720,3 +720,15 @@ SUB_aaz_s 11000001 101 000000 .. 111 ....0 11 ... @az_2x2_o3
SUB_aaz_s 11000001 101 000010 .. 111 ...00 11 ... @az_4x4_o3
SUB_aaz_d 11000001 111 000000 .. 111 ....0 11 ... @az_2x2_o3
SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
+
+### SME2 Multi-vector SVE Constructive Unary
+
+&zz_n zd zn n
+@zz_1x2 ........ ... ..... ...... ..... zd:5 \
+ &zz_n n=1 zn=%zn_ax2
+
+BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2
+BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2
+
+FCVT_n 11000001 001 00000 111000 ....0 ..... @zz_1x2
+FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 42/97] target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN
2025-07-02 12:33 ` [PATCH v3 42/97] target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN Richard Henderson
@ 2025-07-03 10:13 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:13 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 5 +++
> target/arm/tcg/vec_internal.h | 2 +
> target/arm/tcg/sme_helper.c | 74 ++++++++++++++++++++++++++++++++++
> target/arm/tcg/sve_helper.c | 2 +-
> target/arm/tcg/translate-sme.c | 25 ++++++++++++
> target/arm/tcg/sme.decode | 12 ++++++
> 6 files changed, 119 insertions(+), 1 deletion(-)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 43/97] target/arm: Implement SME2 FCVT (widening), FCVTL
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (41 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 42/97] target/arm: Implement SME2 BFCVT, BFCVTN, FCVT, FCVTN Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:14 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 44/97] target/arm: Implement SME2 FCVTZS, FCVTZU Richard Henderson
` (53 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 2 ++
target/arm/tcg/vec_internal.h | 1 +
target/arm/tcg/sme_helper.c | 38 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sve_helper.c | 2 +-
target/arm/tcg/translate-sme.c | 5 +++++
target/arm/tcg/sme.decode | 5 +++++
6 files changed, 52 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 97e70959e8..be4621f2d9 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -217,3 +217,5 @@ DEF_HELPER_FLAGS_4(sme2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_bfcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index c8199a3ef8..bbf76f63b1 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -306,6 +306,7 @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah)
bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst);
bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
+float32 sve_f16_to_f32(float16 f, float_status *fpst);
float16 sve_f32_to_f16(float32 f, float_status *fpst);
#endif /* TARGET_ARM_VEC_INTERNAL_H */
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index d97afdb69c..b0e1fe845b 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1591,3 +1591,41 @@ void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
d[H2(i * 2 + 1)] = d1;
}
}
+
+/* Expand and convert */
+void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ ARMVectorReg scratch;
+ size_t oprsz = simd_oprsz(desc);
+ size_t i, n = oprsz / 4;
+ float16 *s = vs;
+ float32 *d0 = vd;
+ float32 *d1 = vd + sizeof(ARMVectorReg);
+
+ if (vd == vs) {
+ s = memcpy(&scratch, s, oprsz);
+ }
+
+ for (i = 0; i < n; ++i) {
+ d0[H4(i)] = sve_f16_to_f32(s[H2(i)], fpst);
+ }
+ for (i = 0; i < n; ++i) {
+ d1[H4(i)] = sve_f16_to_f32(s[H2(n + i)], fpst);
+ }
+}
+
+/* Deinterleave and convert. */
+void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ size_t i, n = simd_oprsz(desc) / 4;
+ float16 *s = vs;
+ float32 *d0 = vd;
+ float32 *d1 = vd + sizeof(ARMVectorReg);
+
+ for (i = 0; i < n; ++i) {
+ float32 v0 = sve_f16_to_f32(s[H2(i * 2 + 0)], fpst);
+ float32 v1 = sve_f16_to_f32(s[H2(i * 2 + 1)], fpst);
+ d0[H4(i)] = v0;
+ d1[H4(i)] = v1;
+ }
+}
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index b522ddaf7c..4f12723afe 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4554,7 +4554,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, \
* FZ16. When converting from fp16, this affects flushing input denormals;
* when converting to fp16, this affects flushing output denormals.
*/
-static inline float32 sve_f16_to_f32(float16 f, float_status *fpst)
+float32 sve_f16_to_f32(float16 f, float_status *fpst)
{
bool save = get_flush_inputs_to_zero(fpst);
float32 ret;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 10e5b77040..d6167eafe1 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1360,3 +1360,8 @@ TRANS_FEAT(FCVT_n, aa64_sme2, do_zz_fpst, a, 0,
FPST_A64, gen_helper_sme2_fcvt_n)
TRANS_FEAT(FCVTN, aa64_sme2, do_zz_fpst, a, 0,
FPST_A64, gen_helper_sme2_fcvtn)
+
+TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0,
+ FPST_A64_F16, gen_helper_sme2_fcvt_w)
+TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0,
+ FPST_A64_F16, gen_helper_sme2_fcvtl)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 831179c0ee..5100ebaeba 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -726,9 +726,14 @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
&zz_n zd zn n
@zz_1x2 ........ ... ..... ...... ..... zd:5 \
&zz_n n=1 zn=%zn_ax2
+@zz_2x1 ........ ... ..... ...... zn:5 ..... \
+ &zz_n n=1 zd=%zd_ax2
BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2
BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2
FCVT_n 11000001 001 00000 111000 ....0 ..... @zz_1x2
FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2
+
+FCVT_w 11000001 101 00000 111000 ..... ....0 @zz_2x1
+FCVTL 11000001 101 00000 111000 ..... ....1 @zz_2x1
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 43/97] target/arm: Implement SME2 FCVT (widening), FCVTL
2025-07-02 12:33 ` [PATCH v3 43/97] target/arm: Implement SME2 FCVT (widening), FCVTL Richard Henderson
@ 2025-07-03 10:14 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:14 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 2 ++
> target/arm/tcg/vec_internal.h | 1 +
> target/arm/tcg/sme_helper.c | 38 ++++++++++++++++++++++++++++++++++
> target/arm/tcg/sve_helper.c | 2 +-
> target/arm/tcg/translate-sme.c | 5 +++++
> target/arm/tcg/sme.decode | 5 +++++
> 6 files changed, 52 insertions(+), 1 deletion(-)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 44/97] target/arm: Implement SME2 FCVTZS, FCVTZU
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (42 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 43/97] target/arm: Implement SME2 FCVT (widening), FCVTL Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:14 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 45/97] target/arm: Implement SME2 SCVTF, UCVTF Richard Henderson
` (52 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 5 +++++
target/arm/tcg/sme.decode | 9 +++++++++
2 files changed, 14 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index d6167eafe1..3bf2b6935f 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1365,3 +1365,8 @@ TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0,
FPST_A64_F16, gen_helper_sme2_fcvt_w)
TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0,
FPST_A64_F16, gen_helper_sme2_fcvtl)
+
+TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_gvec_vcvt_rz_fs)
+TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_gvec_vcvt_rz_fu)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 5100ebaeba..79df2dcd2b 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -728,6 +728,10 @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
&zz_n n=1 zn=%zn_ax2
@zz_2x1 ........ ... ..... ...... zn:5 ..... \
&zz_n n=1 zd=%zd_ax2
+@zz_2x2 ........ ... ..... ...... .... . ..... \
+ &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2
+@zz_4x4 ........ ... ..... ...... .... . ..... \
+ &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4
BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2
BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2
@@ -737,3 +741,8 @@ FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2
FCVT_w 11000001 101 00000 111000 ..... ....0 @zz_2x1
FCVTL 11000001 101 00000 111000 ..... ....1 @zz_2x1
+
+FCVTZS 11000001 001 00001 111000 ....0 ....0 @zz_2x2
+FCVTZS 11000001 001 10001 111000 ...00 ...00 @zz_4x4
+FCVTZU 11000001 001 00001 111000 ....1 ....0 @zz_2x2
+FCVTZU 11000001 001 10001 111000 ...01 ...00 @zz_4x4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 45/97] target/arm: Implement SME2 SCVTF, UCVTF
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (43 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 44/97] target/arm: Implement SME2 FCVTZS, FCVTZU Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:14 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 46/97] target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA Richard Henderson
` (51 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 2 ++
target/arm/tcg/sme_helper.c | 22 ++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 5 +++++
target/arm/tcg/sme.decode | 5 +++++
4 files changed, 34 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index be4621f2d9..6314ad7e01 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -219,3 +219,5 @@ DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_scvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_4(sme2_ucvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index b0e1fe845b..d69d57c4cb 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1629,3 +1629,25 @@ void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc)
d1[H4(i)] = v1;
}
}
+
+void HELPER(sme2_scvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ size_t i, n = simd_oprsz(desc) / 4;
+ int32_t *d = vd;
+ float32 *s = vs;
+
+ for (i = 0; i < n; ++i) {
+ d[i] = int32_to_float32(s[i], fpst);
+ }
+}
+
+void HELPER(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc)
+{
+ size_t i, n = simd_oprsz(desc) / 4;
+ uint32_t *d = vd;
+ float32 *s = vs;
+
+ for (i = 0; i < n; ++i) {
+ d[i] = uint32_to_float32(s[i], fpst);
+ }
+}
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 3bf2b6935f..dce3b56de2 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1370,3 +1370,8 @@ TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0,
FPST_A64, gen_helper_gvec_vcvt_rz_fs)
TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0,
FPST_A64, gen_helper_gvec_vcvt_rz_fu)
+
+TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_sme2_scvtf)
+TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0,
+ FPST_A64, gen_helper_sme2_ucvtf)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 79df2dcd2b..449d97bd28 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -746,3 +746,8 @@ FCVTZS 11000001 001 00001 111000 ....0 ....0 @zz_2x2
FCVTZS 11000001 001 10001 111000 ...00 ...00 @zz_4x4
FCVTZU 11000001 001 00001 111000 ....1 ....0 @zz_2x2
FCVTZU 11000001 001 10001 111000 ...01 ...00 @zz_4x4
+
+SCVTF 11000001 001 00010 111000 ....0 ....0 @zz_2x2
+SCVTF 11000001 001 10010 111000 ...00 ...00 @zz_4x4
+UCVTF 11000001 001 00010 111000 ....1 ....0 @zz_2x2
+UCVTF 11000001 001 10010 111000 ...01 ...00 @zz_4x4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 46/97] target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (44 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 45/97] target/arm: Implement SME2 SCVTF, UCVTF Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:14 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 47/97] target/arm: Introduce do_[us]sat_[bhs] macros Richard Henderson
` (50 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 9 +++++++++
target/arm/tcg/sme.decode | 9 +++++++++
2 files changed, 18 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index dce3b56de2..4fbc61ae27 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1375,3 +1375,12 @@ TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0,
FPST_A64, gen_helper_sme2_scvtf)
TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0,
FPST_A64, gen_helper_sme2_ucvtf)
+
+TRANS_FEAT(FRINTN, aa64_sme2, do_zz_fpst, a, float_round_nearest_even,
+ FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTP, aa64_sme2, do_zz_fpst, a, float_round_up,
+ FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down,
+ FPST_A64, gen_helper_gvec_vrint_rm_s)
+TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away,
+ FPST_A64, gen_helper_gvec_vrint_rm_s)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 449d97bd28..9cc25622d4 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -751,3 +751,12 @@ SCVTF 11000001 001 00010 111000 ....0 ....0 @zz_2x2
SCVTF 11000001 001 10010 111000 ...00 ...00 @zz_4x4
UCVTF 11000001 001 00010 111000 ....1 ....0 @zz_2x2
UCVTF 11000001 001 10010 111000 ...01 ...00 @zz_4x4
+
+FRINTN 11000001 101 01000 111000 ....0 ....0 @zz_2x2
+FRINTN 11000001 101 11000 111000 ...00 ...00 @zz_4x4
+FRINTP 11000001 101 01001 111000 ....0 ....0 @zz_2x2
+FRINTP 11000001 101 11001 111000 ...00 ...00 @zz_4x4
+FRINTM 11000001 101 01010 111000 ....0 ....0 @zz_2x2
+FRINTM 11000001 101 11010 111000 ...00 ...00 @zz_4x4
+FRINTA 11000001 101 01100 111000 ....0 ....0 @zz_2x2
+FRINTA 11000001 101 11100 111000 ...00 ...00 @zz_4x4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 46/97] target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA
2025-07-02 12:33 ` [PATCH v3 46/97] target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA Richard Henderson
@ 2025-07-03 10:14 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:14 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/translate-sme.c | 9 +++++++++
> target/arm/tcg/sme.decode | 9 +++++++++
> 2 files changed, 18 insertions(+)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 47/97] target/arm: Introduce do_[us]sat_[bhs] macros
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (45 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 46/97] target/arm: Implement SME2 FRINTN, FRINTP, FRINTM, FRINTA Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:15 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 48/97] target/arm: Use do_[us]sat_[bhs] in sve_helper.c Richard Henderson
` (49 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Inputs are a wider type of indeterminate sign.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/vec_internal.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index bbf76f63b1..a1c10c60a1 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -223,6 +223,13 @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *);
int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *);
int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool);
+#define do_ssat_b(val) MIN(MAX(val, INT8_MIN), INT8_MAX)
+#define do_ssat_h(val) MIN(MAX(val, INT16_MIN), INT16_MAX)
+#define do_ssat_s(val) MIN(MAX(val, INT32_MIN), INT32_MAX)
+#define do_usat_b(val) MIN(MAX(val, 0), UINT8_MAX)
+#define do_usat_h(val) MIN(MAX(val, 0), UINT16_MAX)
+#define do_usat_s(val) MIN(MAX(val, 0), UINT32_MAX)
+
/**
* bfdotadd:
* @sum: addend
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 48/97] target/arm: Use do_[us]sat_[bhs] in sve_helper.c
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (46 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 47/97] target/arm: Introduce do_[us]sat_[bhs] macros Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:15 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 49/97] target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU Richard Henderson
` (48 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Replace and remove do_sat_bhs.
This avoids multiple repetitions of INT*_MIN/MAX.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_helper.c | 116 +++++++++++++++---------------------
1 file changed, 48 insertions(+), 68 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 4f12723afe..f9052f2164 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -527,14 +527,9 @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS)
DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS)
DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D)
-static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max)
-{
- return val >= max ? max : val <= min ? min : val;
-}
-
-#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX)
-#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX)
-#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX)
+#define DO_SQADD_B(n, m) do_ssat_b((int64_t)n + m)
+#define DO_SQADD_H(n, m) do_ssat_h((int64_t)n + m)
+#define DO_SQADD_S(n, m) do_ssat_s((int64_t)n + m)
static inline int64_t do_sqadd_d(int64_t n, int64_t m)
{
@@ -551,9 +546,9 @@ DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H)
DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S)
DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d)
-#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX)
-#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX)
-#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX)
+#define DO_UQADD_B(n, m) do_usat_b((int64_t)n + m)
+#define DO_UQADD_H(n, m) do_usat_h((int64_t)n + m)
+#define DO_UQADD_S(n, m) do_usat_s((int64_t)n + m)
static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m)
{
@@ -566,9 +561,9 @@ DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H)
DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S)
DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d)
-#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX)
-#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX)
-#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX)
+#define DO_SQSUB_B(n, m) do_ssat_b((int64_t)n - m)
+#define DO_SQSUB_H(n, m) do_ssat_h((int64_t)n - m)
+#define DO_SQSUB_S(n, m) do_ssat_s((int64_t)n - m)
static inline int64_t do_sqsub_d(int64_t n, int64_t m)
{
@@ -585,9 +580,9 @@ DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H)
DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S)
DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d)
-#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX)
-#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX)
-#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX)
+#define DO_UQSUB_B(n, m) do_usat_b((int64_t)n - m)
+#define DO_UQSUB_H(n, m) do_usat_h((int64_t)n - m)
+#define DO_UQSUB_S(n, m) do_usat_s((int64_t)n - m)
static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m)
{
@@ -599,12 +594,9 @@ DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H)
DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S)
DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d)
-#define DO_SUQADD_B(n, m) \
- do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX)
-#define DO_SUQADD_H(n, m) \
- do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX)
-#define DO_SUQADD_S(n, m) \
- do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX)
+#define DO_SUQADD_B(n, m) do_ssat_b((int64_t)(int8_t)n + m)
+#define DO_SUQADD_H(n, m) do_ssat_h((int64_t)(int16_t)n + m)
+#define DO_SUQADD_S(n, m) do_ssat_s((int64_t)(int32_t)n + m)
static inline int64_t do_suqadd_d(int64_t n, uint64_t m)
{
@@ -634,12 +626,9 @@ DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H)
DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S)
DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d)
-#define DO_USQADD_B(n, m) \
- do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX)
-#define DO_USQADD_H(n, m) \
- do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX)
-#define DO_USQADD_S(n, m) \
- do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX)
+#define DO_USQADD_B(n, m) do_usat_b((int64_t)n + (int8_t)m)
+#define DO_USQADD_H(n, m) do_usat_h((int64_t)n + (int16_t)m)
+#define DO_USQADD_S(n, m) do_usat_s((int64_t)n + (int32_t)m)
static inline uint64_t do_usqadd_d(uint64_t n, int64_t m)
{
@@ -1226,37 +1215,29 @@ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \
} \
}
-#define DO_SQXTN_H(n) do_sat_bhs(n, INT8_MIN, INT8_MAX)
-#define DO_SQXTN_S(n) do_sat_bhs(n, INT16_MIN, INT16_MAX)
-#define DO_SQXTN_D(n) do_sat_bhs(n, INT32_MIN, INT32_MAX)
+DO_XTNB(sve2_sqxtnb_h, int16_t, do_ssat_b)
+DO_XTNB(sve2_sqxtnb_s, int32_t, do_ssat_h)
+DO_XTNB(sve2_sqxtnb_d, int64_t, do_ssat_s)
-DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H)
-DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S)
-DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D)
+DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, do_ssat_b)
+DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, do_ssat_h)
+DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, do_ssat_s)
-DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H)
-DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S)
-DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D)
+DO_XTNB(sve2_uqxtnb_h, uint16_t, do_usat_b)
+DO_XTNB(sve2_uqxtnb_s, uint32_t, do_usat_h)
+DO_XTNB(sve2_uqxtnb_d, uint64_t, do_usat_s)
-#define DO_UQXTN_H(n) do_sat_bhs(n, 0, UINT8_MAX)
-#define DO_UQXTN_S(n) do_sat_bhs(n, 0, UINT16_MAX)
-#define DO_UQXTN_D(n) do_sat_bhs(n, 0, UINT32_MAX)
+DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, do_usat_b)
+DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, do_usat_h)
+DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, do_usat_s)
-DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H)
-DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S)
-DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D)
+DO_XTNB(sve2_sqxtunb_h, int16_t, do_usat_b)
+DO_XTNB(sve2_sqxtunb_s, int32_t, do_usat_h)
+DO_XTNB(sve2_sqxtunb_d, int64_t, do_usat_s)
-DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H)
-DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S)
-DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D)
-
-DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H)
-DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S)
-DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D)
-
-DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H)
-DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S)
-DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D)
+DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, do_usat_b)
+DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, do_usat_h)
+DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, do_usat_s)
#undef DO_XTNB
#undef DO_XTNT
@@ -2187,10 +2168,9 @@ DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr)
DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr)
DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, H1_8, H1_4, do_urshr)
-#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX)
-#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX)
-#define DO_SQSHRUN_D(x, sh) \
- do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX)
+#define DO_SQSHRUN_H(x, sh) do_usat_b((int64_t)(x) >> sh)
+#define DO_SQSHRUN_S(x, sh) do_usat_h((int64_t)(x) >> sh)
+#define DO_SQSHRUN_D(x, sh) do_usat_s((int64_t)(x) >> (sh < 64 ? sh : 63))
DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H)
DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S)
@@ -2200,9 +2180,9 @@ DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H)
DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S)
DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRUN_D)
-#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX)
-#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX)
-#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX)
+#define DO_SQRSHRUN_H(x, sh) do_usat_b(do_srshr(x, sh))
+#define DO_SQRSHRUN_S(x, sh) do_usat_h(do_srshr(x, sh))
+#define DO_SQRSHRUN_D(x, sh) do_usat_s(do_srshr(x, sh))
DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H)
DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S)
@@ -2212,9 +2192,9 @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H)
DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S)
DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQRSHRUN_D)
-#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX)
-#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX)
-#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX)
+#define DO_SQSHRN_H(x, sh) do_ssat_b(x >> sh)
+#define DO_SQSHRN_S(x, sh) do_ssat_h(x >> sh)
+#define DO_SQSHRN_D(x, sh) do_ssat_s(x >> sh)
DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H)
DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S)
@@ -2224,9 +2204,9 @@ DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H)
DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S)
DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRN_D)
-#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX)
-#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX)
-#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX)
+#define DO_SQRSHRN_H(x, sh) do_ssat_b(do_srshr(x, sh))
+#define DO_SQRSHRN_S(x, sh) do_ssat_h(do_srshr(x, sh))
+#define DO_SQRSHRN_D(x, sh) do_ssat_s(do_srshr(x, sh))
DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H)
DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 49/97] target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (47 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 48/97] target/arm: Use do_[us]sat_[bhs] in sve_helper.c Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:20 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 50/97] target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1 Richard Henderson
` (47 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 20 ++++++
target/arm/tcg/sme_helper.c | 116 +++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 35 ++++++++++
target/arm/tcg/sme.decode | 22 +++++++
4 files changed, 193 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 6314ad7e01..792b993695 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -221,3 +221,23 @@ DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_scvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_4(sme2_ucvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_3(sme2_sqcvt_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqcvt_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtu_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtu_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvt_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqcvt_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtu_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_sqcvtn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqcvtn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqcvtn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqcvtun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index d69d57c4cb..906d369d37 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1561,6 +1561,64 @@ void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc)
}
}
+#define SQCVT2(NAME, TW, TN, HW, HN, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(i)] = SAT(s0[HW(i)]); \
+ d[HN(i) + n] = SAT(s1[HW(i)]); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQCVT2(sme2_sqcvt_sh, int32_t, int16_t, H4, H2, do_ssat_h)
+SQCVT2(sme2_uqcvt_sh, uint32_t, uint16_t, H4, H2, do_usat_h)
+SQCVT2(sme2_sqcvtu_sh, int32_t, uint16_t, H4, H2, do_usat_h)
+
+#undef SQCVT2
+
+#define SQCVT4(NAME, TW, TN, HW, HN, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TW *s2 = vs + 2 * sizeof(ARMVectorReg); \
+ TW *s3 = vs + 3 * sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 4 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(i)] = SAT(s0[HW(i)]); \
+ d[HN(i) + n] = SAT(s1[HW(i)]); \
+ d[HN(i) + 2 * n] = SAT(s2[HW(i)]); \
+ d[HN(i) + 3 * n] = SAT(s3[HW(i)]); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQCVT4(sme2_sqcvt_sb, int32_t, int8_t, H4, H2, do_ssat_b)
+SQCVT4(sme2_uqcvt_sb, uint32_t, uint8_t, H4, H2, do_usat_b)
+SQCVT4(sme2_sqcvtu_sb, int32_t, uint8_t, H4, H2, do_usat_b)
+
+SQCVT4(sme2_sqcvt_dh, int64_t, int16_t, H8, H2, do_ssat_h)
+SQCVT4(sme2_uqcvt_dh, uint64_t, uint16_t, H8, H2, do_usat_h)
+SQCVT4(sme2_sqcvtu_dh, int64_t, uint16_t, H8, H2, do_usat_h)
+
+#undef SQCVT4
+
/* Convert and interleave */
void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
{
@@ -1592,6 +1650,64 @@ void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
}
}
+#define SQCVTN2(NAME, TW, TN, HW, HN, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(2 * i + 0)] = SAT(s0[HW(i)]); \
+ d[HN(2 * i + 1)] = SAT(s1[HW(i)]); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQCVTN2(sme2_sqcvtn_sh, int32_t, int16_t, H4, H2, do_ssat_h)
+SQCVTN2(sme2_uqcvtn_sh, uint32_t, uint16_t, H4, H2, do_usat_h)
+SQCVTN2(sme2_sqcvtun_sh, int32_t, uint16_t, H4, H2, do_usat_h)
+
+#undef SQCVTN2
+
+#define SQCVTN4(NAME, TW, TN, HW, HN, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TW *s2 = vs + 2 * sizeof(ARMVectorReg); \
+ TW *s3 = vs + 3 * sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 4 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(4 * i + 0)] = SAT(s0[HW(i)]); \
+ d[HN(4 * i + 1)] = SAT(s1[HW(i)]); \
+ d[HN(4 * i + 2)] = SAT(s2[HW(i)]); \
+ d[HN(4 * i + 3)] = SAT(s3[HW(i)]); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQCVTN4(sme2_sqcvtn_sb, int32_t, int8_t, H4, H1, do_ssat_b)
+SQCVTN4(sme2_uqcvtn_sb, uint32_t, uint8_t, H4, H1, do_usat_b)
+SQCVTN4(sme2_sqcvtun_sb, int32_t, uint8_t, H4, H1, do_usat_b)
+
+SQCVTN4(sme2_sqcvtn_dh, int64_t, int16_t, H8, H2, do_ssat_h)
+SQCVTN4(sme2_uqcvtn_dh, uint64_t, uint16_t, H8, H2, do_usat_h)
+SQCVTN4(sme2_sqcvtun_dh, int64_t, uint16_t, H8, H2, do_usat_h)
+
+#undef SQCVTN4
+
/* Expand and convert */
void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc)
{
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 4fbc61ae27..dd1a6668fb 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1384,3 +1384,38 @@ TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down,
FPST_A64, gen_helper_gvec_vrint_rm_s)
TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away,
FPST_A64, gen_helper_gvec_vrint_rm_s)
+
+static bool do_zz(DisasContext *s, arg_zz_n *a, int data,
+ gen_helper_gvec_2 *fn)
+{
+ if (sme_sm_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+
+ for (int i = 0, n = a->n; i < n; ++i) {
+ tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd + i),
+ vec_full_reg_offset(s, a->zn + i),
+ svl, svl, data, fn);
+ }
+ }
+ return true;
+}
+
+TRANS_FEAT(SQCVT_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_sh)
+TRANS_FEAT(UQCVT_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_sh)
+TRANS_FEAT(SQCVTU_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_sh)
+
+TRANS_FEAT(SQCVT_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_sb)
+TRANS_FEAT(UQCVT_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_sb)
+TRANS_FEAT(SQCVTU_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_sb)
+
+TRANS_FEAT(SQCVT_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_dh)
+TRANS_FEAT(UQCVT_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_dh)
+TRANS_FEAT(SQCVTU_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_dh)
+
+TRANS_FEAT(SQCVTN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_sb)
+TRANS_FEAT(UQCVTN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_sb)
+TRANS_FEAT(SQCVTUN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_sb)
+
+TRANS_FEAT(SQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_dh)
+TRANS_FEAT(UQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_dh)
+TRANS_FEAT(SQCVTUN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_dh)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 9cc25622d4..e005f6e6ed 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -726,6 +726,8 @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
&zz_n zd zn n
@zz_1x2 ........ ... ..... ...... ..... zd:5 \
&zz_n n=1 zn=%zn_ax2
+@zz_1x4 ........ ... ..... ...... ..... zd:5 \
+ &zz_n n=1 zn=%zn_ax4
@zz_2x1 ........ ... ..... ...... zn:5 ..... \
&zz_n n=1 zd=%zd_ax2
@zz_2x2 ........ ... ..... ...... .... . ..... \
@@ -760,3 +762,23 @@ FRINTM 11000001 101 01010 111000 ....0 ....0 @zz_2x2
FRINTM 11000001 101 11010 111000 ...00 ...00 @zz_4x4
FRINTA 11000001 101 01100 111000 ....0 ....0 @zz_2x2
FRINTA 11000001 101 11100 111000 ...00 ...00 @zz_4x4
+
+SQCVT_sh 11000001 001 00011 111000 ....0 ..... @zz_1x2
+UQCVT_sh 11000001 001 00011 111000 ....1 ..... @zz_1x2
+SQCVTU_sh 11000001 011 00011 111000 ....0 ..... @zz_1x2
+
+SQCVT_sb 11000001 001 10011 111000 ...00 ..... @zz_1x4
+UQCVT_sb 11000001 001 10011 111000 ...01 ..... @zz_1x4
+SQCVTU_sb 11000001 011 10011 111000 ...00 ..... @zz_1x4
+
+SQCVT_dh 11000001 101 10011 111000 ...00 ..... @zz_1x4
+UQCVT_dh 11000001 101 10011 111000 ...01 ..... @zz_1x4
+SQCVTU_dh 11000001 111 10011 111000 ...00 ..... @zz_1x4
+
+SQCVTN_sb 11000001 001 10011 111000 ...10 ..... @zz_1x4
+UQCVTN_sb 11000001 001 10011 111000 ...11 ..... @zz_1x4
+SQCVTUN_sb 11000001 011 10011 111000 ...10 ..... @zz_1x4
+
+SQCVTN_dh 11000001 101 10011 111000 ...10 ..... @zz_1x4
+UQCVTN_dh 11000001 101 10011 111000 ...11 ..... @zz_1x4
+SQCVTUN_dh 11000001 111 10011 111000 ...10 ..... @zz_1x4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 49/97] target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU
2025-07-02 12:33 ` [PATCH v3 49/97] target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU Richard Henderson
@ 2025-07-03 10:20 ` Peter Maydell
2025-07-03 15:53 ` Richard Henderson
0 siblings, 1 reply; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:20 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 20 ++++++
> target/arm/tcg/sme_helper.c | 116 +++++++++++++++++++++++++++++++++
> target/arm/tcg/translate-sme.c | 35 ++++++++++
> target/arm/tcg/sme.decode | 22 +++++++
> 4 files changed, 193 insertions(+)
> index d69d57c4cb..906d369d37 100644
> --- a/target/arm/tcg/sme_helper.c
> +++ b/target/arm/tcg/sme_helper.c
> @@ -1561,6 +1561,64 @@ void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc)
> }
> }
>
> +#define SQCVT2(NAME, TW, TN, HW, HN, SAT) \
> +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
> +{ \
> + ARMVectorReg scratch; \
> + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
> + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
> + TN *d = vd; \
> + if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
Does this do the right thing if Vd is less than Vs?
Pointer differences are signed, I think, so for eg vd == 0
vs == 16 we unnecessarily use the scratch reg.
Maybe clearer to write
(vd >= vs && vd < (vs + 2 * sizeof(..))
(Similarly for other use of this condition later in the patch.)
> + d = (TN *)&scratch; \
> + } \
> + for (size_t i = 0; i < n; ++i) { \
> + d[HN(i)] = SAT(s0[HW(i)]); \
> + d[HN(i) + n] = SAT(s1[HW(i)]); \
Should this be HN(i + n) ?
> + } \
> + if (d != vd) { \
> + memcpy(vd, d, oprsz); \
> + } \
> +}
> +
> +SQCVT2(sme2_sqcvt_sh, int32_t, int16_t, H4, H2, do_ssat_h)
> +SQCVT2(sme2_uqcvt_sh, uint32_t, uint16_t, H4, H2, do_usat_h)
> +SQCVT2(sme2_sqcvtu_sh, int32_t, uint16_t, H4, H2, do_usat_h)
> +
> +#undef SQCVT2
> +
> +#define SQCVT4(NAME, TW, TN, HW, HN, SAT) \
> +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
> +{ \
> + ARMVectorReg scratch; \
> + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
> + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
> + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \
> + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \
> + TN *d = vd; \
> + if ((vd - vs) < 4 * sizeof(ARMVectorReg)) { \
> + d = (TN *)&scratch; \
> + } \
> + for (size_t i = 0; i < n; ++i) { \
> + d[HN(i)] = SAT(s0[HW(i)]); \
> + d[HN(i) + n] = SAT(s1[HW(i)]); \
> + d[HN(i) + 2 * n] = SAT(s2[HW(i)]); \
> + d[HN(i) + 3 * n] = SAT(s3[HW(i)]); \
Similarly I thought the Hn macros would need these to be
HN(i + n) etc.
> + } \
> + if (d != vd) { \
> + memcpy(vd, d, oprsz); \
> + } \
> +}
> +#define SQCVTN2(NAME, TW, TN, HW, HN, SAT) \
> +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
> +{ \
> + ARMVectorReg scratch; \
> + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
> + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
> + TN *d = vd; \
> + if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
> + d = (TN *)&scratch; \
> + } \
> + for (size_t i = 0; i < n; ++i) { \
> + d[HN(2 * i + 0)] = SAT(s0[HW(i)]); \
> + d[HN(2 * i + 1)] = SAT(s1[HW(i)]); \
Hmm, here we do do HN(whole expr)...
> + } \
> + if (d != vd) { \
> + memcpy(vd, d, oprsz); \
> + } \
> +}
> +
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread* Re: [PATCH v3 49/97] target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU
2025-07-03 10:20 ` Peter Maydell
@ 2025-07-03 15:53 ` Richard Henderson
0 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-03 15:53 UTC (permalink / raw)
To: Peter Maydell; +Cc: qemu-devel, qemu-arm
On 7/3/25 04:20, Peter Maydell wrote:
> On Wed, 2 Jul 2025 at 13:38, Richard Henderson
> <richard.henderson@linaro.org> wrote:
>>
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>> ---
>> target/arm/tcg/helper-sme.h | 20 ++++++
>> target/arm/tcg/sme_helper.c | 116 +++++++++++++++++++++++++++++++++
>> target/arm/tcg/translate-sme.c | 35 ++++++++++
>> target/arm/tcg/sme.decode | 22 +++++++
>> 4 files changed, 193 insertions(+)
>
>
>> index d69d57c4cb..906d369d37 100644
>> --- a/target/arm/tcg/sme_helper.c
>> +++ b/target/arm/tcg/sme_helper.c
>> @@ -1561,6 +1561,64 @@ void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc)
>> }
>> }
>>
>> +#define SQCVT2(NAME, TW, TN, HW, HN, SAT) \
>> +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
>> +{ \
>> + ARMVectorReg scratch; \
>> + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
>> + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
>> + TN *d = vd; \
>> + if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
>
> Does this do the right thing if Vd is less than Vs?
> Pointer differences are signed, I think, so for eg vd == 0
> vs == 16 we unnecessarily use the scratch reg.
> Maybe clearer to write
> (vd >= vs && vd < (vs + 2 * sizeof(..))
>
> (Similarly for other use of this condition later in the patch.)
I should probably split out a helper for this, there are so many instances.
>
>
>> + d = (TN *)&scratch; \
>> + } \
>> + for (size_t i = 0; i < n; ++i) { \
>> + d[HN(i)] = SAT(s0[HW(i)]); \
>> + d[HN(i) + n] = SAT(s1[HW(i)]); \
>
> Should this be HN(i + n) ?
They're equivalent, because n is the whole vector size, and so does not overlap the xor on
8-byte endianness.
>> + for (size_t i = 0; i < n; ++i) { \
>> + d[HN(2 * i + 0)] = SAT(s0[HW(i)]); \
>> + d[HN(2 * i + 1)] = SAT(s1[HW(i)]); \
>
> Hmm, here we do do HN(whole expr)...
None of these inputs is known to be a multiple of 8.
r~
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 50/97] target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (48 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 49/97] target/arm: Implement SME2 SQCVT, UQCVT, SQCVTU Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:22 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK Richard Henderson
` (46 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 7 +++++++
target/arm/tcg/sve.decode | 20 ++++++++++++++++----
2 files changed, 23 insertions(+), 4 deletions(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 10261e25f9..ac4dc7db46 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7427,3 +7427,10 @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
}
TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+
+TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+ gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
+TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+ gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0)
+TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
+ gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 83c259def6..f808362f23 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -57,6 +57,8 @@
# as propagated via the MOVPRFX instruction.
%reg_movprfx 0:5
+%rn_ax2 6:4 !function=times_2
+
###########################################################################
# Named attribute sets. These are used to make nice(er) names
# when creating helpers common to those for the individual
@@ -102,6 +104,7 @@
# Two operand
@pd_pn ........ esz:2 .. .... ....... rn:4 . rd:4 &rr_esz
@rd_rn ........ esz:2 ...... ...... rn:5 rd:5 &rr_esz
+@rd_rnx2 ........ ... ..... ...... ..... rd:5 &rr_esz rn=%rn_ax2
# Two operand with governing predicate, flags setting
@pd_pg_pn_s ........ . s:1 ...... .. pg:4 . rn:4 . rd:4 &rpr_s
@@ -1507,13 +1510,22 @@ UABA 01000101 .. 0 ..... 11111 1 ..... ..... @rd_rn_rm
#### SVE2 Narrowing
## SVE2 saturating extract narrow
-
# Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0.
-SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl
+
+{
+ SQCVTN_sh 01000101 00 1 10001 010 000 ....0 ..... @rd_rnx2 esz=1
+ SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl
+}
SQXTNT 01000101 .. 1 ..... 010 001 ..... ..... @rd_rn_tszimm_shl
-UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl
+{
+ UQCVTN_sh 01000101 00 1 10001 010 010 ....0 ..... @rd_rnx2 esz=1
+ UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl
+}
UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl
-SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl
+{
+ SQCVTUN_sh 01000101 00 1 10001 010 100 ....0 ..... @rd_rnx2 esz=1
+ SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl
+}
SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl
## SVE2 bitwise shift right narrow
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 50/97] target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1
2025-07-02 12:33 ` [PATCH v3 50/97] target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1 Richard Henderson
@ 2025-07-03 10:22 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:22 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/translate-sve.c | 7 +++++++
> target/arm/tcg/sve.decode | 20 ++++++++++++++++----
> 2 files changed, 23 insertions(+), 4 deletions(-)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (49 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 50/97] target/arm: Implement SQCVTN, UQCVTN, SQCVTUN for SME2/SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:23 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 52/97] target/arm: Implement SME2 ZIP, UZP (four registers) Richard Henderson
` (45 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 13 ++++++++++++
target/arm/tcg/sme_helper.c | 38 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 16 ++++++++++++++
target/arm/tcg/sme.decode | 18 ++++++++++++++++
4 files changed, 85 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 792b993695..893b23aa3b 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -241,3 +241,16 @@ DEF_HELPER_FLAGS_3(sme2_sqcvtun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_sqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_sqcvtun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_sunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 906d369d37..a7d282695d 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1730,6 +1730,44 @@ void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc)
}
}
+#define UNPK(NAME, SREG, TW, TN, HW, HN) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch[SREG]; \
+ size_t oprsz = simd_oprsz(desc); \
+ size_t n = oprsz / sizeof(TW); \
+ if ((vs - vd) < 2 * SREG * sizeof(ARMVectorReg)) { \
+ vs = memcpy(scratch, vs, sizeof(scratch)); \
+ } \
+ for (size_t r = 0; r < SREG; ++r) { \
+ TN *s = vs + r * sizeof(ARMVectorReg); \
+ for (size_t i = 0; i < 2; ++i) { \
+ TW *d = vd + (2 * r + i) * sizeof(ARMVectorReg); \
+ for (size_t e = 0; e < n; ++e) { \
+ d[HW(e)] = s[i * n + HN(e)]; \
+ } \
+ } \
+ } \
+}
+
+UNPK(sme2_sunpk2_bh, 1, int16_t, int8_t, H2, H1)
+UNPK(sme2_sunpk2_hs, 1, int32_t, int16_t, H4, H2)
+UNPK(sme2_sunpk2_sd, 1, int64_t, int32_t, H8, H4)
+
+UNPK(sme2_sunpk4_bh, 2, int16_t, int8_t, H2, H1)
+UNPK(sme2_sunpk4_hs, 2, int32_t, int16_t, H4, H2)
+UNPK(sme2_sunpk4_sd, 2, int64_t, int32_t, H8, H4)
+
+UNPK(sme2_uunpk2_bh, 1, uint16_t, uint8_t, H2, H1)
+UNPK(sme2_uunpk2_hs, 1, uint32_t, uint16_t, H4, H2)
+UNPK(sme2_uunpk2_sd, 1, uint64_t, uint32_t, H8, H4)
+
+UNPK(sme2_uunpk4_bh, 2, uint16_t, uint8_t, H2, H1)
+UNPK(sme2_uunpk4_hs, 2, uint32_t, uint16_t, H4, H2)
+UNPK(sme2_uunpk4_sd, 2, uint64_t, uint32_t, H8, H4)
+
+#undef UNPK
+
/* Deinterleave and convert. */
void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc)
{
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index dd1a6668fb..b45e68750d 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1419,3 +1419,19 @@ TRANS_FEAT(SQCVTUN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_sb)
TRANS_FEAT(SQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_dh)
TRANS_FEAT(UQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_dh)
TRANS_FEAT(SQCVTUN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_dh)
+
+TRANS_FEAT(SUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_bh)
+TRANS_FEAT(SUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_hs)
+TRANS_FEAT(SUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_sd)
+
+TRANS_FEAT(SUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_bh)
+TRANS_FEAT(SUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_hs)
+TRANS_FEAT(SUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_sd)
+
+TRANS_FEAT(UUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_bh)
+TRANS_FEAT(UUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_hs)
+TRANS_FEAT(UUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_sd)
+
+TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh)
+TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs)
+TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index e005f6e6ed..38c210cd4f 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -734,6 +734,8 @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
&zz_n n=2 zd=%zd_ax2 zn=%zn_ax2
@zz_4x4 ........ ... ..... ...... .... . ..... \
&zz_n n=4 zd=%zd_ax4 zn=%zn_ax4
+@zz_4x2_n1 ........ ... ..... ...... .... . ..... \
+ &zz_n n=1 zd=%zd_ax4 zn=%zn_ax2
BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2
BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2
@@ -782,3 +784,19 @@ SQCVTUN_sb 11000001 011 10011 111000 ...10 ..... @zz_1x4
SQCVTN_dh 11000001 101 10011 111000 ...10 ..... @zz_1x4
UQCVTN_dh 11000001 101 10011 111000 ...11 ..... @zz_1x4
SQCVTUN_dh 11000001 111 10011 111000 ...10 ..... @zz_1x4
+
+SUNPK_2bh 11000001 011 00101 111000 ..... ....0 @zz_2x1
+SUNPK_2hs 11000001 101 00101 111000 ..... ....0 @zz_2x1
+SUNPK_2sd 11000001 111 00101 111000 ..... ....0 @zz_2x1
+
+UUNPK_2bh 11000001 011 00101 111000 ..... ....1 @zz_2x1
+UUNPK_2hs 11000001 101 00101 111000 ..... ....1 @zz_2x1
+UUNPK_2sd 11000001 111 00101 111000 ..... ....1 @zz_2x1
+
+SUNPK_4bh 11000001 011 10101 111000 ....0 ...00 @zz_4x2_n1
+SUNPK_4hs 11000001 101 10101 111000 ....0 ...00 @zz_4x2_n1
+SUNPK_4sd 11000001 111 10101 111000 ....0 ...00 @zz_4x2_n1
+
+UUNPK_4bh 11000001 011 10101 111000 ....0 ...01 @zz_4x2_n1
+UUNPK_4hs 11000001 101 10101 111000 ....0 ...01 @zz_4x2_n1
+UUNPK_4sd 11000001 111 10101 111000 ....0 ...01 @zz_4x2_n1
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK
2025-07-02 12:33 ` [PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK Richard Henderson
@ 2025-07-03 10:23 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:23 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> +#define UNPK(NAME, SREG, TW, TN, HW, HN) \
> +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
> +{ \
> + ARMVectorReg scratch[SREG]; \
> + size_t oprsz = simd_oprsz(desc); \
> + size_t n = oprsz / sizeof(TW); \
> + if ((vs - vd) < 2 * SREG * sizeof(ARMVectorReg)) { \
> + vs = memcpy(scratch, vs, sizeof(scratch)); \
> + } \
> + for (size_t r = 0; r < SREG; ++r) { \
> + TN *s = vs + r * sizeof(ARMVectorReg); \
> + for (size_t i = 0; i < 2; ++i) { \
> + TW *d = vd + (2 * r + i) * sizeof(ARMVectorReg); \
> + for (size_t e = 0; e < n; ++e) { \
> + d[HW(e)] = s[i * n + HN(e)]; \
> + } \
> + } \
> + } \
> +}
Similar remarks about the "when do we need to copy" check
and the H macros as patch 49, but otherwise
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 52/97] target/arm: Implement SME2 ZIP, UZP (four registers)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (50 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 51/97] target/arm: Implement SME2 SUNPK, UUNPK Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:25 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 53/97] target/arm: Move do_urshr, do_srshr to vec_internal.h Richard Henderson
` (44 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 12 ++++++
target/arm/tcg/sme_helper.c | 68 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 39 +++++++++++++++++++
target/arm/tcg/sme.decode | 11 ++++++
4 files changed, 130 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 893b23aa3b..7e21f1095a 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -254,3 +254,15 @@ DEF_HELPER_FLAGS_3(sme2_uunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_zip4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_zip4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_zip4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_zip4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_zip4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_uzp4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uzp4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uzp4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uzp4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uzp4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index a7d282695d..83646a3665 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1805,3 +1805,71 @@ void HELPER(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc)
d[i] = uint32_to_float32(s[i], fpst);
}
}
+
+#define ZIP4(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch[4]; \
+ size_t oprsz = simd_oprsz(desc); \
+ size_t quads = oprsz / (sizeof(TYPE) * 4); \
+ TYPE *s0, *s1, *s2, *s3; \
+ if (vs == vd) { \
+ vs = memcpy(scratch, vs, sizeof(scratch)); \
+ } \
+ s0 = vs; \
+ s1 = vs + sizeof(ARMVectorReg); \
+ s2 = vs + 2 * sizeof(ARMVectorReg); \
+ s3 = vs + 3 * sizeof(ARMVectorReg); \
+ for (size_t r = 0; r < 4; ++r) { \
+ TYPE *d = vd + r * sizeof(ARMVectorReg); \
+ size_t base = r * quads; \
+ for (size_t q = 0; q < quads; ++q) { \
+ d[H(4 * q + 0)] = s0[base + H(q)]; \
+ d[H(4 * q + 1)] = s1[base + H(q)]; \
+ d[H(4 * q + 2)] = s2[base + H(q)]; \
+ d[H(4 * q + 3)] = s3[base + H(q)]; \
+ } \
+ } \
+}
+
+ZIP4(sme2_zip4_b, uint8_t, H1)
+ZIP4(sme2_zip4_h, uint16_t, H2)
+ZIP4(sme2_zip4_s, uint32_t, H4)
+ZIP4(sme2_zip4_d, uint64_t, )
+ZIP4(sme2_zip4_q, Int128, )
+
+#undef ZIP4
+
+#define UZP4(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch[4]; \
+ size_t oprsz = simd_oprsz(desc); \
+ size_t quads = oprsz / (sizeof(TYPE) * 4); \
+ TYPE *d0, *d1, *d2, *d3; \
+ if (vs == vd) { \
+ vs = memcpy(scratch, vs, sizeof(scratch)); \
+ } \
+ d0 = vd; \
+ d1 = vd + sizeof(ARMVectorReg); \
+ d2 = vd + 2 * sizeof(ARMVectorReg); \
+ d3 = vd + 3 * sizeof(ARMVectorReg); \
+ for (size_t r = 0; r < 4; ++r) { \
+ TYPE *s = vs + r * sizeof(ARMVectorReg); \
+ size_t base = r * quads; \
+ for (size_t q = 0; q < quads; ++q) { \
+ d0[base + H(q)] = s[H(4 * q + 0)]; \
+ d1[base + H(q)] = s[H(4 * q + 1)]; \
+ d2[base + H(q)] = s[H(4 * q + 2)]; \
+ d3[base + H(q)] = s[H(4 * q + 3)]; \
+ } \
+ } \
+}
+
+UZP4(sme2_uzp4_b, uint8_t, H1)
+UZP4(sme2_uzp4_h, uint16_t, H2)
+UZP4(sme2_uzp4_s, uint32_t, H4)
+UZP4(sme2_uzp4_d, uint64_t, )
+UZP4(sme2_uzp4_q, Int128, )
+
+#undef UZP4
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index b45e68750d..de9545ee6d 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1435,3 +1435,42 @@ TRANS_FEAT(UUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_sd)
TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh)
TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs)
TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd)
+
+static bool do_zipuzp_4(DisasContext *s, arg_zz_e *a,
+ gen_helper_gvec_2 * const fn[5])
+{
+ int bytes_per_op = 4 << a->esz;
+
+ /* Both MO_64 and MO_128 can fail the size test. */
+ if (s->max_svl < bytes_per_op) {
+ unallocated_encoding(s);
+ } else if (sme_sm_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ if (svl < bytes_per_op) {
+ unallocated_encoding(s);
+ } else {
+ tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ svl, svl, 0, fn[a->esz]);
+ }
+ }
+ return true;
+}
+
+static gen_helper_gvec_2 * const zip4_fns[] = {
+ gen_helper_sme2_zip4_b,
+ gen_helper_sme2_zip4_h,
+ gen_helper_sme2_zip4_s,
+ gen_helper_sme2_zip4_d,
+ gen_helper_sme2_zip4_q,
+};
+TRANS_FEAT(ZIP_4, aa64_sme2, do_zipuzp_4, a, zip4_fns)
+
+static gen_helper_gvec_2 * const uzp4_fns[] = {
+ gen_helper_sme2_uzp4_b,
+ gen_helper_sme2_uzp4_h,
+ gen_helper_sme2_uzp4_s,
+ gen_helper_sme2_uzp4_d,
+ gen_helper_sme2_uzp4_q,
+};
+TRANS_FEAT(UZP_4, aa64_sme2, do_zipuzp_4, a, uzp4_fns)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 38c210cd4f..81783b4705 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -723,6 +723,7 @@ SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3
### SME2 Multi-vector SVE Constructive Unary
+&zz_e zd zn esz
&zz_n zd zn n
@zz_1x2 ........ ... ..... ...... ..... zd:5 \
&zz_n n=1 zn=%zn_ax2
@@ -800,3 +801,13 @@ SUNPK_4sd 11000001 111 10101 111000 ....0 ...00 @zz_4x2_n1
UUNPK_4bh 11000001 011 10101 111000 ....0 ...01 @zz_4x2_n1
UUNPK_4hs 11000001 101 10101 111000 ....0 ...01 @zz_4x2_n1
UUNPK_4sd 11000001 111 10101 111000 ....0 ...01 @zz_4x2_n1
+
+ZIP_4 11000001 esz:2 1 10110 111000 ...00 ... 00 \
+ &zz_e zd=%zd_ax4 zn=%zn_ax4
+ZIP_4 11000001 001 10111 111000 ...00 ... 00 \
+ &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4
+
+UZP_4 11000001 esz:2 1 10110 111000 ...00 ... 10 \
+ &zz_e zd=%zd_ax4 zn=%zn_ax4
+UZP_4 11000001 001 10111 111000 ...00 ... 10 \
+ &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 53/97] target/arm: Move do_urshr, do_srshr to vec_internal.h
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (51 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 52/97] target/arm: Implement SME2 ZIP, UZP (four registers) Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:25 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 54/97] target/arm: Implement SME2 SQRSHR, UQRSHR, SQRSHRN Richard Henderson
` (43 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Unify two copies of these inline functions.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/vec_internal.h | 21 +++++++++++++++++++++
target/arm/tcg/mve_helper.c | 21 ---------------------
target/arm/tcg/sve_helper.c | 21 ---------------------
3 files changed, 21 insertions(+), 42 deletions(-)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index a1c10c60a1..5efd257c50 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -230,6 +230,27 @@ int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool);
#define do_usat_h(val) MIN(MAX(val, 0), UINT16_MAX)
#define do_usat_s(val) MIN(MAX(val, 0), UINT32_MAX)
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
+{
+ if (likely(sh < 64)) {
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
+ } else if (sh == 64) {
+ return x >> 63;
+ } else {
+ return 0;
+ }
+}
+
+static inline int64_t do_srshr(int64_t x, unsigned sh)
+{
+ if (likely(sh < 64)) {
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
+ } else {
+ /* Rounding the sign bit always produces 0. */
+ return 0;
+ }
+}
+
/**
* bfdotadd:
* @sum: addend
diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index 506d1c3475..b9b2faa3a7 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -2164,27 +2164,6 @@ DO_VSHLL_ALL(vshllt, true)
DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \
DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
-static inline uint64_t do_urshr(uint64_t x, unsigned sh)
-{
- if (likely(sh < 64)) {
- return (x >> sh) + ((x >> (sh - 1)) & 1);
- } else if (sh == 64) {
- return x >> 63;
- } else {
- return 0;
- }
-}
-
-static inline int64_t do_srshr(int64_t x, unsigned sh)
-{
- if (likely(sh < 64)) {
- return (x >> sh) + ((x >> (sh - 1)) & 1);
- } else {
- /* Rounding the sign bit always produces 0. */
- return 0;
- }
-}
-
DO_VSHRN_ALL(vshrn, DO_SHR)
DO_VSHRN_ALL(vrshrn, do_urshr)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index f9052f2164..0e59ad2262 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -2050,27 +2050,6 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \
when N is negative, add 2**M-1. */
#define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M)
-static inline uint64_t do_urshr(uint64_t x, unsigned sh)
-{
- if (likely(sh < 64)) {
- return (x >> sh) + ((x >> (sh - 1)) & 1);
- } else if (sh == 64) {
- return x >> 63;
- } else {
- return 0;
- }
-}
-
-static inline int64_t do_srshr(int64_t x, unsigned sh)
-{
- if (likely(sh < 64)) {
- return (x >> sh) + ((x >> (sh - 1)) & 1);
- } else {
- /* Rounding the sign bit always produces 0. */
- return 0;
- }
-}
-
DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR)
DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR)
DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 54/97] target/arm: Implement SME2 SQRSHR, UQRSHR, SQRSHRN
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (52 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 53/97] target/arm: Move do_urshr, do_srshr to vec_internal.h Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:28 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 55/97] target/arm: Implement SME2 ZIP, UZP (two registers) Richard Henderson
` (42 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 20 ++++++
target/arm/tcg/sme_helper.c | 120 +++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 33 +++++++++
target/arm/tcg/sme.decode | 37 ++++++++++
4 files changed, 210 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 7e21f1095a..97428bcd6b 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -266,3 +266,23 @@ DEF_HELPER_FLAGS_3(sme2_uzp4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uzp4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uzp4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uzp4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_sqrshr_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqrshr_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshru_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshr_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqrshr_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshru_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshr_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqrshr_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshru_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sme2_sqrshrn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqrshrn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshrun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshrn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqrshrn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshrun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_uqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2_sqrshrun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 83646a3665..987880e310 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1619,6 +1619,66 @@ SQCVT4(sme2_sqcvtu_dh, int64_t, uint16_t, H8, H2, do_usat_h)
#undef SQCVT4
+#define SQRSHR2(NAME, TW, TN, HW, HN, RSHR, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ int shift = simd_data(desc); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(i)] = SAT(RSHR(s0[HW(i)], shift)); \
+ d[HN(i) + n] = SAT(RSHR(s1[HW(i)], shift)); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQRSHR2(sme2_sqrshr_sh, int32_t, int16_t, H4, H2, do_srshr, do_ssat_h)
+SQRSHR2(sme2_uqrshr_sh, uint32_t, uint16_t, H4, H2, do_urshr, do_usat_h)
+SQRSHR2(sme2_sqrshru_sh, int32_t, uint16_t, H4, H2, do_srshr, do_usat_h)
+
+#undef SQRSHR2
+
+#define SQRSHR4(NAME, TW, TN, HW, HN, RSHR, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ int shift = simd_data(desc); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TW *s2 = vs + 2 * sizeof(ARMVectorReg); \
+ TW *s3 = vs + 3 * sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 4 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(i)] = SAT(RSHR(s0[HW(i)], shift)); \
+ d[HN(i) + n] = SAT(RSHR(s1[HW(i)], shift)); \
+ d[HN(i) + 2 * n] = SAT(RSHR(s2[HW(i)], shift)); \
+ d[HN(i) + 3 * n] = SAT(RSHR(s3[HW(i)], shift)); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQRSHR4(sme2_sqrshr_sb, int32_t, int8_t, H4, H2, do_srshr, do_ssat_b)
+SQRSHR4(sme2_uqrshr_sb, uint32_t, uint8_t, H4, H2, do_urshr, do_usat_b)
+SQRSHR4(sme2_sqrshru_sb, int32_t, uint8_t, H4, H2, do_srshr, do_usat_b)
+
+SQRSHR4(sme2_sqrshr_dh, int64_t, int16_t, H8, H2, do_srshr, do_ssat_h)
+SQRSHR4(sme2_uqrshr_dh, uint64_t, uint16_t, H8, H2, do_urshr, do_usat_h)
+SQRSHR4(sme2_sqrshru_dh, int64_t, uint16_t, H8, H2, do_srshr, do_usat_h)
+
+#undef SQRSHR4
+
/* Convert and interleave */
void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc)
{
@@ -1708,6 +1768,66 @@ SQCVTN4(sme2_sqcvtun_dh, int64_t, uint16_t, H8, H2, do_usat_h)
#undef SQCVTN4
+#define SQRSHRN2(NAME, TW, TN, HW, HN, RSHR, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ int shift = simd_data(desc); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 2 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(2 * i + 0)] = SAT(RSHR(s0[HW(i)], shift)); \
+ d[HN(2 * i + 1)] = SAT(RSHR(s1[HW(i)], shift)); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQRSHRN2(sme2_sqrshrn_sh, int32_t, int16_t, H4, H2, do_srshr, do_ssat_h)
+SQRSHRN2(sme2_uqrshrn_sh, uint32_t, uint16_t, H4, H2, do_urshr, do_usat_h)
+SQRSHRN2(sme2_sqrshrun_sh, int32_t, uint16_t, H4, H2, do_srshr, do_usat_h)
+
+#undef SQRSHRN2
+
+#define SQRSHRN4(NAME, TW, TN, HW, HN, RSHR, SAT) \
+void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
+{ \
+ ARMVectorReg scratch; \
+ size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \
+ int shift = simd_data(desc); \
+ TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \
+ TW *s2 = vs + 2 * sizeof(ARMVectorReg); \
+ TW *s3 = vs + 3 * sizeof(ARMVectorReg); \
+ TN *d = vd; \
+ if ((vd - vs) < 4 * sizeof(ARMVectorReg)) { \
+ d = (TN *)&scratch; \
+ } \
+ for (size_t i = 0; i < n; ++i) { \
+ d[HN(4 * i + 0)] = SAT(RSHR(s0[HW(i)], shift)); \
+ d[HN(4 * i + 1)] = SAT(RSHR(s1[HW(i)], shift)); \
+ d[HN(4 * i + 2)] = SAT(RSHR(s2[HW(i)], shift)); \
+ d[HN(4 * i + 3)] = SAT(RSHR(s3[HW(i)], shift)); \
+ } \
+ if (d != vd) { \
+ memcpy(vd, d, oprsz); \
+ } \
+}
+
+SQRSHRN4(sme2_sqrshrn_sb, int32_t, int8_t, H4, H1, do_srshr, do_ssat_b)
+SQRSHRN4(sme2_uqrshrn_sb, uint32_t, uint8_t, H4, H1, do_urshr, do_usat_b)
+SQRSHRN4(sme2_sqrshrun_sb, int32_t, uint8_t, H4, H1, do_srshr, do_usat_b)
+
+SQRSHRN4(sme2_sqrshrn_dh, int64_t, int16_t, H8, H2, do_srshr, do_ssat_h)
+SQRSHRN4(sme2_uqrshrn_dh, uint64_t, uint16_t, H8, H2, do_urshr, do_usat_h)
+SQRSHRN4(sme2_sqrshrun_dh, int64_t, uint16_t, H8, H2, do_srshr, do_usat_h)
+
+#undef SQRSHRN4
+
/* Expand and convert */
void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc)
{
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index de9545ee6d..d413efd20e 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1474,3 +1474,36 @@ static gen_helper_gvec_2 * const uzp4_fns[] = {
gen_helper_sme2_uzp4_q,
};
TRANS_FEAT(UZP_4, aa64_sme2, do_zipuzp_4, a, uzp4_fns)
+
+static bool do_zz_rshr(DisasContext *s, arg_rshr *a, gen_helper_gvec_2 *fn)
+{
+ if (sve_access_check(s)) {
+ int vl = vec_full_reg_size(s);
+ tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ vl, vl, a->shift, fn);
+ }
+ return true;
+}
+
+TRANS_FEAT(SQRSHR_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_sh)
+TRANS_FEAT(UQRSHR_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_sh)
+TRANS_FEAT(SQRSHRU_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_sh)
+
+TRANS_FEAT(SQRSHR_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_sb)
+TRANS_FEAT(SQRSHR_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_dh)
+TRANS_FEAT(UQRSHR_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_sb)
+TRANS_FEAT(UQRSHR_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_dh)
+TRANS_FEAT(SQRSHRU_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_sb)
+TRANS_FEAT(SQRSHRU_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_dh)
+
+TRANS_FEAT(SQRSHRN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_sqrshrn_sh)
+TRANS_FEAT(UQRSHRN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sh)
+TRANS_FEAT(SQRSHRUN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sh)
+
+TRANS_FEAT(SQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrn_sb)
+TRANS_FEAT(SQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrn_dh)
+TRANS_FEAT(UQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sb)
+TRANS_FEAT(UQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_dh)
+TRANS_FEAT(SQRSHRUN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sb)
+TRANS_FEAT(SQRSHRUN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_dh)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 81783b4705..05d513efba 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -811,3 +811,40 @@ UZP_4 11000001 esz:2 1 10110 111000 ...00 ... 10 \
&zz_e zd=%zd_ax4 zn=%zn_ax4
UZP_4 11000001 001 10111 111000 ...00 ... 10 \
&zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4
+
+### SME2 Multi-vector SVE Constructive Binary
+
+&rshr zd zn shift
+
+%rshr_sh_shift 16:4 !function=rsub_16
+%rshr_sb_shift 16:5 !function=rsub_32
+%rshr_dh_shift 22:1 16:5 !function=rsub_64
+
+@rshr_sh ........ .... .... ...... ..... zd:5 \
+ &rshr zn=%zn_ax2 shift=%rshr_sh_shift
+@rshr_sb ........ ... ..... ...... ..... zd:5 \
+ &rshr zn=%zn_ax4 shift=%rshr_sb_shift
+@rshr_dh ........ ... ..... ...... ..... zd:5 \
+ &rshr zn=%zn_ax4 shift=%rshr_dh_shift
+
+SQRSHR_sh 11000001 1110 .... 110101 ....0 ..... @rshr_sh
+UQRSHR_sh 11000001 1110 .... 110101 ....1 ..... @rshr_sh
+SQRSHRU_sh 11000001 1111 .... 110101 ....0 ..... @rshr_sh
+
+SQRSHR_sb 11000001 011 ..... 110110 ...00 ..... @rshr_sb
+SQRSHR_dh 11000001 1.1 ..... 110110 ...00 ..... @rshr_dh
+UQRSHR_sb 11000001 011 ..... 110110 ...01 ..... @rshr_sb
+UQRSHR_dh 11000001 1.1 ..... 110110 ...01 ..... @rshr_dh
+SQRSHRU_sb 11000001 011 ..... 110110 ...10 ..... @rshr_sb
+SQRSHRU_dh 11000001 1.1 ..... 110110 ...10 ..... @rshr_dh
+
+SQRSHRN_sh 01000101 1011 .... 001010 ....0 ..... @rshr_sh
+UQRSHRN_sh 01000101 1011 .... 001110 ....0 ..... @rshr_sh
+SQRSHRUN_sh 01000101 1011 .... 000010 ....0 ..... @rshr_sh
+
+SQRSHRN_sb 11000001 011 ..... 110111 ...00 ..... @rshr_sb
+SQRSHRN_dh 11000001 1.1 ..... 110111 ...00 ..... @rshr_dh
+UQRSHRN_sb 11000001 011 ..... 110111 ...01 ..... @rshr_sb
+UQRSHRN_dh 11000001 1.1 ..... 110111 ...01 ..... @rshr_dh
+SQRSHRUN_sb 11000001 011 ..... 110111 ...10 ..... @rshr_sb
+SQRSHRUN_dh 11000001 1.1 ..... 110111 ...10 ..... @rshr_dh
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 55/97] target/arm: Implement SME2 ZIP, UZP (two registers)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (53 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 54/97] target/arm: Implement SME2 SQRSHR, UQRSHR, SQRSHRN Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:27 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 56/97] target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP Richard Henderson
` (41 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 12 +++++++
target/arm/tcg/sme_helper.c | 62 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 40 ++++++++++++++++++++++
target/arm/tcg/sme.decode | 12 +++++++
4 files changed, 126 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 97428bcd6b..06b95da3c3 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -255,6 +255,18 @@ DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_zip2_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_zip2_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_zip2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_zip2_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_zip2_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_uzp2_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uzp2_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uzp2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uzp2_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uzp2_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_3(sme2_zip4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_zip4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_zip4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 987880e310..7a869f6b9c 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1926,6 +1926,37 @@ void HELPER(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc)
}
}
+#define ZIP2(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ ARMVectorReg scratch[2]; \
+ size_t oprsz = simd_oprsz(desc); \
+ size_t pairs = oprsz / (sizeof(TYPE) * 2); \
+ TYPE *n = vn, *m = vm; \
+ if (vd <= vn && vn < vd + 2 * sizeof(ARMVectorReg)) { \
+ n = memcpy(&scratch[0], vn, oprsz); \
+ } \
+ if (vd <= vm && vm < vd + 2 * sizeof(ARMVectorReg)) { \
+ m = memcpy(&scratch[1], vm, oprsz); \
+ } \
+ for (size_t r = 0; r < 2; ++r) { \
+ TYPE *d = vd + r * sizeof(ARMVectorReg); \
+ size_t base = r * pairs; \
+ for (size_t p = 0; p < pairs; ++p) { \
+ d[H(2 * p + 0)] = n[base + H(p)]; \
+ d[H(2 * p + 1)] = m[base + H(p)]; \
+ } \
+ } \
+}
+
+ZIP2(sme2_zip2_b, uint8_t, H1)
+ZIP2(sme2_zip2_h, uint16_t, H2)
+ZIP2(sme2_zip2_s, uint32_t, H4)
+ZIP2(sme2_zip2_d, uint64_t, )
+ZIP2(sme2_zip2_q, Int128, )
+
+#undef ZIP2
+
#define ZIP4(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
{ \
@@ -1960,6 +1991,37 @@ ZIP4(sme2_zip4_q, Int128, )
#undef ZIP4
+#define UZP2(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ ARMVectorReg scratch[2]; \
+ size_t oprsz = simd_oprsz(desc); \
+ size_t pairs = oprsz / (sizeof(TYPE) * 2); \
+ TYPE *d0 = vd, *d1 = vd + sizeof(ARMVectorReg); \
+ if (vd <= vn && vn < vd + 2 * sizeof(ARMVectorReg)) { \
+ vn = memcpy(&scratch[0], vn, oprsz); \
+ } \
+ if (vd <= vm && vm < vd + 2 * sizeof(ARMVectorReg)) { \
+ vm = memcpy(&scratch[1], vm, oprsz); \
+ } \
+ for (size_t r = 0; r < 2; ++r) { \
+ TYPE *s = r ? vm : vn; \
+ size_t base = r * pairs; \
+ for (size_t p = 0; p < pairs; ++p) { \
+ d0[base + H(p)] = s[H(2 * p + 0)]; \
+ d1[base + H(p)] = s[H(2 * p + 1)]; \
+ } \
+ } \
+}
+
+UZP2(sme2_uzp2_b, uint8_t, H1)
+UZP2(sme2_uzp2_h, uint16_t, H2)
+UZP2(sme2_uzp2_s, uint32_t, H4)
+UZP2(sme2_uzp2_d, uint64_t, )
+UZP2(sme2_uzp2_q, Int128, )
+
+#undef UZP2
+
#define UZP4(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \
{ \
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index d413efd20e..d52ccf2ac5 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1507,3 +1507,43 @@ TRANS_FEAT(UQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sb)
TRANS_FEAT(UQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_dh)
TRANS_FEAT(SQRSHRUN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sb)
TRANS_FEAT(SQRSHRUN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_dh)
+
+static bool do_zipuzp_2(DisasContext *s, arg_zzz_e *a,
+ gen_helper_gvec_3 * const fn[5])
+{
+ int bytes_per_op = 2 << a->esz;
+
+ /* MO_128 can fail the size test. */
+ if (s->max_svl < bytes_per_op) {
+ unallocated_encoding(s);
+ } else if (sme_sm_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ if (svl < bytes_per_op) {
+ unallocated_encoding(s);
+ } else {
+ tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ vec_full_reg_offset(s, a->zm),
+ svl, svl, 0, fn[a->esz]);
+ }
+ }
+ return true;
+}
+
+static gen_helper_gvec_3 * const zip2_fns[] = {
+ gen_helper_sme2_zip2_b,
+ gen_helper_sme2_zip2_h,
+ gen_helper_sme2_zip2_s,
+ gen_helper_sme2_zip2_d,
+ gen_helper_sme2_zip2_q,
+};
+TRANS_FEAT(ZIP_2, aa64_sme2, do_zipuzp_2, a, zip2_fns)
+
+static gen_helper_gvec_3 * const uzp2_fns[] = {
+ gen_helper_sme2_uzp2_b,
+ gen_helper_sme2_uzp2_h,
+ gen_helper_sme2_uzp2_s,
+ gen_helper_sme2_uzp2_d,
+ gen_helper_sme2_uzp2_q,
+};
+TRANS_FEAT(UZP_2, aa64_sme2, do_zipuzp_2, a, uzp2_fns)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 05d513efba..c1f73d9f63 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -848,3 +848,15 @@ UQRSHRN_sb 11000001 011 ..... 110111 ...01 ..... @rshr_sb
UQRSHRN_dh 11000001 1.1 ..... 110111 ...01 ..... @rshr_dh
SQRSHRUN_sb 11000001 011 ..... 110111 ...10 ..... @rshr_sb
SQRSHRUN_dh 11000001 1.1 ..... 110111 ...10 ..... @rshr_dh
+
+&zzz_e zd zn zm esz
+
+ZIP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 0 \
+ &zzz_e zd=%zd_ax2
+ZIP_2 11000001 00 1 zm:5 110101 zn:5 .... 0 \
+ &zzz_e zd=%zd_ax2 esz=4
+
+UZP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 1 \
+ &zzz_e zd=%zd_ax2
+UZP_2 11000001 00 1 zm:5 110101 zn:5 .... 1 \
+ &zzz_e zd=%zd_ax2 esz=4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 56/97] target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (54 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 55/97] target/arm: Implement SME2 ZIP, UZP (two registers) Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:31 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 57/97] target/arm: Enable SCLAMP, UCLAMP for SVE2p1 Richard Henderson
` (40 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 15 +++++++
target/arm/tcg/sme_helper.c | 52 +++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 75 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 17 ++++++++
4 files changed, 159 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 06b95da3c3..78ba3d1f20 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -298,3 +298,18 @@ DEF_HELPER_FLAGS_3(sme2_sqrshrun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_sqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_uqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_sqrshrun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_sclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_sclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_sclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_sclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_uclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sme2_uclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 7a869f6b9c..bfcedef3d9 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -2055,3 +2055,55 @@ UZP4(sme2_uzp4_d, uint64_t, )
UZP4(sme2_uzp4_q, Int128, )
#undef UZP4
+
+#define ICLAMP(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \
+ size_t elements = simd_oprsz(desc) / sizeof(TYPE); \
+ size_t nreg = simd_data(desc); \
+ TYPE *d = vd, *n = vn, *m = vm; \
+ for (size_t e = 0; e < elements; e++) { \
+ TYPE nn = n[H(e)], mm = m[H(e)]; \
+ for (size_t r = 0; r < nreg; r++) { \
+ TYPE *dd = &d[r * stride + H(e)]; \
+ *dd = MIN(MAX(*dd, nn), mm); \
+ } \
+ } \
+}
+
+ICLAMP(sme2_sclamp_b, int8_t, H1)
+ICLAMP(sme2_sclamp_h, int16_t, H2)
+ICLAMP(sme2_sclamp_s, int32_t, H4)
+ICLAMP(sme2_sclamp_d, int64_t, H8)
+
+ICLAMP(sme2_uclamp_b, uint8_t, H1)
+ICLAMP(sme2_uclamp_h, uint16_t, H2)
+ICLAMP(sme2_uclamp_s, uint32_t, H4)
+ICLAMP(sme2_uclamp_d, uint64_t, H8)
+
+#undef ICLAMP
+
+#define FCLAMP(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, \
+ float_status *fpst, uint32_t desc) \
+{ \
+ size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \
+ size_t elements = simd_oprsz(desc) / sizeof(TYPE); \
+ size_t nreg = simd_data(desc); \
+ TYPE *d = vd, *n = vn, *m = vm; \
+ for (size_t e = 0; e < elements; e++) { \
+ TYPE nn = n[H(e)], mm = m[H(e)]; \
+ for (size_t r = 0; r < nreg; r++) { \
+ TYPE *dd = &d[r * stride + H(e)]; \
+ *dd = TYPE##_minnum(TYPE##_maxnum(nn, *dd, fpst), mm, fpst); \
+ } \
+ } \
+}
+
+FCLAMP(sme2_fclamp_h, float16, H2)
+FCLAMP(sme2_fclamp_s, float32, H4)
+FCLAMP(sme2_fclamp_d, float64, H8)
+FCLAMP(sme2_bfclamp, bfloat16, H2)
+
+#undef FCLAMP
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index d52ccf2ac5..99e4056316 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1547,3 +1547,78 @@ static gen_helper_gvec_3 * const uzp2_fns[] = {
gen_helper_sme2_uzp2_q,
};
TRANS_FEAT(UZP_2, aa64_sme2, do_zipuzp_2, a, uzp2_fns)
+
+static bool trans_FCLAMP(DisasContext *s, arg_zzz_en *a)
+{
+ static gen_helper_gvec_3_ptr * const fn[] = {
+ gen_helper_sme2_bfclamp,
+ gen_helper_sme2_fclamp_h,
+ gen_helper_sme2_fclamp_s,
+ gen_helper_sme2_fclamp_d,
+ };
+ TCGv_ptr fpst;
+ int vl;
+
+ if (!dc_isar_feature(aa64_sme2, s)) {
+ return false;
+ }
+ /* This insn uses MO_8 to encode BFloat16. */
+ if (a->esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) {
+ return false;
+ }
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+
+ fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+ vl = vec_full_reg_size(s);
+
+ tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ vec_full_reg_offset(s, a->zm),
+ fpst, vl, vl, a->n, fn[a->esz]);
+ return true;
+}
+
+static bool do_clamp(DisasContext *s, arg_zzz_en *a,
+ gen_helper_gvec_3 * const fn[4])
+{
+ int vl;
+
+ if (!dc_isar_feature(aa64_sme2, s)) {
+ return false;
+ }
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+
+ /*
+ * Clamp is just a min+max, easily supported by most host
+ * vector operations -- we already have such an expansion in
+ * translate-sve.c for a single output.
+ * TODO: Add support in gvec for multiple simultaneous output,
+ * and/or copy to temporary upon overlap.
+ */
+ vl = vec_full_reg_size(s);
+ tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ vec_full_reg_offset(s, a->zm),
+ vl, vl, a->n, fn[a->esz]);
+ return true;
+}
+
+static gen_helper_gvec_3 * const sclamp_fns[] = {
+ gen_helper_sme2_sclamp_b,
+ gen_helper_sme2_sclamp_h,
+ gen_helper_sme2_sclamp_s,
+ gen_helper_sme2_sclamp_d,
+};
+TRANS(SCLAMP, do_clamp, a, sclamp_fns)
+
+static gen_helper_gvec_3 * const uclamp_fns[] = {
+ gen_helper_sme2_uclamp_b,
+ gen_helper_sme2_uclamp_h,
+ gen_helper_sme2_uclamp_s,
+ gen_helper_sme2_uclamp_d,
+};
+TRANS(UCLAMP, do_clamp, a, uclamp_fns)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index c1f73d9f63..47adcb5a15 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -860,3 +860,20 @@ UZP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 1 \
&zzz_e zd=%zd_ax2
UZP_2 11000001 00 1 zm:5 110101 zn:5 .... 1 \
&zzz_e zd=%zd_ax2 esz=4
+
+&zzz_en zd zn zm esz n
+
+FCLAMP 11000001 esz:2 1 zm:5 110000 zn:5 .... 0 \
+ &zzz_en zd=%zd_ax2 n=2
+FCLAMP 11000001 esz:2 1 zm:5 110010 zn:5 ...0 0 \
+ &zzz_en zd=%zd_ax4 n=4
+
+SCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 0 \
+ &zzz_en zd=%zd_ax2 n=2
+SCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 0 \
+ &zzz_en zd=%zd_ax4 n=4
+
+UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \
+ &zzz_en zd=%zd_ax2 n=2
+UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \
+ &zzz_en zd=%zd_ax4 n=4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 56/97] target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP
2025-07-02 12:33 ` [PATCH v3 56/97] target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP Richard Henderson
@ 2025-07-03 10:31 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:31 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 15 +++++++
> target/arm/tcg/sme_helper.c | 52 +++++++++++++++++++++++
> target/arm/tcg/translate-sme.c | 75 ++++++++++++++++++++++++++++++++++
> target/arm/tcg/sme.decode | 17 ++++++++
> 4 files changed, 159 insertions(+)
> +#define FCLAMP(NAME, TYPE, H) \
> +void HELPER(NAME)(void *vd, void *vn, void *vm, \
> + float_status *fpst, uint32_t desc) \
> +{ \
> + size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \
> + size_t elements = simd_oprsz(desc) / sizeof(TYPE); \
> + size_t nreg = simd_data(desc); \
> + TYPE *d = vd, *n = vn, *m = vm; \
> + for (size_t e = 0; e < elements; e++) { \
> + TYPE nn = n[H(e)], mm = m[H(e)]; \
> + for (size_t r = 0; r < nreg; r++) { \
> + TYPE *dd = &d[r * stride + H(e)]; \
Probably worth a comment here that the order of the operands
to the min and max is important to get the right result when
some of the inputs are NaNs.
> + *dd = TYPE##_minnum(TYPE##_maxnum(nn, *dd, fpst), mm, fpst); \
> + } \
> + } \
> +}
> +
Otherwise
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 57/97] target/arm: Enable SCLAMP, UCLAMP for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (55 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 56/97] target/arm: Implement SME2 FCLAMP, SCLAMP, UCLAMP Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:32 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 58/97] target/arm: Implement FCLAMP for SME2, SVE2p1 Richard Henderson
` (39 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
These instructions are present in both SME(1) and SVE2.1 extensions.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index ac4dc7db46..ff70bf27b0 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7375,7 +7375,7 @@ static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
}
-TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
+TRANS_FEAT(SCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a)
{
@@ -7426,7 +7426,7 @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
}
-TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 57/97] target/arm: Enable SCLAMP, UCLAMP for SVE2p1
2025-07-02 12:33 ` [PATCH v3 57/97] target/arm: Enable SCLAMP, UCLAMP for SVE2p1 Richard Henderson
@ 2025-07-03 10:32 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:32 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> These instructions are present in both SME(1) and SVE2.1 extensions.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/translate-sve.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
> index ac4dc7db46..ff70bf27b0 100644
> --- a/target/arm/tcg/translate-sve.c
> +++ b/target/arm/tcg/translate-sve.c
> @@ -7375,7 +7375,7 @@ static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
> tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
> }
>
> -TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
> +TRANS_FEAT(SCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_sclamp, a)
>
> static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a)
> {
> @@ -7426,7 +7426,7 @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
> tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]);
> }
>
> -TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
> +TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
>
> TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
> gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
> --
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 58/97] target/arm: Implement FCLAMP for SME2, SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (56 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 57/97] target/arm: Enable SCLAMP, UCLAMP for SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:32 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 59/97] target/arm: Implement SME2p1 Multiple Zero Richard Henderson
` (38 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell, Alex Bennée
This is the single vector version within SVE decode space.
Tested-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 22 ++++++++++++++++++++++
target/arm/tcg/sve.decode | 2 ++
2 files changed, 24 insertions(+)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index ff70bf27b0..210a029ab8 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7428,6 +7428,28 @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m,
TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a)
+static bool trans_FCLAMP(DisasContext *s, arg_FCLAMP *a)
+{
+ static gen_helper_gvec_3_ptr * const fn[] = {
+ gen_helper_sme2_bfclamp,
+ gen_helper_sme2_fclamp_h,
+ gen_helper_sme2_fclamp_s,
+ gen_helper_sme2_fclamp_d,
+ };
+
+ /* This insn uses MO_8 to encode BFloat16. */
+ if (a->esz == MO_8
+ ? !dc_isar_feature(aa64_sve_b16b16, s)
+ : !dc_isar_feature(aa64_sme2_or_sve2p1, s)) {
+ return false;
+ }
+
+ /* So far we never optimize rda with MOVPRFX */
+ assert(a->rd == a->ra);
+ return gen_gvec_fpst_zzz(s, fn[a->esz], a->rd, a->rn, a->rm, 1,
+ a->esz == MO_16 ? FPST_A64_F16 : FPST_A64);
+}
+
TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0)
TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index f808362f23..dcfc40ef44 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1721,3 +1721,5 @@ PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \
SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm
UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm
+
+FCLAMP 01100100 .. 1 ..... 001001 ..... ..... @rda_rn_rm
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 59/97] target/arm: Implement SME2p1 Multiple Zero
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (57 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 58/97] target/arm: Implement FCLAMP for SME2, SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:33 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 60/97] target/arm: Introduce pred_count_test Richard Henderson
` (37 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sme.c | 20 ++++++++++++++++++++
target/arm/tcg/sme.decode | 23 +++++++++++++++++++++++
2 files changed, 43 insertions(+)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 99e4056316..b6316ac716 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -173,6 +173,26 @@ static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
return true;
}
+static bool trans_ZERO_za(DisasContext *s, arg_ZERO_za *a)
+{
+ if (!dc_isar_feature(aa64_sme2p1, s)) {
+ return false;
+ }
+ if (sme_smza_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ int vstride = svl / a->ngrp;
+ TCGv_ptr t_za = get_zarray(s, a->rv, a->off, a->ngrp, a->nvec);
+
+ for (int r = 0; r < a->ngrp; ++r) {
+ for (int i = 0; i < a->nvec; ++i) {
+ int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+ tcg_gen_gvec_dup_imm_var(MO_64, t_za, o_za, svl, svl, 0);
+ }
+ }
+ }
+ return true;
+}
+
static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
{
static gen_helper_gvec_4 * const h_fns[5] = {
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 47adcb5a15..c4b85a36d0 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -877,3 +877,26 @@ UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \
&zzz_en zd=%zd_ax2 n=2
UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \
&zzz_en zd=%zd_ax4 n=4
+
+### SME Multiple Zero
+
+&zero_za rv off ngrp nvec
+
+ZERO_za 11000000 000011 000 .. 0000000000 off:3 \
+ &zero_za ngrp=2 nvec=1 rv=%mova_rv
+ZERO_za 11000000 000011 100 .. 0000000000 off:3 \
+ &zero_za ngrp=4 nvec=1 rv=%mova_rv
+
+ZERO_za 11000000 000011 001 .. 0000000000 ... \
+ &zero_za ngrp=1 nvec=2 rv=%mova_rv off=%off3_x2
+ZERO_za 11000000 000011 010 .. 0000000000 0.. \
+ &zero_za ngrp=2 nvec=2 rv=%mova_rv off=%off2_x2
+ZERO_za 11000000 000011 011 .. 0000000000 0.. \
+ &zero_za ngrp=4 nvec=2 rv=%mova_rv off=%off2_x2
+
+ZERO_za 11000000 000011 101 .. 0000000000 0.. \
+ &zero_za ngrp=1 nvec=4 rv=%mova_rv off=%off2_x4
+ZERO_za 11000000 000011 110 .. 0000000000 00. \
+ &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
+ZERO_za 11000000 000011 111 .. 0000000000 00. \
+ &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 60/97] target/arm: Introduce pred_count_test
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (58 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 59/97] target/arm: Implement SME2p1 Multiple Zero Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 13:34 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 61/97] target/arm: Fold predtest_ones into helper_sve_brkns Richard Henderson
` (36 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
For WHILE, we have the count of enabled predicates, so we don't
need to search to compute the PredTest result. Reuse the logic
that will shortly be required for counted predicates.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_helper.c | 47 ++++++++++++++++++++++---------------
1 file changed, 28 insertions(+), 19 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 0e59ad2262..8fb9d0241d 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4102,20 +4102,35 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
return sum;
}
+/* C.f. Arm pseudocode PredCountTest */
+static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
+{
+ uint32_t flags;
+
+ if (count == 0) {
+ flags = 1; /* !N, Z, C */
+ } else if (!invert) {
+ flags = (1u << 31) | 2; /* N, !Z */
+ flags |= count != elements; /* C */
+ } else {
+ flags = 2; /* !Z, !C */
+ flags |= (count == elements) << 31; /* N */
+ }
+ return flags;
+}
+
uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
{
intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
uint64_t esz_mask = pred_esz_masks[esz];
ARMPredicateReg *d = vd;
- uint32_t flags;
- intptr_t i;
+ intptr_t i, oprbits = oprsz * 8;
+
+ tcg_debug_assert(count <= oprbits);
/* Begin with a zero predicate register. */
- flags = do_zero(d, oprsz);
- if (count == 0) {
- return flags;
- }
+ do_zero(d, oprsz);
/* Set all of the requested bits. */
for (i = 0; i < count / 64; ++i) {
@@ -4125,7 +4140,7 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
}
- return predtest_ones(d, oprsz, esz_mask);
+ return pred_count_test(oprbits, count, false);
}
uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
@@ -4134,16 +4149,15 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
uint64_t esz_mask = pred_esz_masks[esz];
ARMPredicateReg *d = vd;
- intptr_t i, invcount, oprbits;
+ intptr_t i, invcount, oprbits = oprsz * 8;
uint64_t bits;
- if (count == 0) {
- return do_zero(d, oprsz);
- }
-
- oprbits = oprsz * 8;
tcg_debug_assert(count <= oprbits);
+ /* Begin with a zero predicate register. */
+ do_zero(d, oprsz);
+
+ /* Set all of the requested bits. */
bits = esz_mask;
if (oprbits & 63) {
bits &= MAKE_64BIT_MASK(0, oprbits & 63);
@@ -4154,14 +4168,9 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
d->p[i] = bits;
bits = esz_mask;
}
-
d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
- while (--i >= 0) {
- d->p[i] = 0;
- }
-
- return predtest_ones(d, oprsz, esz_mask);
+ return pred_count_test(oprbits, count, true);
}
/* Recursive reduction on a function;
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 60/97] target/arm: Introduce pred_count_test
2025-07-02 12:33 ` [PATCH v3 60/97] target/arm: Introduce pred_count_test Richard Henderson
@ 2025-07-02 13:34 ` Richard Henderson
0 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 13:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
On 7/2/25 06:33, Richard Henderson wrote:
> For WHILE, we have the count of enabled predicates, so we don't
> need to search to compute the PredTest result. Reuse the logic
> that will shortly be required for counted predicates.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/sve_helper.c | 47 ++++++++++++++++++++++---------------
> 1 file changed, 28 insertions(+), 19 deletions(-)
Hmm.
> @@ -4134,16 +4149,15 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
> intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
> uint64_t esz_mask = pred_esz_masks[esz];
> ARMPredicateReg *d = vd;
> - intptr_t i, invcount, oprbits;
> + intptr_t i, invcount, oprbits = oprsz * 8;
> uint64_t bits;
>
> - if (count == 0) {
> - return do_zero(d, oprsz);
> - }
It's possible this breaks sve_whileg until it's fixed by patch 63.
r~
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 61/97] target/arm: Fold predtest_ones into helper_sve_brkns
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (59 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 60/97] target/arm: Introduce pred_count_test Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:36 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 62/97] target/arm: Split out do_whilel from helper_sve_whilel Richard Henderson
` (35 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Merge predtest_ones into its only caller.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_helper.c | 34 ++++++++++++++--------------------
1 file changed, 14 insertions(+), 20 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 8fb9d0241d..5014fd135d 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4061,31 +4061,25 @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc)
}
}
-/* As if PredTest(Ones(PL), D, esz). */
-static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz,
- uint64_t esz_mask)
-{
- uint32_t flags = PREDTEST_INIT;
- intptr_t i;
-
- for (i = 0; i < oprsz / 8; i++) {
- flags = iter_predtest_fwd(d->p[i], esz_mask, flags);
- }
- if (oprsz & 7) {
- uint64_t mask = ~(-1ULL << (8 * (oprsz & 7)));
- flags = iter_predtest_fwd(d->p[i], esz_mask & mask, flags);
- }
- return flags;
-}
-
uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc)
{
intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
if (last_active_pred(vn, vg, oprsz)) {
- return predtest_ones(vd, oprsz, -1);
- } else {
- return do_zero(vd, oprsz);
+ ARMPredicateReg *d = vd;
+ uint32_t flags = PREDTEST_INIT;
+ intptr_t i;
+
+ /* As if PredTest(Ones(PL), D, MO_8). */
+ for (i = 0; i < oprsz / 8; i++) {
+ flags = iter_predtest_fwd(d->p[i], -1, flags);
+ }
+ if (oprsz & 7) {
+ uint64_t mask = ~(-1ULL << (8 * (oprsz & 7)));
+ flags = iter_predtest_fwd(d->p[i], mask, flags);
+ }
+ return flags;
}
+ return do_zero(vd, oprsz);
}
uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 62/97] target/arm: Split out do_whilel from helper_sve_whilel
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (60 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 61/97] target/arm: Fold predtest_ones into helper_sve_brkns Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 10:38 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 63/97] target/arm: Split out do_whileg from helper_sve_whileg Richard Henderson
` (34 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_helper.c | 28 ++++++++++++++++------------
1 file changed, 16 insertions(+), 12 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 5014fd135d..4497e9107b 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4113,26 +4113,30 @@ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
return flags;
}
-uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
+static void do_whilel(uint64_t *d, uint64_t esz_mask,
+ uint32_t count, uint32_t oprbits)
{
- intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
- intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
- uint64_t esz_mask = pred_esz_masks[esz];
- ARMPredicateReg *d = vd;
- intptr_t i, oprbits = oprsz * 8;
+ uint32_t i;
tcg_debug_assert(count <= oprbits);
- /* Begin with a zero predicate register. */
- do_zero(d, oprsz);
-
- /* Set all of the requested bits. */
for (i = 0; i < count / 64; ++i) {
- d->p[i] = esz_mask;
+ d[i] = esz_mask;
}
if (count & 63) {
- d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
+ d[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
}
+}
+
+uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+ uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+ uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+ uint32_t oprbits = oprsz * 8;
+ uint64_t esz_mask = pred_esz_masks[esz];
+
+ do_zero(vd, oprsz);
+ do_whilel(vd, esz_mask, count, oprbits);
return pred_count_test(oprbits, count, false);
}
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 62/97] target/arm: Split out do_whilel from helper_sve_whilel
2025-07-02 12:33 ` [PATCH v3 62/97] target/arm: Split out do_whilel from helper_sve_whilel Richard Henderson
@ 2025-07-03 10:38 ` Peter Maydell
2025-07-03 16:02 ` Richard Henderson
0 siblings, 1 reply; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 10:38 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/sve_helper.c | 28 ++++++++++++++++------------
> 1 file changed, 16 insertions(+), 12 deletions(-)
>
> diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
> index 5014fd135d..4497e9107b 100644
> --- a/target/arm/tcg/sve_helper.c
> +++ b/target/arm/tcg/sve_helper.c
> @@ -4113,26 +4113,30 @@ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
> return flags;
> }
>
> -uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
> +static void do_whilel(uint64_t *d, uint64_t esz_mask,
> + uint32_t count, uint32_t oprbits)
Does the compiler generate worse code if we give the right
typed argument for d here (ArmPredicateReg *d) vs uint64_t * ?
> {
> - intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
> - intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
> - uint64_t esz_mask = pred_esz_masks[esz];
> - ARMPredicateReg *d = vd;
> - intptr_t i, oprbits = oprsz * 8;
> + uint32_t i;
>
> tcg_debug_assert(count <= oprbits);
>
> - /* Begin with a zero predicate register. */
> - do_zero(d, oprsz);
> -
> - /* Set all of the requested bits. */
> for (i = 0; i < count / 64; ++i) {
> - d->p[i] = esz_mask;
> + d[i] = esz_mask;
> }
> if (count & 63) {
> - d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
> + d[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask;
> }
> +}
Either way
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread* Re: [PATCH v3 62/97] target/arm: Split out do_whilel from helper_sve_whilel
2025-07-03 10:38 ` Peter Maydell
@ 2025-07-03 16:02 ` Richard Henderson
0 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-03 16:02 UTC (permalink / raw)
To: Peter Maydell; +Cc: qemu-devel, qemu-arm
On 7/3/25 04:38, Peter Maydell wrote:
> On Wed, 2 Jul 2025 at 13:38, Richard Henderson
> <richard.henderson@linaro.org> wrote:
>>
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>> ---
>> target/arm/tcg/sve_helper.c | 28 ++++++++++++++++------------
>> 1 file changed, 16 insertions(+), 12 deletions(-)
>>
>> diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
>> index 5014fd135d..4497e9107b 100644
>> --- a/target/arm/tcg/sve_helper.c
>> +++ b/target/arm/tcg/sve_helper.c
>> @@ -4113,26 +4113,30 @@ static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
>> return flags;
>> }
>>
>> -uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
>> +static void do_whilel(uint64_t *d, uint64_t esz_mask,
>> + uint32_t count, uint32_t oprbits)
>
> Does the compiler generate worse code if we give the right
> typed argument for d here (ArmPredicateReg *d) vs uint64_t * ?
It'll almost certainly be identical.
I believe my original split for this was written with the idea that I'd be expanding
CounterToPredicate for LD1 et al exactly like the pseudocode does. If I had done that, I
would have needed to pass an array of uint64_t with 4x the elements in ARMPredicateReg.
Thus uint64_t* instead of ARMPredicateReg*.
But in the end, decode_counter does not expand all of the predicate bits explicitly.
r~
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 63/97] target/arm: Split out do_whileg from helper_sve_whileg
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (61 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 62/97] target/arm: Split out do_whilel from helper_sve_whilel Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-02 12:33 ` [PATCH v3 64/97] target/arm: Move scale by esz into helper_sve_while* Richard Henderson
` (33 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_helper.c | 41 +++++++++++++++++++------------------
1 file changed, 21 insertions(+), 20 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 4497e9107b..ba5ab6b513 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4141,32 +4141,33 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
return pred_count_test(oprbits, count, false);
}
-uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
+static void do_whileg(uint64_t *d, uint64_t esz_mask,
+ uint32_t count, uint32_t oprbits)
{
- intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
- intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
- uint64_t esz_mask = pred_esz_masks[esz];
- ARMPredicateReg *d = vd;
- intptr_t i, invcount, oprbits = oprsz * 8;
- uint64_t bits;
+ uint32_t invcount = oprbits - count;
+ uint32_t i = invcount / 64;
+ uint64_t bits = esz_mask & MAKE_64BIT_MASK(invcount & 63, 64);
tcg_debug_assert(count <= oprbits);
- /* Begin with a zero predicate register. */
- do_zero(d, oprsz);
-
- /* Set all of the requested bits. */
- bits = esz_mask;
- if (oprbits & 63) {
- bits &= MAKE_64BIT_MASK(0, oprbits & 63);
- }
-
- invcount = oprbits - count;
- for (i = (oprsz - 1) / 8; i > invcount / 64; --i) {
- d->p[i] = bits;
+ for (; i < oprbits / 64; ++i) {
+ d[i] = bits;
bits = esz_mask;
}
- d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64);
+ if (oprbits & 63) {
+ d[i] = MAKE_64BIT_MASK(0, oprbits & 63) & bits;
+ }
+}
+
+uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+ uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+ uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+ uint32_t oprbits = oprsz * 8;
+ uint64_t esz_mask = pred_esz_masks[esz];
+
+ do_zero(vd, oprsz);
+ do_whileg(vd, esz_mask, count, oprbits);
return pred_count_test(oprbits, count, true);
}
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 64/97] target/arm: Move scale by esz into helper_sve_while*
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (62 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 63/97] target/arm: Split out do_whileg from helper_sve_whileg Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:10 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 65/97] target/arm: Split trans_WHILE to lt and gt Richard Henderson
` (32 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Change the API to pass element count rather than bit count.
This will be helpful later for predicate as counter.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_helper.c | 2 ++
target/arm/tcg/translate-sve.c | 13 +++++--------
2 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index ba5ab6b513..dbade6ece0 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4135,6 +4135,7 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
uint32_t oprbits = oprsz * 8;
uint64_t esz_mask = pred_esz_masks[esz];
+ count <<= esz;
do_zero(vd, oprsz);
do_whilel(vd, esz_mask, count, oprbits);
@@ -4166,6 +4167,7 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
uint32_t oprbits = oprsz * 8;
uint64_t esz_mask = pred_esz_masks[esz];
+ count <<= esz;
do_zero(vd, oprsz);
do_whileg(vd, esz_mask, count, oprbits);
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 210a029ab8..f74f2bb1b3 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3198,9 +3198,6 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
t2 = tcg_temp_new_i32();
tcg_gen_extrl_i64_i32(t2, t0);
- /* Scale elements to bits. */
- tcg_gen_shli_i32(t2, t2, a->esz);
-
desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8);
desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
@@ -3234,7 +3231,7 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
op0 = read_cpu_reg(s, a->rn, 1);
op1 = read_cpu_reg(s, a->rm, 1);
- tmax = tcg_constant_i64(vsz);
+ tmax = tcg_constant_i64(vsz >> a->esz);
diff = tcg_temp_new_i64();
if (a->rw) {
@@ -3244,15 +3241,15 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
tcg_gen_sub_i64(diff, op0, op1);
tcg_gen_sub_i64(t1, op1, op0);
tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1);
- /* Round down to a multiple of ESIZE. */
- tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+ /* Divide, rounding down, by ESIZE. */
+ tcg_gen_shri_i64(diff, diff, a->esz);
/* If op1 == op0, diff == 0, and the condition is always true. */
tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff);
} else {
/* WHILEWR */
tcg_gen_sub_i64(diff, op1, op0);
- /* Round down to a multiple of ESIZE. */
- tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+ /* Divide, rounding down, by ESIZE. */
+ tcg_gen_shri_i64(diff, diff, a->esz);
/* If op0 >= op1, diff <= 0, the condition is always true. */
tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff);
}
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 65/97] target/arm: Split trans_WHILE to lt and gt
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (63 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 64/97] target/arm: Move scale by esz into helper_sve_while* Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:10 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 66/97] target/arm: Enable PSEL for SVE2p1 Richard Henderson
` (31 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Use TRANS_FEAT to select the correct predicate.
Pass the helper and a boolean to do_WHILE.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 23 +++++++++--------------
target/arm/tcg/sve.decode | 4 +++-
2 files changed, 12 insertions(+), 15 deletions(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index f74f2bb1b3..62d3e2efd6 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3108,7 +3108,8 @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a)
return true;
}
-static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
+typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
+static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
{
TCGv_i64 op0, op1, t0, t1, tmax;
TCGv_i32 t2;
@@ -3118,14 +3119,8 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
TCGCond cond;
uint64_t maxval;
/* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */
- bool eq = a->eq == a->lt;
+ bool eq = a->eq == lt;
- /* The greater-than conditions are all SVE2. */
- if (a->lt
- ? !dc_isar_feature(aa64_sve, s)
- : !dc_isar_feature(aa64_sve2, s)) {
- return false;
- }
if (!sve_access_check(s)) {
return true;
}
@@ -3149,7 +3144,7 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
t0 = tcg_temp_new_i64();
t1 = tcg_temp_new_i64();
- if (a->lt) {
+ if (lt) {
tcg_gen_sub_i64(t0, op1, op0);
if (a->u) {
maxval = a->sf ? UINT64_MAX : UINT32_MAX;
@@ -3204,15 +3199,15 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
ptr = tcg_temp_new_ptr();
tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd));
- if (a->lt) {
- gen_helper_sve_whilel(t2, ptr, t2, tcg_constant_i32(desc));
- } else {
- gen_helper_sve_whileg(t2, ptr, t2, tcg_constant_i32(desc));
- }
+ fn(t2, ptr, t2, tcg_constant_i32(desc));
+
do_pred_flags(t2);
return true;
}
+TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel)
+TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg)
+
static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
{
TCGv_i64 op0, op1, diff, t1, tmax;
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index dcfc40ef44..c90d975ebf 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -789,7 +789,9 @@ SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred
CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000
# SVE integer compare scalar count and limit
-WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4
+&while esz rd rn rm sf u eq
+WHILE_lt 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 &while
+WHILE_gt 00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4 &while
# SVE2 pointer conflict compare
WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 66/97] target/arm: Enable PSEL for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (64 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 65/97] target/arm: Split trans_WHILE to lt and gt Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:10 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 67/97] target/arm: Implement SVE2p1 WHILE (predicate pair) Richard Henderson
` (30 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
This instruction is present in both SME(1) and SVE2.1 extensions.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 62d3e2efd6..cb60b533e9 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7273,7 +7273,7 @@ static bool trans_PSEL(DisasContext *s, arg_psel *a)
TCGv_i64 tmp, didx, dbit;
TCGv_ptr ptr;
- if (!dc_isar_feature(aa64_sme, s)) {
+ if (!dc_isar_feature(aa64_sme_or_sve2p1, s)) {
return false;
}
if (!sve_access_check(s)) {
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 67/97] target/arm: Implement SVE2p1 WHILE (predicate pair)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (65 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 66/97] target/arm: Enable PSEL for SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:11 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 68/97] target/arm: Implement SVE2p1 WHILE (predicate as counter) Richard Henderson
` (29 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 3 +++
target/arm/tcg/sve_helper.c | 44 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 14 +++++++----
target/arm/tcg/sve.decode | 8 +++++++
4 files changed, 65 insertions(+), 4 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 0b1b588783..eac23e75b9 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -941,6 +941,9 @@ DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+
DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index dbade6ece0..2aec963f74 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4142,6 +4142,28 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
return pred_count_test(oprbits, count, false);
}
+uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+ uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+ uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+ uint32_t oprbits = oprsz * 8;
+ uint64_t esz_mask = pred_esz_masks[esz];
+ ARMPredicateReg *d = vd;
+
+ do_zero(&d[0], oprsz);
+ do_zero(&d[1], oprsz);
+
+ count <<= esz;
+ if (count <= oprbits) {
+ do_whilel(d[0].p, esz_mask, count, oprbits);
+ } else {
+ do_whilel(d[0].p, esz_mask, oprbits, oprbits);
+ do_whilel(d[1].p, esz_mask, count - oprbits, oprbits);
+ }
+
+ return pred_count_test(2 * oprbits, count, false);
+}
+
static void do_whileg(uint64_t *d, uint64_t esz_mask,
uint32_t count, uint32_t oprbits)
{
@@ -4174,6 +4196,28 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
return pred_count_test(oprbits, count, true);
}
+uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+ uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+ uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+ uint32_t oprbits = oprsz * 8;
+ uint64_t esz_mask = pred_esz_masks[esz];
+ ARMPredicateReg *d = vd;
+
+ do_zero(&d[0], oprsz);
+ do_zero(&d[1], oprsz);
+
+ count <<= esz;
+ if (count <= oprbits) {
+ do_whileg(d[1].p, esz_mask, count, oprbits);
+ } else {
+ do_whileg(d[1].p, esz_mask, oprbits, oprbits);
+ do_whileg(d[0].p, esz_mask, count - oprbits, oprbits);
+ }
+
+ return pred_count_test(2 * oprbits, count, true);
+}
+
/* Recursive reduction on a function;
* C.f. the ARM ARM function ReducePredicated.
*
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index cb60b533e9..de6ffe7511 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3109,7 +3109,8 @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a)
}
typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
-static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
+static bool do_WHILE(DisasContext *s, arg_while *a,
+ bool lt, int scale, gen_while_fn *fn)
{
TCGv_i64 op0, op1, t0, t1, tmax;
TCGv_i32 t2;
@@ -3164,7 +3165,7 @@ static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
}
}
- tmax = tcg_constant_i64(vsz >> a->esz);
+ tmax = tcg_constant_i64((vsz << scale) >> a->esz);
if (eq) {
/* Equality means one more iteration. */
tcg_gen_addi_i64(t0, t0, 1);
@@ -3205,8 +3206,13 @@ static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
return true;
}
-TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel)
-TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg)
+TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, 0, gen_helper_sve_whilel)
+TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, 0, gen_helper_sve_whileg)
+
+TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE,
+ a, true, 1, gen_helper_sve_while2l)
+TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE,
+ a, false, 1, gen_helper_sve_while2g)
static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
{
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index c90d975ebf..968b2a57e9 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -796,6 +796,14 @@ WHILE_gt 00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4 &while
# SVE2 pointer conflict compare
WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
+# SVE2.1 predicate pair
+%pd_pair 1:3 !function=times_2
+@while_pair ........ esz:2 . rm:5 .... u:1 . rn:5 . ... eq:1 \
+ &while rd=%pd_pair sf=1
+
+WHILE_lt_pair 00100101 .. 1 ..... 0101 . 1 ..... 1 ... . @while_pair
+WHILE_gt_pair 00100101 .. 1 ..... 0101 . 0 ..... 1 ... . @while_pair
+
### SVE Integer Wide Immediate - Unpredicated Group
# SVE broadcast floating-point immediate (unpredicated)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 68/97] target/arm: Implement SVE2p1 WHILE (predicate as counter)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (66 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 67/97] target/arm: Implement SVE2p1 WHILE (predicate pair) Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:12 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 69/97] target/arm: Implement SVE2p1 PTRUE " Richard Henderson
` (28 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 3 ++
target/arm/tcg/sve_helper.c | 51 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 22 +++++++++++----
target/arm/tcg/sve.decode | 11 ++++++++
4 files changed, 82 insertions(+), 5 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index eac23e75b9..74029c641b 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -944,6 +944,9 @@ DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+DEF_HELPER_FLAGS_3(sve_whilecl, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+DEF_HELPER_FLAGS_3(sve_whilecg, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+
DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 2aec963f74..f5fbfb751e 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4096,6 +4096,29 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
return sum;
}
+/* C.f. Arm pseudocode EncodePredCount */
+static uint64_t encode_pred_count(uint32_t elements, uint32_t count,
+ uint32_t esz, bool invert)
+{
+ uint32_t pred;
+
+ if (count == 0) {
+ return 0;
+ }
+ if (invert) {
+ count = elements - count;
+ } else if (count == elements) {
+ count = 0;
+ invert = true;
+ }
+
+ pred = (count << 1) | 1;
+ pred <<= esz;
+ pred |= invert << 15;
+
+ return pred;
+}
+
/* C.f. Arm pseudocode PredCountTest */
static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert)
{
@@ -4164,6 +4187,20 @@ uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc)
return pred_count_test(2 * oprbits, count, false);
}
+uint32_t HELPER(sve_whilecl)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+ uint32_t pl = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+ uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+ uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA);
+ uint32_t vl = pl * 8;
+ uint32_t elements = (vl >> esz) << scale;
+ ARMPredicateReg *d = vd;
+
+ do_zero(d, pl);
+ d->p[0] = encode_pred_count(elements, count, esz, false);
+ return pred_count_test(elements, count, false);
+}
+
static void do_whileg(uint64_t *d, uint64_t esz_mask,
uint32_t count, uint32_t oprbits)
{
@@ -4218,6 +4255,20 @@ uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc)
return pred_count_test(2 * oprbits, count, true);
}
+uint32_t HELPER(sve_whilecg)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+ uint32_t pl = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+ uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+ uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA);
+ uint32_t vl = pl * 8;
+ uint32_t elements = (vl >> esz) << scale;
+ ARMPredicateReg *d = vd;
+
+ do_zero(d, pl);
+ d->p[0] = encode_pred_count(elements, count, esz, true);
+ return pred_count_test(elements, count, true);
+}
+
/* Recursive reduction on a function;
* C.f. the ARM ARM function ReducePredicated.
*
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index de6ffe7511..c93dca224c 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3110,7 +3110,7 @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a)
typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
static bool do_WHILE(DisasContext *s, arg_while *a,
- bool lt, int scale, gen_while_fn *fn)
+ bool lt, int scale, int data, gen_while_fn *fn)
{
TCGv_i64 op0, op1, t0, t1, tmax;
TCGv_i32 t2;
@@ -3196,6 +3196,7 @@ static bool do_WHILE(DisasContext *s, arg_while *a,
desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8);
desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
+ desc = FIELD_DP32(desc, PREDDESC, DATA, data);
ptr = tcg_temp_new_ptr();
tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd));
@@ -3206,13 +3207,24 @@ static bool do_WHILE(DisasContext *s, arg_while *a,
return true;
}
-TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, 0, gen_helper_sve_whilel)
-TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, 0, gen_helper_sve_whileg)
+TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE,
+ a, true, 0, 0, gen_helper_sve_whilel)
+TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE,
+ a, false, 0, 0, gen_helper_sve_whileg)
TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE,
- a, true, 1, gen_helper_sve_while2l)
+ a, true, 1, 0, gen_helper_sve_while2l)
TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE,
- a, false, 1, gen_helper_sve_while2g)
+ a, false, 1, 0, gen_helper_sve_while2g)
+
+TRANS_FEAT(WHILE_lt_cnt2, aa64_sme2_or_sve2p1, do_WHILE,
+ a, true, 1, 1, gen_helper_sve_whilecl)
+TRANS_FEAT(WHILE_lt_cnt4, aa64_sme2_or_sve2p1, do_WHILE,
+ a, true, 2, 2, gen_helper_sve_whilecl)
+TRANS_FEAT(WHILE_gt_cnt2, aa64_sme2_or_sve2p1, do_WHILE,
+ a, false, 1, 1, gen_helper_sve_whilecg)
+TRANS_FEAT(WHILE_gt_cnt4, aa64_sme2_or_sve2p1, do_WHILE,
+ a, false, 2, 2, gen_helper_sve_whilecg)
static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
{
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 968b2a57e9..389a72d824 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -59,6 +59,8 @@
%rn_ax2 6:4 !function=times_2
+%pnd 0:3 !function=plus_8
+
###########################################################################
# Named attribute sets. These are used to make nice(er) names
# when creating helpers common to those for the individual
@@ -804,6 +806,15 @@ WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
WHILE_lt_pair 00100101 .. 1 ..... 0101 . 1 ..... 1 ... . @while_pair
WHILE_gt_pair 00100101 .. 1 ..... 0101 . 0 ..... 1 ... . @while_pair
+# SVE2.1 predicate as count
+@while_cnt ........ esz:2 . rm:5 .... u:1 . rn:5 . eq:1 ... \
+ &while rd=%pnd sf=1
+
+WHILE_lt_cnt2 00100101 .. 1 ..... 0100 . 1 ..... 1 . ... @while_cnt
+WHILE_lt_cnt4 00100101 .. 1 ..... 0110 . 1 ..... 1 . ... @while_cnt
+WHILE_gt_cnt2 00100101 .. 1 ..... 0100 . 0 ..... 1 . ... @while_cnt
+WHILE_gt_cnt4 00100101 .. 1 ..... 0110 . 0 ..... 1 . ... @while_cnt
+
### SVE Integer Wide Immediate - Unpredicated Group
# SVE broadcast floating-point immediate (unpredicated)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 69/97] target/arm: Implement SVE2p1 PTRUE (predicate as counter)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (67 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 68/97] target/arm: Implement SVE2p1 WHILE (predicate as counter) Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:14 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 70/97] target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1 Richard Henderson
` (27 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 16 ++++++++++++++++
target/arm/tcg/sve.decode | 1 +
2 files changed, 17 insertions(+)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index c93dca224c..651b4aa378 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -1679,6 +1679,22 @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag)
TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s)
+static bool trans_PTRUE_cnt(DisasContext *s, arg_PTRUE_cnt *a)
+{
+ if (!dc_isar_feature(aa64_sme2_or_sve2p1, s)) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ /* Canonical TRUE is 0 count, invert bit, plus element size. */
+ int val = (1 << 15) | (1 << a->esz);
+
+ /* Write val to the first uint64_t; clear all of the rest. */
+ tcg_gen_gvec_dup_imm(MO_64, pred_full_reg_offset(s, a->rd),
+ 8, size_for_gvec(pred_full_reg_size(s)), val);
+ }
+ return true;
+}
+
/* Note pat == 31 is #all, to set all elements. */
TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve,
do_predset, 0, FFR_PRED_NUM, 31, false)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 389a72d824..3517efb31b 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -730,6 +730,7 @@ PTEST 00100101 01 010000 11 pg:4 0 rn:4 0 0000
# SVE predicate initialize
PTRUE 00100101 esz:2 01100 s:1 111000 pat:5 0 rd:4
+PTRUE_cnt 00100101 esz:2 1000000111100000010 ... rd=%pnd
# SVE initialize FFR
SETFFR 00100101 0010 1100 1001 0000 0000 0000
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 70/97] target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (68 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 69/97] target/arm: Implement SVE2p1 PTRUE " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:15 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 71/97] target/arm: Implement SVE2p1 PEXT Richard Henderson
` (26 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 25 ++++++++++++++++++
target/arm/tcg/sve_helper.c | 46 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 35 ++++++++++++++++++++++++++
target/arm/tcg/sve.decode | 7 ++++++
4 files changed, 113 insertions(+)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 74029c641b..5f5ecc2e0d 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -2928,3 +2928,28 @@ DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_addqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_addqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_addqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_addqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index f5fbfb751e..cc706db901 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -1814,6 +1814,52 @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN)
#undef DO_VPZ
#undef DO_VPZ_D
+#define DO_VPQ(NAME, TYPE, H, INIT, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \
+{ \
+ TYPE tmp[16 / sizeof(TYPE)] = { [0 ... 16 / sizeof(TYPE) - 1] = INIT }; \
+ TYPE *n = vn; uint16_t *g = vg; \
+ uintptr_t oprsz = simd_oprsz(desc); \
+ uintptr_t nseg = oprsz / 16, nsegelt = 16 / sizeof(TYPE); \
+ for (uintptr_t s = 0; s < nseg; s++) { \
+ uint16_t pg = g[H2(s)]; \
+ for (uintptr_t e = 0; e < nsegelt; e++, pg >>= sizeof(TYPE)) { \
+ if (pg & 1) { \
+ tmp[e] = OP(tmp[H(e)], n[s * nsegelt + H(e)]); \
+ } \
+ } \
+ } \
+ memcpy(vd, tmp, 16); \
+ clear_tail(vd, 16, simd_maxsz(desc)); \
+}
+
+DO_VPQ(sve2p1_addqv_b, uint8_t, H1, 0, DO_ADD)
+DO_VPQ(sve2p1_addqv_h, uint16_t, H2, 0, DO_ADD)
+DO_VPQ(sve2p1_addqv_s, uint32_t, H4, 0, DO_ADD)
+DO_VPQ(sve2p1_addqv_d, uint64_t, H8, 0, DO_ADD)
+
+DO_VPQ(sve2p1_smaxqv_b, int8_t, H1, INT8_MIN, DO_MAX)
+DO_VPQ(sve2p1_smaxqv_h, int16_t, H2, INT16_MIN, DO_MAX)
+DO_VPQ(sve2p1_smaxqv_s, int32_t, H4, INT32_MIN, DO_MAX)
+DO_VPQ(sve2p1_smaxqv_d, int64_t, H8, INT64_MIN, DO_MAX)
+
+DO_VPQ(sve2p1_sminqv_b, int8_t, H1, INT8_MAX, DO_MIN)
+DO_VPQ(sve2p1_sminqv_h, int16_t, H2, INT16_MAX, DO_MIN)
+DO_VPQ(sve2p1_sminqv_s, int32_t, H4, INT32_MAX, DO_MIN)
+DO_VPQ(sve2p1_sminqv_d, int64_t, H8, INT64_MAX, DO_MIN)
+
+DO_VPQ(sve2p1_umaxqv_b, uint8_t, H1, 0, DO_MAX)
+DO_VPQ(sve2p1_umaxqv_h, uint16_t, H2, 0, DO_MAX)
+DO_VPQ(sve2p1_umaxqv_s, uint32_t, H4, 0, DO_MAX)
+DO_VPQ(sve2p1_umaxqv_d, uint64_t, H8, 0, DO_MAX)
+
+DO_VPQ(sve2p1_uminqv_b, uint8_t, H1, -1, DO_MIN)
+DO_VPQ(sve2p1_uminqv_h, uint16_t, H2, -1, DO_MIN)
+DO_VPQ(sve2p1_uminqv_s, uint32_t, H4, -1, DO_MIN)
+DO_VPQ(sve2p1_uminqv_d, uint64_t, H8, -1, DO_MIN)
+
+#undef DO_VPQ
+
/* Two vector operand, one scalar operand, unpredicated. */
#define DO_ZZI(NAME, TYPE, OP) \
void HELPER(NAME)(void *vd, void *vn, uint64_t s64, uint32_t desc) \
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 651b4aa378..2e29dff989 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -828,6 +828,41 @@ TRANS_FEAT(SXTW, aa64_sve, gen_gvec_ool_arg_zpz,
TRANS_FEAT(UXTW, aa64_sve, gen_gvec_ool_arg_zpz,
a->esz == 3 ? gen_helper_sve_uxtw_d : NULL, a, 0)
+static gen_helper_gvec_3 * const addqv_fns[4] = {
+ gen_helper_sve2p1_addqv_b, gen_helper_sve2p1_addqv_h,
+ gen_helper_sve2p1_addqv_s, gen_helper_sve2p1_addqv_d,
+};
+TRANS_FEAT(ADDQV, aa64_sme2p1_or_sve2p1,
+ gen_gvec_ool_arg_zpz, addqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const smaxqv_fns[4] = {
+ gen_helper_sve2p1_smaxqv_b, gen_helper_sve2p1_smaxqv_h,
+ gen_helper_sve2p1_smaxqv_s, gen_helper_sve2p1_smaxqv_d,
+};
+TRANS_FEAT(SMAXQV, aa64_sme2p1_or_sve2p1,
+ gen_gvec_ool_arg_zpz, smaxqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const sminqv_fns[4] = {
+ gen_helper_sve2p1_sminqv_b, gen_helper_sve2p1_sminqv_h,
+ gen_helper_sve2p1_sminqv_s, gen_helper_sve2p1_sminqv_d,
+};
+TRANS_FEAT(SMINQV, aa64_sme2p1_or_sve2p1,
+ gen_gvec_ool_arg_zpz, sminqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const umaxqv_fns[4] = {
+ gen_helper_sve2p1_umaxqv_b, gen_helper_sve2p1_umaxqv_h,
+ gen_helper_sve2p1_umaxqv_s, gen_helper_sve2p1_umaxqv_d,
+};
+TRANS_FEAT(UMAXQV, aa64_sme2p1_or_sve2p1,
+ gen_gvec_ool_arg_zpz, umaxqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const uminqv_fns[4] = {
+ gen_helper_sve2p1_uminqv_b, gen_helper_sve2p1_uminqv_h,
+ gen_helper_sve2p1_uminqv_s, gen_helper_sve2p1_uminqv_d,
+};
+TRANS_FEAT(UMINQV, aa64_sme2p1_or_sve2p1,
+ gen_gvec_ool_arg_zpz, uminqv_fns[a->esz], a, 0)
+
/*
*** SVE Integer Reduction Group
*/
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 3517efb31b..a3221308ad 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -340,6 +340,13 @@ UMAXV 00000100 .. 001 001 001 ... ..... ..... @rd_pg_rn
SMINV 00000100 .. 001 010 001 ... ..... ..... @rd_pg_rn
UMINV 00000100 .. 001 011 001 ... ..... ..... @rd_pg_rn
+# SVE2.1 segment reduction
+ADDQV 00000100 .. 000 101 001 ... ..... ..... @rd_pg_rn
+SMAXQV 00000100 .. 001 100 001 ... ..... ..... @rd_pg_rn
+SMINQV 00000100 .. 001 110 001 ... ..... ..... @rd_pg_rn
+UMAXQV 00000100 .. 001 101 001 ... ..... ..... @rd_pg_rn
+UMINQV 00000100 .. 001 111 001 ... ..... ..... @rd_pg_rn
+
### SVE Shift by Immediate - Predicated Group
# SVE bitwise shift by immediate (predicated)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 70/97] target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1
2025-07-02 12:33 ` [PATCH v3 70/97] target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1 Richard Henderson
@ 2025-07-03 12:15 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:15 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 71/97] target/arm: Implement SVE2p1 PEXT
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (69 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 70/97] target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:19 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 72/97] target/arm: Implement SME2 SEL Richard Henderson
` (25 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 2 +
target/arm/tcg/vec_internal.h | 74 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sve_helper.c | 27 +++++++++++++
target/arm/tcg/translate-sve.c | 36 +++++++++++++++++
target/arm/tcg/sve.decode | 6 +++
5 files changed, 145 insertions(+)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 5f5ecc2e0d..ec82d0a4e7 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -2953,3 +2953,5 @@ DEF_HELPER_FLAGS_4(sve2p1_uminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_uminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(pext, TCG_CALL_NO_RWG, void, ptr, i32, i32)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index 5efd257c50..236927c640 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -337,4 +337,78 @@ bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
float32 sve_f16_to_f32(float16 f, float_status *fpst);
float16 sve_f32_to_f16(float32 f, float_status *fpst);
+/*
+ * Decode helper functions for predicate as counter.
+ */
+
+typedef struct {
+ unsigned count;
+ unsigned stride;
+ bool invert;
+} DecodeCounter;
+
+static inline DecodeCounter
+decode_counter(unsigned png, unsigned vl, unsigned v_esz)
+{
+ DecodeCounter ret = { .stride = 1 };
+
+ /* C.f. Arm pseudocode CounterToPredicate. */
+ if (likely(png & 0xf)) {
+ unsigned p_esz = ctz32(png);
+
+ /*
+ * maxbit = log2(pl(bits) * 4)
+ * = log2(vl(bytes) * 4)
+ * = log2(vl) + 2
+ * maxbit_mask = ones<maxbit:0>
+ * = (1 << (maxbit + 1)) - 1
+ * = (1 << (log2(vl) + 2 + 1)) - 1
+ * = (1 << (log2(vl) + 3)) - 1
+ * = (pow2ceil(vl) << 3) - 1
+ */
+ ret.count = png & (((unsigned)pow2ceil(vl) << 3) - 1);
+ ret.count >>= p_esz + 1;
+
+ ret.invert = (png >> 15) & 1;
+
+ /*
+ * The Arm pseudocode for CounterToPredicate expands the count to
+ * a set of bits, and then the operation proceeds as for the original
+ * interpretation of predicates as a set of bits.
+ *
+ * We can avoid the expansion by adjusting the count and supplying
+ * an element stride.
+ */
+ if (unlikely(p_esz != v_esz)) {
+ if (p_esz < v_esz) {
+ /*
+ * For predicate esz < vector esz, the expanded predicate
+ * will have more bits set than will be consumed.
+ * Adjust the count down, rounding up.
+ * Consider p_esz = MO_8, v_esz = MO_64, count 14:
+ * The expanded predicate would be
+ * 0011 1111 1111 1111
+ * The significant bits are
+ * ...1 ...1 ...1 ...1
+ */
+ unsigned shift = v_esz - p_esz;
+ unsigned trunc = ret.count >> shift;
+ ret.count = trunc + (ret.count != (trunc << shift));
+ } else {
+ /*
+ * For predicate esz > vector esz, the expanded predicate
+ * will have bits set only at power-of-two multiples of
+ * the vector esz. Bits at other multiples will all be
+ * false. Adjust the count up, and supply the caller
+ * with a stride of elements to skip.
+ */
+ unsigned shift = p_esz - v_esz;
+ ret.count <<= shift;
+ ret.stride = 1 << shift;
+ }
+ }
+ }
+ return ret;
+}
+
#endif /* TARGET_ARM_VEC_INTERNAL_H */
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index cc706db901..59ba1caf02 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -7825,3 +7825,30 @@ DO_FCVTLT(sve2_fcvtlt_sd, uint64_t, uint32_t, H1_8, H1_4, float32_to_float64)
#undef DO_FCVTLT
#undef DO_FCVTNT
+
+void HELPER(pext)(void *vd, uint32_t png, uint32_t desc)
+{
+ int pl = FIELD_EX32(desc, PREDDESC, OPRSZ);
+ int vl = pl * 8;
+ unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ);
+ int part = FIELD_EX32(desc, PREDDESC, DATA);
+ DecodeCounter p = decode_counter(png, vl, v_esz);
+ uint64_t mask = pred_esz_masks[v_esz + ctz32(p.stride)];
+
+ /*
+ * Convert from element count to byte count and adjust
+ * for the portion of the 4*VL counter to be extracted.
+ */
+ int b_count = (p.count << v_esz) - vl * part;
+
+ do_zero(vd, pl);
+ if (p.invert) {
+ if (b_count <= 0) {
+ do_whilel(vd, mask, vl, vl);
+ } else if (b_count < vl) {
+ do_whileg(vd, mask, vl - b_count, vl);
+ }
+ } else if (b_count > 0) {
+ do_whilel(vd, mask, MIN(b_count, vl), vl);
+ }
+}
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 2e29dff989..6ad4d1e289 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3336,6 +3336,42 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
return true;
}
+static bool do_pext(DisasContext *s, arg_pext *a, int n)
+{
+ TCGv_i32 t_png;
+ TCGv_ptr t_pd;
+ int pl;
+
+ if (!sve_access_check(s)) {
+ return true;
+ }
+
+ t_png = tcg_temp_new_i32();
+ tcg_gen_ld16u_i32(t_png, tcg_env,
+ pred_full_reg_offset(s, a->rn) ^
+ (HOST_BIG_ENDIAN ? 6 : 0));
+
+ t_pd = tcg_temp_new_ptr();
+ pl = pred_full_reg_size(s);
+
+ for (int i = 0; i < n; ++i) {
+ int rd = (a->rd + i) % 16;
+ int part = a->imm * n + i;
+ unsigned desc = 0;
+
+ desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pl);
+ desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
+ desc = FIELD_DP32(desc, PREDDESC, DATA, part);
+
+ tcg_gen_addi_ptr(t_pd, tcg_env, pred_full_reg_offset(s, rd));
+ gen_helper_pext(t_pd, t_png, tcg_constant_i32(desc));
+ }
+ return true;
+}
+
+TRANS_FEAT(PEXT_1, aa64_sme2_or_sve2p1, do_pext, a, 1)
+TRANS_FEAT(PEXT_2, aa64_sme2_or_sve2p1, do_pext, a, 2)
+
/*
*** SVE Integer Wide Immediate - Unpredicated Group
*/
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index a3221308ad..b762257759 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -60,6 +60,7 @@
%rn_ax2 6:4 !function=times_2
%pnd 0:3 !function=plus_8
+%pnn 5:3 !function=plus_8
###########################################################################
# Named attribute sets. These are used to make nice(er) names
@@ -823,6 +824,11 @@ WHILE_lt_cnt4 00100101 .. 1 ..... 0110 . 1 ..... 1 . ... @while_cnt
WHILE_gt_cnt2 00100101 .. 1 ..... 0100 . 0 ..... 1 . ... @while_cnt
WHILE_gt_cnt4 00100101 .. 1 ..... 0110 . 0 ..... 1 . ... @while_cnt
+# SVE2.1 extract mask predicate from predicate-as-counter
+&pext rd rn esz imm
+PEXT_1 00100101 esz:2 1 00000 0111 00 imm:2 ... 1 rd:4 &pext rn=%pnn
+PEXT_2 00100101 esz:2 1 00000 0111 010 imm:1 ... 1 rd:4 &pext rn=%pnn
+
### SVE Integer Wide Immediate - Unpredicated Group
# SVE broadcast floating-point immediate (unpredicated)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 71/97] target/arm: Implement SVE2p1 PEXT
2025-07-02 12:33 ` [PATCH v3 71/97] target/arm: Implement SVE2p1 PEXT Richard Henderson
@ 2025-07-03 12:19 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:19 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sve.h | 2 +
> target/arm/tcg/vec_internal.h | 74 ++++++++++++++++++++++++++++++++++
> target/arm/tcg/sve_helper.c | 27 +++++++++++++
> target/arm/tcg/translate-sve.c | 36 +++++++++++++++++
> target/arm/tcg/sve.decode | 6 +++
> 5 files changed, 145 insertions(+)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 72/97] target/arm: Implement SME2 SEL
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (70 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 71/97] target/arm: Implement SVE2p1 PEXT Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:21 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 73/97] target/arm: Implement ANDQV, ORQV, EORQV for SVE2p1 Richard Henderson
` (24 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 5 +
target/arm/tcg/sme_helper.c | 315 +++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 31 ++++
target/arm/tcg/sme.decode | 9 +
4 files changed, 360 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 78ba3d1f20..467073ea25 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -313,3 +313,8 @@ DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i3
DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sme2_sel_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
+DEF_HELPER_FLAGS_5(sme2_sel_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index bfcedef3d9..77eab68870 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -2107,3 +2107,318 @@ FCLAMP(sme2_fclamp_d, float64, H8)
FCLAMP(sme2_bfclamp, bfloat16, H2)
#undef FCLAMP
+
+void HELPER(sme2_sel_b)(void *vd, void *vn, void *vm,
+ uint32_t png, uint32_t desc)
+{
+ int vl = simd_oprsz(desc);
+ int nreg = simd_data(desc);
+ int elements = vl / sizeof(uint8_t);
+ DecodeCounter p = decode_counter(png, vl, MO_8);
+
+ if (p.stride == 1) {
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint8_t *d = vd + r * sizeof(ARMVectorReg);
+ uint8_t *n = vn + r * sizeof(ARMVectorReg);
+ uint8_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, n, vl); /* all true */
+ } else if (elements <= split) {
+ memcpy(d, m, vl); /* all false */
+ } else {
+ for (int e = 0; e < split; e++) {
+ d[H1(e)] = m[H1(e)];
+ }
+ for (int e = split; e < elements; e++) {
+ d[H1(e)] = n[H1(e)];
+ }
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint8_t *d = vd + r * sizeof(ARMVectorReg);
+ uint8_t *n = vn + r * sizeof(ARMVectorReg);
+ uint8_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, m, vl); /* all false */
+ } else if (elements <= split) {
+ memcpy(d, n, vl); /* all true */
+ } else {
+ for (int e = 0; e < split; e++) {
+ d[H1(e)] = n[H1(e)];
+ }
+ for (int e = split; e < elements; e++) {
+ d[H1(e)] = m[H1(e)];
+ }
+ }
+ }
+ }
+ } else {
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint8_t *d = vd + r * sizeof(ARMVectorReg);
+ uint8_t *n = vn + r * sizeof(ARMVectorReg);
+ uint8_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+ int e = 0;
+
+ for (; e < MIN(split, elements); e++) {
+ d[H1(e)] = m[H1(e)];
+ }
+ for (; e < elements; e += p.stride) {
+ d[H1(e)] = n[H1(e)];
+ for (int i = 1; i < p.stride; i++) {
+ d[H1(e + i)] = m[H1(e + i)];
+ }
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint8_t *d = vd + r * sizeof(ARMVectorReg);
+ uint8_t *n = vn + r * sizeof(ARMVectorReg);
+ uint8_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+ int e = 0;
+
+ for (; e < MIN(split, elements); e += p.stride) {
+ d[H1(e)] = n[H1(e)];
+ for (int i = 1; i < p.stride; i++) {
+ d[H1(e + i)] = m[H1(e + i)];
+ }
+ }
+ for (; e < elements; e++) {
+ d[H1(e)] = m[H1(e)];
+ }
+ }
+ }
+ }
+}
+
+void HELPER(sme2_sel_h)(void *vd, void *vn, void *vm,
+ uint32_t png, uint32_t desc)
+{
+ int vl = simd_oprsz(desc);
+ int nreg = simd_data(desc);
+ int elements = vl / sizeof(uint16_t);
+ DecodeCounter p = decode_counter(png, vl, MO_16);
+
+ if (p.stride == 1) {
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint16_t *d = vd + r * sizeof(ARMVectorReg);
+ uint16_t *n = vn + r * sizeof(ARMVectorReg);
+ uint16_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, n, vl); /* all true */
+ } else if (elements <= split) {
+ memcpy(d, m, vl); /* all false */
+ } else {
+ for (int e = 0; e < split; e++) {
+ d[H2(e)] = m[H2(e)];
+ }
+ for (int e = split; e < elements; e++) {
+ d[H2(e)] = n[H2(e)];
+ }
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint16_t *d = vd + r * sizeof(ARMVectorReg);
+ uint16_t *n = vn + r * sizeof(ARMVectorReg);
+ uint16_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, m, vl); /* all false */
+ } else if (elements <= split) {
+ memcpy(d, n, vl); /* all true */
+ } else {
+ for (int e = 0; e < split; e++) {
+ d[H2(e)] = n[H2(e)];
+ }
+ for (int e = split; e < elements; e++) {
+ d[H2(e)] = m[H2(e)];
+ }
+ }
+ }
+ }
+ } else {
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint16_t *d = vd + r * sizeof(ARMVectorReg);
+ uint16_t *n = vn + r * sizeof(ARMVectorReg);
+ uint16_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+ int e = 0;
+
+ for (; e < MIN(split, elements); e++) {
+ d[H2(e)] = m[H2(e)];
+ }
+ for (; e < elements; e += p.stride) {
+ d[H2(e)] = n[H2(e)];
+ for (int i = 1; i < p.stride; i++) {
+ d[H2(e + i)] = m[H2(e + i)];
+ }
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint16_t *d = vd + r * sizeof(ARMVectorReg);
+ uint16_t *n = vn + r * sizeof(ARMVectorReg);
+ uint16_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+ int e = 0;
+
+ for (; e < MIN(split, elements); e += p.stride) {
+ d[H2(e)] = n[H2(e)];
+ for (int i = 1; i < p.stride; i++) {
+ d[H2(e + i)] = m[H2(e + i)];
+ }
+ }
+ for (; e < elements; e++) {
+ d[H2(e)] = m[H2(e)];
+ }
+ }
+ }
+ }
+}
+
+void HELPER(sme2_sel_s)(void *vd, void *vn, void *vm,
+ uint32_t png, uint32_t desc)
+{
+ int vl = simd_oprsz(desc);
+ int nreg = simd_data(desc);
+ int elements = vl / sizeof(uint32_t);
+ DecodeCounter p = decode_counter(png, vl, MO_32);
+
+ if (p.stride == 1) {
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint32_t *d = vd + r * sizeof(ARMVectorReg);
+ uint32_t *n = vn + r * sizeof(ARMVectorReg);
+ uint32_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, n, vl); /* all true */
+ } else if (elements <= split) {
+ memcpy(d, m, vl); /* all false */
+ } else {
+ for (int e = 0; e < split; e++) {
+ d[H4(e)] = m[H4(e)];
+ }
+ for (int e = split; e < elements; e++) {
+ d[H4(e)] = n[H4(e)];
+ }
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint32_t *d = vd + r * sizeof(ARMVectorReg);
+ uint32_t *n = vn + r * sizeof(ARMVectorReg);
+ uint32_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, m, vl); /* all false */
+ } else if (elements <= split) {
+ memcpy(d, n, vl); /* all true */
+ } else {
+ for (int e = 0; e < split; e++) {
+ d[H4(e)] = n[H4(e)];
+ }
+ for (int e = split; e < elements; e++) {
+ d[H4(e)] = m[H4(e)];
+ }
+ }
+ }
+ }
+ } else {
+ /* p.esz must be MO_64, so stride must be 2. */
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint32_t *d = vd + r * sizeof(ARMVectorReg);
+ uint32_t *n = vn + r * sizeof(ARMVectorReg);
+ uint32_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+ int e = 0;
+
+ for (; e < MIN(split, elements); e++) {
+ d[H4(e)] = m[H4(e)];
+ }
+ for (; e < elements; e += 2) {
+ d[H4(e)] = n[H4(e)];
+ d[H4(e + 1)] = m[H4(e + 1)];
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint32_t *d = vd + r * sizeof(ARMVectorReg);
+ uint32_t *n = vn + r * sizeof(ARMVectorReg);
+ uint32_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+ int e = 0;
+
+ for (; e < MIN(split, elements); e += 2) {
+ d[H4(e)] = n[H4(e)];
+ d[H4(e + 1)] = m[H4(e + 1)];
+ }
+ for (; e < elements; e++) {
+ d[H4(e)] = m[H4(e)];
+ }
+ }
+ }
+ }
+}
+
+void HELPER(sme2_sel_d)(void *vd, void *vn, void *vm,
+ uint32_t png, uint32_t desc)
+{
+ int vl = simd_oprsz(desc);
+ int nreg = simd_data(desc);
+ int elements = vl / sizeof(uint64_t);
+ DecodeCounter p = decode_counter(png, vl, MO_64);
+
+ if (p.invert) {
+ for (int r = 0; r < nreg; r++) {
+ uint64_t *d = vd + r * sizeof(ARMVectorReg);
+ uint64_t *n = vn + r * sizeof(ARMVectorReg);
+ uint64_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, n, vl); /* all true */
+ } else if (elements <= split) {
+ memcpy(d, m, vl); /* all false */
+ } else {
+ memcpy(d, m, split * sizeof(uint64_t));
+ memcpy(d + split, n + split,
+ (elements - split) * sizeof(uint64_t));
+ }
+ }
+ } else {
+ for (int r = 0; r < nreg; r++) {
+ uint64_t *d = vd + r * sizeof(ARMVectorReg);
+ uint64_t *n = vn + r * sizeof(ARMVectorReg);
+ uint64_t *m = vm + r * sizeof(ARMVectorReg);
+ int split = p.count - r * elements;
+
+ if (split <= 0) {
+ memcpy(d, m, vl); /* all false */
+ } else if (elements <= split) {
+ memcpy(d, n, vl); /* all true */
+ } else {
+ memcpy(d, n, split * sizeof(uint64_t));
+ memcpy(d + split, m + split,
+ (elements - split) * sizeof(uint64_t));
+ }
+ }
+ }
+}
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index b6316ac716..7407597177 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1642,3 +1642,34 @@ static gen_helper_gvec_3 * const uclamp_fns[] = {
gen_helper_sme2_uclamp_d,
};
TRANS(UCLAMP, do_clamp, a, uclamp_fns)
+
+static bool trans_SEL(DisasContext *s, arg_SEL *a)
+{
+ typedef void sme_sel_fn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32);
+ static sme_sel_fn * const fns[4] = {
+ gen_helper_sme2_sel_b, gen_helper_sme2_sel_h,
+ gen_helper_sme2_sel_s, gen_helper_sme2_sel_d
+ };
+
+ if (!dc_isar_feature(aa64_sme2, s)) {
+ return false;
+ }
+ if (sme_sm_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ uint32_t desc = simd_desc(svl, svl, a->n);
+ TCGv_ptr t_d = tcg_temp_new_ptr();
+ TCGv_ptr t_n = tcg_temp_new_ptr();
+ TCGv_ptr t_m = tcg_temp_new_ptr();
+ TCGv_i32 png = tcg_temp_new_i32();
+
+ tcg_gen_addi_ptr(t_d, tcg_env, vec_full_reg_offset(s, a->zd));
+ tcg_gen_addi_ptr(t_n, tcg_env, vec_full_reg_offset(s, a->zn));
+ tcg_gen_addi_ptr(t_m, tcg_env, vec_full_reg_offset(s, a->zm));
+
+ tcg_gen_ld16u_i32(png, tcg_env, pred_full_reg_offset(s, a->pg)
+ ^ (HOST_BIG_ENDIAN ? 6 : 0));
+
+ fns[a->esz](t_d, t_n, t_m, png, tcg_constant_i32(desc));
+ }
+ return true;
+}
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index c4b85a36d0..0a2ceea8be 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -878,6 +878,15 @@ UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \
UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \
&zzz_en zd=%zd_ax4 n=4
+### SME2 Multi-vector SVE Select
+
+%sel_pg 10:3 !function=plus_8
+
+SEL 11000001 esz:2 1 ....0 100 ... ....0 ....0 \
+ n=2 zd=%zd_ax2 zn=%zn_ax2 zm=%zm_ax2 pg=%sel_pg
+SEL 11000001 esz:2 1 ...01 100 ... ...00 ...00 \
+ n=4 zd=%zd_ax4 zn=%zn_ax4 zm=%zm_ax4 pg=%sel_pg
+
### SME Multiple Zero
&zero_za rv off ngrp nvec
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 73/97] target/arm: Implement ANDQV, ORQV, EORQV for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (71 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 72/97] target/arm: Implement SME2 SEL Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:23 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 74/97] target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV " Richard Henderson
` (23 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 15 ++++++++++++
target/arm/tcg/sve_helper.c | 42 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 3 +++
target/arm/tcg/sve.decode | 5 ++++
4 files changed, 65 insertions(+)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index ec82d0a4e7..9758613b2d 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -2955,3 +2955,18 @@ DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(pext, TCG_CALL_NO_RWG, void, ptr, i32, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_orqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_orqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_orqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_orqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_eorqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_eorqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_eorqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_eorqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_andqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_andqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_andqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_andqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 59ba1caf02..bc5e039689 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -123,6 +123,11 @@ static inline uint64_t expand_pred_s(uint8_t byte)
return word[byte & 0x11];
}
+static inline uint64_t expand_pred_d(uint8_t byte)
+{
+ return -(uint64_t)(byte & 1);
+}
+
#define LOGICAL_PPPP(NAME, FUNC) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \
{ \
@@ -206,6 +211,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \
#define DO_EOR(N, M) (N ^ M)
#define DO_ORR(N, M) (N | M)
#define DO_BIC(N, M) (N & ~M)
+#define DO_ORC(N, M) (N | ~M)
#define DO_ADD(N, M) (N + M)
#define DO_SUB(N, M) (N - M)
#define DO_MAX(N, M) ((N) >= (M) ? (N) : (M))
@@ -1900,10 +1906,46 @@ DO_ZZI(sve_umini_d, uint64_t, DO_MIN)
#undef DO_ZZI
+#define DO_LOGIC_QV(NAME, SUFF, INIT, VOP, POP) \
+void HELPER(NAME ## _ ## SUFF)(void *vd, void *vn, void *vg, uint32_t desc) \
+{ \
+ unsigned seg = simd_oprsz(desc) / 16; \
+ uint64_t r0 = INIT, r1 = INIT; \
+ for (unsigned s = 0; s < seg; s++) { \
+ uint64_t p0 = expand_pred_##SUFF(*(uint8_t *)(vg + H1(s * 2))); \
+ uint64_t p1 = expand_pred_##SUFF(*(uint8_t *)(vg + H1(s * 2 + 1))); \
+ uint64_t v0 = *(uint64_t *)(vn + s * 16); \
+ uint64_t v1 = *(uint64_t *)(vn + s * 16 + 8); \
+ v0 = POP(v0, p0), v1 = POP(v1, p1); \
+ r0 = VOP(r0, v0), r1 = VOP(r1, v1); \
+ } \
+ *(uint64_t *)(vd + 0) = r0; \
+ *(uint64_t *)(vd + 8) = r1; \
+ clear_tail(vd, 16, simd_maxsz(desc)); \
+}
+
+DO_LOGIC_QV(sve2p1_orqv, b, 0, DO_ORR, DO_AND)
+DO_LOGIC_QV(sve2p1_orqv, h, 0, DO_ORR, DO_AND)
+DO_LOGIC_QV(sve2p1_orqv, s, 0, DO_ORR, DO_AND)
+DO_LOGIC_QV(sve2p1_orqv, d, 0, DO_ORR, DO_AND)
+
+DO_LOGIC_QV(sve2p1_eorqv, b, 0, DO_EOR, DO_AND)
+DO_LOGIC_QV(sve2p1_eorqv, h, 0, DO_EOR, DO_AND)
+DO_LOGIC_QV(sve2p1_eorqv, s, 0, DO_EOR, DO_AND)
+DO_LOGIC_QV(sve2p1_eorqv, d, 0, DO_EOR, DO_AND)
+
+DO_LOGIC_QV(sve2p1_andqv, b, -1, DO_AND, DO_ORC)
+DO_LOGIC_QV(sve2p1_andqv, h, -1, DO_AND, DO_ORC)
+DO_LOGIC_QV(sve2p1_andqv, s, -1, DO_AND, DO_ORC)
+DO_LOGIC_QV(sve2p1_andqv, d, -1, DO_AND, DO_ORC)
+
+#undef DO_LOGIC_QV
+
#undef DO_AND
#undef DO_ORR
#undef DO_EOR
#undef DO_BIC
+#undef DO_ORC
#undef DO_ADD
#undef DO_SUB
#undef DO_MAX
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 6ad4d1e289..2114b2ecca 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -778,6 +778,9 @@ DO_ZPZ(NOT_zpz, aa64_sve, sve_not_zpz)
DO_ZPZ(ABS, aa64_sve, sve_abs)
DO_ZPZ(NEG, aa64_sve, sve_neg)
DO_ZPZ(RBIT, aa64_sve, sve_rbit)
+DO_ZPZ(ORQV, aa64_sme2p1_or_sve2p1, sve2p1_orqv)
+DO_ZPZ(EORQV, aa64_sme2p1_or_sve2p1, sve2p1_eorqv)
+DO_ZPZ(ANDQV, aa64_sme2p1_or_sve2p1, sve2p1_andqv)
static gen_helper_gvec_3 * const fabs_fns[4] = {
NULL, gen_helper_sve_fabs_h,
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index b762257759..ff740f7b40 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -326,6 +326,11 @@ ORV 00000100 .. 011 000 001 ... ..... ..... @rd_pg_rn
EORV 00000100 .. 011 001 001 ... ..... ..... @rd_pg_rn
ANDV 00000100 .. 011 010 001 ... ..... ..... @rd_pg_rn
+# SVE2.1 bitwise logical reduction (quadwords)
+ORQV 00000100 .. 011 100 001 ... ..... ..... @rd_pg_rn
+EORQV 00000100 .. 011 101 001 ... ..... ..... @rd_pg_rn
+ANDQV 00000100 .. 011 110 001 ... ..... ..... @rd_pg_rn
+
# SVE constructive prefix (predicated)
MOVPRFX_z 00000100 .. 010 000 001 ... ..... ..... @rd_pg_rn
MOVPRFX_m 00000100 .. 010 001 001 ... ..... ..... @rd_pg_rn
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 74/97] target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (72 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 73/97] target/arm: Implement ANDQV, ORQV, EORQV for SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:24 ` [PATCH v3 74/97] target/arm: Implement FADDQV, F{MIN,MAX}{NM}QV " Peter Maydell
2025-07-02 12:33 ` [PATCH v3 75/97] target/arm: Implement BFMLSLB{L,T} for SME2/SVE2p1 Richard Henderson
` (22 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 49 ++++++++++++++++++++++++
target/arm/tcg/sve_helper.c | 70 +++++++++++++++++++++-------------
target/arm/tcg/translate-sve.c | 48 +++++++++++++++++++++++
target/arm/tcg/sve.decode | 8 ++++
4 files changed, 148 insertions(+), 27 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 9758613b2d..906da384dc 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1077,6 +1077,55 @@ DEF_HELPER_FLAGS_4(sve_ah_fminv_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_4(sve_ah_fminv_d, TCG_CALL_NO_RWG,
i64, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_faddqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_faddqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_faddqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_fminqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fminqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_fminqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, fpst, i32)
+
DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG,
i64, i64, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index bc5e039689..11139e6405 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4365,19 +4365,20 @@ uint32_t HELPER(sve_whilecg)(void *vd, uint32_t count, uint32_t pred_desc)
* The recursion is bounded to depth 7 (128 fp16 elements), so there's
* little to gain with a more complex non-recursive form.
*/
-#define DO_REDUCE(NAME, TYPE, H, FUNC, IDENT) \
-static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \
+#define DO_REDUCE(NAME, SUF, TYPE, H, FUNC, IDENT) \
+static TYPE FUNC##_reduce(TYPE *data, float_status *status, uintptr_t n) \
{ \
if (n == 1) { \
return *data; \
} else { \
uintptr_t half = n / 2; \
- TYPE lo = NAME##_reduce(data, status, half); \
- TYPE hi = NAME##_reduce(data + half, status, half); \
+ TYPE lo = FUNC##_reduce(data, status, half); \
+ TYPE hi = FUNC##_reduce(data + half, status, half); \
return FUNC(lo, hi, status); \
} \
} \
-uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \
+uint64_t helper_sve_##NAME##v_##SUF(void *vn, void *vg, \
+ float_status *s, uint32_t desc) \
{ \
uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_data(desc); \
TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \
@@ -4392,39 +4393,54 @@ uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \
for (; i < maxsz; i += sizeof(TYPE)) { \
*(TYPE *)((void *)data + i) = IDENT; \
} \
- return NAME##_reduce(data, s, maxsz / sizeof(TYPE)); \
+ return FUNC##_reduce(data, s, maxsz / sizeof(TYPE)); \
+} \
+void helper_sve2p1_##NAME##qv_##SUF(void *vd, void *vn, void *vg, \
+ float_status *status, uint32_t desc) \
+{ \
+ unsigned oprsz = simd_oprsz(desc), segments = oprsz / 16; \
+ for (unsigned e = 0; e < 16; e += sizeof(TYPE)) { \
+ TYPE data[ARM_MAX_VQ]; \
+ for (unsigned s = 0; s < segments; s++) { \
+ uint16_t pg = *(uint16_t *)(vg + H1_2(s * 2)); \
+ TYPE nn = *(TYPE *)(vn + H(s * 16 + H(e))); \
+ data[s] = (pg >> e) & 1 ? nn : IDENT; \
+ } \
+ *(TYPE *)(vd + H(e)) = FUNC##_reduce(data, status, segments); \
+ } \
+ clear_tail(vd, 16, simd_maxsz(desc)); \
}
-DO_REDUCE(sve_faddv_h, float16, H1_2, float16_add, float16_zero)
-DO_REDUCE(sve_faddv_s, float32, H1_4, float32_add, float32_zero)
-DO_REDUCE(sve_faddv_d, float64, H1_8, float64_add, float64_zero)
+DO_REDUCE(fadd,h, float16, H1_2, float16_add, float16_zero)
+DO_REDUCE(fadd,s, float32, H1_4, float32_add, float32_zero)
+DO_REDUCE(fadd,d, float64, H1_8, float64_add, float64_zero)
/* Identity is floatN_default_nan, without the function call. */
-DO_REDUCE(sve_fminnmv_h, float16, H1_2, float16_minnum, 0x7E00)
-DO_REDUCE(sve_fminnmv_s, float32, H1_4, float32_minnum, 0x7FC00000)
-DO_REDUCE(sve_fminnmv_d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL)
+DO_REDUCE(fminnm,h, float16, H1_2, float16_minnum, 0x7E00)
+DO_REDUCE(fminnm,s, float32, H1_4, float32_minnum, 0x7FC00000)
+DO_REDUCE(fminnm,d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL)
-DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, float16_maxnum, 0x7E00)
-DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, float32_maxnum, 0x7FC00000)
-DO_REDUCE(sve_fmaxnmv_d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL)
+DO_REDUCE(fmaxnm,h, float16, H1_2, float16_maxnum, 0x7E00)
+DO_REDUCE(fmaxnm,s, float32, H1_4, float32_maxnum, 0x7FC00000)
+DO_REDUCE(fmaxnm,d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL)
-DO_REDUCE(sve_fminv_h, float16, H1_2, float16_min, float16_infinity)
-DO_REDUCE(sve_fminv_s, float32, H1_4, float32_min, float32_infinity)
-DO_REDUCE(sve_fminv_d, float64, H1_8, float64_min, float64_infinity)
+DO_REDUCE(fmin,h, float16, H1_2, float16_min, float16_infinity)
+DO_REDUCE(fmin,s, float32, H1_4, float32_min, float32_infinity)
+DO_REDUCE(fmin,d, float64, H1_8, float64_min, float64_infinity)
-DO_REDUCE(sve_fmaxv_h, float16, H1_2, float16_max, float16_chs(float16_infinity))
-DO_REDUCE(sve_fmaxv_s, float32, H1_4, float32_max, float32_chs(float32_infinity))
-DO_REDUCE(sve_fmaxv_d, float64, H1_8, float64_max, float64_chs(float64_infinity))
+DO_REDUCE(fmax,h, float16, H1_2, float16_max, float16_chs(float16_infinity))
+DO_REDUCE(fmax,s, float32, H1_4, float32_max, float32_chs(float32_infinity))
+DO_REDUCE(fmax,d, float64, H1_8, float64_max, float64_chs(float64_infinity))
-DO_REDUCE(sve_ah_fminv_h, float16, H1_2, helper_vfp_ah_minh, float16_infinity)
-DO_REDUCE(sve_ah_fminv_s, float32, H1_4, helper_vfp_ah_mins, float32_infinity)
-DO_REDUCE(sve_ah_fminv_d, float64, H1_8, helper_vfp_ah_mind, float64_infinity)
+DO_REDUCE(ah_fmin,h, float16, H1_2, helper_vfp_ah_minh, float16_infinity)
+DO_REDUCE(ah_fmin,s, float32, H1_4, helper_vfp_ah_mins, float32_infinity)
+DO_REDUCE(ah_fmin,d, float64, H1_8, helper_vfp_ah_mind, float64_infinity)
-DO_REDUCE(sve_ah_fmaxv_h, float16, H1_2, helper_vfp_ah_maxh,
+DO_REDUCE(ah_fmax,h, float16, H1_2, helper_vfp_ah_maxh,
float16_chs(float16_infinity))
-DO_REDUCE(sve_ah_fmaxv_s, float32, H1_4, helper_vfp_ah_maxs,
+DO_REDUCE(ah_fmax,s, float32, H1_4, helper_vfp_ah_maxs,
float32_chs(float32_infinity))
-DO_REDUCE(sve_ah_fmaxv_d, float64, H1_8, helper_vfp_ah_maxd,
+DO_REDUCE(ah_fmax,d, float64, H1_8, helper_vfp_ah_maxd,
float64_chs(float64_infinity))
#undef DO_REDUCE
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 2114b2ecca..05c0fc948a 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3743,6 +3743,54 @@ DO_VPZ_AH(FMAXV, fmaxv)
#undef DO_VPZ
+static gen_helper_gvec_3_ptr * const faddqv_fns[4] = {
+ NULL, gen_helper_sve2p1_faddqv_h,
+ gen_helper_sve2p1_faddqv_s, gen_helper_sve2p1_faddqv_d,
+};
+TRANS_FEAT(FADDQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz,
+ faddqv_fns[a->esz], a, 0,
+ a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
+
+static gen_helper_gvec_3_ptr * const fmaxnmqv_fns[4] = {
+ NULL, gen_helper_sve2p1_fmaxnmqv_h,
+ gen_helper_sve2p1_fmaxnmqv_s, gen_helper_sve2p1_fmaxnmqv_d,
+};
+TRANS_FEAT(FMAXNMQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz,
+ fmaxnmqv_fns[a->esz], a, 0,
+ a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
+
+static gen_helper_gvec_3_ptr * const fminnmqv_fns[4] = {
+ NULL, gen_helper_sve2p1_fminnmqv_h,
+ gen_helper_sve2p1_fminnmqv_s, gen_helper_sve2p1_fminnmqv_d,
+};
+TRANS_FEAT(FMINNMQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz,
+ fminnmqv_fns[a->esz], a, 0,
+ a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
+
+static gen_helper_gvec_3_ptr * const fmaxqv_fns[4] = {
+ NULL, gen_helper_sve2p1_fmaxqv_h,
+ gen_helper_sve2p1_fmaxqv_s, gen_helper_sve2p1_fmaxqv_d,
+};
+static gen_helper_gvec_3_ptr * const fmaxqv_ah_fns[4] = {
+ NULL, gen_helper_sve2p1_ah_fmaxqv_h,
+ gen_helper_sve2p1_ah_fmaxqv_s, gen_helper_sve2p1_ah_fmaxqv_d,
+};
+TRANS_FEAT(FMAXQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz,
+ (s->fpcr_ah ? fmaxqv_fns : fmaxqv_ah_fns)[a->esz], a, 0,
+ a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
+
+static gen_helper_gvec_3_ptr * const fminqv_fns[4] = {
+ NULL, gen_helper_sve2p1_fminqv_h,
+ gen_helper_sve2p1_fminqv_s, gen_helper_sve2p1_fminqv_d,
+};
+static gen_helper_gvec_3_ptr * const fminqv_ah_fns[4] = {
+ NULL, gen_helper_sve2p1_ah_fminqv_h,
+ gen_helper_sve2p1_ah_fminqv_s, gen_helper_sve2p1_ah_fminqv_d,
+};
+TRANS_FEAT(FMINQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz,
+ (s->fpcr_ah ? fminqv_fns : fminqv_ah_fns)[a->esz], a, 0,
+ a->esz == MO_16 ? FPST_A64_F16 : FPST_A64)
+
/*
*** SVE Floating Point Unary Operations - Unpredicated Group
*/
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index ff740f7b40..10cac2de22 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1036,6 +1036,14 @@ FMINNMV 01100101 .. 000 101 001 ... ..... ..... @rd_pg_rn
FMAXV 01100101 .. 000 110 001 ... ..... ..... @rd_pg_rn
FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn
+### SVE FP recursive reduction (quadwords)
+
+FADDQV 01100100 .. 010 000 101 ... ..... ..... @rd_pg_rn
+FMAXNMQV 01100100 .. 010 100 101 ... ..... ..... @rd_pg_rn
+FMINNMQV 01100100 .. 010 101 101 ... ..... ..... @rd_pg_rn
+FMAXQV 01100100 .. 010 110 101 ... ..... ..... @rd_pg_rn
+FMINQV 01100100 .. 010 111 101 ... ..... ..... @rd_pg_rn
+
## SVE Floating Point Unary Operations - Unpredicated Group
FRECPE 01100101 .. 001 110 001100 ..... ..... @rd_rn
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 74/97] target/arm: Implement FADDQV, F{MIN,MAX}{NM}QV for SVE2p1
2025-07-02 12:33 ` [PATCH v3 74/97] target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV " Richard Henderson
@ 2025-07-03 12:24 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:24 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sve.h | 49 ++++++++++++++++++++++++
> target/arm/tcg/sve_helper.c | 70 +++++++++++++++++++++-------------
> target/arm/tcg/translate-sve.c | 48 +++++++++++++++++++++++
> target/arm/tcg/sve.decode | 8 ++++
> 4 files changed, 148 insertions(+), 27 deletions(-)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 75/97] target/arm: Implement BFMLSLB{L,T} for SME2/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (73 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 74/97] target/arm: Implement FADDQV, F{MIN, MAX}{NM}QV " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:24 ` [PATCH v3 75/97] target/arm: Implement BFMLSLB{L, T} " Peter Maydell
2025-07-02 12:33 ` [PATCH v3 76/97] target/arm: Implement CNTP (predicate as counter) " Richard Henderson
` (21 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++
target/arm/tcg/sve.decode | 6 ++++++
2 files changed, 36 insertions(+)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 05c0fc948a..079d310960 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7421,6 +7421,36 @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false)
TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true)
+static bool do_BFMLSL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel)
+{
+ if (s->fpcr_ah) {
+ return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl,
+ a->rd, a->rn, a->rm, a->ra, sel, FPST_AH);
+ } else {
+ return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl,
+ a->rd, a->rn, a->rm, a->ra, sel, FPST_A64);
+ }
+}
+
+TRANS_FEAT(BFMLSLB_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, false)
+TRANS_FEAT(BFMLSLT_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, true)
+
+static bool do_BFMLSL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel)
+{
+ if (s->fpcr_ah) {
+ return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl_idx,
+ a->rd, a->rn, a->rm, a->ra,
+ (a->index << 1) | sel, FPST_AH);
+ } else {
+ return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl_idx,
+ a->rd, a->rn, a->rm, a->ra,
+ (a->index << 1) | sel, FPST_A64);
+ }
+}
+
+TRANS_FEAT(BFMLSLB_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, false)
+TRANS_FEAT(BFMLSLT_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, true)
+
static bool trans_PSEL(DisasContext *s, arg_psel *a)
{
int vl = vec_full_reg_size(s);
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 10cac2de22..0df3312739 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1727,18 +1727,24 @@ FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2
BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2
BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2
+BFMLSLB_zzzw 01100100 11 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_ex esz=2
+BFMLSLT_zzzw 01100100 11 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2
### SVE2 floating-point dot-product
FDOT_zzzz 01100100 00 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2
BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2
### SVE2 floating-point multiply-add long (indexed)
+
FMLALB_zzxw 01100100 10 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2
FMLALT_zzxw 01100100 10 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2
FMLSLB_zzxw 01100100 10 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2
FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2
+
BFMLALB_zzxw 01100100 11 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2
BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2
+BFMLSLB_zzxw 01100100 11 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2
+BFMLSLT_zzxw 01100100 11 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2
### SVE2 floating-point dot-product (indexed)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 76/97] target/arm: Implement CNTP (predicate as counter) for SME2/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (74 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 75/97] target/arm: Implement BFMLSLB{L,T} for SME2/SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:25 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 77/97] target/arm: Implement DUPQ for SME2p1/SVE2p1 Richard Henderson
` (20 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 1 +
target/arm/tcg/sve_helper.c | 21 +++++++++++++++++++++
target/arm/tcg/translate-sve.c | 30 ++++++++++++++++++++++++++++++
target/arm/tcg/sve.decode | 3 ++-
4 files changed, 54 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 906da384dc..733828a880 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -937,6 +937,7 @@ DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32)
+DEF_HELPER_FLAGS_2(sve2p1_cntp_c, TCG_CALL_NO_RWG_SE, i64, i32, i32)
DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 11139e6405..c41143468a 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4184,6 +4184,27 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
return sum;
}
+uint64_t HELPER(sve2p1_cntp_c)(uint32_t png, uint32_t desc)
+{
+ int pl = FIELD_EX32(desc, PREDDESC, OPRSZ);
+ int vl = pl * 8;
+ unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ);
+ int lg2_width = FIELD_EX32(desc, PREDDESC, DATA) + 1;
+ DecodeCounter p = decode_counter(png, vl, v_esz);
+ unsigned maxelem = (vl << lg2_width) >> v_esz;
+ unsigned count = p.count;
+
+ if (p.invert) {
+ if (count >= maxelem) {
+ return 0;
+ }
+ count = maxelem - count;
+ } else {
+ count = MIN(count, maxelem);
+ }
+ return count / p.stride;
+}
+
/* C.f. Arm pseudocode EncodePredCount */
static uint64_t encode_pred_count(uint32_t elements, uint32_t count,
uint32_t esz, bool invert)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 079d310960..53db8851bf 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3052,6 +3052,36 @@ static bool trans_CNTP(DisasContext *s, arg_CNTP *a)
return true;
}
+static bool trans_CNTP_c(DisasContext *s, arg_CNTP_c *a)
+{
+ TCGv_i32 t_png;
+ uint32_t desc = 0;
+
+ if (dc_isar_feature(aa64_sve2p1, s)) {
+ if (!sve_access_check(s)) {
+ return true;
+ }
+ } else if (dc_isar_feature(aa64_sme2, s)) {
+ if (!sme_sm_enabled_check(s)) {
+ return true;
+ }
+ } else {
+ return false;
+ }
+
+ t_png = tcg_temp_new_i32();
+ tcg_gen_ld16u_i32(t_png, tcg_env,
+ pred_full_reg_offset(s, a->rn) ^
+ (HOST_BIG_ENDIAN ? 6 : 0));
+
+ desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pred_full_reg_size(s));
+ desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
+ desc = FIELD_DP32(desc, PREDDESC, DATA, a->vl);
+
+ gen_helper_sve2p1_cntp_c(cpu_reg(s, a->rd), t_png, tcg_constant_i32(desc));
+ return true;
+}
+
static bool trans_INCDECP_r(DisasContext *s, arg_incdec_pred *a)
{
if (!dc_isar_feature(aa64_sve, s)) {
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 0df3312739..db16849731 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -784,7 +784,8 @@ BRKN 00100101 0. 01100001 .... 0 .... 0 .... @pd_pg_pn_s
### SVE Predicate Count Group
# SVE predicate count
-CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn
+CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn
+CNTP_c 00100101 esz:2 100 000 10 000 vl:1 1 rn:4 rd:5
# SVE inc/dec register by predicate count
INCDECP_r 00100101 .. 10110 d:1 10001 00 .... ..... @incdec_pred u=1
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 77/97] target/arm: Implement DUPQ for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (75 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 76/97] target/arm: Implement CNTP (predicate as counter) " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:27 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 78/97] target/arm: Implement EXTQ " Richard Henderson
` (19 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 21 +++++++++++++++++++++
target/arm/tcg/sve.decode | 6 ++++++
2 files changed, 27 insertions(+)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 53db8851bf..e33b2eb2a4 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2249,6 +2249,27 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
return true;
}
+static bool trans_DUPQ(DisasContext *s, arg_DUPQ *a)
+{
+ unsigned vl, dofs, nofs;
+
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
+ if (!sve_access_check(s)) {
+ return true;
+ }
+
+ vl = vec_full_reg_size(s);
+ dofs = vec_full_reg_offset(s, a->rd);
+ nofs = vec_reg_offset(s, a->rn, a->imm, a->esz);
+
+ for (unsigned i = 0; i < vl; i += 16) {
+ tcg_gen_gvec_dup_mem(a->esz, dofs + i, nofs + i, 16, 16);
+ }
+ return true;
+}
+
static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val)
{
typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32);
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index db16849731..2650e00f80 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -577,6 +577,12 @@ DUP_s 00000101 .. 1 00000 001110 ..... ..... @rd_rn
DUP_x 00000101 .. 1 ..... 001000 rn:5 rd:5 \
&rri imm=%imm7_22_16
+# SVE Permute Vector - one source quadwords
+DUPQ 00000101 001 imm:4 1 001001 rn:5 rd:5 &rri_esz esz=0
+DUPQ 00000101 001 imm:3 10 001001 rn:5 rd:5 &rri_esz esz=1
+DUPQ 00000101 001 imm:2 100 001001 rn:5 rd:5 &rri_esz esz=2
+DUPQ 00000101 001 imm:1 1000 001001 rn:5 rd:5 &rri_esz esz=3
+
# SVE insert SIMD&FP scalar register
INSR_f 00000101 .. 1 10100 001110 ..... ..... @rdn_rm
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 78/97] target/arm: Implement EXTQ for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (76 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 77/97] target/arm: Implement DUPQ for SME2p1/SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:27 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 79/97] target/arm: Implement PMOV " Richard Henderson
` (18 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sve.decode | 2 ++
2 files changed, 51 insertions(+)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index e33b2eb2a4..a918da31fe 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2202,6 +2202,55 @@ static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm)
TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm)
TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm)
+static bool trans_EXTQ(DisasContext *s, arg_EXTQ *a)
+{
+ unsigned vl, dofs, sofs0, sofs1, sofs2, imm;
+
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
+ if (!sve_access_check(s)) {
+ return true;
+ }
+
+ imm = a->imm;
+ if (imm == 0) {
+ /* So far we never optimize Zdn with MOVPRFX, so zd = zn is a nop. */
+ return true;
+ }
+
+ vl = vec_full_reg_size(s);
+ dofs = vec_full_reg_offset(s, a->rd);
+ sofs2 = vec_full_reg_offset(s, a->rn);
+
+ if (imm & 8) {
+ sofs0 = dofs + 8;
+ sofs1 = sofs2;
+ sofs2 += 8;
+ } else {
+ sofs0 = dofs;
+ sofs1 = dofs + 8;
+ }
+ imm = (imm & 7) << 3;
+
+ for (unsigned i = 0; i < vl; i += 16) {
+ TCGv_i64 s0 = tcg_temp_new_i64();
+ TCGv_i64 s1 = tcg_temp_new_i64();
+ TCGv_i64 s2 = tcg_temp_new_i64();
+
+ tcg_gen_ld_i64(s0, tcg_env, sofs0 + i);
+ tcg_gen_ld_i64(s1, tcg_env, sofs1 + i);
+ tcg_gen_ld_i64(s2, tcg_env, sofs2 + i);
+
+ tcg_gen_extract2_i64(s0, s0, s1, imm);
+ tcg_gen_extract2_i64(s1, s1, s2, imm);
+
+ tcg_gen_st_i64(s0, tcg_env, dofs + i);
+ tcg_gen_st_i64(s1, tcg_env, dofs + i + 8);
+ }
+ return true;
+}
+
/*
*** SVE Permute - Unpredicated Group
*/
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 2650e00f80..af4fb966bf 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -583,6 +583,8 @@ DUPQ 00000101 001 imm:3 10 001001 rn:5 rd:5 &rri_esz esz=1
DUPQ 00000101 001 imm:2 100 001001 rn:5 rd:5 &rri_esz esz=2
DUPQ 00000101 001 imm:1 1000 001001 rn:5 rd:5 &rri_esz esz=3
+EXTQ 00000101 0110 imm:4 001001 rn:5 rd:5 &rri
+
# SVE insert SIMD&FP scalar register
INSR_f 00000101 .. 1 10100 001110 ..... ..... @rdn_rm
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 79/97] target/arm: Implement PMOV for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (77 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 78/97] target/arm: Implement EXTQ " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 13:24 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 80/97] target/arm: Implement ZIPQ, UZPQ " Richard Henderson
` (17 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 8 +
target/arm/tcg/sve_helper.c | 317 +++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 93 ++++++++++
target/arm/tcg/sve.decode | 17 ++
4 files changed, 435 insertions(+)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 733828a880..04b9545c11 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -3020,3 +3020,11 @@ DEF_HELPER_FLAGS_4(sve2p1_andqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_andqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_andqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2p1_andqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(pmov_pv_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(pmov_pv_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index c41143468a..7af5c59fa5 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -3035,6 +3035,323 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc)
}
}
+static uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
+{
+ uint64_t x;
+
+ p += pos / 64;
+ pos = pos % 64;
+
+ x = p[0];
+ if (pos + len > 64) {
+ x = (x >> pos) | (p[1] << (-pos & 63));
+ pos = 0;
+ }
+ return extract64(x, pos, len);
+}
+
+static void depositn(uint64_t *p, unsigned pos, unsigned len, uint64_t val)
+{
+ p += pos / 64;
+ pos = pos % 64;
+
+ if (pos + len <= 64) {
+ p[0] = deposit64(p[0], pos, len, val);
+ } else {
+ unsigned len0 = 64 - pos;
+ unsigned len1 = len - len0;
+
+ p[0] = deposit64(p[0], pos, len0, val);
+ p[1] = deposit64(p[1], 0, len1, val >> len0);
+ }
+}
+
+void HELPER(pmov_pv_h)(void *vd, void *vs, uint32_t desc)
+{
+ uint64_t *dst = vd;
+ unsigned vl = simd_oprsz(desc);
+ unsigned vq = vl / 16;
+ unsigned vofs = simd_data(desc) * vq;
+ uint64_t x;
+
+ for (; vq >= 4; vq -= 4) {
+ x = *(uint32_t *)(vs + H1_4(vofs));
+ vofs += 4;
+ *dst++ = half_shuffle64(x);
+ }
+
+ if (vq) {
+ x = *(uint32_t *)(vs + H1_4(vofs));
+ x = extract32(x, 0, vq * 8);
+ *dst++ = half_shuffle64(x);
+ }
+}
+
+static uint64_t one_pmov_pv_s(uint64_t x)
+{
+ x = ((x & 0xff00) << 24) | (x & 0xff);
+ x = ((x << 12) | x) & 0x000f000f000f000full;
+ x = ((x << 6) | x) & 0x0303030303030303ull;
+ x = ((x << 3) | x) & 0x1111111111111111ull;
+ return x;
+}
+
+void HELPER(pmov_pv_s)(void *vd, void *vs, uint32_t desc)
+{
+ uint64_t *dst = vd, *src = vs;
+ unsigned vl = simd_oprsz(desc);
+ unsigned idx = simd_data(desc);
+ unsigned width = (vl * 8) / 32;
+ uint64_t x0, x1, x2, x3;
+
+ switch (vl / 16) {
+ case 1:
+ x0 = extract64(*src, idx * 4, 4);
+ goto one;
+ case 2:
+ x0 = ((uint8_t *)vs)[H1(idx)];
+ goto one;
+ case 3:
+ x0 = extract64(*src, idx * 12, 12);
+ goto one;
+ case 4:
+ x0 = ((uint16_t *)vs)[H2(idx)];
+ goto one;
+ case 5:
+ case 6:
+ case 7:
+ x0 = extractn(src, idx * width, 16);
+ x1 = extractn(src, idx * width + 16, width - 16);
+ goto two;
+ case 8:
+ x0 = ((uint32_t *)vs)[H4(idx)];
+ x1 = x0 >> 16;
+ goto two;
+ case 9:
+ case 10:
+ case 11:
+ case 12:
+ x0 = extractn(src, idx * width, 16);
+ x1 = extractn(src, idx * width + 16, 16);
+ x2 = extractn(src, idx * width + 32, width - 32);
+ goto three;
+ case 13:
+ case 14:
+ case 15:
+ x0 = extractn(src, idx * width, 16);
+ x1 = extractn(src, idx * width + 16, 16);
+ x2 = extractn(src, idx * width + 32, 16);
+ x3 = extractn(src, idx * width + 48, width - 48);
+ break;
+ case 16:
+ x0 = src[idx];
+ x1 = x0 >> 16;
+ x2 = x0 >> 32;
+ x3 = x0 >> 48;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ dst[3] = one_pmov_pv_s(x3);
+ three:
+ dst[2] = one_pmov_pv_s(x2);
+ two:
+ dst[1] = one_pmov_pv_s(x1);
+ one:
+ dst[0] = one_pmov_pv_s(x0);
+}
+
+static uint64_t one_pmov_pv_d(uint64_t x)
+{
+ x = ((x & 0xf0) << 28) | (x & 0xf);
+ x = ((x << 14) | x) & 0x0003000300030003ull;
+ x = ((x << 7) | x) & 0x0101010101010101ull;
+ return x;
+}
+
+void HELPER(pmov_pv_d)(void *vd, void *vs, uint32_t desc)
+{
+ uint64_t *dst = vd, *src = vs;
+ unsigned vl = simd_oprsz(desc);
+ unsigned idx = simd_data(desc);
+ unsigned width = (vl * 8) / 64;
+ uint64_t x0, x1, x2, x3;
+
+ switch (vl / 16) {
+ case 1:
+ x0 = extract64(*src, idx * 2, 2);
+ goto one;
+ case 2:
+ x0 = extract64(*src, idx * 4, 4);
+ goto one;
+ case 3:
+ x0 = extract64(*src, idx * 6, 6);
+ goto one;
+ case 4:
+ x0 = ((uint8_t *)vs)[H1(idx)];
+ goto one;
+ case 5:
+ case 6:
+ case 7:
+ x0 = extractn(src, idx * width, 8);
+ x1 = extractn(src, idx * width + 8, width - 8);
+ goto two;
+ case 8:
+ x0 = ((uint16_t *)vs)[H2(idx)];
+ x1 = x0 >> 8;
+ goto two;
+ case 9:
+ case 10:
+ case 11:
+ case 12:
+ x0 = extractn(src, idx * width, 8);
+ x1 = extractn(src, idx * width + 8, 8);
+ x2 = extractn(src, idx * width + 16, width - 16);
+ goto three;
+ case 13:
+ case 14:
+ case 15:
+ x0 = extractn(src, idx * width, 8);
+ x1 = extractn(src, idx * width + 8, 8);
+ x2 = extractn(src, idx * width + 16, 8);
+ x3 = extractn(src, idx * width + 24, width - 24);
+ break;
+ case 16:
+ x0 = ((uint32_t *)vs)[H4(idx)];
+ x1 = x0 >> 8;
+ x2 = x0 >> 16;
+ x3 = x0 >> 24;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ dst[3] = one_pmov_pv_d(x3);
+ three:
+ dst[2] = one_pmov_pv_d(x2);
+ two:
+ dst[1] = one_pmov_pv_d(x1);
+ one:
+ dst[0] = one_pmov_pv_d(x0);
+}
+
+static void pmov_vp_tail(uint64_t *dst, unsigned vl, unsigned width,
+ unsigned idx, uint64_t val)
+{
+ /* Index 0 clears the rest of the vector; others just insert. */
+ if (idx == 0) {
+ dst[0] = val;
+ clear_tail(dst, 8, vl);
+ return;
+ }
+
+ switch (width) {
+ case 8:
+ ((uint8_t *)dst)[H1(idx)] = val;
+ break;
+ case 16:
+ ((uint16_t *)dst)[H2(idx)] = val;
+ break;
+ case 32:
+ ((uint32_t *)dst)[H4(idx)] = val;
+ break;
+ case 64:
+ dst[idx] = val;
+ break;
+ default:
+ depositn(dst, idx * width, width, val);
+ break;
+ }
+}
+
+void HELPER(pmov_vp_h)(void *vd, void *vs, uint32_t desc)
+{
+ uint64_t *dst = vd, *src = vs;
+ unsigned vl = simd_oprsz(desc);
+ unsigned idx = simd_data(desc);
+ unsigned pl_dr8 = DIV_ROUND_UP(vl, 64);
+ unsigned width = (vl * 8) / 16;
+ uint64_t x0 = 0, x1 = 0;
+
+ switch (pl_dr8) {
+ case 4:
+ x1 = half_unshuffle64(src[3]);
+ /* fall through */
+ case 3:
+ x1 = (x1 << 32) | half_unshuffle64(src[2]);
+ /* fall through */
+ case 2:
+ x0 = half_unshuffle64(src[1]);
+ /* fall through */
+ case 1:
+ x0 = (x0 << 32) | half_unshuffle64(src[0]);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ if (width <= 64) {
+ pmov_vp_tail(dst, vl, width, idx, x0);
+ } else if (idx == 0) {
+ dst[0] = x0;
+ dst[1] = x1;
+ clear_tail(dst, 16, vl);
+ } else {
+ depositn(dst, idx * width, 64, x0);
+ depositn(dst, idx * width + 64, width - 64, x0);
+ }
+}
+
+static uint64_t one_pmov_vp_s(uint64_t x)
+{
+ x &= 0x1111111111111111ull;
+ x = ((x >> 3) | x) & 0x0303030303030303ull;
+ x = ((x >> 6) | x) & 0x000f000f000f000full;
+ x = ((x >> 12) | x) & 0x000000ff000000ffull;
+ x = ((x >> 24) | x) & 0xffff;
+ return x;
+}
+
+void HELPER(pmov_vp_s)(void *vd, void *vs, uint32_t desc)
+{
+ uint64_t *dst = vd, *src = vs;
+ unsigned vl = simd_oprsz(desc);
+ unsigned idx = simd_data(desc);
+ unsigned pl_dr8 = DIV_ROUND_UP(vl, 64);
+ unsigned width = (vl * 8) / 32;
+ uint64_t x = 0;
+
+ for (int i = pl_dr8 - 1; i >= 0; --i) {
+ x = (x << 16) | one_pmov_vp_s(src[i]);
+ }
+ pmov_vp_tail(dst, vl, width, idx, x);
+}
+
+static uint64_t one_pmov_vp_d(uint64_t x)
+{
+ x &= 0x0101010101010101ull;
+ x = ((x >> 7) | x) & 0x0003000300030003ull;
+ x = ((x >> 14) | x) & 0x0000000f0000000full;
+ x = ((x >> 28) | x) & 0xff;
+ return x;
+}
+
+void HELPER(pmov_vp_d)(void *vd, void *vs, uint32_t desc)
+{
+ uint64_t *dst = vd, *src = vs;
+ unsigned vl = simd_oprsz(desc);
+ unsigned idx = simd_data(desc);
+ unsigned pl_dr8 = DIV_ROUND_UP(vl, 64);
+ unsigned width = (vl * 8) / 64;
+ uint64_t x = 0;
+
+ for (int i = pl_dr8 - 1; i >= 0; --i) {
+ x = (x << 8) | one_pmov_vp_d(src[i]);
+ }
+ pmov_vp_tail(dst, vl, width, idx, x);
+}
+
typedef void tb_impl_fn(void *, void *, void *, void *, uintptr_t, bool);
static inline void do_tbl1(void *vd, void *vn, void *vm, uint32_t desc,
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index a918da31fe..7f35d1d23c 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2386,6 +2386,99 @@ static gen_helper_gvec_3 * const tbx_fns[4] = {
};
TRANS_FEAT(TBX, aa64_sve2, gen_gvec_ool_arg_zzz, tbx_fns[a->esz], a, 0)
+static bool trans_PMOV_pv(DisasContext *s, arg_PMOV_pv *a)
+{
+ static gen_helper_gvec_2 * const fns[4] = {
+ NULL, gen_helper_pmov_pv_h,
+ gen_helper_pmov_pv_s, gen_helper_pmov_pv_d
+ };
+ unsigned vl, pl, vofs, pofs;
+ TCGv_i64 tmp;
+
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
+ if (!sve_access_check(s)) {
+ return true;
+ }
+
+ vl = vec_full_reg_size(s);
+ if (a->esz != MO_8) {
+ tcg_gen_gvec_2_ool(pred_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vl, vl, a->imm, fns[a->esz]);
+ return true;
+ }
+
+ pl = vl / 8;
+ pofs = pred_full_reg_offset(s, a->rd);
+ vofs = vec_full_reg_offset(s, a->rn);
+
+ QEMU_BUILD_BUG_ON(sizeof(ARMPredicateReg) != 32);
+ for (unsigned i = 32; i >= 8; i >>= 1) {
+ if (pl & i) {
+ tcg_gen_gvec_mov(MO_64, pofs, vofs, i, i);
+ pofs += i;
+ vofs += i;
+ }
+ }
+ switch (pl & 7) {
+ case 0:
+ return true;
+ case 2:
+ tmp = tcg_temp_new_i64();
+ tcg_gen_ld16u_i64(tmp, tcg_env, vofs + (HOST_BIG_ENDIAN ? 6 : 0));
+ break;
+ case 4:
+ tmp = tcg_temp_new_i64();
+ tcg_gen_ld32u_i64(tmp, tcg_env, vofs + (HOST_BIG_ENDIAN ? 4 : 0));
+ break;
+ case 6:
+ tmp = tcg_temp_new_i64();
+ tcg_gen_ld_i64(tmp, tcg_env, vofs);
+ tcg_gen_extract_i64(tmp, tmp, 0, 48);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ tcg_gen_st_i64(tmp, tcg_env, pofs);
+ return true;
+}
+
+static bool trans_PMOV_vp(DisasContext *s, arg_PMOV_pv *a)
+{
+ static gen_helper_gvec_2 * const fns[4] = {
+ NULL, gen_helper_pmov_vp_h,
+ gen_helper_pmov_vp_s, gen_helper_pmov_vp_d
+ };
+ unsigned vl;
+
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
+ if (!sve_access_check(s)) {
+ return true;
+ }
+
+ vl = vec_full_reg_size(s);
+
+ if (a->esz == MO_8) {
+ /*
+ * The low pl bytes are copied from p to v unchanged.
+ * We know that the unused portion of p is zero, and
+ * that imm == 0, so the balance of v must be zeroed.
+ */
+ tcg_gen_gvec_mov(MO_64, vec_full_reg_offset(s, a->rd),
+ pred_full_reg_offset(s, a->rn),
+ size_for_gvec(vl / 8), vl);
+ } else {
+ tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd),
+ pred_full_reg_offset(s, a->rn),
+ vl, vl, a->imm, fns[a->esz]);
+ }
+ return true;
+}
+
static bool trans_UNPK(DisasContext *s, arg_UNPK *a)
{
static gen_helper_gvec_2 * const fns[4][2] = {
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index af4fb966bf..3271c9cf78 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -30,6 +30,7 @@
%size_23 23:2
%dtype_23_13 23:2 13:2
%index3_22_19 22:1 19:2
+%index3_22_17 22:1 17:2
%index3_19_11 19:2 11:1
%index2_20_11 20:1 11:1
@@ -594,6 +595,22 @@ INSR_r 00000101 .. 1 00100 001110 ..... ..... @rdn_rm
# SVE reverse vector elements
REV_v 00000101 .. 1 11000 001110 ..... ..... @rd_rn
+# SVE move predicate to/from vector
+
+PMOV_pv 00000101 00 101 01 0001110 rn:5 0 rd:4 \
+ &rri_esz esz=0 imm=0
+PMOV_pv 00000101 00 101 1 imm:1 0001110 rn:5 0 rd:4 &rri_esz esz=1
+PMOV_pv 00000101 01 101 imm:2 0001110 rn:5 0 rd:4 &rri_esz esz=2
+PMOV_pv 00000101 1. 101 .. 0001110 rn:5 0 rd:4 \
+ &rri_esz esz=3 imm=%index3_22_17
+
+PMOV_vp 00000101 00 101 01 1001110 0 rn:4 rd:5 \
+ &rri_esz esz=0 imm=0
+PMOV_vp 00000101 00 101 1 imm:1 1001110 0 rn:4 rd:5 &rri_esz esz=1
+PMOV_vp 00000101 01 101 imm:2 1001110 0 rn:4 rd:5 &rri_esz esz=2
+PMOV_vp 00000101 1. 101 .. 1001110 0 rn:4 rd:5 \
+ &rri_esz esz=3 imm=%index3_22_17
+
# SVE vector table lookup
TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 79/97] target/arm: Implement PMOV for SME2p1/SVE2p1
2025-07-02 12:33 ` [PATCH v3 79/97] target/arm: Implement PMOV " Richard Henderson
@ 2025-07-03 13:24 ` Peter Maydell
2025-07-03 23:27 ` Richard Henderson
0 siblings, 1 reply; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 13:24 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sve.h | 8 +
> target/arm/tcg/sve_helper.c | 317 +++++++++++++++++++++++++++++++++
> target/arm/tcg/translate-sve.c | 93 ++++++++++
> target/arm/tcg/sve.decode | 17 ++
> 4 files changed, 435 insertions(+)
Given how much code we end up with here for insns which are
implemented in the pseudocode as a two-line loop, I think
some more comments on what's going on would be helpful.
I assume we're just specializing the arbitrary-length
pack and unpack operations for element size and also vector
length, but especially the bitwise operation magic could
use some description of what it's doing.
> diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
> index 733828a880..04b9545c11 100644
> --- a/target/arm/tcg/helper-sve.h
> +++ b/target/arm/tcg/helper-sve.h
> @@ -3020,3 +3020,11 @@ DEF_HELPER_FLAGS_4(sve2p1_andqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
> DEF_HELPER_FLAGS_4(sve2p1_andqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
> DEF_HELPER_FLAGS_4(sve2p1_andqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
> DEF_HELPER_FLAGS_4(sve2p1_andqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
> +
> +DEF_HELPER_FLAGS_3(pmov_pv_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> +DEF_HELPER_FLAGS_3(pmov_pv_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> +DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> +
> +DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> +DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> +DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
> diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
> index c41143468a..7af5c59fa5 100644
> --- a/target/arm/tcg/sve_helper.c
> +++ b/target/arm/tcg/sve_helper.c
> @@ -3035,6 +3035,323 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc)
> }
> }
>
> +static uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
> +{
> + uint64_t x;
> +
> + p += pos / 64;
> + pos = pos % 64;
> +
> + x = p[0];
> + if (pos + len > 64) {
> + x = (x >> pos) | (p[1] << (-pos & 63));
> + pos = 0;
> + }
> + return extract64(x, pos, len);
> +}
This gets moved to a different file in a later patch, so we should
put it in that place from the start.
> +
> +static void depositn(uint64_t *p, unsigned pos, unsigned len, uint64_t val)
This could use a brief doc comment, like the one extractn() gets in
the later patch.
> +{
> + p += pos / 64;
> + pos = pos % 64;
> +
> + if (pos + len <= 64) {
> + p[0] = deposit64(p[0], pos, len, val);
> + } else {
> + unsigned len0 = 64 - pos;
> + unsigned len1 = len - len0;
> +
> + p[0] = deposit64(p[0], pos, len0, val);
> + p[1] = deposit64(p[1], 0, len1, val >> len0);
> + }
> +}
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread* Re: [PATCH v3 79/97] target/arm: Implement PMOV for SME2p1/SVE2p1
2025-07-03 13:24 ` Peter Maydell
@ 2025-07-03 23:27 ` Richard Henderson
0 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-03 23:27 UTC (permalink / raw)
To: Peter Maydell; +Cc: qemu-devel, qemu-arm
On 7/3/25 07:24, Peter Maydell wrote:
> On Wed, 2 Jul 2025 at 13:38, Richard Henderson
> <richard.henderson@linaro.org> wrote:
>>
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>> ---
>> target/arm/tcg/helper-sve.h | 8 +
>> target/arm/tcg/sve_helper.c | 317 +++++++++++++++++++++++++++++++++
>> target/arm/tcg/translate-sve.c | 93 ++++++++++
>> target/arm/tcg/sve.decode | 17 ++
>> 4 files changed, 435 insertions(+)
>
> Given how much code we end up with here for insns which are
> implemented in the pseudocode as a two-line loop, I think
> some more comments on what's going on would be helpful.
This one was hard for me to think about, and even now I'm not sure I've got it right. I'm
going to re-implement exactly with the two-line loop, and not think about how it might be
"optimized".
r~
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 80/97] target/arm: Implement ZIPQ, UZPQ for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (78 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 79/97] target/arm: Implement PMOV " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:28 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 81/97] target/arm: Implement TBLQ, TBXQ " Richard Henderson
` (16 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 10 ++++++++++
target/arm/tcg/sve_helper.c | 29 +++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 19 ++++++++++++++++++-
target/arm/tcg/sve.decode | 6 ++++++
4 files changed, 63 insertions(+), 1 deletion(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 04b9545c11..0f510ea610 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -701,12 +701,22 @@ DEF_HELPER_FLAGS_4(sve_zip_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_zip_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_zip_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_zipq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_zipq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_zipq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_zipq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_4(sve_uzp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_uzp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_uzp_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uzpq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uzpq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uzpq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uzpq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_4(sve_trn_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 7af5c59fa5..0fc602fb12 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -3817,6 +3817,35 @@ DO_UZP(sve_uzp_s, uint32_t, H1_4)
DO_UZP(sve_uzp_d, uint64_t, H1_8)
DO_UZP(sve2_uzp_q, Int128, )
+typedef void perseg_zzz_fn(void *vd, void *vn, void *vm, uint32_t desc);
+
+static void do_perseg_zzz(void *vd, void *vn, void *vm,
+ uint32_t desc, perseg_zzz_fn *fn)
+{
+ intptr_t oprsz = simd_oprsz(desc);
+
+ desc = simd_desc(16, 16, simd_data(desc));
+ for (intptr_t i = 0; i < oprsz; i += 16) {
+ fn(vd + i, vn + i, vm + i, desc);
+ }
+}
+
+#define DO_PERSEG_ZZZ(NAME, FUNC) \
+ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+ { do_perseg_zzz(vd, vn, vm, desc, FUNC); }
+
+DO_PERSEG_ZZZ(sve2p1_uzpq_b, helper_sve_uzp_b)
+DO_PERSEG_ZZZ(sve2p1_uzpq_h, helper_sve_uzp_h)
+DO_PERSEG_ZZZ(sve2p1_uzpq_s, helper_sve_uzp_s)
+DO_PERSEG_ZZZ(sve2p1_uzpq_d, helper_sve_uzp_d)
+
+DO_PERSEG_ZZZ(sve2p1_zipq_b, helper_sve_zip_b)
+DO_PERSEG_ZZZ(sve2p1_zipq_h, helper_sve_zip_h)
+DO_PERSEG_ZZZ(sve2p1_zipq_s, helper_sve_zip_s)
+DO_PERSEG_ZZZ(sve2p1_zipq_d, helper_sve_zip_d)
+
+#undef DO_PERSEG_ZZZ
+
#define DO_TRN(NAME, TYPE, H) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 7f35d1d23c..4ed0fe0480 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2601,11 +2601,19 @@ TRANS_FEAT_NONSTREAMING(ZIP2_q, aa64_sve_f64mm, do_interleave_q,
gen_helper_sve2_zip_q, a,
QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2)
+static gen_helper_gvec_3 * const zipq_fns[4] = {
+ gen_helper_sve2p1_zipq_b, gen_helper_sve2p1_zipq_h,
+ gen_helper_sve2p1_zipq_s, gen_helper_sve2p1_zipq_d,
+};
+TRANS_FEAT(ZIPQ1, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz,
+ zipq_fns[a->esz], a, 0)
+TRANS_FEAT(ZIPQ2, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz,
+ zipq_fns[a->esz], a, 16 / 2)
+
static gen_helper_gvec_3 * const uzp_fns[4] = {
gen_helper_sve_uzp_b, gen_helper_sve_uzp_h,
gen_helper_sve_uzp_s, gen_helper_sve_uzp_d,
};
-
TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz,
uzp_fns[a->esz], a, 0)
TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz,
@@ -2616,6 +2624,15 @@ TRANS_FEAT_NONSTREAMING(UZP1_q, aa64_sve_f64mm, do_interleave_q,
TRANS_FEAT_NONSTREAMING(UZP2_q, aa64_sve_f64mm, do_interleave_q,
gen_helper_sve2_uzp_q, a, 16)
+static gen_helper_gvec_3 * const uzpq_fns[4] = {
+ gen_helper_sve2p1_uzpq_b, gen_helper_sve2p1_uzpq_h,
+ gen_helper_sve2p1_uzpq_s, gen_helper_sve2p1_uzpq_d,
+};
+TRANS_FEAT(UZPQ1, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz,
+ uzpq_fns[a->esz], a, 0)
+TRANS_FEAT(UZPQ2, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz,
+ uzpq_fns[a->esz], a, 1 << a->esz)
+
static gen_helper_gvec_3 * const trn_fns[4] = {
gen_helper_sve_trn_b, gen_helper_sve_trn_h,
gen_helper_sve_trn_s, gen_helper_sve_trn_d,
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 3271c9cf78..e98275eec1 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -657,6 +657,12 @@ UZP2_q 00000101 10 1 ..... 000 011 ..... ..... @rd_rn_rm_e0
TRN1_q 00000101 10 1 ..... 000 110 ..... ..... @rd_rn_rm_e0
TRN2_q 00000101 10 1 ..... 000 111 ..... ..... @rd_rn_rm_e0
+# SVE2.1 permute vector elements (quadwords)
+ZIPQ1 01000100 .. 0 ..... 111 000 ..... ..... @rd_rn_rm
+ZIPQ2 01000100 .. 0 ..... 111 001 ..... ..... @rd_rn_rm
+UZPQ1 01000100 .. 0 ..... 111 010 ..... ..... @rd_rn_rm
+UZPQ2 01000100 .. 0 ..... 111 011 ..... ..... @rd_rn_rm
+
### SVE Permute - Predicated Group
# SVE compress active elements
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 80/97] target/arm: Implement ZIPQ, UZPQ for SME2p1/SVE2p1
2025-07-02 12:33 ` [PATCH v3 80/97] target/arm: Implement ZIPQ, UZPQ " Richard Henderson
@ 2025-07-03 12:28 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:28 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:41, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sve.h | 10 ++++++++++
> target/arm/tcg/sve_helper.c | 29 +++++++++++++++++++++++++++++
> target/arm/tcg/translate-sve.c | 19 ++++++++++++++++++-
> target/arm/tcg/sve.decode | 6 ++++++
> 4 files changed, 63 insertions(+), 1 deletion(-)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 81/97] target/arm: Implement TBLQ, TBXQ for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (79 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 80/97] target/arm: Implement ZIPQ, UZPQ " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:29 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 82/97] target/arm: Implement SME2 counted predicate register load/store Richard Henderson
` (15 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 10 ++++++++++
target/arm/tcg/sve_helper.c | 10 ++++++++++
target/arm/tcg/translate-sve.c | 14 ++++++++++++++
target/arm/tcg/sve.decode | 3 +++
4 files changed, 37 insertions(+)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 0f510ea610..5f4b4aa036 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -676,11 +676,21 @@ DEF_HELPER_FLAGS_5(sve2_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tblq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tblq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tblq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tblq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_4(sve2_tbx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_tbx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_tbx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_tbx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tbxq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tbxq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tbxq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_tbxq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 0fc602fb12..c45d36433c 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -3844,6 +3844,16 @@ DO_PERSEG_ZZZ(sve2p1_zipq_h, helper_sve_zip_h)
DO_PERSEG_ZZZ(sve2p1_zipq_s, helper_sve_zip_s)
DO_PERSEG_ZZZ(sve2p1_zipq_d, helper_sve_zip_d)
+DO_PERSEG_ZZZ(sve2p1_tblq_b, helper_sve_tbl_b)
+DO_PERSEG_ZZZ(sve2p1_tblq_h, helper_sve_tbl_h)
+DO_PERSEG_ZZZ(sve2p1_tblq_s, helper_sve_tbl_s)
+DO_PERSEG_ZZZ(sve2p1_tblq_d, helper_sve_tbl_d)
+
+DO_PERSEG_ZZZ(sve2p1_tbxq_b, helper_sve2_tbx_b)
+DO_PERSEG_ZZZ(sve2p1_tbxq_h, helper_sve2_tbx_h)
+DO_PERSEG_ZZZ(sve2p1_tbxq_s, helper_sve2_tbx_s)
+DO_PERSEG_ZZZ(sve2p1_tbxq_d, helper_sve2_tbx_d)
+
#undef DO_PERSEG_ZZZ
#define DO_TRN(NAME, TYPE, H) \
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 4ed0fe0480..cf8497a388 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2380,12 +2380,26 @@ static gen_helper_gvec_4 * const sve2_tbl_fns[4] = {
TRANS_FEAT(TBL_sve2, aa64_sve2, gen_gvec_ool_zzzz, sve2_tbl_fns[a->esz],
a->rd, a->rn, (a->rn + 1) % 32, a->rm, 0)
+static gen_helper_gvec_3 * const tblq_fns[4] = {
+ gen_helper_sve2p1_tblq_b, gen_helper_sve2p1_tblq_h,
+ gen_helper_sve2p1_tblq_s, gen_helper_sve2p1_tblq_d
+};
+TRANS_FEAT(TBLQ, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz,
+ tblq_fns[a->esz], a, 0)
+
static gen_helper_gvec_3 * const tbx_fns[4] = {
gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h,
gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d
};
TRANS_FEAT(TBX, aa64_sve2, gen_gvec_ool_arg_zzz, tbx_fns[a->esz], a, 0)
+static gen_helper_gvec_3 * const tbxq_fns[4] = {
+ gen_helper_sve2p1_tbxq_b, gen_helper_sve2p1_tbxq_h,
+ gen_helper_sve2p1_tbxq_s, gen_helper_sve2p1_tbxq_d
+};
+TRANS_FEAT(TBXQ, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz,
+ tbxq_fns[a->esz], a, 0)
+
static bool trans_PMOV_pv(DisasContext *s, arg_PMOV_pv *a)
{
static gen_helper_gvec_2 * const fns[4] = {
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index e98275eec1..52a56d3341 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -663,6 +663,9 @@ ZIPQ2 01000100 .. 0 ..... 111 001 ..... ..... @rd_rn_rm
UZPQ1 01000100 .. 0 ..... 111 010 ..... ..... @rd_rn_rm
UZPQ2 01000100 .. 0 ..... 111 011 ..... ..... @rd_rn_rm
+TBLQ 01000100 .. 0 ..... 111 110 ..... ..... @rd_rn_rm
+TBXQ 00000101 .. 1 ..... 001 101 ..... ..... @rd_rn_rm
+
### SVE Permute - Predicated Group
# SVE compress active elements
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 82/97] target/arm: Implement SME2 counted predicate register load/store
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (80 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 81/97] target/arm: Implement TBLQ, TBXQ " Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 13:30 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 83/97] target/arm: Split the ST_zpri and ST_zprr patterns Richard Henderson
` (14 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Implement the SVE2p1 consecutive register LD1/ST1,
and the SME2 strided register LD1/ST1.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 16 ++
target/arm/tcg/sve_helper.c | 493 +++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sve.c | 103 +++++++
target/arm/tcg/sve.decode | 50 ++++
4 files changed, 662 insertions(+)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 5f4b4aa036..c4736d7510 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -3048,3 +3048,19 @@ DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_ld1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_ld1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+
+DEF_HELPER_FLAGS_5(sve2p1_st1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
+DEF_HELPER_FLAGS_5(sve2p1_st1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index c45d36433c..34e0a9752a 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -7857,6 +7857,499 @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64)
#undef DO_ST1_ZPZ_S
#undef DO_ST1_ZPZ_D
+/*
+ * SVE2.1 consecutive register load/store
+ */
+
+static unsigned sve2p1_cont_ldst_elements(SVEContLdSt *info, vaddr addr,
+ uint32_t png, intptr_t reg_max,
+ int N, int v_esz)
+{
+ const int esize = 1 << v_esz;
+ intptr_t reg_off_first = -1, reg_off_last = -1, reg_off_split;
+ DecodeCounter p = decode_counter(png, reg_max, v_esz);
+ unsigned b_count = p.count << v_esz;
+ unsigned b_stride = esize * p.stride;
+ intptr_t page_split;
+
+ /* Set all of the element indices to -1, and the TLB data to 0. */
+ memset(info, -1, offsetof(SVEContLdSt, page));
+ memset(info->page, 0, sizeof(info->page));
+
+ if (p.invert) {
+ if (b_count >= reg_max * N) {
+ return 0;
+ }
+ reg_off_first = b_count;
+ reg_off_last = reg_max * N - b_stride;
+ } else {
+ if (b_count == 0) {
+ return 0;
+ }
+ reg_off_first = 0;
+ reg_off_last = MIN(b_count - esize, reg_max * N - b_stride);
+ }
+
+ info->reg_off_first[0] = reg_off_first;
+ info->mem_off_first[0] = reg_off_first;
+
+ page_split = -(addr | TARGET_PAGE_MASK);
+ if (reg_off_last + esize <= page_split || reg_off_first >= page_split) {
+ /* The entire operation fits within a single page. */
+ info->reg_off_last[0] = reg_off_last;
+ return b_stride;
+ }
+
+ info->page_split = page_split;
+ reg_off_split = ROUND_DOWN(page_split, esize);
+
+ /*
+ * This is the last full element on the first page, but it is not
+ * necessarily active. If there is no full element, i.e. the first
+ * active element is the one that's split, this value remains -1.
+ * It is useful as iteration bounds.
+ */
+ if (reg_off_split != 0) {
+ info->reg_off_last[0] = ROUND_DOWN(reg_off_split - esize, b_stride);
+ }
+
+ /* Determine if an unaligned element spans the pages. */
+ if (page_split & (esize - 1)) {
+ /* It is helpful to know if the split element is active. */
+ if ((reg_off_split & (b_stride - 1)) == 0) {
+ info->reg_off_split = reg_off_split;
+ info->mem_off_split = reg_off_split;
+ }
+ reg_off_split += esize;
+ }
+
+ /*
+ * We do want the first active element on the second page, because
+ * this may affect the address reported in an exception.
+ */
+ reg_off_split = ROUND_UP(reg_off_split, b_stride);
+ if (reg_off_split <= reg_off_last) {
+ info->reg_off_first[1] = reg_off_split;
+ info->mem_off_first[1] = reg_off_split;
+ info->reg_off_last[1] = reg_off_last;
+ }
+ return b_stride;
+}
+
+static void sve2p1_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env,
+ target_ulong addr, unsigned estride,
+ int esize, int wp_access, uintptr_t ra)
+{
+#ifndef CONFIG_USER_ONLY
+ intptr_t count_off, count_last;
+ int flags0 = info->page[0].flags;
+ int flags1 = info->page[1].flags;
+
+ if (likely(!((flags0 | flags1) & TLB_WATCHPOINT))) {
+ return;
+ }
+
+ /* Indicate that watchpoints are handled. */
+ info->page[0].flags = flags0 & ~TLB_WATCHPOINT;
+ info->page[1].flags = flags1 & ~TLB_WATCHPOINT;
+
+ if (flags0 & TLB_WATCHPOINT) {
+ count_off = info->reg_off_first[0];
+ count_last = info->reg_off_split;
+ if (count_last < 0) {
+ count_last = info->reg_off_last[0];
+ }
+ do {
+ cpu_check_watchpoint(env_cpu(env), addr + count_off,
+ esize, info->page[0].attrs, wp_access, ra);
+ count_off += estride;
+ } while (count_off <= count_last);
+ }
+
+ count_off = info->reg_off_first[1];
+ if ((flags1 & TLB_WATCHPOINT) && count_off >= 0) {
+ count_last = info->reg_off_last[1];
+ do {
+ cpu_check_watchpoint(env_cpu(env), addr + count_off,
+ esize, info->page[1].attrs,
+ wp_access, ra);
+ count_off += estride;
+ } while (count_off <= count_last);
+ }
+#endif
+}
+
+static void sve2p1_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env,
+ target_ulong addr, unsigned estride,
+ int esize, uint32_t mtedesc,
+ uintptr_t ra)
+{
+ intptr_t count_off, count_last;
+
+ /*
+ * TODO: estride is always a small power of two, <= 8.
+ * Manipulate the stride within the loops such that
+ * - first iteration hits addr + off, as required,
+ * - second iteration hits ALIGN_UP(addr, 16),
+ * - other iterations advance addr by 16.
+ * This will minimize the probing to once per MTE granule.
+ */
+
+ /* Process the page only if MemAttr == Tagged. */
+ if (info->page[0].tagged) {
+ count_off = info->reg_off_first[0];
+ count_last = info->reg_off_split;
+ if (count_last < 0) {
+ count_last = info->reg_off_last[0];
+ }
+
+ do {
+ mte_check(env, mtedesc, addr + count_off, ra);
+ count_off += estride;
+ } while (count_off <= count_last);
+ }
+
+ count_off = info->reg_off_first[1];
+ if (count_off >= 0 && info->page[1].tagged) {
+ count_last = info->reg_off_last[1];
+ do {
+ mte_check(env, mtedesc, addr + count_off, ra);
+ count_off += estride;
+ } while (count_off <= count_last);
+ }
+}
+
+static inline QEMU_ALWAYS_INLINE
+void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr,
+ uint32_t png, uint32_t desc,
+ const uintptr_t ra, const MemOp esz,
+ sve_ldst1_host_fn *host_fn,
+ sve_ldst1_tlb_fn *tlb_fn)
+{
+ const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2;
+ const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4);
+ uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT);
+ const intptr_t reg_max = simd_oprsz(desc);
+ const unsigned esize = 1 << esz;
+ intptr_t count_off, count_last;
+ intptr_t reg_off, reg_last, reg_n;
+ SVEContLdSt info;
+ unsigned estride, flags;
+ void *host;
+
+ estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz);
+ if (estride == 0) {
+ /* The entire predicate was false; no load occurs. */
+ for (unsigned n = 0; n < N; n++) {
+ memset(zd + n * rstride, 0, reg_max);
+ }
+ return;
+ }
+
+ /* Probe the page(s). Exit with exception for any invalid page. */
+ sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra);
+
+ /* Handle watchpoints for all active elements. */
+ sve2p1_cont_ldst_watchpoints(&info, env, addr, estride,
+ esize, BP_MEM_READ, ra);
+
+ /*
+ * Handle mte checks for all active elements.
+ * Since TBI must be set for MTE, !mtedesc => !mte_active.
+ */
+ if (mtedesc) {
+ sve2p1_cont_ldst_mte_check(&info, env, estride, addr,
+ esize, mtedesc, ra);
+ }
+
+ flags = info.page[0].flags | info.page[1].flags;
+ if (unlikely(flags != 0)) {
+ /*
+ * At least one page includes MMIO.
+ * Any bus operation can fail with cpu_transaction_failed,
+ * which for ARM will raise SyncExternal. Perform the load
+ * into scratch memory to preserve register state until the end.
+ */
+ ARMVectorReg scratch[4] = { };
+
+ count_off = info.reg_off_first[0];
+ count_last = info.reg_off_last[1];
+ if (count_last < 0) {
+ count_last = info.reg_off_split;
+ if (count_last < 0) {
+ count_last = info.reg_off_last[0];
+ }
+ }
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+
+ do {
+ reg_last = MIN(count_last - count_off, reg_max - esize);
+ do {
+ tlb_fn(env, &scratch[reg_n], reg_off, addr + count_off, ra);
+ reg_off += estride;
+ count_off += estride;
+ } while (reg_off <= reg_last);
+ reg_off = 0;
+ reg_n++;
+ } while (count_off <= count_last);
+
+ for (unsigned n = 0; n < N; ++n) {
+ memcpy(&zd[n * rstride], &scratch[n], reg_max);
+ }
+ return;
+ }
+
+ /* The entire operation is in RAM, on valid pages. */
+
+ for (unsigned n = 0; n < N; ++n) {
+ memset(&zd[n * rstride], 0, reg_max);
+ }
+
+ count_off = info.reg_off_first[0];
+ count_last = info.reg_off_last[0];
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+ host = info.page[0].host;
+
+ set_helper_retaddr(ra);
+
+ do {
+ reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+ do {
+ host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+ reg_off += estride;
+ count_off += estride;
+ } while (reg_off <= reg_last);
+ reg_off = 0;
+ reg_n++;
+ } while (count_off <= count_last);
+
+ clear_helper_retaddr();
+
+ /*
+ * Use the slow path to manage the cross-page misalignment.
+ * But we know this is RAM and cannot trap.
+ */
+ count_off = info.reg_off_split;
+ if (unlikely(count_off >= 0)) {
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+ tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+ }
+
+ count_off = info.reg_off_first[1];
+ if (unlikely(count_off >= 0)) {
+ count_last = info.reg_off_last[1];
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+ host = info.page[1].host;
+
+ set_helper_retaddr(ra);
+
+ do {
+ reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+ do {
+ host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+ reg_off += estride;
+ count_off += estride;
+ } while (reg_off <= reg_last);
+ reg_off = 0;
+ reg_n++;
+ } while (count_off <= count_last);
+
+ clear_helper_retaddr();
+ }
+}
+
+void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr,
+ uint32_t png, uint32_t desc)
+{
+ sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), MO_8,
+ sve_ld1bb_host, sve_ld1bb_tlb);
+}
+
+#define DO_LD1_2(NAME, ESZ) \
+void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \
+ target_ulong addr, uint32_t png, \
+ uint32_t desc) \
+{ \
+ sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \
+ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \
+} \
+void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \
+ target_ulong addr, uint32_t png, \
+ uint32_t desc) \
+{ \
+ sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \
+ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \
+}
+
+DO_LD1_2(ld1hh, MO_16)
+DO_LD1_2(ld1ss, MO_32)
+DO_LD1_2(ld1dd, MO_64)
+
+#undef DO_LD1_2
+
+static inline QEMU_ALWAYS_INLINE
+void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr,
+ uint32_t png, uint32_t desc,
+ const uintptr_t ra, const int esz,
+ sve_ldst1_host_fn *host_fn,
+ sve_ldst1_tlb_fn *tlb_fn)
+{
+ const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2;
+ const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4);
+ uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT);
+ const intptr_t reg_max = simd_oprsz(desc);
+ const unsigned esize = 1 << esz;
+ intptr_t count_off, count_last;
+ intptr_t reg_off, reg_last, reg_n;
+ SVEContLdSt info;
+ unsigned estride, flags;
+ void *host;
+
+ estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz);
+ if (estride == 0) {
+ /* The entire predicate was false; no store occurs. */
+ return;
+ }
+
+ /* Probe the page(s). Exit with exception for any invalid page. */
+ sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra);
+
+ /* Handle watchpoints for all active elements. */
+ sve2p1_cont_ldst_watchpoints(&info, env, addr, estride,
+ esize, BP_MEM_WRITE, ra);
+
+ /*
+ * Handle mte checks for all active elements.
+ * Since TBI must be set for MTE, !mtedesc => !mte_active.
+ */
+ if (mtedesc) {
+ sve2p1_cont_ldst_mte_check(&info, env, estride, addr,
+ esize, mtedesc, ra);
+ }
+
+ flags = info.page[0].flags | info.page[1].flags;
+ if (unlikely(flags != 0)) {
+ /*
+ * At least one page includes MMIO.
+ * Any bus operation can fail with cpu_transaction_failed,
+ * which for ARM will raise SyncExternal. Perform the load
+ * into scratch memory to preserve register state until the end.
+ */
+ count_off = info.reg_off_first[0];
+ count_last = info.reg_off_last[1];
+ if (count_last < 0) {
+ count_last = info.reg_off_split;
+ if (count_last < 0) {
+ count_last = info.reg_off_last[0];
+ }
+ }
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+
+ do {
+ reg_last = MIN(count_last - count_off, reg_max - esize);
+ do {
+ tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+ reg_off += estride;
+ count_off += estride;
+ } while (reg_off <= reg_last);
+ reg_off = 0;
+ reg_n++;
+ } while (count_off <= count_last);
+ return;
+ }
+
+ /* The entire operation is in RAM, on valid pages. */
+
+ count_off = info.reg_off_first[0];
+ count_last = info.reg_off_last[0];
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+ host = info.page[0].host;
+
+ set_helper_retaddr(ra);
+
+ do {
+ reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+ do {
+ host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+ reg_off += estride;
+ count_off += estride;
+ } while (reg_off <= reg_last);
+ reg_off = 0;
+ reg_n++;
+ } while (count_off <= count_last);
+
+ clear_helper_retaddr();
+
+ /*
+ * Use the slow path to manage the cross-page misalignment.
+ * But we know this is RAM and cannot trap.
+ */
+ count_off = info.reg_off_split;
+ if (unlikely(count_off >= 0)) {
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+ tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra);
+ }
+
+ count_off = info.reg_off_first[1];
+ if (unlikely(count_off >= 0)) {
+ count_last = info.reg_off_last[1];
+ reg_off = count_off % reg_max;
+ reg_n = count_off / reg_max;
+ host = info.page[1].host;
+
+ set_helper_retaddr(ra);
+
+ do {
+ reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize);
+ do {
+ host_fn(&zd[reg_n * rstride], reg_off, host + count_off);
+ reg_off += estride;
+ count_off += estride;
+ } while (reg_off <= reg_last);
+ reg_off = 0;
+ reg_n++;
+ } while (count_off <= count_last);
+
+ clear_helper_retaddr();
+ }
+}
+
+void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr,
+ uint32_t png, uint32_t desc)
+{
+ sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), MO_8,
+ sve_st1bb_host, sve_st1bb_tlb);
+}
+
+#define DO_ST1_2(NAME, ESZ) \
+void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \
+ target_ulong addr, uint32_t png, \
+ uint32_t desc) \
+{ \
+ sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \
+ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \
+} \
+void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \
+ target_ulong addr, uint32_t png, \
+ uint32_t desc) \
+{ \
+ sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \
+ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \
+}
+
+DO_ST1_2(st1hh, MO_16)
+DO_ST1_2(st1ss, MO_32)
+DO_ST1_2(st1dd, MO_64)
+
+#undef DO_ST1_2
+
void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc)
{
intptr_t i, opr_sz = simd_oprsz(desc) / 8;
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index cf8497a388..469fda6f63 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -7858,3 +7858,106 @@ TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0)
TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz,
gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0)
+
+static bool gen_ldst_c(DisasContext *s, TCGv_i64 addr, int zd, int png,
+ MemOp esz, bool is_write, int n, bool strided)
+{
+ typedef void ldst_c_fn(TCGv_env, TCGv_ptr, TCGv_i64,
+ TCGv_i32, TCGv_i32);
+ static ldst_c_fn * const f_ldst[2][2][4] = {
+ { { gen_helper_sve2p1_ld1bb_c,
+ gen_helper_sve2p1_ld1hh_le_c,
+ gen_helper_sve2p1_ld1ss_le_c,
+ gen_helper_sve2p1_ld1dd_le_c, },
+ { gen_helper_sve2p1_ld1bb_c,
+ gen_helper_sve2p1_ld1hh_be_c,
+ gen_helper_sve2p1_ld1ss_be_c,
+ gen_helper_sve2p1_ld1dd_be_c, } },
+
+ { { gen_helper_sve2p1_st1bb_c,
+ gen_helper_sve2p1_st1hh_le_c,
+ gen_helper_sve2p1_st1ss_le_c,
+ gen_helper_sve2p1_st1dd_le_c, },
+ { gen_helper_sve2p1_st1bb_c,
+ gen_helper_sve2p1_st1hh_be_c,
+ gen_helper_sve2p1_st1ss_be_c,
+ gen_helper_sve2p1_st1dd_be_c, } }
+ };
+
+ TCGv_i32 t_png, t_desc;
+ TCGv_ptr t_zd;
+ uint32_t desc, lg2_rstride = 0;
+ bool be = s->be_data == MO_BE;
+
+ assert(n == 2 || n == 4);
+ if (strided) {
+ lg2_rstride = 3;
+ if (n == 4) {
+ /* Validate ZD alignment. */
+ if (zd & 4) {
+ return false;
+ }
+ lg2_rstride = 2;
+ }
+ /* Ignore non-temporal bit */
+ zd &= ~8;
+ }
+
+ if (strided || !dc_isar_feature(aa64_sve2p1, s)
+ ? !sme_sm_enabled_check(s)
+ : !sve_access_check(s)) {
+ return true;
+ }
+
+ if (!s->mte_active[0]) {
+ addr = clean_data_tbi(s, addr);
+ }
+
+ desc = n == 2 ? 0 : 1;
+ desc = desc | (lg2_rstride << 1);
+ desc = make_svemte_desc(s, vec_full_reg_size(s), 1, esz, is_write, desc);
+ t_desc = tcg_constant_i32(desc);
+
+ t_png = tcg_temp_new_i32();
+ tcg_gen_ld16u_i32(t_png, tcg_env,
+ pred_full_reg_offset(s, png) ^
+ (HOST_BIG_ENDIAN ? 6 : 0));
+
+ t_zd = tcg_temp_new_ptr();
+ tcg_gen_addi_ptr(t_zd, tcg_env, vec_full_reg_offset(s, zd));
+
+ f_ldst[is_write][be][esz](tcg_env, t_zd, addr, t_png, t_desc);
+ return true;
+}
+
+static bool gen_ldst_zcrr_c(DisasContext *s, arg_zcrr_ldst *a,
+ bool is_write, bool strided)
+{
+ TCGv_i64 addr = tcg_temp_new_i64();
+
+ tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz);
+ tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn));
+ return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write,
+ a->nreg, strided);
+}
+
+static bool gen_ldst_zcri_c(DisasContext *s, arg_zcri_ldst *a,
+ bool is_write, bool strided)
+{
+ TCGv_i64 addr = tcg_temp_new_i64();
+
+ tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn),
+ a->imm * a->nreg * vec_full_reg_size(s));
+ return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write,
+ a->nreg, strided);
+}
+
+TRANS_FEAT(LD1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, false, false)
+TRANS_FEAT(LD1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, false, false)
+TRANS_FEAT(ST1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, true, false)
+TRANS_FEAT(ST1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, true, false)
+
+TRANS_FEAT(LD1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, false, true)
+TRANS_FEAT(LD1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, false, true)
+TRANS_FEAT(ST1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, true, true)
+TRANS_FEAT(ST1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, true, true)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 52a56d3341..bf3d4f4853 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1812,3 +1812,53 @@ SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm
UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm
FCLAMP 01100100 .. 1 ..... 001001 ..... ..... @rda_rn_rm
+
+### SVE2p1 multi-vec contiguous load
+
+&zcrr_ldst rd png rn rm esz nreg
+&zcri_ldst rd png rn imm esz nreg
+%png 10:3 !function=plus_8
+%zd_ax2 1:4 !function=times_2
+%zd_ax4 2:3 !function=times_4
+
+LD1_zcrr 10100000000 rm:5 0 esz:2 ... rn:5 .... - \
+ &zcrr_ldst %png rd=%zd_ax2 nreg=2
+LD1_zcrr 10100000000 rm:5 1 esz:2 ... rn:5 ... 0- \
+ &zcrr_ldst %png rd=%zd_ax4 nreg=4
+
+ST1_zcrr 10100000001 rm:5 0 esz:2 ... rn:5 .... - \
+ &zcrr_ldst %png rd=%zd_ax2 nreg=2
+ST1_zcrr 10100000001 rm:5 1 esz:2 ... rn:5 ... 0- \
+ &zcrr_ldst %png rd=%zd_ax4 nreg=4
+
+LD1_zcri 101000000100 imm:s4 0 esz:2 ... rn:5 .... - \
+ &zcri_ldst %png rd=%zd_ax2 nreg=2
+LD1_zcri 101000000100 imm:s4 1 esz:2 ... rn:5 ... 0- \
+ &zcri_ldst %png rd=%zd_ax4 nreg=4
+
+ST1_zcri 101000000110 imm:s4 0 esz:2 ... rn:5 .... - \
+ &zcri_ldst %png rd=%zd_ax2 nreg=2
+ST1_zcri 101000000110 imm:s4 1 esz:2 ... rn:5 ... 0- \
+ &zcri_ldst %png rd=%zd_ax4 nreg=4
+
+# Note: N bit and 0 bit (for nreg4) still mashed in rd.
+# This is handled within gen_ldst_c().
+LD1_zcrr_stride 10100001000 rm:5 0 esz:2 ... rn:5 rd:5 \
+ &zcrr_ldst %png nreg=2
+LD1_zcrr_stride 10100001000 rm:5 1 esz:2 ... rn:5 rd:5 \
+ &zcrr_ldst %png nreg=4
+
+ST1_zcrr_stride 10100001001 rm:5 0 esz:2 ... rn:5 rd:5 \
+ &zcrr_ldst %png nreg=2
+ST1_zcrr_stride 10100001001 rm:5 1 esz:2 ... rn:5 rd:5 \
+ &zcrr_ldst %png nreg=4
+
+LD1_zcri_stride 101000010100 imm:s4 0 esz:2 ... rn:5 rd:5 \
+ &zcri_ldst %png nreg=2
+LD1_zcri_stride 101000010100 imm:s4 1 esz:2 ... rn:5 rd:5 \
+ &zcri_ldst %png nreg=4
+
+ST1_zcri_stride 101000010110 imm:s4 0 esz:2 ... rn:5 rd:5 \
+ &zcri_ldst %png nreg=2
+ST1_zcri_stride 101000010110 imm:s4 1 esz:2 ... rn:5 rd:5 \
+ &zcri_ldst %png nreg=4
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 83/97] target/arm: Split the ST_zpri and ST_zprr patterns
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (81 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 82/97] target/arm: Implement SME2 counted predicate register load/store Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:30 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 84/97] target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1 Richard Henderson
` (13 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
The msz > esz encodings are reserved, and some of
them are about to be reused. Split these patterns
so that the new insns do not overlap.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve.decode | 26 ++++++++++++++++++--------
1 file changed, 18 insertions(+), 8 deletions(-)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index bf3d4f4853..7020771898 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -252,7 +252,7 @@
# Stores; user must fill in ESZ, MSZ, NREG as needed.
@rprr_store ....... .. .. rm:5 ... pg:3 rn:5 rd:5 &rprr_store
-@rpri_store_msz ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store
+@rpri_store ....... .. .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store
@rprr_store_esz_n0 ....... .. esz:2 rm:5 ... pg:3 rn:5 rd:5 \
&rprr_store nreg=0
@rprr_scatter_store ....... msz:2 .. rm:5 ... pg:3 rn:5 rd:5 \
@@ -1334,8 +1334,16 @@ STR_zri 1110010 11 0. ..... 010 ... ..... ..... @rd_rn_i9
# SVE contiguous store (scalar plus immediate)
# ST1B, ST1H, ST1W, ST1D; require msz <= esz
-ST_zpri 1110010 .. esz:2 0.... 111 ... ..... ..... \
- @rpri_store_msz nreg=0
+ST_zpri 1110010 00 esz:2 0.... 111 ... ..... ..... \
+ @rpri_store msz=0 nreg=0
+ST_zpri 1110010 01 esz:2 0.... 111 ... ..... ..... \
+ @rpri_store msz=1 nreg=0
+ST_zpri 1110010 10 10 0.... 111 ... ..... ..... \
+ @rpri_store msz=2 esz=2 nreg=0
+ST_zpri 1110010 10 11 0.... 111 ... ..... ..... \
+ @rpri_store msz=2 esz=3 nreg=0
+ST_zpri 1110010 11 11 0.... 111 ... ..... ..... \
+ @rpri_store msz=3 esz=3 nreg=0
# SVE contiguous store (scalar plus scalar)
# ST1B, ST1H, ST1W, ST1D; require msz <= esz
@@ -1344,20 +1352,22 @@ ST_zprr 1110010 00 .. ..... 010 ... ..... ..... \
@rprr_store_esz_n0 msz=0
ST_zprr 1110010 01 .. ..... 010 ... ..... ..... \
@rprr_store_esz_n0 msz=1
-ST_zprr 1110010 10 .. ..... 010 ... ..... ..... \
- @rprr_store_esz_n0 msz=2
+ST_zprr 1110010 10 10 ..... 010 ... ..... ..... \
+ @rprr_store msz=2 esz=2 nreg=0
+ST_zprr 1110010 10 11 ..... 010 ... ..... ..... \
+ @rprr_store msz=2 esz=3 nreg=0
ST_zprr 1110010 11 11 ..... 010 ... ..... ..... \
@rprr_store msz=3 esz=3 nreg=0
# SVE contiguous non-temporal store (scalar plus immediate) (nreg == 0)
# SVE store multiple structures (scalar plus immediate) (nreg != 0)
ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \
- @rpri_store_msz esz=%size_23
+ @rpri_store msz=%size_23 esz=%size_23
# SVE contiguous non-temporal store (scalar plus scalar) (nreg == 0)
# SVE store multiple structures (scalar plus scalar) (nreg != 0)
-ST_zprr 1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \
- @rprr_store esz=%size_23
+ST_zprr 1110010 .. nreg:2 ..... 011 ... ..... ..... \
+ @rprr_store msz=%size_23 esz=%size_23
# SVE 32-bit scatter store (scalar plus 32-bit scaled offsets)
# Require msz > 0 && msz <= esz.
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 84/97] target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (82 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 83/97] target/arm: Split the ST_zpri and ST_zprr patterns Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:33 ` [PATCH v3 84/97] target/arm: Implement {LD1,ST1}{W,D} " Peter Maydell
2025-07-02 12:33 ` [PATCH v3 85/97] target/arm: Move ld1qq and st1qq primitives to sve_ldst_internal.h Richard Henderson
` (12 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 22 +++++
target/arm/tcg/sve_ldst_internal.h | 26 ++++++
target/arm/tcg/sve_helper.c | 6 ++
target/arm/tcg/translate-sve.c | 134 +++++++++++++++++++++++------
target/arm/tcg/sve.decode | 20 +++++
5 files changed, 181 insertions(+), 27 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index c4736d7510..1999c4bb1f 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1678,9 +1678,15 @@ DEF_HELPER_FLAGS_4(sve_ld1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1squ_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1dqu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1squ_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1dqu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_ld1bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld2bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld3bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1736,9 +1742,15 @@ DEF_HELPER_FLAGS_4(sve_ld1hds_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1sds_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1squ_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1dqu_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1sds_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1squ_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld1dqu_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ldff1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1946,6 +1958,11 @@ DEF_HELPER_FLAGS_4(sve_st1hd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1sd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1sq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1sq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1dq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1dq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_st1bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st2bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st3bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1993,6 +2010,11 @@ DEF_HELPER_FLAGS_4(sve_st1hd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1sd_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1sd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1sq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1sq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1dq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1dq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_ldhsu_le_zsu, TCG_CALL_NO_WG,
diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h
index f2243daf37..e87beba435 100644
--- a/target/arm/tcg/sve_ldst_internal.h
+++ b/target/arm/tcg/sve_ldst_internal.h
@@ -116,6 +116,31 @@ DO_ST_PRIM_2(sd, H1_8, uint64_t, uint32_t, stl)
DO_LD_PRIM_2(dd, H1_8, uint64_t, uint64_t, ldq)
DO_ST_PRIM_2(dd, H1_8, uint64_t, uint64_t, stq)
+#define DO_LD_PRIM_3(NAME, FUNC) \
+ static inline void sve_##NAME##_host(void *vd, \
+ intptr_t reg_off, void *host) \
+ { sve_##FUNC##_host(vd, reg_off, host); \
+ *(uint64_t *)(vd + reg_off + 8) = 0; } \
+ static inline void sve_##NAME##_tlb(CPUARMState *env, void *vd, \
+ intptr_t reg_off, target_ulong addr, uintptr_t ra) \
+ { sve_##FUNC##_tlb(env, vd, reg_off, addr, ra); \
+ *(uint64_t *)(vd + reg_off + 8) = 0; }
+
+DO_LD_PRIM_3(ld1squ_be, ld1sdu_be)
+DO_LD_PRIM_3(ld1squ_le, ld1sdu_le)
+DO_LD_PRIM_3(ld1dqu_be, ld1dd_be)
+DO_LD_PRIM_3(ld1dqu_le, ld1dd_le)
+
+#define sve_st1sq_be_host sve_st1sd_be_host
+#define sve_st1sq_le_host sve_st1sd_le_host
+#define sve_st1sq_be_tlb sve_st1sd_be_tlb
+#define sve_st1sq_le_tlb sve_st1sd_le_tlb
+
+#define sve_st1dq_be_host sve_st1dd_be_host
+#define sve_st1dq_le_host sve_st1dd_le_host
+#define sve_st1dq_be_tlb sve_st1dd_be_tlb
+#define sve_st1dq_le_tlb sve_st1dd_le_tlb
+
#undef DO_LD_TLB
#undef DO_ST_TLB
#undef DO_LD_HOST
@@ -123,6 +148,7 @@ DO_ST_PRIM_2(dd, H1_8, uint64_t, uint64_t, stq)
#undef DO_ST_PRIM_1
#undef DO_LD_PRIM_2
#undef DO_ST_PRIM_2
+#undef DO_LD_PRIM_3
/*
* Resolve the guest virtual address to info->host and info->flags.
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 34e0a9752a..bcfe8f5d43 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -6630,6 +6630,9 @@ DO_LD1_2(ld1sds, MO_64, MO_32)
DO_LD1_2(ld1dd, MO_64, MO_64)
+DO_LD1_2(ld1squ, MO_32, MO_128)
+DO_LD1_2(ld1dqu, MO_64, MO_128)
+
#undef DO_LD1_1
#undef DO_LD1_2
@@ -7252,6 +7255,9 @@ DO_STN_2(2, dd, MO_64, MO_64)
DO_STN_2(3, dd, MO_64, MO_64)
DO_STN_2(4, dd, MO_64, MO_64)
+DO_STN_2(1, sq, MO_128, MO_32)
+DO_STN_2(1, dq, MO_128, MO_64)
+
#undef DO_STN_1
#undef DO_STN_2
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 469fda6f63..62accdfe1e 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -4812,21 +4812,23 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
*/
/* The memory mode of the dtype. */
-static const MemOp dtype_mop[16] = {
+static const MemOp dtype_mop[18] = {
MO_UB, MO_UB, MO_UB, MO_UB,
MO_SL, MO_UW, MO_UW, MO_UW,
MO_SW, MO_SW, MO_UL, MO_UL,
- MO_SB, MO_SB, MO_SB, MO_UQ
+ MO_SB, MO_SB, MO_SB, MO_UQ,
+ MO_UL, MO_UQ,
};
#define dtype_msz(x) (dtype_mop[x] & MO_SIZE)
/* The vector element size of dtype. */
-static const uint8_t dtype_esz[16] = {
+static const uint8_t dtype_esz[18] = {
0, 1, 2, 3,
3, 1, 2, 3,
3, 2, 2, 3,
- 3, 2, 1, 3
+ 3, 2, 1, 3,
+ 4, 4,
};
uint32_t make_svemte_desc(DisasContext *s, unsigned vsz, uint32_t nregs,
@@ -4877,7 +4879,7 @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
}
/* Indexed by [mte][be][dtype][nreg] */
-static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = {
+static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = {
{ /* mte inactive, little-endian */
{ { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r,
gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r },
@@ -4901,7 +4903,11 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = {
{ gen_helper_sve_ld1bss_r, NULL, NULL, NULL },
{ gen_helper_sve_ld1bhs_r, NULL, NULL, NULL },
{ gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r,
- gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } },
+ gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r },
+
+ { gen_helper_sve_ld1squ_le_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1dqu_le_r, NULL, NULL, NULL },
+ },
/* mte inactive, big-endian */
{ { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r,
@@ -4926,7 +4932,12 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = {
{ gen_helper_sve_ld1bss_r, NULL, NULL, NULL },
{ gen_helper_sve_ld1bhs_r, NULL, NULL, NULL },
{ gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r,
- gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } },
+ gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r },
+
+ { gen_helper_sve_ld1squ_be_r, NULL, NULL, NULL },
+ { gen_helper_sve_ld1dqu_be_r, NULL, NULL, NULL },
+ },
+ },
{ /* mte active, little-endian */
{ { gen_helper_sve_ld1bb_r_mte,
@@ -4959,7 +4970,11 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = {
{ gen_helper_sve_ld1dd_le_r_mte,
gen_helper_sve_ld2dd_le_r_mte,
gen_helper_sve_ld3dd_le_r_mte,
- gen_helper_sve_ld4dd_le_r_mte } },
+ gen_helper_sve_ld4dd_le_r_mte },
+
+ { gen_helper_sve_ld1squ_le_r_mte, NULL, NULL, NULL },
+ { gen_helper_sve_ld1dqu_le_r_mte, NULL, NULL, NULL },
+ },
/* mte active, big-endian */
{ { gen_helper_sve_ld1bb_r_mte,
@@ -4992,7 +5007,12 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = {
{ gen_helper_sve_ld1dd_be_r_mte,
gen_helper_sve_ld2dd_be_r_mte,
gen_helper_sve_ld3dd_be_r_mte,
- gen_helper_sve_ld4dd_be_r_mte } } },
+ gen_helper_sve_ld4dd_be_r_mte },
+
+ { gen_helper_sve_ld1squ_be_r_mte, NULL, NULL, NULL },
+ { gen_helper_sve_ld1dqu_be_r_mte, NULL, NULL, NULL },
+ },
+ },
};
static void do_ld_zpa(DisasContext *s, int zt, int pg,
@@ -5011,9 +5031,22 @@ static void do_ld_zpa(DisasContext *s, int zt, int pg,
static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a)
{
- if (a->rm == 31 || !dc_isar_feature(aa64_sve, s)) {
+ if (a->rm == 31) {
return false;
}
+
+ /* dtypes 16 and 17 are artificial, representing 128-bit element */
+ if (a->dtype < 16) {
+ if (!dc_isar_feature(aa64_sve, s)) {
+ return false;
+ }
+ } else {
+ if (!dc_isar_feature(aa64_sve2p1, s)) {
+ return false;
+ }
+ s->is_nonstreaming = true;
+ }
+
if (sve_access_check(s)) {
TCGv_i64 addr = tcg_temp_new_i64();
tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype));
@@ -5025,9 +5058,18 @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a)
static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a)
{
- if (!dc_isar_feature(aa64_sve, s)) {
- return false;
+ /* dtypes 16 and 17 are artificial, representing 128-bit element */
+ if (a->dtype < 16) {
+ if (!dc_isar_feature(aa64_sve, s)) {
+ return false;
+ }
+ } else {
+ if (!dc_isar_feature(aa64_sve2p1, s)) {
+ return false;
+ }
+ s->is_nonstreaming = true;
}
+
if (sve_access_check(s)) {
int vsz = vec_full_reg_size(s);
int elements = vsz >> dtype_esz[a->dtype];
@@ -5474,7 +5516,7 @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a)
static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
int msz, int esz, int nreg)
{
- static gen_helper_gvec_mem * const fn_single[2][2][4][4] = {
+ static gen_helper_gvec_mem * const fn_single[2][2][4][5] = {
{ { { gen_helper_sve_st1bb_r,
gen_helper_sve_st1bh_r,
gen_helper_sve_st1bs_r,
@@ -5485,9 +5527,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
gen_helper_sve_st1hd_le_r },
{ NULL, NULL,
gen_helper_sve_st1ss_le_r,
- gen_helper_sve_st1sd_le_r },
+ gen_helper_sve_st1sd_le_r,
+ gen_helper_sve_st1sq_le_r, },
{ NULL, NULL, NULL,
- gen_helper_sve_st1dd_le_r } },
+ gen_helper_sve_st1dd_le_r,
+ gen_helper_sve_st1dq_le_r, } },
{ { gen_helper_sve_st1bb_r,
gen_helper_sve_st1bh_r,
gen_helper_sve_st1bs_r,
@@ -5498,9 +5542,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
gen_helper_sve_st1hd_be_r },
{ NULL, NULL,
gen_helper_sve_st1ss_be_r,
- gen_helper_sve_st1sd_be_r },
+ gen_helper_sve_st1sd_be_r,
+ gen_helper_sve_st1sq_be_r },
{ NULL, NULL, NULL,
- gen_helper_sve_st1dd_be_r } } },
+ gen_helper_sve_st1dd_be_r,
+ gen_helper_sve_st1dq_be_r } } },
{ { { gen_helper_sve_st1bb_r_mte,
gen_helper_sve_st1bh_r_mte,
@@ -5512,9 +5558,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
gen_helper_sve_st1hd_le_r_mte },
{ NULL, NULL,
gen_helper_sve_st1ss_le_r_mte,
- gen_helper_sve_st1sd_le_r_mte },
+ gen_helper_sve_st1sd_le_r_mte,
+ gen_helper_sve_st1sq_le_r_mte },
{ NULL, NULL, NULL,
- gen_helper_sve_st1dd_le_r_mte } },
+ gen_helper_sve_st1dd_le_r_mte,
+ gen_helper_sve_st1dq_le_r_mte } },
{ { gen_helper_sve_st1bb_r_mte,
gen_helper_sve_st1bh_r_mte,
gen_helper_sve_st1bs_r_mte,
@@ -5525,9 +5573,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
gen_helper_sve_st1hd_be_r_mte },
{ NULL, NULL,
gen_helper_sve_st1ss_be_r_mte,
- gen_helper_sve_st1sd_be_r_mte },
+ gen_helper_sve_st1sd_be_r_mte,
+ gen_helper_sve_st1sq_be_r_mte },
{ NULL, NULL, NULL,
- gen_helper_sve_st1dd_be_r_mte } } },
+ gen_helper_sve_st1dd_be_r_mte,
+ gen_helper_sve_st1dq_be_r_mte } } },
};
static gen_helper_gvec_mem * const fn_multiple[2][2][3][4] = {
{ { { gen_helper_sve_st2bb_r,
@@ -5596,12 +5646,27 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a)
{
- if (!dc_isar_feature(aa64_sve, s)) {
- return false;
- }
if (a->rm == 31 || a->msz > a->esz) {
return false;
}
+ switch (a->esz) {
+ case MO_8 ... MO_64:
+ if (!dc_isar_feature(aa64_sve, s)) {
+ return false;
+ }
+ break;
+ case MO_128:
+ assert(a->msz < a->esz);
+ assert(a->nreg == 0);
+ if (!dc_isar_feature(aa64_sve2p1, s)) {
+ return false;
+ }
+ s->is_nonstreaming = true;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
if (sve_access_check(s)) {
TCGv_i64 addr = tcg_temp_new_i64();
tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->msz);
@@ -5613,12 +5678,27 @@ static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a)
static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a)
{
- if (!dc_isar_feature(aa64_sve, s)) {
- return false;
- }
if (a->msz > a->esz) {
return false;
}
+ switch (a->esz) {
+ case MO_8 ... MO_64:
+ if (!dc_isar_feature(aa64_sve, s)) {
+ return false;
+ }
+ break;
+ case MO_128:
+ assert(a->msz < a->esz);
+ assert(a->nreg == 0);
+ if (!dc_isar_feature(aa64_sve2p1, s)) {
+ return false;
+ }
+ s->is_nonstreaming = true;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
if (sve_access_check(s)) {
int vsz = vec_full_reg_size(s);
int elements = vsz >> a->esz;
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 7020771898..bf33bc305f 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1240,12 +1240,24 @@ LD1_zpiz 1000010 .. 01 ..... 1.. ... ..... ..... \
# SVE contiguous load (scalar plus scalar)
LD_zprr 1010010 .... ..... 010 ... ..... ..... @rprr_load_dt nreg=0
+# LD1W (128-bit element)
+LD_zprr 1010010 1000 rm:5 100 pg:3 rn:5 rd:5 \
+ &rprr_load dtype=16 nreg=0
+# LD1D (128-bit element)
+LD_zprr 1010010 1100 rm:5 100 pg:3 rn:5 rd:5 \
+ &rprr_load dtype=17 nreg=0
# SVE contiguous first-fault load (scalar plus scalar)
LDFF1_zprr 1010010 .... ..... 011 ... ..... ..... @rprr_load_dt nreg=0
# SVE contiguous load (scalar plus immediate)
LD_zpri 1010010 .... 0.... 101 ... ..... ..... @rpri_load_dt nreg=0
+# LD1W (128-bit element)
+LD_zpri 1010010 1000 1 imm:s4 001 pg:3 rn:5 rd:5 \
+ &rpri_load dtype=16 nreg=0
+# LD1D (128-bit element)
+LD_zpri 1010010 1100 1 imm:s4 001 pg:3 rn:5 rd:5 \
+ &rpri_load dtype=17 nreg=0
# SVE contiguous non-fault load (scalar plus immediate)
LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0
@@ -1344,6 +1356,10 @@ ST_zpri 1110010 10 11 0.... 111 ... ..... ..... \
@rpri_store msz=2 esz=3 nreg=0
ST_zpri 1110010 11 11 0.... 111 ... ..... ..... \
@rpri_store msz=3 esz=3 nreg=0
+ST_zpri 1110010 10 00 0.... 111 ... ..... ..... \
+ @rpri_store msz=2 esz=4 nreg=0
+ST_zpri 1110010 11 10 0.... 111 ... ..... ..... \
+ @rpri_store msz=3 esz=4 nreg=0
# SVE contiguous store (scalar plus scalar)
# ST1B, ST1H, ST1W, ST1D; require msz <= esz
@@ -1358,6 +1374,10 @@ ST_zprr 1110010 10 11 ..... 010 ... ..... ..... \
@rprr_store msz=2 esz=3 nreg=0
ST_zprr 1110010 11 11 ..... 010 ... ..... ..... \
@rprr_store msz=3 esz=3 nreg=0
+ST_zprr 1110010 10 00 ..... 010 ... ..... ..... \
+ @rprr_store msz=2 esz=4 nreg=0
+ST_zprr 1110010 11 10 ..... 010 ... ..... ..... \
+ @rprr_store msz=3 esz=4 nreg=0
# SVE contiguous non-temporal store (scalar plus immediate) (nreg == 0)
# SVE store multiple structures (scalar plus immediate) (nreg != 0)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 84/97] target/arm: Implement {LD1,ST1}{W,D} (128-bit element) for SVE2p1
2025-07-02 12:33 ` [PATCH v3 84/97] target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1 Richard Henderson
@ 2025-07-03 12:33 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:33 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:42, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sve.h | 22 +++++
> target/arm/tcg/sve_ldst_internal.h | 26 ++++++
> target/arm/tcg/sve_helper.c | 6 ++
> target/arm/tcg/translate-sve.c | 134 +++++++++++++++++++++++------
> target/arm/tcg/sve.decode | 20 +++++
> 5 files changed, 181 insertions(+), 27 deletions(-)
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 85/97] target/arm: Move ld1qq and st1qq primitives to sve_ldst_internal.h
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (83 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 84/97] target/arm: Implement {LD1, ST1}{W, D} (128-bit element) for SVE2p1 Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:35 ` Peter Maydell
2025-07-02 12:33 ` [PATCH v3 86/97] target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1 Richard Henderson
` (11 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Move from sme_helper.c to the shared header.
Add a comment noting the lack of atomicity.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/sve_ldst_internal.h | 63 ++++++++++++++++++++++++++++++
target/arm/tcg/sme_helper.c | 44 +++------------------
2 files changed, 69 insertions(+), 38 deletions(-)
diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h
index e87beba435..c67cda9d3b 100644
--- a/target/arm/tcg/sve_ldst_internal.h
+++ b/target/arm/tcg/sve_ldst_internal.h
@@ -141,6 +141,69 @@ DO_LD_PRIM_3(ld1dqu_le, ld1dd_le)
#define sve_st1dq_be_tlb sve_st1dd_be_tlb
#define sve_st1dq_le_tlb sve_st1dd_le_tlb
+/*
+ * The ARMVectorReg elements are stored in host-endian 64-bit units.
+ * For 128-bit quantities, the sequence defined by the Elem[] pseudocode
+ * corresponds to storing the two 64-bit pieces in little-endian order.
+ */
+/* FIXME: Nothing in this file makes any effort at atomicity. */
+
+static inline void sve_ld1qq_be_host(void *vd, intptr_t reg_off, void *host)
+{
+ sve_ld1dd_be_host(vd, reg_off + 8, host);
+ sve_ld1dd_be_host(vd, reg_off, host + 8);
+}
+
+static inline void sve_ld1qq_le_host(void *vd, intptr_t reg_off, void *host)
+{
+ sve_ld1dd_le_host(vd, reg_off, host);
+ sve_ld1dd_le_host(vd, reg_off + 8, host + 8);
+}
+
+static inline void
+sve_ld1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+ target_ulong addr, uintptr_t ra)
+{
+ sve_ld1dd_be_tlb(env, vd, reg_off + 8, addr, ra);
+ sve_ld1dd_be_tlb(env, vd, reg_off, addr + 8, ra);
+}
+
+static inline void
+sve_ld1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+ target_ulong addr, uintptr_t ra)
+{
+ sve_ld1dd_le_tlb(env, vd, reg_off, addr, ra);
+ sve_ld1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra);
+}
+
+static inline void sve_st1qq_be_host(void *vd, intptr_t reg_off, void *host)
+{
+ sve_st1dd_be_host(vd, reg_off + 8, host);
+ sve_st1dd_be_host(vd, reg_off, host + 8);
+}
+
+static inline void sve_st1qq_le_host(void *vd, intptr_t reg_off, void *host)
+{
+ sve_st1dd_le_host(vd, reg_off, host);
+ sve_st1dd_le_host(vd, reg_off + 8, host + 8);
+}
+
+static inline void
+sve_st1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+ target_ulong addr, uintptr_t ra)
+{
+ sve_st1dd_be_tlb(env, vd, reg_off + 8, addr, ra);
+ sve_st1dd_be_tlb(env, vd, reg_off, addr + 8, ra);
+}
+
+static inline void
+sve_st1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off,
+ target_ulong addr, uintptr_t ra)
+{
+ sve_st1dd_le_tlb(env, vd, reg_off, addr, ra);
+ sve_st1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra);
+}
+
#undef DO_LD_TLB
#undef DO_ST_TLB
#undef DO_LD_HOST
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 77eab68870..19c4c2efa2 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -408,54 +408,22 @@ static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \
TLB(env, useronly_clean_ptr(addr), val, ra); \
}
-/*
- * The ARMVectorReg elements are stored in host-endian 64-bit units.
- * For 128-bit quantities, the sequence defined by the Elem[] pseudocode
- * corresponds to storing the two 64-bit pieces in little-endian order.
- */
-#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB) \
-static inline void HNAME##_host(void *za, intptr_t off, void *host) \
-{ \
- uint64_t val0 = HOST(host), val1 = HOST(host + 8); \
- uint64_t *ptr = za + off; \
- ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \
-} \
+#define DO_LDQ(HNAME, VNAME) \
static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \
{ \
HNAME##_host(za, tile_vslice_offset(off), host); \
} \
-static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \
- target_ulong addr, uintptr_t ra) \
-{ \
- uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra); \
- uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra); \
- uint64_t *ptr = za + off; \
- ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \
-} \
static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \
target_ulong addr, uintptr_t ra) \
{ \
HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \
}
-#define DO_STQ(HNAME, VNAME, BE, HOST, TLB) \
-static inline void HNAME##_host(void *za, intptr_t off, void *host) \
-{ \
- uint64_t *ptr = za + off; \
- HOST(host, ptr[BE]); \
- HOST(host + 8, ptr[!BE]); \
-} \
+#define DO_STQ(HNAME, VNAME) \
static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \
{ \
HNAME##_host(za, tile_vslice_offset(off), host); \
} \
-static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \
- target_ulong addr, uintptr_t ra) \
-{ \
- uint64_t *ptr = za + off; \
- TLB(env, useronly_clean_ptr(addr), ptr[BE], ra); \
- TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra); \
-} \
static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \
target_ulong addr, uintptr_t ra) \
{ \
@@ -470,8 +438,8 @@ DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra)
DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra)
DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra)
-DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra)
-DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra)
+DO_LDQ(sve_ld1qq_be, sme_ld1q_be)
+DO_LDQ(sve_ld1qq_le, sme_ld1q_le)
DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra)
DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra)
@@ -481,8 +449,8 @@ DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra)
DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra)
DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra)
-DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra)
-DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra)
+DO_STQ(sve_st1qq_be, sme_st1q_be)
+DO_STQ(sve_st1qq_le, sme_st1q_le)
#undef DO_LD
#undef DO_ST
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 86/97] target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (84 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 85/97] target/arm: Move ld1qq and st1qq primitives to sve_ldst_internal.h Richard Henderson
@ 2025-07-02 12:33 ` Richard Henderson
2025-07-03 12:37 ` Peter Maydell
2025-07-02 12:34 ` [PATCH v3 87/97] target/arm: Implement LD1Q, ST1Q for SVE2p1 Richard Henderson
` (10 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:33 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 32 +++++++++
target/arm/tcg/sve_helper.c | 8 +++
target/arm/tcg/translate-sve.c | 126 ++++++++++++++++++++++++---------
target/arm/tcg/sve.decode | 31 ++++++++
4 files changed, 162 insertions(+), 35 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 1999c4bb1f..ade76ff664 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -1658,6 +1658,14 @@ DEF_HELPER_FLAGS_4(sve_ld2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld2qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1722,6 +1730,14 @@ DEF_HELPER_FLAGS_4(sve_ld2dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld3dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld4dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld2qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_ld2qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld3qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_ld4qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_ld1bhu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bsu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_ld1bdu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1946,6 +1962,14 @@ DEF_HELPER_FLAGS_4(sve_st2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st2qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
@@ -1998,6 +2022,14 @@ DEF_HELPER_FLAGS_4(sve_st2dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st3dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st4dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st2qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
DEF_HELPER_FLAGS_4(sve_st1bh_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1bs_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve_st1bd_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index bcfe8f5d43..cf46ff9947 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -6692,6 +6692,10 @@ DO_LDN_2(2, dd, MO_64)
DO_LDN_2(3, dd, MO_64)
DO_LDN_2(4, dd, MO_64)
+DO_LDN_2(2, qq, MO_128)
+DO_LDN_2(3, qq, MO_128)
+DO_LDN_2(4, qq, MO_128)
+
#undef DO_LDN_1
#undef DO_LDN_2
@@ -7258,6 +7262,10 @@ DO_STN_2(4, dd, MO_64, MO_64)
DO_STN_2(1, sq, MO_128, MO_32)
DO_STN_2(1, dq, MO_128, MO_64)
+DO_STN_2(2, qq, MO_128, MO_128)
+DO_STN_2(3, qq, MO_128, MO_128)
+DO_STN_2(4, qq, MO_128, MO_128)
+
#undef DO_STN_1
#undef DO_STN_2
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 62accdfe1e..994839e8b4 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -89,7 +89,7 @@ static inline int expand_imm_sh8u(DisasContext *s, int x)
*/
static inline int msz_dtype(DisasContext *s, int msz)
{
- static const uint8_t dtype[4] = { 0, 5, 10, 15 };
+ static const uint8_t dtype[5] = { 0, 5, 10, 15, 18 };
return dtype[msz];
}
@@ -4812,23 +4812,25 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
*/
/* The memory mode of the dtype. */
-static const MemOp dtype_mop[18] = {
+static const MemOp dtype_mop[19] = {
MO_UB, MO_UB, MO_UB, MO_UB,
MO_SL, MO_UW, MO_UW, MO_UW,
MO_SW, MO_SW, MO_UL, MO_UL,
MO_SB, MO_SB, MO_SB, MO_UQ,
- MO_UL, MO_UQ,
+ /* Artificial values used by decode */
+ MO_UL, MO_UQ, MO_128
};
#define dtype_msz(x) (dtype_mop[x] & MO_SIZE)
/* The vector element size of dtype. */
-static const uint8_t dtype_esz[18] = {
+static const uint8_t dtype_esz[19] = {
0, 1, 2, 3,
3, 1, 2, 3,
3, 2, 2, 3,
3, 2, 1, 3,
- 4, 4,
+ /* Artificial values used by decode */
+ 4, 4, 4,
};
uint32_t make_svemte_desc(DisasContext *s, unsigned vsz, uint32_t nregs,
@@ -4879,7 +4881,7 @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
}
/* Indexed by [mte][be][dtype][nreg] */
-static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = {
+static gen_helper_gvec_mem * const ldr_fns[2][2][19][4] = {
{ /* mte inactive, little-endian */
{ { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r,
gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r },
@@ -4907,6 +4909,8 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = {
{ gen_helper_sve_ld1squ_le_r, NULL, NULL, NULL },
{ gen_helper_sve_ld1dqu_le_r, NULL, NULL, NULL },
+ { NULL, gen_helper_sve_ld2qq_le_r,
+ gen_helper_sve_ld3qq_le_r, gen_helper_sve_ld4qq_le_r },
},
/* mte inactive, big-endian */
@@ -4936,6 +4940,8 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = {
{ gen_helper_sve_ld1squ_be_r, NULL, NULL, NULL },
{ gen_helper_sve_ld1dqu_be_r, NULL, NULL, NULL },
+ { NULL, gen_helper_sve_ld2qq_be_r,
+ gen_helper_sve_ld3qq_be_r, gen_helper_sve_ld4qq_be_r },
},
},
@@ -4974,6 +4980,10 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = {
{ gen_helper_sve_ld1squ_le_r_mte, NULL, NULL, NULL },
{ gen_helper_sve_ld1dqu_le_r_mte, NULL, NULL, NULL },
+ { NULL,
+ gen_helper_sve_ld2qq_le_r_mte,
+ gen_helper_sve_ld3qq_le_r_mte,
+ gen_helper_sve_ld4qq_le_r_mte },
},
/* mte active, big-endian */
@@ -5011,6 +5021,10 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][18][4] = {
{ gen_helper_sve_ld1squ_be_r_mte, NULL, NULL, NULL },
{ gen_helper_sve_ld1dqu_be_r_mte, NULL, NULL, NULL },
+ { NULL,
+ gen_helper_sve_ld2qq_be_r_mte,
+ gen_helper_sve_ld3qq_be_r_mte,
+ gen_helper_sve_ld4qq_be_r_mte },
},
},
};
@@ -5035,16 +5049,26 @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a)
return false;
}
- /* dtypes 16 and 17 are artificial, representing 128-bit element */
- if (a->dtype < 16) {
+ /* dtypes 16-18 are artificial, representing 128-bit element */
+ switch (a->dtype) {
+ case 0 ... 15:
if (!dc_isar_feature(aa64_sve, s)) {
return false;
}
- } else {
+ break;
+ case 16: case 17:
if (!dc_isar_feature(aa64_sve2p1, s)) {
return false;
}
s->is_nonstreaming = true;
+ break;
+ case 18:
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
+ break;
+ default:
+ g_assert_not_reached();
}
if (sve_access_check(s)) {
@@ -5058,16 +5082,26 @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a)
static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a)
{
- /* dtypes 16 and 17 are artificial, representing 128-bit element */
- if (a->dtype < 16) {
+ /* dtypes 16-18 are artificial, representing 128-bit element */
+ switch (a->dtype) {
+ case 0 ... 15:
if (!dc_isar_feature(aa64_sve, s)) {
return false;
}
- } else {
+ break;
+ case 16: case 17:
if (!dc_isar_feature(aa64_sve2p1, s)) {
return false;
}
s->is_nonstreaming = true;
+ break;
+ case 18:
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
+ break;
+ default:
+ g_assert_not_reached();
}
if (sve_access_check(s)) {
@@ -5579,55 +5613,67 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
gen_helper_sve_st1dd_be_r_mte,
gen_helper_sve_st1dq_be_r_mte } } },
};
- static gen_helper_gvec_mem * const fn_multiple[2][2][3][4] = {
+ static gen_helper_gvec_mem * const fn_multiple[2][2][3][5] = {
{ { { gen_helper_sve_st2bb_r,
gen_helper_sve_st2hh_le_r,
gen_helper_sve_st2ss_le_r,
- gen_helper_sve_st2dd_le_r },
+ gen_helper_sve_st2dd_le_r,
+ gen_helper_sve_st2qq_le_r },
{ gen_helper_sve_st3bb_r,
gen_helper_sve_st3hh_le_r,
gen_helper_sve_st3ss_le_r,
- gen_helper_sve_st3dd_le_r },
+ gen_helper_sve_st3dd_le_r,
+ gen_helper_sve_st3qq_le_r },
{ gen_helper_sve_st4bb_r,
gen_helper_sve_st4hh_le_r,
gen_helper_sve_st4ss_le_r,
- gen_helper_sve_st4dd_le_r } },
+ gen_helper_sve_st4dd_le_r,
+ gen_helper_sve_st4qq_le_r } },
{ { gen_helper_sve_st2bb_r,
gen_helper_sve_st2hh_be_r,
gen_helper_sve_st2ss_be_r,
- gen_helper_sve_st2dd_be_r },
+ gen_helper_sve_st2dd_be_r,
+ gen_helper_sve_st2qq_be_r },
{ gen_helper_sve_st3bb_r,
gen_helper_sve_st3hh_be_r,
gen_helper_sve_st3ss_be_r,
- gen_helper_sve_st3dd_be_r },
+ gen_helper_sve_st3dd_be_r,
+ gen_helper_sve_st3qq_be_r },
{ gen_helper_sve_st4bb_r,
gen_helper_sve_st4hh_be_r,
gen_helper_sve_st4ss_be_r,
- gen_helper_sve_st4dd_be_r } } },
+ gen_helper_sve_st4dd_be_r,
+ gen_helper_sve_st4qq_be_r } } },
{ { { gen_helper_sve_st2bb_r_mte,
gen_helper_sve_st2hh_le_r_mte,
gen_helper_sve_st2ss_le_r_mte,
- gen_helper_sve_st2dd_le_r_mte },
+ gen_helper_sve_st2dd_le_r_mte,
+ gen_helper_sve_st2qq_le_r_mte },
{ gen_helper_sve_st3bb_r_mte,
gen_helper_sve_st3hh_le_r_mte,
gen_helper_sve_st3ss_le_r_mte,
- gen_helper_sve_st3dd_le_r_mte },
+ gen_helper_sve_st3dd_le_r_mte,
+ gen_helper_sve_st3qq_le_r_mte },
{ gen_helper_sve_st4bb_r_mte,
gen_helper_sve_st4hh_le_r_mte,
gen_helper_sve_st4ss_le_r_mte,
- gen_helper_sve_st4dd_le_r_mte } },
+ gen_helper_sve_st4dd_le_r_mte,
+ gen_helper_sve_st4qq_le_r_mte } },
{ { gen_helper_sve_st2bb_r_mte,
gen_helper_sve_st2hh_be_r_mte,
gen_helper_sve_st2ss_be_r_mte,
- gen_helper_sve_st2dd_be_r_mte },
+ gen_helper_sve_st2dd_be_r_mte,
+ gen_helper_sve_st2qq_be_r_mte },
{ gen_helper_sve_st3bb_r_mte,
gen_helper_sve_st3hh_be_r_mte,
gen_helper_sve_st3ss_be_r_mte,
- gen_helper_sve_st3dd_be_r_mte },
+ gen_helper_sve_st3dd_be_r_mte,
+ gen_helper_sve_st3qq_be_r_mte },
{ gen_helper_sve_st4bb_r_mte,
gen_helper_sve_st4hh_be_r_mte,
gen_helper_sve_st4ss_be_r_mte,
- gen_helper_sve_st4dd_be_r_mte } } },
+ gen_helper_sve_st4dd_be_r_mte,
+ gen_helper_sve_st4qq_be_r_mte } } },
};
gen_helper_gvec_mem *fn;
int be = s->be_data == MO_BE;
@@ -5656,12 +5702,17 @@ static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a)
}
break;
case MO_128:
- assert(a->msz < a->esz);
- assert(a->nreg == 0);
- if (!dc_isar_feature(aa64_sve2p1, s)) {
- return false;
+ if (a->nreg == 0) {
+ assert(a->msz < a->esz);
+ if (!dc_isar_feature(aa64_sve2p1, s)) {
+ return false;
+ }
+ s->is_nonstreaming = true;
+ } else {
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
}
- s->is_nonstreaming = true;
break;
default:
g_assert_not_reached();
@@ -5688,12 +5739,17 @@ static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a)
}
break;
case MO_128:
- assert(a->msz < a->esz);
- assert(a->nreg == 0);
- if (!dc_isar_feature(aa64_sve2p1, s)) {
- return false;
+ if (a->nreg == 0) {
+ assert(a->msz < a->esz);
+ if (!dc_isar_feature(aa64_sve2p1, s)) {
+ return false;
+ }
+ s->is_nonstreaming = true;
+ } else {
+ if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+ return false;
+ }
}
- s->is_nonstreaming = true;
break;
default:
g_assert_not_reached();
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index bf33bc305f..3eda029146 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -229,6 +229,9 @@
@rprr_load_dt ....... dtype:4 rm:5 ... pg:3 rn:5 rd:5 &rprr_load
@rpri_load_dt ....... dtype:4 . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load
+@rprr_load ....... .... rm:5 ... pg:3 rn:5 rd:5 &rprr_load
+@rpri_load ....... .... . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load
+
@rprr_load_msz ....... .... rm:5 ... pg:3 rn:5 rd:5 \
&rprr_load dtype=%msz_dtype
@rpri_load_msz ....... .... . imm:s4 ... pg:3 rn:5 rd:5 \
@@ -1267,12 +1270,26 @@ LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0
# SVE load multiple structures (scalar plus scalar)
# LD2B, LD2H, LD2W, LD2D; etc.
LD_zprr 1010010 .. nreg:2 ..... 110 ... ..... ..... @rprr_load_msz
+# LD[234]Q
+LD_zprr 1010010 01 01 ..... 100 ... ..... ..... \
+ @rprr_load dtype=18 nreg=1
+LD_zprr 1010010 10 01 ..... 100 ... ..... ..... \
+ @rprr_load dtype=18 nreg=2
+LD_zprr 1010010 11 01 ..... 100 ... ..... ..... \
+ @rprr_load dtype=18 nreg=3
# SVE contiguous non-temporal load (scalar plus immediate)
# LDNT1B, LDNT1H, LDNT1W, LDNT1D
# SVE load multiple structures (scalar plus immediate)
# LD2B, LD2H, LD2W, LD2D; etc.
LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz
+# LD[234]Q
+LD_zpri 1010010 01 001 .... 111 ... ..... ..... \
+ @rpri_load dtype=18 nreg=1
+LD_zpri 1010010 10 001 .... 111 ... ..... ..... \
+ @rpri_load dtype=18 nreg=2
+LD_zpri 1010010 11 001 .... 111 ... ..... ..... \
+ @rpri_load dtype=18 nreg=3
# SVE load and broadcast quadword (scalar plus scalar)
LD1RQ_zprr 1010010 .. 00 ..... 000 ... ..... ..... \
@@ -1383,11 +1400,25 @@ ST_zprr 1110010 11 10 ..... 010 ... ..... ..... \
# SVE store multiple structures (scalar plus immediate) (nreg != 0)
ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \
@rpri_store msz=%size_23 esz=%size_23
+# ST[234]Q
+ST_zpri 11100100 01 00 .... 000 ... ..... ..... \
+ @rpri_store msz=4 esz=4 nreg=1
+ST_zpri 11100100 10 00 .... 000 ... ..... ..... \
+ @rpri_store msz=4 esz=4 nreg=2
+ST_zpri 11100100 11 00 .... 000 ... ..... ..... \
+ @rpri_store msz=4 esz=4 nreg=3
# SVE contiguous non-temporal store (scalar plus scalar) (nreg == 0)
# SVE store multiple structures (scalar plus scalar) (nreg != 0)
ST_zprr 1110010 .. nreg:2 ..... 011 ... ..... ..... \
@rprr_store msz=%size_23 esz=%size_23
+# ST[234]Q
+ST_zprr 11100100 01 1 ..... 000 ... ..... ..... \
+ @rprr_store msz=4 esz=4 nreg=1
+ST_zprr 11100100 10 1 ..... 000 ... ..... ..... \
+ @rprr_store msz=4 esz=4 nreg=2
+ST_zprr 11100100 11 1 ..... 000 ... ..... ..... \
+ @rprr_store msz=4 esz=4 nreg=3
# SVE 32-bit scatter store (scalar plus 32-bit scaled offsets)
# Require msz > 0 && msz <= esz.
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 86/97] target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1
2025-07-02 12:33 ` [PATCH v3 86/97] target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1 Richard Henderson
@ 2025-07-03 12:37 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:37 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:42, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sve.h | 32 +++++++++
> target/arm/tcg/sve_helper.c | 8 +++
> target/arm/tcg/translate-sve.c | 126 ++++++++++++++++++++++++---------
> target/arm/tcg/sve.decode | 31 ++++++++
> 4 files changed, 162 insertions(+), 35 deletions(-)
> @@ -4812,23 +4812,25 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
> */
>
> /* The memory mode of the dtype. */
> -static const MemOp dtype_mop[18] = {
> +static const MemOp dtype_mop[19] = {
> MO_UB, MO_UB, MO_UB, MO_UB,
> MO_SL, MO_UW, MO_UW, MO_UW,
> MO_SW, MO_SW, MO_UL, MO_UL,
> MO_SB, MO_SB, MO_SB, MO_UQ,
> - MO_UL, MO_UQ,
> + /* Artificial values used by decode */
This comment and the similar one in dtype_esz should have been
added in the earlier patch that added elements 16 and 17.
> + MO_UL, MO_UQ, MO_128
> };
>
> #define dtype_msz(x) (dtype_mop[x] & MO_SIZE)
>
> /* The vector element size of dtype. */
> -static const uint8_t dtype_esz[18] = {
> +static const uint8_t dtype_esz[19] = {
> 0, 1, 2, 3,
> 3, 1, 2, 3,
> 3, 2, 2, 3,
> 3, 2, 1, 3,
> - 4, 4,
> + /* Artificial values used by decode */
> + 4, 4, 4,
> };
Otherwise
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 87/97] target/arm: Implement LD1Q, ST1Q for SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (85 preceding siblings ...)
2025-07-02 12:33 ` [PATCH v3 86/97] target/arm: Implement {LD, ST}[234]Q for SME2p1/SVE2p1 Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 12:37 ` Peter Maydell
2025-07-02 12:34 ` [PATCH v3 88/97] target/arm: Implement MOVAZ for SME2p1 Richard Henderson
` (9 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sve.h | 16 ++++++++++++++++
target/arm/tcg/sve_helper.c | 6 ++++++
target/arm/tcg/translate-sve.c | 34 ++++++++++++++++++++++++++++++++--
target/arm/tcg/sve.decode | 8 ++++++++
4 files changed, 62 insertions(+), 2 deletions(-)
diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index ade76ff664..c36090d13d 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -2155,6 +2155,10 @@ DEF_HELPER_FLAGS_6(sve_ldsds_le_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_ldsds_be_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_ldqq_le_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_ldqq_be_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_ldbsu_zsu_mte, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
@@ -2264,6 +2268,10 @@ DEF_HELPER_FLAGS_6(sve_ldsds_le_zd_mte, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_ldsds_be_zd_mte, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_ldqq_le_zd_mte, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_ldqq_be_zd_mte, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
@@ -2549,6 +2557,10 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stqq_le_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stqq_be_zd, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stbs_zsu_mte, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
@@ -2616,6 +2628,10 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG,
void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stqq_le_zd_mte, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
+DEF_HELPER_FLAGS_6(sve_stqq_be_zd_mte, TCG_CALL_NO_WG,
+ void, env, ptr, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index cf46ff9947..dfce9697e2 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -7482,6 +7482,9 @@ DO_LD1_ZPZ_D(dd_be, zsu, MO_64)
DO_LD1_ZPZ_D(dd_be, zss, MO_64)
DO_LD1_ZPZ_D(dd_be, zd, MO_64)
+DO_LD1_ZPZ_D(qq_le, zd, MO_128)
+DO_LD1_ZPZ_D(qq_be, zd, MO_128)
+
#undef DO_LD1_ZPZ_S
#undef DO_LD1_ZPZ_D
@@ -7868,6 +7871,9 @@ DO_ST1_ZPZ_D(sd_be, zd, MO_32)
DO_ST1_ZPZ_D(dd_le, zd, MO_64)
DO_ST1_ZPZ_D(dd_be, zd, MO_64)
+DO_ST1_ZPZ_D(qq_le, zd, MO_128)
+DO_ST1_ZPZ_D(qq_be, zd, MO_128)
+
#undef DO_ST1_ZPZ_S
#undef DO_ST1_ZPZ_D
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 994839e8b4..262670ed89 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -6116,13 +6116,23 @@ gather_load_fn64[2][2][2][3][2][4] = {
gen_helper_sve_ldffdd_be_zd_mte, } } } } },
};
+static gen_helper_gvec_mem_scatter * const
+gather_load_fn128[2][2] = {
+ { gen_helper_sve_ldqq_le_zd,
+ gen_helper_sve_ldqq_be_zd },
+ { gen_helper_sve_ldqq_le_zd_mte,
+ gen_helper_sve_ldqq_be_zd_mte }
+};
+
static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a)
{
gen_helper_gvec_mem_scatter *fn = NULL;
bool be = s->be_data == MO_BE;
bool mte = s->mte_active[0];
- if (!dc_isar_feature(aa64_sve, s)) {
+ if (a->esz < MO_128
+ ? !dc_isar_feature(aa64_sve, s)
+ : !dc_isar_feature(aa64_sve2p1, s)) {
return false;
}
s->is_nonstreaming = true;
@@ -6137,6 +6147,12 @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a)
case MO_64:
fn = gather_load_fn64[mte][be][a->ff][a->xs][a->u][a->msz];
break;
+ case MO_128:
+ assert(!a->ff && a->u && a->xs == 2 && a->msz == MO_128);
+ fn = gather_load_fn128[mte][be];
+ break;
+ default:
+ g_assert_not_reached();
}
assert(fn != NULL);
@@ -6304,6 +6320,14 @@ static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][2][3][4] = {
gen_helper_sve_stdd_be_zd_mte, } } },
};
+static gen_helper_gvec_mem_scatter * const
+scatter_store_fn128[2][2] = {
+ { gen_helper_sve_stqq_le_zd,
+ gen_helper_sve_stqq_be_zd },
+ { gen_helper_sve_stqq_le_zd_mte,
+ gen_helper_sve_stqq_be_zd_mte }
+};
+
static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a)
{
gen_helper_gvec_mem_scatter *fn;
@@ -6313,7 +6337,9 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a)
if (a->esz < a->msz || (a->msz == 0 && a->scale)) {
return false;
}
- if (!dc_isar_feature(aa64_sve, s)) {
+ if (a->esz < MO_128
+ ? !dc_isar_feature(aa64_sve, s)
+ : !dc_isar_feature(aa64_sve2p1, s)) {
return false;
}
s->is_nonstreaming = true;
@@ -6327,6 +6353,10 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a)
case MO_64:
fn = scatter_store_fn64[mte][be][a->xs][a->msz];
break;
+ case MO_128:
+ assert(a->xs == 2 && a->msz == MO_128);
+ fn = scatter_store_fn128[mte][be];
+ break;
default:
g_assert_not_reached();
}
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 3eda029146..2efd5f57e4 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -1340,6 +1340,10 @@ LD1_zprz 1100010 10 1. ..... 1.. ... ..... ..... \
LD1_zprz 1100010 11 1. ..... 11. ... ..... ..... \
@rprr_g_load_sc esz=3 msz=3 u=1
+# LD1Q
+LD1_zprz 1100 0100 000 rm:5 101 pg:3 rn:5 rd:5 \
+ &rprr_gather_load u=0 ff=0 xs=2 esz=4 msz=4 scale=0
+
# SVE 64-bit gather load (vector plus immediate)
LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \
@rpri_g_load esz=3
@@ -1443,6 +1447,10 @@ ST1_zprz 1110010 .. 01 ..... 101 ... ..... ..... \
ST1_zprz 1110010 .. 00 ..... 101 ... ..... ..... \
@rprr_scatter_store xs=2 esz=3 scale=0
+# ST1Q
+ST1_zprz 1110 0100 001 rm:5 001 pg:3 rn:5 rd:5 \
+ &rprr_scatter_store xs=2 msz=4 esz=4 scale=0
+
# SVE 64-bit scatter store (vector plus immediate)
ST1_zpiz 1110010 .. 10 ..... 101 ... ..... ..... \
@rpri_scatter_store esz=3
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 88/97] target/arm: Implement MOVAZ for SME2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (86 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 87/97] target/arm: Implement LD1Q, ST1Q for SVE2p1 Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 12:38 ` Peter Maydell
2025-07-02 12:34 ` [PATCH v3 89/97] target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1 Richard Henderson
` (8 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 6 ++++
target/arm/tcg/sme_helper.c | 60 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 46 +++++++++++++++++++-------
target/arm/tcg/sme.decode | 36 ++++++++++++++++++++
4 files changed, 137 insertions(+), 11 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 467073ea25..c9961d6b7f 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -42,6 +42,12 @@ DEF_HELPER_FLAGS_3(sme2_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sme2_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 19c4c2efa2..bcaa67b0fd 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -250,6 +250,66 @@ void HELPER(sme2_mova_zc_d)(void *vdst, void *vsrc, uint32_t desc)
}
}
+void HELPER(sme2p1_movaz_zc_b)(void *vdst, void *vsrc, uint32_t desc)
+{
+ uint8_t *src = vsrc;
+ uint8_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc);
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ src[tile_vslice_index(i)] = 0;
+ }
+}
+
+void HELPER(sme2p1_movaz_zc_h)(void *vdst, void *vsrc, uint32_t desc)
+{
+ uint16_t *src = vsrc;
+ uint16_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 2;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ src[tile_vslice_index(i)] = 0;
+ }
+}
+
+void HELPER(sme2p1_movaz_zc_s)(void *vdst, void *vsrc, uint32_t desc)
+{
+ uint32_t *src = vsrc;
+ uint32_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 4;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ src[tile_vslice_index(i)] = 0;
+ }
+}
+
+void HELPER(sme2p1_movaz_zc_d)(void *vdst, void *vsrc, uint32_t desc)
+{
+ uint64_t *src = vsrc;
+ uint64_t *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 8;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ src[tile_vslice_index(i)] = 0;
+ }
+}
+
+void HELPER(sme2p1_movaz_zc_q)(void *vdst, void *vsrc, uint32_t desc)
+{
+ Int128 *src = vsrc;
+ Int128 *dst = vdst;
+ size_t i, n = simd_oprsz(desc) / 16;
+
+ for (i = 0; i < n; ++i) {
+ dst[i] = src[tile_vslice_index(i)];
+ memset(&src[tile_vslice_index(i)], 0, 16);
+ }
+}
+
/*
* Clear elements in a tile slice comprising len bytes.
*/
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 7407597177..9592f6a996 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -247,7 +247,8 @@ static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false)
TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true)
-static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
+static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n,
+ bool to_vec, bool zero)
{
static gen_helper_gvec_2 * const cz_fns[] = {
gen_helper_sme2_mova_cz_b, gen_helper_sme2_mova_cz_h,
@@ -257,6 +258,11 @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
gen_helper_sme2_mova_zc_b, gen_helper_sme2_mova_zc_h,
gen_helper_sme2_mova_zc_s, gen_helper_sme2_mova_zc_d,
};
+ static gen_helper_gvec_2 * const zc_z_fns[] = {
+ gen_helper_sme2p1_movaz_zc_b, gen_helper_sme2p1_movaz_zc_h,
+ gen_helper_sme2p1_movaz_zc_s, gen_helper_sme2p1_movaz_zc_d,
+ gen_helper_sme2p1_movaz_zc_q,
+ };
TCGv_ptr t_za;
int svl, bytes_per_op = n << a->esz;
@@ -270,6 +276,8 @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
return true;
}
+ assert(a->esz <= MO_64 + zero);
+
if (!sme_smza_enabled_check(s)) {
return true;
}
@@ -292,7 +300,9 @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
TCGv_ptr t_zr = vec_full_reg_ptr(s, a->zr * n + i);
t_za = get_tile_rowcol(s, a->esz, a->rs, a->za,
a->off * n + i, 1, n, a->v);
- if (to_vec) {
+ if (zero) {
+ zc_z_fns[a->esz](t_zr, t_za, t_desc);
+ } else if (to_vec) {
zc_fns[a->esz](t_zr, t_za, t_desc);
} else {
cz_fns[a->esz](t_za, t_zr, t_desc);
@@ -305,6 +315,9 @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
a->off * n + i, 1, n, a->v);
if (to_vec) {
tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, 0, svl, svl);
+ if (zero) {
+ tcg_gen_gvec_dup_imm_var(MO_8, t_za, 0, svl, svl, 0);
+ }
} else {
tcg_gen_gvec_mov_var(MO_8, t_za, 0, tcg_env, o_zr, svl, svl);
}
@@ -313,12 +326,17 @@ static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, bool to_vec)
return true;
}
-TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false)
-TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false)
-TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true)
-TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true)
+TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false, false)
+TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false, false)
+TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true, false)
+TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true, false)
-static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
+TRANS_FEAT(MOVAZ_zt, aa64_sme2p1, do_mova_tile_n, a, 1, true, true)
+TRANS_FEAT(MOVAZ_zt2, aa64_sme2p1, do_mova_tile_n, a, 2, true, true)
+TRANS_FEAT(MOVAZ_zt4, aa64_sme2p1, do_mova_tile_n, a, 4, true, true)
+
+static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n,
+ bool to_vec, bool zero)
{
TCGv_ptr t_za;
int svl;
@@ -336,6 +354,9 @@ static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
if (to_vec) {
tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl);
+ if (zero) {
+ tcg_gen_gvec_dup_imm_var(MO_8, t_za, o_za, svl, svl, 0);
+ }
} else {
tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl);
}
@@ -343,10 +364,13 @@ static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, bool to_vec)
return true;
}
-TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false)
-TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false)
-TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true)
-TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true)
+TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false, false)
+TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false, false)
+TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true, false)
+TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true, false)
+
+TRANS_FEAT(MOVAZ_za2, aa64_sme2p1, do_mova_array_n, a, 2, true, true)
+TRANS_FEAT(MOVAZ_za4, aa64_sme2p1, do_mova_array_n, a, 4, true, true)
static bool do_movt(DisasContext *s, arg_MOVT_rzt *a,
void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long))
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 0a2ceea8be..f7e4143b7d 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -100,6 +100,42 @@ MOVA_za2 11000000 00 00011 00 .. 010 00 off:3 zr:4 0 \
MOVA_za4 11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \
&mova_a rv=%mova_rv
+### SME Move and Zero
+
+MOVAZ_za2 11000000 00000110 0 .. 01010 off:3 zr:4 0 \
+ &mova_a rv=%mova_rv
+MOVAZ_za4 11000000 00000110 0 .. 01110 off:3 zr:3 00 \
+ &mova_a rv=%mova_rv
+
+MOVAZ_zt 11000000 00 00001 0 v:1 .. 0001 off:4 zr:5 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVAZ_zt 11000000 01 00001 0 v:1 .. 0001 za:1 off:3 zr:5 \
+ &mova_t rs=%mova_rs esz=1
+MOVAZ_zt 11000000 10 00001 0 v:1 .. 0001 za:2 off:2 zr:5 \
+ &mova_t rs=%mova_rs esz=2
+MOVAZ_zt 11000000 11 00001 0 v:1 .. 0001 za:3 off:1 zr:5 \
+ &mova_t rs=%mova_rs esz=3
+MOVAZ_zt 11000000 11 00001 1 v:1 .. 0001 za:4 zr:5 \
+ &mova_t rs=%mova_rs esz=4 off=0
+
+MOVAZ_zt2 11000000 00 00011 0 v:1 .. 00010 off:3 zr:4 0 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVAZ_zt2 11000000 01 00011 0 v:1 .. 00010 za:1 off:2 zr:4 0 \
+ &mova_t rs=%mova_rs esz=1
+MOVAZ_zt2 11000000 10 00011 0 v:1 .. 00010 za:2 off:1 zr:4 0 \
+ &mova_t rs=%mova_rs esz=2
+MOVAZ_zt2 11000000 11 00011 0 v:1 .. 00010 za:3 zr:4 0 \
+ &mova_t rs=%mova_rs esz=3 off=0
+
+MOVAZ_zt4 11000000 00 00011 0 v:1 .. 001100 off:2 zr:3 00 \
+ &mova_t rs=%mova_rs esz=0 za=0
+MOVAZ_zt4 11000000 01 00011 0 v:1 .. 001100 za:1 off:1 zr:3 00 \
+ &mova_t rs=%mova_rs esz=1
+MOVAZ_zt4 11000000 10 00011 0 v:1 .. 001100 za:2 zr:3 00 \
+ &mova_t rs=%mova_rs esz=2 off=0
+MOVAZ_zt4 11000000 11 00011 0 v:1 .. 00110 za:3 zr:3 00 \
+ &mova_t rs=%mova_rs esz=3 off=0
+
### SME Move into/from ZT0
MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 88/97] target/arm: Implement MOVAZ for SME2p1
2025-07-02 12:34 ` [PATCH v3 88/97] target/arm: Implement MOVAZ for SME2p1 Richard Henderson
@ 2025-07-03 12:38 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:38 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:42, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 6 ++++
> target/arm/tcg/sme_helper.c | 60 ++++++++++++++++++++++++++++++++++
> target/arm/tcg/translate-sme.c | 46 +++++++++++++++++++-------
> target/arm/tcg/sme.decode | 36 ++++++++++++++++++++
> 4 files changed, 137 insertions(+), 11 deletions(-)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 89/97] target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (87 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 88/97] target/arm: Implement MOVAZ for SME2p1 Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 12:42 ` Peter Maydell
2025-07-02 12:34 ` [PATCH v3 90/97] target/arm: Rename FMOPA_h to FMOPA_w_h Richard Henderson
` (7 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper.h | 24 ++++++++++
target/arm/tcg/vec_internal.h | 16 +++++++
target/arm/tcg/sve_helper.c | 15 ------
target/arm/tcg/translate-sme.c | 56 ++++++++++++++++++++++
target/arm/tcg/vec_helper.c | 88 ++++++++++++++++++++++++++++++++++
target/arm/tcg/sme.decode | 42 ++++++++++++++++
6 files changed, 226 insertions(+), 15 deletions(-)
diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h
index 392bf7b9b5..d9565c8069 100644
--- a/target/arm/tcg/helper.h
+++ b/target/arm/tcg/helper.h
@@ -1188,3 +1188,27 @@ DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti2_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti2_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_4(sme2_luti4_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_4(sme2_luti4_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32)
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index 236927c640..ad3bfabc34 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -337,6 +337,22 @@ bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
float32 sve_f16_to_f32(float16 f, float_status *fpst);
float16 sve_f32_to_f16(float32 f, float_status *fpst);
+/* Extract @len bits from an array of uint64_t at offset @pos bits. */
+static inline uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
+{
+ uint64_t x;
+
+ p += pos / 64;
+ pos = pos % 64;
+
+ x = p[0];
+ if (pos + len > 64) {
+ x = (x >> pos) | (p[1] << (-pos & 63));
+ pos = 0;
+ }
+ return extract64(x, pos, len);
+}
+
/*
* Decode helper functions for predicate as counter.
*/
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index dfce9697e2..70baa7a6b0 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -3035,21 +3035,6 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc)
}
}
-static uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
-{
- uint64_t x;
-
- p += pos / 64;
- pos = pos % 64;
-
- x = p[0];
- if (pos + len > 64) {
- x = (x >> pos) | (p[1] << (-pos & 63));
- pos = 0;
- }
- return extract64(x, pos, len);
-}
-
static void depositn(uint64_t *p, unsigned pos, unsigned len, uint64_t val)
{
p += pos / 64;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 9592f6a996..d38b8a5ca2 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -1697,3 +1697,59 @@ static bool trans_SEL(DisasContext *s, arg_SEL *a)
}
return true;
}
+
+static bool do_lut(DisasContext *s, arg_lut *a,
+ gen_helper_gvec_2_ptr *fn, bool strided)
+{
+ if (sme_sm_enabled_check(s) && sme2_zt0_enabled_check(s)) {
+ int svl = streaming_vec_reg_size(s);
+ tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd),
+ vec_full_reg_offset(s, a->zn),
+ tcg_env, svl, svl, strided | (a->idx << 1), fn);
+ }
+ return true;
+}
+
+TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, false)
+TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, false)
+TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, false)
+
+TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, false)
+TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, false)
+TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, false)
+
+TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, false)
+TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, false)
+TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, false)
+
+TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, false)
+TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, false)
+TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, false)
+
+TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, false)
+TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, false)
+TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, false)
+
+TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, false)
+TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, false)
+
+static bool do_lut_s4(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+ return !(a->zd & 0b01100) && do_lut(s, a, fn, true);
+}
+
+static bool do_lut_s8(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn)
+{
+ return !(a->zd & 0b01000) && do_lut(s, a, fn, true);
+}
+
+TRANS_FEAT(LUTI2_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2b)
+TRANS_FEAT(LUTI2_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2h)
+
+TRANS_FEAT(LUTI2_s_4b, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4b)
+TRANS_FEAT(LUTI2_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4h)
+
+TRANS_FEAT(LUTI4_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2b)
+TRANS_FEAT(LUTI4_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2h)
+
+TRANS_FEAT(LUTI4_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti4_4h)
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index e1ded43af7..91881d68fd 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -3443,3 +3443,91 @@ void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc)
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
+
+static inline void do_lut_b(void *zd, uint64_t *indexes, uint64_t *table,
+ unsigned elements, unsigned segbase,
+ unsigned dstride, unsigned isize,
+ unsigned tsize, unsigned nreg)
+{
+ for (unsigned r = 0; r < nreg; ++r) {
+ uint8_t *dst = zd + dstride * r;
+ unsigned base = segbase + r * elements;
+
+ for (unsigned e = 0; e < elements; ++e) {
+ unsigned index = extractn(indexes, (base + e) * isize, isize);
+ dst[H1(e)] = extractn(table, index * tsize, 8);
+ }
+ }
+}
+
+static inline void do_lut_h(void *zd, uint64_t *indexes, uint64_t *table,
+ unsigned elements, unsigned segbase,
+ unsigned dstride, unsigned isize,
+ unsigned tsize, unsigned nreg)
+{
+ for (unsigned r = 0; r < nreg; ++r) {
+ uint16_t *dst = zd + dstride * r;
+ unsigned base = segbase + r * elements;
+
+ for (unsigned e = 0; e < elements; ++e) {
+ unsigned index = extractn(indexes, (base + e) * isize, isize);
+ dst[H2(e)] = extractn(table, index * tsize, 16);
+ }
+ }
+}
+
+static inline void do_lut_s(void *zd, uint64_t *indexes, uint32_t *table,
+ unsigned elements, unsigned segbase,
+ unsigned dstride, unsigned isize,
+ unsigned tsize, unsigned nreg)
+{
+ for (unsigned r = 0; r < nreg; ++r) {
+ uint32_t *dst = zd + dstride * r;
+ unsigned base = segbase + r * elements;
+
+ for (unsigned e = 0; e < elements; ++e) {
+ unsigned index = extractn(indexes, (base + e) * isize, isize);
+ dst[H4(e)] = table[H4(index)];
+ }
+ }
+}
+
+#define DO_SME2_LUT(ISIZE, NREG, SUFF, ESIZE) \
+void helper_sme2_luti##ISIZE##_##NREG##SUFF \
+ (void *zd, void *zn, CPUARMState *env, uint32_t desc) \
+{ \
+ unsigned vl = simd_oprsz(desc); \
+ unsigned strided = extract32(desc, SIMD_DATA_SHIFT, 1); \
+ unsigned idx = extract32(desc, SIMD_DATA_SHIFT + 1, 4); \
+ unsigned elements = vl / ESIZE; \
+ unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8); \
+ unsigned segments = (ESIZE * 8) / (ISIZE * NREG); \
+ unsigned segment = idx & (segments - 1); \
+ ARMVectorReg indexes; \
+ memcpy(&indexes, zn, vl); \
+ do_lut_##SUFF(zd, indexes.d, (void *)env->za_state.zt0, elements, \
+ segment * NREG * elements, \
+ dstride * sizeof(ARMVectorReg), ISIZE, 32, NREG); \
+}
+
+DO_SME2_LUT(2,1,b, 1)
+DO_SME2_LUT(2,1,h, 2)
+DO_SME2_LUT(2,1,s, 4)
+DO_SME2_LUT(2,2,b, 1)
+DO_SME2_LUT(2,2,h, 2)
+DO_SME2_LUT(2,2,s, 4)
+DO_SME2_LUT(2,4,b, 1)
+DO_SME2_LUT(2,4,h, 2)
+DO_SME2_LUT(2,4,s, 4)
+
+DO_SME2_LUT(4,1,b, 1)
+DO_SME2_LUT(4,1,h, 2)
+DO_SME2_LUT(4,1,s, 4)
+DO_SME2_LUT(4,2,b, 1)
+DO_SME2_LUT(4,2,h, 2)
+DO_SME2_LUT(4,2,s, 4)
+DO_SME2_LUT(4,4,b, 1)
+DO_SME2_LUT(4,4,h, 2)
+DO_SME2_LUT(4,4,s, 4)
+
+#undef DO_SME2_LUT
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index f7e4143b7d..5a5b8ff8a5 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -945,3 +945,45 @@ ZERO_za 11000000 000011 110 .. 0000000000 00. \
&zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
ZERO_za 11000000 000011 111 .. 0000000000 00. \
&zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4
+
+### SME Lookup Table Read
+
+&lut zd zn idx
+
+# LUTI2, consecutive
+LUTI2_c_1b 1100 0000 1100 11 idx:4 00 00 zn:5 zd:5 &lut
+LUTI2_c_1h 1100 0000 1100 11 idx:4 01 00 zn:5 zd:5 &lut
+LUTI2_c_1s 1100 0000 1100 11 idx:4 10 00 zn:5 zd:5 &lut
+
+LUTI2_c_2b 1100 0000 1000 11 idx:3 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI2_c_2h 1100 0000 1000 11 idx:3 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI2_c_2s 1100 0000 1000 11 idx:3 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2
+
+LUTI2_c_4b 1100 0000 1000 11 idx:2 10 00 00 zn:5 ... 00 &lut zd=%zd_ax4
+LUTI2_c_4h 1100 0000 1000 11 idx:2 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4
+LUTI2_c_4s 1100 0000 1000 11 idx:2 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4
+
+# LUTI2, strided (must check zd alignment)
+LUTI2_s_2b 1100 0000 1001 11 idx:3 1 00 00 zn:5 zd:5 &lut
+LUTI2_s_2h 1100 0000 1001 11 idx:3 1 01 00 zn:5 zd:5 &lut
+
+LUTI2_s_4b 1100 0000 1001 11 idx:2 10 00 00 zn:5 zd:5 &lut
+LUTI2_s_4h 1100 0000 1001 11 idx:2 10 01 00 zn:5 zd:5 &lut
+
+# LUTI4, consecutive
+LUTI4_c_1b 1100 0000 1100 101 idx:3 00 00 zn:5 zd:5 &lut
+LUTI4_c_1h 1100 0000 1100 101 idx:3 01 00 zn:5 zd:5 &lut
+LUTI4_c_1s 1100 0000 1100 101 idx:3 10 00 zn:5 zd:5 &lut
+
+LUTI4_c_2b 1100 0000 1000 101 idx:2 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI4_c_2h 1100 0000 1000 101 idx:2 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2
+LUTI4_c_2s 1100 0000 1000 101 idx:2 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2
+
+LUTI4_c_4h 1100 0000 1000 101 idx:1 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4
+LUTI4_c_4s 1100 0000 1000 101 idx:1 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4
+
+# LUTI4, strided (must check zd alignment)
+LUTI4_s_2b 1100 0000 1001 101 idx:2 1 00 00 zn:5 zd:5 &lut
+LUTI4_s_2h 1100 0000 1001 101 idx:2 1 01 00 zn:5 zd:5 &lut
+
+LUTI4_s_4h 1100 0000 1001 101 idx:1 10 01 00 zn:5 zd:5 &lut
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 89/97] target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1
2025-07-02 12:34 ` [PATCH v3 89/97] target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1 Richard Henderson
@ 2025-07-03 12:42 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:42 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:42, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
> index 236927c640..ad3bfabc34 100644
> --- a/target/arm/tcg/vec_internal.h
> +++ b/target/arm/tcg/vec_internal.h
> @@ -337,6 +337,22 @@ bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst);
> float32 sve_f16_to_f32(float16 f, float_status *fpst);
> float16 sve_f32_to_f16(float32 f, float_status *fpst);
>
> +/* Extract @len bits from an array of uint64_t at offset @pos bits. */
> +static inline uint64_t extractn(uint64_t *p, unsigned pos, unsigned len)
> +{
> + uint64_t x;
> +
> + p += pos / 64;
> + pos = pos % 64;
> +
> + x = p[0];
> + if (pos + len > 64) {
> + x = (x >> pos) | (p[1] << (-pos & 63));
> + pos = 0;
> + }
> + return extract64(x, pos, len);
> +}
We added this in patch 79, I think, so we could put it in
vec_internal.h from the start (with the comment).
Otherwise
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 90/97] target/arm: Rename FMOPA_h to FMOPA_w_h
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (88 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 89/97] target/arm: Implement LUTI2, LUTI4 for SME2/SME2p1 Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-02 12:34 ` [PATCH v3 91/97] target/arm: Rename BFMOPA to BFMOPA_w Richard Henderson
` (6 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
From: Peter Maydell <peter.maydell@linaro.org>
The pattern we currently have as FMOPA_h is the "widening" insn
that takes fp16 inputs and produces single-precision outputs.
This is unlike FMOPA_s and FMOPA_d, which are non-widening
produce outputs the same size as their inputs.
SME2 introduces a non-widening fp16 FMOPA operation; rename
FMOPA_h to FMOPA_w_h (for 'widening'), so we can use FMOPA_h
for the non-widening version, giving it a name in line with
the other non-widening ops FMOPA_s and FMOPA_d.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 2 +-
target/arm/tcg/sme_helper.c | 4 ++--
target/arm/tcg/translate-sme.c | 4 ++--
target/arm/tcg/sme.decode | 2 +-
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index c9961d6b7f..67d620e456 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -135,7 +135,7 @@ DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_7(sme_fmopa_w_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index bcaa67b0fd..00ff4b4c15 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1139,8 +1139,8 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
return float32_add(sum, t32, s_std);
}
-void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
- void *vpm, CPUARMState *env, uint32_t desc)
+void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
uint32_t neg = simd_data(desc) * 0x80008000u;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index d38b8a5ca2..1167aa4964 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -565,8 +565,8 @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
return true;
}
-TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a,
- MO_32, gen_helper_sme_fmopa_h)
+TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a,
+ MO_32, gen_helper_sme_fmopa_w_h)
TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
MO_32, FPST_ZA, gen_helper_sme_fmopa_s)
TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 5a5b8ff8a5..77744eef4f 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -190,7 +190,7 @@ FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64
BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32
-FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32
+FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32
SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32
SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 91/97] target/arm: Rename BFMOPA to BFMOPA_w
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (89 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 90/97] target/arm: Rename FMOPA_h to FMOPA_w_h Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-02 12:34 ` [PATCH v3 92/97] target/arm: Support FPCR.AH in SME FMOPS, BFMOPS Richard Henderson
` (5 subsequent siblings)
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
From: Peter Maydell <peter.maydell@linaro.org>
Our current BFMOPA opcode pattern is the widening version
of the insn. Rename it to BFMOPA_w, to make way for
the non-widening version added in SME2.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 2 +-
target/arm/tcg/sme_helper.c | 4 ++--
target/arm/tcg/translate-sme.c | 2 +-
target/arm/tcg/sme.decode | 2 +-
4 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 67d620e456..16083660e2 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -141,7 +141,7 @@ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
-DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG,
+DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 00ff4b4c15..b6d1adbbf2 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1254,8 +1254,8 @@ void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va,
}
}
-void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm,
- void *vpn, void *vpm, CPUARMState *env, uint32_t desc)
+void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm,
+ void *vpn, void *vpm, CPUARMState *env, uint32_t desc)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
uint32_t neg = simd_data(desc) * 0x80008000u;
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 1167aa4964..38d0231b0a 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -572,7 +572,7 @@ TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
MO_64, FPST_ZA, gen_helper_sme_fmopa_d)
-TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa)
+TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa_w)
TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s)
TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s)
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 77744eef4f..8ad86f707e 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -189,7 +189,7 @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64
FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64
-BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32
+BFMOPA_w 10000001 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32
SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 92/97] target/arm: Support FPCR.AH in SME FMOPS, BFMOPS
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (90 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 91/97] target/arm: Rename BFMOPA to BFMOPA_w Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 12:45 ` Peter Maydell
2025-07-02 12:34 ` [PATCH v3 93/97] target/arm: Implement FMOPA (non-widening) for fp16 Richard Henderson
` (4 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
For non-widening, we can use float_muladd_negate_product,
For widening, which uses dot-product, we need to handle
the negation explicitly.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 19 +++++
target/arm/tcg/vec_internal.h | 5 ++
target/arm/tcg/sme_helper.c | 141 +++++++++++++++++++++++++++------
target/arm/tcg/translate-sme.c | 27 ++++---
4 files changed, 160 insertions(+), 32 deletions(-)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 16083660e2..2b22c6aee5 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -143,6 +143,25 @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_fmops_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_ah_fmops_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
+DEF_HELPER_FLAGS_7(sme_ah_bfmops_w, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, env, i32)
+
DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h
index ad3bfabc34..609ec09062 100644
--- a/target/arm/tcg/vec_internal.h
+++ b/target/arm/tcg/vec_internal.h
@@ -300,6 +300,11 @@ bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp);
/*
* Negate as for FPCR.AH=1 -- do not negate NaNs.
*/
+static inline float16 bfloat16_ah_chs(float16 a)
+{
+ return bfloat16_is_any_nan(a) ? a : bfloat16_chs(a);
+}
+
static inline float16 float16_ah_chs(float16 a)
{
return float16_is_any_nan(a) ? a : float16_chs(a);
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index b6d1adbbf2..cf7ac3eda0 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -995,19 +995,18 @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
}
}
-void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
- void *vpm, float_status *fpst, uint32_t desc)
+static void do_fmopa_s(void *vza, void *vzn, void *vzm, uint16_t *pn,
+ uint16_t *pm, float_status *fpst, uint32_t desc,
+ uint32_t negx, int negf)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
- uint32_t neg = simd_data(desc) << 31;
- uint16_t *pn = vpn, *pm = vpm;
for (row = 0; row < oprsz; ) {
uint16_t pa = pn[H2(row >> 4)];
do {
if (pa & 1) {
void *vza_row = vza + tile_vslice_offset(row);
- uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg;
+ uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ negx;
for (col = 0; col < oprsz; ) {
uint16_t pb = pm[H2(col >> 4)];
@@ -1015,7 +1014,7 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
if (pb & 1) {
uint32_t *a = vza_row + H1_4(col);
uint32_t *m = vzm + H1_4(col);
- *a = float32_muladd(n, *m, *a, 0, fpst);
+ *a = float32_muladd(n, *m, *a, negf, fpst);
}
col += 4;
pb >>= 4;
@@ -1028,29 +1027,65 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
}
}
-void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
+void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn,
void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_fmops_s)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 31, 0);
+}
+
+void HELPER(sme_ah_fmops_s)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+ float_muladd_negate_product);
+}
+
+static void do_fmopa_d(uint64_t *za, uint64_t *zn, uint64_t *zm, uint8_t *pn,
+ uint8_t *pm, float_status *fpst, uint32_t desc,
+ uint64_t negx, int negf)
{
intptr_t row, col, oprsz = simd_oprsz(desc) / 8;
- uint64_t neg = (uint64_t)simd_data(desc) << 63;
- uint64_t *za = vza, *zn = vzn, *zm = vzm;
- uint8_t *pn = vpn, *pm = vpm;
for (row = 0; row < oprsz; ++row) {
if (pn[H1(row)] & 1) {
uint64_t *za_row = &za[tile_vslice_index(row)];
- uint64_t n = zn[row] ^ neg;
+ uint64_t n = zn[row] ^ negx;
for (col = 0; col < oprsz; ++col) {
if (pm[H1(col)] & 1) {
uint64_t *a = &za_row[col];
- *a = float64_muladd(n, zm[col], *a, 0, fpst);
+ *a = float64_muladd(n, zm[col], *a, negf, fpst);
}
}
}
}
}
+void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 1ull << 63, 0);
+}
+
+void HELPER(sme_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+ float_muladd_negate_product);
+}
+
/*
* Alter PAIR as needed for controlling predicates being false,
* and for NEG on an enabled row element.
@@ -1071,6 +1106,20 @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg)
return pair;
}
+static inline uint32_t f16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg)
+{
+ uint32_t l = pg & 1 ? float16_ah_chs(pair) : 0;
+ uint32_t h = pg & 4 ? float16_ah_chs(pair >> 16) : 0;
+ return l | (h << 16);
+}
+
+static inline uint32_t bf16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg)
+{
+ uint32_t l = pg & 1 ? bfloat16_ah_chs(pair) : 0;
+ uint32_t h = pg & 4 ? bfloat16_ah_chs(pair >> 16) : 0;
+ return l | (h << 16);
+}
+
static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
float_status *s_f16, float_status *s_std,
float_status *s_odd)
@@ -1139,12 +1188,11 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2,
return float32_add(sum, t32, s_std);
}
-void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
- void *vpm, CPUARMState *env, uint32_t desc)
+static void do_fmopa_w_h(void *vza, void *vzn, void *vzm, uint16_t *pn,
+ uint16_t *pm, CPUARMState *env, uint32_t desc,
+ uint32_t negx, bool ah_neg)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
- uint32_t neg = simd_data(desc) * 0x80008000u;
- uint16_t *pn = vpn, *pm = vpm;
float_status fpst_odd = env->vfp.fp_status[FPST_ZA];
set_float_rounding_mode(float_round_to_odd, &fpst_odd);
@@ -1155,7 +1203,11 @@ void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
void *vza_row = vza + tile_vslice_offset(row);
uint32_t n = *(uint32_t *)(vzn + H1_4(row));
- n = f16mop_adj_pair(n, prow, neg);
+ if (ah_neg) {
+ n = f16mop_ah_neg_adj_pair(n, prow);
+ } else {
+ n = f16mop_adj_pair(n, prow, negx);
+ }
for (col = 0; col < oprsz; ) {
uint16_t pcol = pm[H2(col >> 4)];
@@ -1180,6 +1232,24 @@ void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
}
}
+void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0, false);
+}
+
+void HELPER(sme_fmops_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0x80008000u, false);
+}
+
+void HELPER(sme_ah_fmops_w_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0, true);
+}
+
void HELPER(sme2_fdot_h)(void *vd, void *vn, void *vm, void *va,
CPUARMState *env, uint32_t desc)
{
@@ -1254,12 +1324,11 @@ void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va,
}
}
-void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm,
- void *vpn, void *vpm, CPUARMState *env, uint32_t desc)
+static void do_bfmopa_w(void *vza, void *vzn, void *vzm,
+ uint16_t *pn, uint16_t *pm, CPUARMState *env,
+ uint32_t desc, uint32_t negx, bool ah_neg)
{
intptr_t row, col, oprsz = simd_maxsz(desc);
- uint32_t neg = simd_data(desc) * 0x80008000u;
- uint16_t *pn = vpn, *pm = vpm;
float_status fpst, fpst_odd;
if (is_ebf(env, &fpst, &fpst_odd)) {
@@ -1269,7 +1338,11 @@ void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm,
void *vza_row = vza + tile_vslice_offset(row);
uint32_t n = *(uint32_t *)(vzn + H1_4(row));
- n = f16mop_adj_pair(n, prow, neg);
+ if (ah_neg) {
+ n = bf16mop_ah_neg_adj_pair(n, prow);
+ } else {
+ n = f16mop_adj_pair(n, prow, negx);
+ }
for (col = 0; col < oprsz; ) {
uint16_t pcol = pm[H2(col >> 4)];
@@ -1296,7 +1369,11 @@ void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm,
void *vza_row = vza + tile_vslice_offset(row);
uint32_t n = *(uint32_t *)(vzn + H1_4(row));
- n = f16mop_adj_pair(n, prow, neg);
+ if (ah_neg) {
+ n = bf16mop_ah_neg_adj_pair(n, prow);
+ } else {
+ n = f16mop_adj_pair(n, prow, negx);
+ }
for (col = 0; col < oprsz; ) {
uint16_t pcol = pm[H2(col >> 4)];
@@ -1319,6 +1396,24 @@ void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm,
}
}
+void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0, false);
+}
+
+void HELPER(sme_bfmops_w)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0x80008000u, false);
+}
+
+void HELPER(sme_ah_bfmops_w)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, CPUARMState *env, uint32_t desc)
+{
+ do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0, true);
+}
+
typedef uint32_t IMOPFn32(uint32_t, uint32_t, uint32_t, uint8_t, bool);
static inline void do_imopa_s(uint32_t *za, uint32_t *zn, uint32_t *zm,
uint8_t *pn, uint8_t *pm,
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 38d0231b0a..782f408061 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -526,7 +526,7 @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz,
gen_helper_gvec_5_ptr *fn)
{
int svl = streaming_vec_reg_size(s);
- uint32_t desc = simd_desc(svl, svl, a->sub);
+ uint32_t desc = simd_desc(svl, svl, 0);
TCGv_ptr za, zn, zm, pn, pm, fpst;
if (!sme_smza_enabled_check(s)) {
@@ -548,7 +548,7 @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
gen_helper_gvec_5_ptr *fn)
{
int svl = streaming_vec_reg_size(s);
- uint32_t desc = simd_desc(svl, svl, a->sub);
+ uint32_t desc = simd_desc(svl, svl, 0);
TCGv_ptr za, zn, zm, pn, pm;
if (!sme_smza_enabled_check(s)) {
@@ -565,14 +565,23 @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz,
return true;
}
-TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a,
- MO_32, gen_helper_sme_fmopa_w_h)
-TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a,
- MO_32, FPST_ZA, gen_helper_sme_fmopa_s)
-TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
- MO_64, FPST_ZA, gen_helper_sme_fmopa_d)
+TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, MO_32,
+ !a->sub ? gen_helper_sme_fmopa_w_h
+ : !s->fpcr_ah ? gen_helper_sme_fmops_w_h
+ : gen_helper_sme_ah_fmops_w_h)
+TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA,
+ !a->sub ? gen_helper_sme_fmopa_s
+ : !s->fpcr_ah ? gen_helper_sme_fmops_s
+ : gen_helper_sme_ah_fmops_s)
+TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA,
+ !a->sub ? gen_helper_sme_fmopa_d
+ : !s->fpcr_ah ? gen_helper_sme_fmops_d
+ : gen_helper_sme_ah_fmops_d)
-TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa_w)
+TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32,
+ !a->sub ? gen_helper_sme_bfmopa_w
+ : !s->fpcr_ah ? gen_helper_sme_bfmops_w
+ : gen_helper_sme_ah_bfmops_w)
TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s)
TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 92/97] target/arm: Support FPCR.AH in SME FMOPS, BFMOPS
2025-07-02 12:34 ` [PATCH v3 92/97] target/arm: Support FPCR.AH in SME FMOPS, BFMOPS Richard Henderson
@ 2025-07-03 12:45 ` Peter Maydell
0 siblings, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:45 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:42, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> For non-widening, we can use float_muladd_negate_product,
> For widening, which uses dot-product, we need to handle
> the negation explicitly.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 93/97] target/arm: Implement FMOPA (non-widening) for fp16
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (91 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 92/97] target/arm: Support FPCR.AH in SME FMOPS, BFMOPS Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 17:15 ` Alex Bennée
2025-07-02 12:34 ` [PATCH v3 94/97] target/arm: Implement SME2 BFMOPA (non-widening) Richard Henderson
` (3 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
From: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 6 ++++
target/arm/tcg/sme_helper.c | 51 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 4 +++
target/arm/tcg/sme.decode | 2 ++
4 files changed, 63 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index 2b22c6aee5..fac70a82b9 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -137,6 +137,8 @@ DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_7(sme_fmopa_w_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
@@ -146,6 +148,8 @@ DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_fmops_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_fmops_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG,
@@ -155,6 +159,8 @@ DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_ah_fmops_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_ah_fmops_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG,
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index cf7ac3eda0..3420685198 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -995,6 +995,57 @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn,
}
}
+static void do_fmopa_h(void *vza, void *vzn, void *vzm, uint16_t *pn,
+ uint16_t *pm, float_status *fpst, uint32_t desc,
+ uint16_t negx, int negf)
+{
+ intptr_t row, col, oprsz = simd_maxsz(desc);
+
+ for (row = 0; row < oprsz; ) {
+ uint16_t pa = pn[H2(row >> 4)];
+ do {
+ if (pa & 1) {
+ void *vza_row = vza + tile_vslice_offset(row);
+ uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx;
+
+ for (col = 0; col < oprsz; ) {
+ uint16_t pb = pm[H2(col >> 4)];
+ do {
+ if (pb & 1) {
+ uint16_t *a = vza_row + H1_2(col);
+ uint16_t *m = vzm + H1_2(col);
+ *a = float16_muladd(n, *m, *a, negf, fpst);
+ }
+ col += 2;
+ pb >>= 2;
+ } while (col & 15);
+ }
+ }
+ row += 2;
+ pa >>= 2;
+ } while (row & 15);
+ }
+}
+
+void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0);
+}
+
+void HELPER(sme_ah_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+ float_muladd_negate_product);
+}
+
static void do_fmopa_s(void *vza, void *vzn, void *vzm, uint16_t *pn,
uint16_t *pm, float_status *fpst, uint32_t desc,
uint32_t negx, int negf)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 782f408061..119a5665e6 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -569,6 +569,10 @@ TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, MO_32,
!a->sub ? gen_helper_sme_fmopa_w_h
: !s->fpcr_ah ? gen_helper_sme_fmops_w_h
: gen_helper_sme_ah_fmops_w_h)
+TRANS_FEAT(FMOPA_h, aa64_sme_f16f16, do_outprod_fpst, a, MO_16, FPST_ZA_F16,
+ !a->sub ? gen_helper_sme_fmopa_h
+ : !s->fpcr_ah ? gen_helper_sme_fmops_h
+ : gen_helper_sme_ah_fmops_h)
TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA,
!a->sub ? gen_helper_sme_fmopa_s
: !s->fpcr_ah ? gen_helper_sme_fmops_s
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 8ad86f707e..3c58fdd2a0 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -183,9 +183,11 @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64
### SME Outer Product
&op zad zn zm pm pn sub:bool
+@op_16 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 ... zad:1 &op
@op_32 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op
@op_64 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 . zad:3 &op
+FMOPA_h 10000001 100 ..... ... ... ..... . 100 . @op_16
FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 94/97] target/arm: Implement SME2 BFMOPA (non-widening)
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (92 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 93/97] target/arm: Implement FMOPA (non-widening) for fp16 Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 17:16 ` Alex Bennée
2025-07-02 12:34 ` [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max Richard Henderson
` (2 subsequent siblings)
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
From: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/helper-sme.h | 6 ++++
target/arm/tcg/sme_helper.c | 51 ++++++++++++++++++++++++++++++++++
target/arm/tcg/translate-sme.c | 5 ++++
target/arm/tcg/sme.decode | 2 ++
4 files changed, 64 insertions(+)
diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
index fac70a82b9..1fc756bec6 100644
--- a/target/arm/tcg/helper-sme.h
+++ b/target/arm/tcg/helper-sme.h
@@ -145,6 +145,8 @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
@@ -156,6 +158,8 @@ DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_bfmops, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
@@ -167,6 +171,8 @@ DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_7(sme_ah_bfmops_w, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_FLAGS_7(sme_ah_bfmops, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 3420685198..fb2b3d9321 100644
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1137,6 +1137,57 @@ void HELPER(sme_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn,
float_muladd_negate_product);
}
+static void do_bfmopa(void *vza, void *vzn, void *vzm, uint16_t *pn,
+ uint16_t *pm, float_status *fpst, uint32_t desc,
+ uint16_t negx, int negf)
+{
+ intptr_t row, col, oprsz = simd_maxsz(desc);
+
+ for (row = 0; row < oprsz; ) {
+ uint16_t pa = pn[H2(row >> 4)];
+ do {
+ if (pa & 1) {
+ void *vza_row = vza + tile_vslice_offset(row);
+ uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx;
+
+ for (col = 0; col < oprsz; ) {
+ uint16_t pb = pm[H2(col >> 4)];
+ do {
+ if (pb & 1) {
+ uint16_t *a = vza_row + H1_2(col);
+ uint16_t *m = vzm + H1_2(col);
+ *a = bfloat16_muladd(n, *m, *a, negf, fpst);
+ }
+ col += 2;
+ pb >>= 2;
+ } while (col & 15);
+ }
+ }
+ row += 2;
+ pa >>= 2;
+ } while (row & 15);
+ }
+}
+
+void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0);
+}
+
+void HELPER(sme_bfmops)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0);
+}
+
+void HELPER(sme_ah_bfmops)(void *vza, void *vzn, void *vzm, void *vpn,
+ void *vpm, float_status *fpst, uint32_t desc)
+{
+ do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0,
+ float_muladd_negate_product);
+}
+
/*
* Alter PAIR as needed for controlling predicates being false,
* and for NEG on an enabled row element.
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 119a5665e6..65fc8bc9b2 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -582,6 +582,11 @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA,
: !s->fpcr_ah ? gen_helper_sme_fmops_d
: gen_helper_sme_ah_fmops_d)
+TRANS_FEAT(BFMOPA, aa64_sme_b16b16, do_outprod_fpst, a, MO_16, FPST_ZA,
+ !a->sub ? gen_helper_sme_bfmopa
+ : !s->fpcr_ah ? gen_helper_sme_bfmops
+ : gen_helper_sme_ah_bfmops)
+
TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32,
!a->sub ? gen_helper_sme_bfmopa_w
: !s->fpcr_ah ? gen_helper_sme_bfmops_w
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 3c58fdd2a0..6bb9aa2a90 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -191,6 +191,8 @@ FMOPA_h 10000001 100 ..... ... ... ..... . 100 . @op_16
FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64
+BFMOPA 10000001 101 ..... ... ... ..... . 100 . @op_16
+
BFMOPA_w 10000001 100 ..... ... ... ..... . 00 .. @op_32
FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (93 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 94/97] target/arm: Implement SME2 BFMOPA (non-widening) Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 12:46 ` Peter Maydell
2025-07-03 17:17 ` Alex Bennée
2025-07-02 12:34 ` [PATCH v3 96/97] linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1 Richard Henderson
2025-07-02 12:34 ` [PATCH v3 97/97] tests/tcg/aarch64: Add sme2-matmul test case Richard Henderson
96 siblings, 2 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/cpu64.c | 10 ++++++++--
docs/system/arm/emulation.rst | 6 ++++++
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
index 5d8ed2794d..f73729926b 100644
--- a/target/arm/tcg/cpu64.c
+++ b/target/arm/tcg/cpu64.c
@@ -1194,7 +1194,7 @@ void aarch64_max_tcg_initfn(Object *obj)
*/
t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */
t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */
- t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */
+ t = FIELD_DP64(t, ID_AA64PFR1, SME, 2); /* FEAT_SME2 */
t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_3 */
t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1); /* FEAT_NMI */
cpu->isar.id_aa64pfr1 = t;
@@ -1245,10 +1245,11 @@ void aarch64_max_tcg_initfn(Object *obj)
cpu->isar.id_aa64mmfr3 = t;
t = cpu->isar.id_aa64zfr0;
- t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1);
+ t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 2); /* FEAT_SVE2p1 */
t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* FEAT_SVE_PMULL128 */
t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); /* FEAT_SVE_BitPerm */
t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 2); /* FEAT_BF16, FEAT_EBF16 */
+ t = FIELD_DP64(t, ID_AA64ZFR0, B16B16, 1); /* FEAT_SVE_B16B16 */
t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); /* FEAT_SVE_SHA3 */
t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); /* FEAT_SVE_SM4 */
t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); /* FEAT_I8MM */
@@ -1264,11 +1265,16 @@ void aarch64_max_tcg_initfn(Object *obj)
t = cpu->isar.id_aa64smfr0;
t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */
+ t = FIELD_DP64(t, ID_AA64SMFR0, BI32I32, 1); /* FEAT_SME2 */
t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */
t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */
t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */
+ t = FIELD_DP64(t, ID_AA64SMFR0, F16F16, 1); /* FEAT_SME_F16F16 */
+ t = FIELD_DP64(t, ID_AA64SMFR0, B16B16, 1); /* FEAT_SME_B16B16 */
+ t = FIELD_DP64(t, ID_AA64SMFR0, I16I32, 5); /* FEAT_SME2 */
t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */
t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */
+ t = FIELD_DP64(t, ID_AA64SMFR0, SMEVER, 2); /* FEAT_SME2p1 */
t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */
cpu->isar.id_aa64smfr0 = t;
diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst
index 78c2fd2113..890dc6fee2 100644
--- a/docs/system/arm/emulation.rst
+++ b/docs/system/arm/emulation.rst
@@ -129,16 +129,22 @@ the following architecture extensions:
- FEAT_SM3 (Advanced SIMD SM3 instructions)
- FEAT_SM4 (Advanced SIMD SM4 instructions)
- FEAT_SME (Scalable Matrix Extension)
+- FEAT_SME2 (Scalable Matrix Extension version 2)
+- FEAT_SME2p1 (Scalable Matrix Extension version 2.1)
+- FEAT_SME_B16B16 (Non-widening BFloat16 arithmetic for SME2)
- FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode)
+- FEAT_SME_F16F16 (Non-widening half-precision FP16 arithmetic for SME2)
- FEAT_SME_F64F64 (Double-precision floating-point outer product instructions)
- FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions)
- FEAT_SVE (Scalable Vector Extension)
- FEAT_SVE_AES (Scalable Vector AES instructions)
+- FEAT_SVE_B16B16 (Non-widening BFloat16 arithmetic for SVE2)
- FEAT_SVE_BitPerm (Scalable Vector Bit Permutes instructions)
- FEAT_SVE_PMULL128 (Scalable Vector PMULL instructions)
- FEAT_SVE_SHA3 (Scalable Vector SHA3 instructions)
- FEAT_SVE_SM4 (Scalable Vector SM4 instructions)
- FEAT_SVE2 (Scalable Vector Extension version 2)
+- FEAT_SVE2p1 (Scalable Vector Extension version 2.1)
- FEAT_SPECRES (Speculation restriction instructions)
- FEAT_SSBS (Speculative Store Bypass Safe)
- FEAT_SSBS2 (MRS and MSR instructions for SSBS version 2)
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* Re: [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max
2025-07-02 12:34 ` [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max Richard Henderson
@ 2025-07-03 12:46 ` Peter Maydell
2025-07-03 17:17 ` Alex Bennée
1 sibling, 0 replies; 172+ messages in thread
From: Peter Maydell @ 2025-07-03 12:46 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm
On Wed, 2 Jul 2025 at 13:42, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/cpu64.c | 10 ++++++++--
> docs/system/arm/emulation.rst | 6 ++++++
> 2 files changed, 14 insertions(+), 2 deletions(-)
>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
thanks
-- PMM
^ permalink raw reply [flat|nested] 172+ messages in thread
* Re: [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max
2025-07-02 12:34 ` [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max Richard Henderson
2025-07-03 12:46 ` Peter Maydell
@ 2025-07-03 17:17 ` Alex Bennée
2025-07-04 3:12 ` Richard Henderson
1 sibling, 1 reply; 172+ messages in thread
From: Alex Bennée @ 2025-07-03 17:17 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm, peter.maydell
Richard Henderson <richard.henderson@linaro.org> writes:
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
> target/arm/tcg/cpu64.c | 10 ++++++++--
> docs/system/arm/emulation.rst | 6 ++++++
> 2 files changed, 14 insertions(+), 2 deletions(-)
>
> diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
> index 5d8ed2794d..f73729926b 100644
> --- a/target/arm/tcg/cpu64.c
> +++ b/target/arm/tcg/cpu64.c
> @@ -1194,7 +1194,7 @@ void aarch64_max_tcg_initfn(Object *obj)
> */
> t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */
> t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */
> - t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */
> + t = FIELD_DP64(t, ID_AA64PFR1, SME, 2); /* FEAT_SME2 */
With -cpu max moving to SME2 is there any way to test just plain SME
now?
--
Alex Bennée
Virtualisation Tech Lead @ Linaro
^ permalink raw reply [flat|nested] 172+ messages in thread
* Re: [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max
2025-07-03 17:17 ` Alex Bennée
@ 2025-07-04 3:12 ` Richard Henderson
2025-07-04 9:30 ` Alex Bennée
0 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-04 3:12 UTC (permalink / raw)
To: Alex Bennée; +Cc: qemu-devel, qemu-arm, peter.maydell
On 7/3/25 11:17, Alex Bennée wrote:
> Richard Henderson <richard.henderson@linaro.org> writes:
>
>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>> ---
>> target/arm/tcg/cpu64.c | 10 ++++++++--
>> docs/system/arm/emulation.rst | 6 ++++++
>> 2 files changed, 14 insertions(+), 2 deletions(-)
>>
>> diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
>> index 5d8ed2794d..f73729926b 100644
>> --- a/target/arm/tcg/cpu64.c
>> +++ b/target/arm/tcg/cpu64.c
>> @@ -1194,7 +1194,7 @@ void aarch64_max_tcg_initfn(Object *obj)
>> */
>> t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */
>> t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */
>> - t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */
>> + t = FIELD_DP64(t, ID_AA64PFR1, SME, 2); /* FEAT_SME2 */
>
> With -cpu max moving to SME2 is there any way to test just plain SME
> now?
No. What we'd want, I guess, is a real cpu model with just sme1.
r~
^ permalink raw reply [flat|nested] 172+ messages in thread
* Re: [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max
2025-07-04 3:12 ` Richard Henderson
@ 2025-07-04 9:30 ` Alex Bennée
0 siblings, 0 replies; 172+ messages in thread
From: Alex Bennée @ 2025-07-04 9:30 UTC (permalink / raw)
To: Richard Henderson; +Cc: qemu-devel, qemu-arm, peter.maydell
Richard Henderson <richard.henderson@linaro.org> writes:
> On 7/3/25 11:17, Alex Bennée wrote:
>> Richard Henderson <richard.henderson@linaro.org> writes:
>>
>>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
>>> ---
>>> target/arm/tcg/cpu64.c | 10 ++++++++--
>>> docs/system/arm/emulation.rst | 6 ++++++
>>> 2 files changed, 14 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c
>>> index 5d8ed2794d..f73729926b 100644
>>> --- a/target/arm/tcg/cpu64.c
>>> +++ b/target/arm/tcg/cpu64.c
>>> @@ -1194,7 +1194,7 @@ void aarch64_max_tcg_initfn(Object *obj)
>>> */
>>> t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */
>>> t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */
>>> - t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */
>>> + t = FIELD_DP64(t, ID_AA64PFR1, SME, 2); /* FEAT_SME2 */
>> With -cpu max moving to SME2 is there any way to test just plain SME
>> now?
>
> No. What we'd want, I guess, is a real cpu model with just sme1.
I've had a bit of a look around and I think the only thing shipping SME
at the moment is the Apple M4 and I can't tell if that's 1 & 2 or just
1. Even then we'd need a full set of idregs for it from someone with
actual HW.
IOW I think we'll be fine for now.
>
>
> r~
--
Alex Bennée
Virtualisation Tech Lead @ Linaro
^ permalink raw reply [flat|nested] 172+ messages in thread
* [PATCH v3 96/97] linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (94 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 95/97] target/arm: Enable FEAT_SME2p1 on -cpu max Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
2025-07-03 12:50 ` Peter Maydell
2025-07-02 12:34 ` [PATCH v3 97/97] tests/tcg/aarch64: Add sme2-matmul test case Richard Henderson
96 siblings, 1 reply; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
linux-user/elfload.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index 2add1665c7..ea214105ff 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -915,6 +915,14 @@ uint64_t get_elf_hwcap2(void)
GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64);
GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC);
GET_FEATURE_ID(aa64_mops, ARM_HWCAP2_A64_MOPS);
+ GET_FEATURE_ID(aa64_sve2p1, ARM_HWCAP2_A64_SVE2P1);
+ GET_FEATURE_ID(aa64_sme2, (ARM_HWCAP2_A64_SME2 |
+ ARM_HWCAP2_A64_SME_I16I32 |
+ ARM_HWCAP2_A64_SME_BI32I32));
+ GET_FEATURE_ID(aa64_sme2p1, ARM_HWCAP2_A64_SME2P1);
+ GET_FEATURE_ID(aa64_sme_b16b16, ARM_HWCAP2_A64_SME_B16B16);
+ GET_FEATURE_ID(aa64_sme_f16f16, ARM_HWCAP2_A64_SME_F16F16);
+ GET_FEATURE_ID(aa64_sve_b16b16, ARM_HWCAP2_A64_SVE_B16B16);
return hwcaps;
}
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread* [PATCH v3 97/97] tests/tcg/aarch64: Add sme2-matmul test case
2025-07-02 12:32 [PATCH v3 00/97] target/arm: Implement FEAT_SME2p1 Richard Henderson
` (95 preceding siblings ...)
2025-07-02 12:34 ` [PATCH v3 96/97] linux-user/aarch64: Set hwcap bits for SME2p1/SVE2p1 Richard Henderson
@ 2025-07-02 12:34 ` Richard Henderson
96 siblings, 0 replies; 172+ messages in thread
From: Richard Henderson @ 2025-07-02 12:34 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, peter.maydell
Extract from
https://learn.arm.com/learning-paths/cross-platform/multiplying-matrices-with-sme2/
Merge into two files and drop the EL3 setup code for FVP.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tests/tcg/aarch64/sme2-matmul-0.c | 236 ++++++++++++++++++++++
tests/tcg/aarch64/Makefile.target | 11 +-
tests/tcg/aarch64/sme2-matmul-1.S | 321 ++++++++++++++++++++++++++++++
3 files changed, 567 insertions(+), 1 deletion(-)
create mode 100644 tests/tcg/aarch64/sme2-matmul-0.c
create mode 100644 tests/tcg/aarch64/sme2-matmul-1.S
diff --git a/tests/tcg/aarch64/sme2-matmul-0.c b/tests/tcg/aarch64/sme2-matmul-0.c
new file mode 100644
index 0000000000..35737c5694
--- /dev/null
+++ b/tests/tcg/aarch64/sme2-matmul-0.c
@@ -0,0 +1,236 @@
+/*
+ * SPDX-FileCopyrightText: Copyright 2024 Arm Limited and/or its affiliates <open-source-office@arm.com>
+ * SPDX-License-Identifier: BSD-3-Clause-Clear
+ *
+ * Copied from
+ * https://learn.arm.com/learning-paths/cross-platform/multiplying-matrices-with-sme2/
+ *
+ * and modified for testing with qemu-aarch64.
+ */
+
+#include <stdint.h>
+#include <string.h>
+#include <inttypes.h>
+#include <math.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#define DEBUG 0
+
+/*
+ * Vanilla matrix multiplication using the by-the-book definition.
+ */
+
+void preprocess_l(uint64_t nbr, uint64_t nbc, uint64_t SVL,
+ const float *restrict a, float *restrict a_mod)
+{
+ // For all tiles of SVL x SVL data
+ for (uint64_t By = 0; By < nbr; By += SVL) {
+ for (uint64_t Bx = 0; Bx < nbc; Bx += SVL) {
+ // For this tile
+ const uint64_t dest = By * nbc + Bx * SVL;
+ for (uint64_t j = 0; j < SVL; j++) {
+ for (uint64_t i = 0; i < SVL && (Bx + i) < nbc; i++) {
+ if (By + j < nbr) {
+ a_mod[dest + i * SVL + j] = a[(By + j) * nbc + Bx + i];
+ } else {
+ // These elements are outside of matrix a, so zero them.
+ a_mod[dest + i * SVL + j] = 0.0;
+ }
+ }
+ }
+ }
+ }
+}
+
+void matmul(uint64_t M, uint64_t K, uint64_t N,
+ const float *restrict matLeft, const float *restrict matRight,
+ float *restrict matResult)
+{
+ for (uint64_t m = 0; m < M; m++) {
+ for (uint64_t n = 0; n < N; n++) {
+ float acc = 0.0;
+
+ for (uint64_t k = 0; k < K; k++) {
+ acc += matLeft[m * K + k] * matRight[k * N + n];
+ }
+
+ matResult[m * N + n] = acc;
+ }
+ }
+}
+
+/*
+ * SME2 Matrix multiplication handwritten in assembly code. This is split in 2
+ * functions that have to be invoked one after the other, with a top level
+ * binding.
+ */
+
+/* Matrix preprocessing, in assembly. */
+void preprocess_l_asm(uint64_t M, uint64_t K, const float *restrict a,
+ float *restrict a_mod);
+
+/* Matrix multiplication (with the *transposed* RHS), in assembly. */
+void matmul_asm_impl(uint64_t M, uint64_t K, uint64_t N,
+ const float *restrict matLeft_mod,
+ const float *restrict matRight, float *restrict matResult);
+
+/* The top level matrix multiplication. */
+void matmul_asm(uint64_t M, uint64_t K, uint64_t N,
+ const float *restrict matLeft, const float *restrict matRight,
+ float *restrict matLeft_mod, float *restrict matResult)
+{
+ __asm volatile("" : : :
+ "v0", "v1", "v2", "v3", "v4", "v5", "v6", "v7",
+ "v8", "v9", "v10", "v11", "v12", "v13", "v14", "v15",
+ "v16", "v17", "v18", "v19", "v20", "v21", "v22", "v23",
+ "v24", "v25", "v26", "v27", "v28", "v29", "v30", "v31");
+
+ preprocess_l_asm(M, K, matLeft, matLeft_mod);
+ matmul_asm_impl(M, K, N, matLeft_mod, matRight, matResult);
+
+ __asm volatile("" : : :
+ "v0", "v1", "v2", "v3", "v4", "v5", "v6", "v7",
+ "v8", "v9", "v10", "v11", "v12", "v13", "v14", "v15",
+ "v16", "v17", "v18", "v19", "v20", "v21", "v22", "v23",
+ "v24", "v25", "v26", "v27", "v28", "v29", "v30", "v31");
+}
+
+
+// Initialize an array of float.
+enum InitKind { RANDOM_INIT, LINEAR_INIT, DEAD_INIT };
+void initialize_matrix(float *mat, size_t num_elements, enum InitKind kind)
+{
+ for (size_t i = 0; i < num_elements; i++)
+ switch (kind) {
+ case RANDOM_INIT:
+ mat[i] = (((float)(rand() % 10000) / 100.0f) - 30.0);
+ break;
+ case LINEAR_INIT:
+ mat[i] = i+1;
+ break;
+ case DEAD_INIT:
+ mat[i] = nan("");
+ break;
+ }
+}
+
+/* Pretty print a matrix. */
+void print_matrix(size_t nbr, size_t nbc, const float *mat, const char *name)
+{
+ printf("%s(%lu,%lu) = [", name, nbr, nbc);
+ for (size_t y = 0; y < nbr; y++) {
+ printf("\n ");
+ for (size_t x = 0; x < nbc; x++)
+ printf("%9.2f, ", mat[y * nbc + x]);
+ }
+ printf("\n];\n");
+}
+
+/* Compare 2 matrices for equality. */
+unsigned compare_matrices(size_t nbr, size_t nbc, const float *reference,
+ const float *result, const char *str)
+{
+ unsigned error = 0;
+
+ for (size_t y = 0; y < nbr; y++) {
+ for (size_t x = 0; x < nbc; x++) {
+ if (fabsf(reference[y * nbc + x] - result[y * nbc + x]) >
+ fabsf(0.0002f * reference[y * nbc + x])) {
+ error = 1;
+ if (DEBUG) {
+ printf("%lu (%lu,%lu): %f <> %f\n", y * nbc + x, x, y,
+ reference[y * nbc + x], result[y * nbc + x]);
+ }
+ }
+ }
+ }
+ if (DEBUG) {
+ if (error) {
+ print_matrix(nbr, nbc, reference, "reference");
+ print_matrix(nbr, nbc, result, "result");
+ }
+ printf("%s: %s !\n", str, error ? "FAILED" : "PASS");
+ }
+
+ return error;
+}
+
+uint64_t ool_svcntsw(void);
+
+/*
+ * Assumptions:
+ * nbr in matLeft (M): any
+ * nbc in matLeft, nbr in matRight (K): any K > 2
+ * nbc in matRight (N): any
+ */
+
+int main(int argc, char **argv)
+{
+ /* Size parameters */
+ uint64_t M, N, K;
+ if (argc >= 4) {
+ M = strtoul(argv[1], NULL, 0);
+ K = strtoul(argv[2], NULL, 0);
+ N = strtoul(argv[3], NULL, 0);
+ } else {
+ /* Default: 125x35x70 */
+ M = 125;
+ K = 35;
+ N = 70;
+ }
+
+ if (DEBUG) {
+ printf("\nSME2 Matrix Multiply fp32 *asm* example "
+ "with args %lu %lu %lu\n", M, K, N);
+ }
+
+ const uint64_t SVL = ool_svcntsw();
+
+ /* Calculate M of transformed matLeft. */
+ const uint64_t M_mod = SVL * (M / SVL + (M % SVL != 0 ? 1 : 0));
+
+ float *matRight = (float *)malloc(K * N * sizeof(float));
+
+ float *matLeft = (float *)malloc(M * K * sizeof(float));
+ float *matLeft_mod = (float *)malloc(M_mod * K * sizeof(float));
+ float *matLeft_mod_ref = (float *)malloc(M_mod * K * sizeof(float));
+
+ float *matResult = (float *)malloc(M * N * sizeof(float));
+ float *matResult_ref = (float *)malloc(M * N * sizeof(float));
+
+ // initialize_matrix(matLeft, M * K, RANDOM_INIT);
+ // initialize_matrix(matRight, K * N, RANDOM_INIT);
+ initialize_matrix(matLeft, M * K, LINEAR_INIT);
+ initialize_matrix(matRight, K * N, LINEAR_INIT);
+ initialize_matrix(matLeft_mod, M_mod * K, DEAD_INIT);
+ initialize_matrix(matResult, M * N, DEAD_INIT);
+
+ if (DEBUG) {
+ print_matrix(M, K, matLeft, "matLeft");
+ print_matrix(K, N, matRight, "matRight");
+ }
+
+ matmul_asm(M, K, N, matLeft, matRight, matLeft_mod, matResult);
+
+ /* Compute the reference values with the vanilla implementations. */
+ matmul(M, K, N, matLeft, matRight, matResult_ref);
+ preprocess_l(M, K, SVL, matLeft, matLeft_mod_ref);
+
+ unsigned error = compare_matrices(K, M_mod, matLeft_mod_ref, matLeft_mod,
+ "Matrix preprocessing");
+ if (!error)
+ error = compare_matrices(M, N, matResult_ref, matResult,
+ "Matrix multiplication");
+
+ free(matRight);
+
+ free(matLeft);
+ free(matLeft_mod);
+ free(matLeft_mod_ref);
+
+ free(matResult);
+ free(matResult_ref);
+
+ return error ? EXIT_FAILURE : EXIT_SUCCESS;
+}
diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target
index 16ddcf4f88..641c00cf02 100644
--- a/tests/tcg/aarch64/Makefile.target
+++ b/tests/tcg/aarch64/Makefile.target
@@ -28,7 +28,8 @@ config-cc.mak: Makefile
$(call cc-option,-march=armv8.5-a, CROSS_CC_HAS_ARMV8_5); \
$(call cc-option,-mbranch-protection=standard, CROSS_CC_HAS_ARMV8_BTI); \
$(call cc-option,-march=armv8.5-a+memtag, CROSS_CC_HAS_ARMV8_MTE); \
- $(call cc-option,-Wa$(COMMA)-march=armv9-a+sme $$fnia, CROSS_AS_HAS_ARMV9_SME)) 3> config-cc.mak
+ $(call cc-option,-Wa$(COMMA)-march=armv9-a+sme $$fnia, CROSS_AS_HAS_ARMV9_SME); \
+ $(call cc-option,-Wa$(COMMA)-march=armv9-a+sme2 $$fnia, CROSS_AS_HAS_ARMV9_SME2)) 3> config-cc.mak
-include config-cc.mak
ifneq ($(CROSS_CC_HAS_ARMV8_2),)
@@ -75,6 +76,14 @@ AARCH64_TESTS += $(SME_TESTS)
$(SME_TESTS): CFLAGS += $(CROSS_AS_HAS_ARMV9_SME)
endif
+# SME2 Tests
+ifneq ($(CROSS_AS_HAS_ARMV9_SME2),)
+sme2-matmul: CFLAGS += $(CROSS_AS_HAS_ARMV9_SME2)
+sme2-matmul: sme2-matmul-0.c sme2-matmul-1.S
+ $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $^ -o $@ $(LDFLAGS)
+AARCH64_TESTS += sme2-matmul
+endif
+
# System Registers Tests
AARCH64_TESTS += sysregs
diff --git a/tests/tcg/aarch64/sme2-matmul-1.S b/tests/tcg/aarch64/sme2-matmul-1.S
new file mode 100644
index 0000000000..5562e24c62
--- /dev/null
+++ b/tests/tcg/aarch64/sme2-matmul-1.S
@@ -0,0 +1,321 @@
+/*
+ * SPDX-FileCopyrightText: Copyright 2024 Arm Limited and/or its affiliates <open-source-office@arm.com>
+ * SPDX-License-Identifier: BSD-3-Clause-Clear
+ *
+ * Copied from
+ * https://learn.arm.com/learning-paths/cross-platform/multiplying-matrices-with-sme2/
+ *
+ * and modified for testing with qemu-aarch64.
+ */
+
+ .text
+ .cfi_sections .debug_frame // put stack frame info into .debug_frame instead of .eh_frame
+
+ .global ool_svcntsw
+ .type ool_svcntsw, "function"
+ .cfi_startproc
+ool_svcntsw:
+ rdsvl x0, #1
+ lsr x0, x0, #1
+ ret
+ .cfi_endproc
+ .size ool_svcntsw, .-ool_svcntsw
+
+ .global preprocess_l_asm
+ .type preprocess_l_asm, "function"
+ .cfi_startproc
+
+preprocess_l_asm:
+ // preprocess_l_asm(uint64_t nbr, uint64_t nbc, const float * restrict a, float * a_mod);
+ // x0 : nbr
+ // x1 : nbc
+ // x2 : &a
+ // x3 : &a_mod
+ // x4 : SVLs (=cntw)
+ // x5 : Exit condition for inner loop
+ // x6 : a_ptr
+ // x7 : Outer loop counter
+ // x8 : a_base
+ // x9 : a_mod store base address
+ // x10: 32b Tile0 store end pointer
+ // x11: SVLs*nbc
+ // x12: Load/Store loop counter
+ // x13: 32b Tile1 store end pointer
+ // x14: 2*nbc
+ // x15: 3*nbc
+ // x16: 32b tile size
+
+// Assumptions:
+// nbr in matLeft (M): any
+// nbc in matLeft, nbr in matRight (K): any K > 2
+// nbc in matRight (N): any
+//
+// Left matrix re-arrangement:
+// Block of SVLs rows is transposed and contiguously stored.
+// Then the same transformation is applied to remaining blocks of SVLs rows.
+// The last block of rows is zero-padded to SVLs rows, if applicable.
+
+ smstart
+
+// constants
+ cntw x4 // SVLs
+ mul x11, x4, x1 // SVLs*nbc
+ lsl x14, x1, #1 // 2*nbc
+ add x15, x14, x1 // 3*nbc
+
+ mul x16, x4, x4 // SVLs*SVLs
+
+ mov x7, #0
+ whilelt p0.s, x7, x0 // Tile predicate (M dimension)
+
+.Loop_outer:
+ mov x8, x2 // a load base address
+ mov x9, x3 // a_mod store base address
+ add x5, x2, x1, lsl #2 // Exit condition for inner loop
+
+ add x10, x9 , x11, lsl #2 // 32b Tile0 store predicate condition
+ sub x13, x10, x16, lsl #2 // 32b Tile1 store predicate condition
+ whilelt pn8.b, x8, x5, vlx2 // Tile predicate-as-counter (K dimension)
+
+.Loop_inner:
+ mov x6, x8 // a_ptr
+
+ mov w12, #0 // Load_loop counter
+
+.Load_loop:
+ psel pn10, pn8, p0.s[w12, 0]
+ psel pn11, pn8, p0.s[w12, 1]
+ psel pn12, pn8, p0.s[w12, 2]
+ psel pn13, pn8, p0.s[w12, 3]
+ ld1w {z20.s, z28.s}, pn10/z, [x6] // Load 2 row vectors from a_ptr
+ ld1w {z21.s, z29.s}, pn11/z, [x6, x1, lsl #2] // Load " " " from a_ptr + nbc
+ ld1w {z22.s, z30.s}, pn12/z, [x6, x14, lsl #2] // Load " " " from a_ptr + nbc*2
+ ld1w {z23.s, z31.s}, pn13/z, [x6, x15, lsl #2] // Load " " " from a_ptr + nbc*3
+ mova za0h.s[w12, 0:3], {z20.s-z23.s}
+ mova za1h.s[w12, 0:3], {z28.s-z31.s}
+
+ add x6, x6, x1, lsl #4 // a_ptr+=4*nbc FP32 elms [Bytes]
+ add w12, w12, #4 // increment counter
+ cmp w12, w4
+ b.mi .Load_loop
+
+ mov w12, #0 // Store_loop counter
+
+.Store_loop:
+ whilelt pn10.b, x9, x10, vlx4
+ whilelt pn11.b, x9, x13, vlx4
+ mova {z0.s-z3.s}, za0v.s[w12, 0:3]
+ mova {z4.s-z7.s}, za1v.s[w12, 0:3]
+ st1w {z0.s-z3.s}, pn10, [x9] // Store 4 col vectors to a_mod
+ st1w {z4.s-z7.s}, pn11, [x9, x16, lsl #2] // Store 4 col vectors to a_mod + SVLs*SVLs
+ addvl x9, x9, #4 // a_mod += 4*SVLb [Bytes]
+ add w12, w12, #4 // increment counter
+ cmp w12, w4
+ b.mi .Store_loop
+
+ add x9, x9, x16, lsl #2
+ addvl x8, x8, #2 // a_base += 2*SVLb [Bytes]
+ whilelt pn8.b, x8, x5, vlx2
+ b.first .Loop_inner
+
+ add x3, x3, x11, lsl #2 // &a_mod += SVLs*nbc FP32 elms [Bytes]
+ add x2, x2, x11, lsl #2 // &a += SVLs*nbc FP32 elms [Bytes]
+ incw x7
+
+ whilelt p0.s, x7, x0
+ b.first .Loop_outer
+
+ smstop
+
+ ret
+ .cfi_endproc
+ .size preprocess_l_asm, .-preprocess_l_asm
+
+ .global matmul_asm_impl
+ .type matmul_asm_impl, "function"
+ .cfi_startproc
+
+matmul_asm_impl:
+ // matmul_asm_impl(M, K, N, matLeft, matRight, matResult_opt);
+ // x0 : M
+ // x1 : K, lda
+ // x2 : N, ldc, ldb
+ // x3 : &matLeft
+ // x4 : &matRight
+ // x5 : &matResult_opt
+ // x6 : SVLs-2
+ // x7 : a_ptr pointer
+ // x8 : a_ptr end address
+ // x9 : c_base pointer
+ // x10: c_ptr0 pointer
+ // x11: Exit condition for N loop
+ // x12: M loop counter
+ // x13: Store loop counter
+ // x14: Predicate select index
+ // x15: Exit condition for K loop
+ // x16: b_base pointer
+ // x17: b_ptr pointer
+ // x18: (SVLs+1)*ldc
+ // x19: ldb + SVLs
+ // x20: SVLs*lda + SVLs
+ // x21: c_ptr1 pointer
+ // x22: SVLs*lda
+ // x23: SVLs*ldc
+
+// Assumptions:
+// nbr in matLeft (M): any
+// nbc in matLeft, nbr in matRight (K): any K > 2
+// nbc in matRight (N): any
+//
+// Left matrix is pre-arranged.
+//
+// 32-bit accumulator mapping with 2x2 tiles processing
+
+ stp x19, x20, [sp, #-48]!
+ stp x21, x22, [sp, #16]
+ stp x23, x24, [sp, #32]
+
+ smstart
+
+// constants
+ cntw x6 // SVLs
+ mul x22, x6, x1 // SVLs*lda
+ mul x23, x6, x2 // SVLs*ldc
+ add x18, x23, x2 // SVLs*ldc + ldc
+ add x11, x4, x2, lsl #2 // Exit condition for N loop
+ mov x12, #0
+ cntb x6 // SVLb
+ mov x14, #0
+ ptrue pn10.b // Predicate as counter for SME2 VLx2 (a_ptr loads)
+ whilelt pn8.s, x12, x0, vlx2 // tiles predicate (M dimension)
+ sub w6, w6, #8 // SVLb-8
+
+.Loop_M:
+ // Extracting tile 0/1 and tile 2/3 predicates (M dimension) from vlx2 predicate.
+ pext { p2.s, p3.s }, pn8[0]
+ mov x16, x4 // b_base
+ mov x9, x5 // c_base
+
+ whilelt pn9.b, x16, x11, vlx2 // tiles predicate (N dimension)
+
+.Loop_N:
+ mov x7, x3 // a_ptr = a_base
+ mov x17, x16 // b_ptr = b_base
+ mov x10, x9 // c_ptr0 = c_base
+
+ // Extracting tile 0/2 and tile 1/3 predicates (N dimension) from vlx2 predicate.
+ pext { p0.b, p1.b }, pn9[0]
+
+ add x8, x3, x22, lsl #2 // a_base + SVLs*lda FP32 elms [Bytes]
+ addvl x15, x8, #-1 // Exit condition for K loop
+ ld1w {z1.s}, p2/z, [x7] // Load 1st vector from a_ptr
+
+ zero {za}
+ ld1w {z2.s-z3.s}, pn9/z, [x17] // Load 2 vectors from b_ptr
+
+ fmopa za0.s, p2/m, p0/m, z1.s, z2.s // ZA0 += 1st a_ptr vector OP 1st b_ptr vector
+ ld1w {z5.s}, p3/z, [x7, x22, lsl #2] // Load 2nd vector from a_ptr
+ addvl x7, x7, #1 // a_ptr += SVLb [Bytes]
+
+.Loop_K:
+ fmopa za2.s, p3/m, p0/m, z5.s, z2.s // ZA2 += 2nd a_ptr vector OP 1st b_ptr vector
+
+ fmopa za1.s, p2/m, p1/m, z1.s, z3.s // ZA1 += 1st a_ptr vector OP 2nd b_ptr vector
+ ld1w {z0.s-z1.s}, pn10/z, [x7] // Load next 2 vectors from a_ptr
+
+ fmopa za3.s, p3/m, p1/m, z5.s, z3.s // ZA3 += 2nd a_ptr vector OP 2nd b_ptr vector
+ ld1w {z6.s-z7.s}, pn9/z, [x17, x2, lsl #2] // Load next 2 vectors from b_ptr
+
+ fmopa za0.s, p2/m, p0/m, z0.s, z6.s // ZA0 += 1st a_ptr vector OP 1st b_ptr vector
+ psel pn11, pn10, p3.s[w14, 0] // Select predicate-as-counter
+ ld1w {z4.s-z5.s}, pn11/z, [x7, x22, lsl #2] // Load next 2 vectors from a_ptr
+
+ fmopa za2.s, p3/m, p0/m, z4.s, z6.s // ZA2 += 2nd a_ptr vector OP 1st b_ptr vector
+ add x17, x17, x2, lsl #3 // b_ptr += 2*ldb FP32 elms [Bytes]
+
+ fmopa za1.s, p2/m, p1/m, z0.s, z7.s // ZA1 += 1st a_ptr vector OP 2nd b_ptr vector
+
+ fmopa za3.s, p3/m, p1/m, z4.s, z7.s // ZA3 += 2nd a_ptr vector OP 2nd b_ptr vector
+ ld1w {z2.s-z3.s}, pn9/z, [x17] // Load next 2 vectors from b_ptr
+
+ fmopa za0.s, p2/m, p0/m, z1.s, z2.s // ZA0 += 1st a_ptr vector OP 1st b_ptr vector
+ addvl x7, x7, #2 // a_ptr += 2*SVLb [Bytes]
+
+ cmp x7, x15
+ b.mi .Loop_K
+
+ fmopa za2.s, p3/m, p0/m, z5.s, z2.s // ZA2 += 2nd a_ptr vector OP 1st b_ptr vector
+
+ fmopa za1.s, p2/m, p1/m, z1.s, z3.s // ZA1 += 1st a_ptr vector OP 2nd b_ptr vector
+
+ fmopa za3.s, p3/m, p1/m, z5.s, z3.s // ZA3 += 2nd a_ptr vector OP 2nd b_ptr vector
+ add x17, x17, x2, lsl #2 // b_ptr += 2*ldb FP32 elms [Bytes]
+
+ cmp x7, x8
+ b.pl .Ktail_end
+
+.Ktail_start:
+ ld1w {z1.s}, p2/z, [x7]
+ ld1w {z2.s-z3.s}, pn9/z, [x17]
+
+ fmopa za0.s, p2/m, p0/m, z1.s, z2.s
+ ld1w {z5.s}, p3/z, [x7, x22, lsl #2]
+
+ fmopa za2.s, p3/m, p0/m, z5.s, z2.s
+
+ fmopa za1.s, p2/m, p1/m, z1.s, z3.s
+
+ fmopa za3.s, p3/m, p1/m, z5.s, z3.s
+
+.Ktail_end:
+ mov w13, #0
+ psel pn11, pn9, p2.b[w13, 0]
+ psel pn12, pn9, p3.b[w13, 0]
+ // Move from ZA tiles to vectors: z0 = za0h[1], z1 = za1h[1], z2 = za2h[1], z3 = za3h[1]
+ mova { z0.b-z3.b }, za0h.b[w13, 0:3]
+ st1w { z0.s-z1.s }, pn11, [x10] // Store to c_ptr0
+ st1w { z2.s-z3.s }, pn12, [x10, x23, lsl #2] // Store to c_ptr0 + SVLs*ldc
+.Loop_store_ZA:
+ psel pn11, pn9, p2.b[w13, 4]
+ psel pn12, pn9, p3.b[w13, 4]
+ mova { z0.b-z3.b }, za0h.b[w13, 4:7]
+ st1w { z0.s-z1.s }, pn11, [x10, x2, lsl #2] // Store to c_ptr0 + ldc
+ st1w { z2.s-z3.s }, pn12, [x10, x18, lsl #2] // Store to c_ptr0 + (SVLs+1)*ldc
+
+ add x10, x10, x2, lsl #3 // c_ptr0 += 2*ldc FP32 elms [Bytes]
+ add w13, w13, #8
+
+ psel pn11, pn9, p2.b[w13, 0]
+ psel pn12, pn9, p3.b[w13, 0]
+ mova { z0.b-z3.b }, za0h.b[w13, 0:3]
+ st1w { z0.s-z1.s }, pn11, [x10] // Store to c_ptr0
+ st1w { z2.s-z3.s }, pn12, [x10, x23, lsl #2] // Store to c_ptr0 + SVLs*ldc
+ cmp w13, w6
+ b.mi .Loop_store_ZA
+
+ psel pn11, pn9, p2.b[w13, 4]
+ psel pn12, pn9, p3.b[w13, 4]
+ mova { z0.b-z3.b }, za0h.b[w13, 4:7]
+ st1w { z0.s-z1.s }, pn11, [x10, x2, lsl #2] // Store to c_ptr0 + ldc
+ st1w { z2.s-z3.s }, pn12, [x10, x18, lsl #2] // Store to c_ptr0 + (SVLs+1)*ldc
+
+ addvl x9, x9, #2
+ addvl x16, x16, #2 // b_base += 2*SVLb [Bytes]
+ whilelt pn9.b, x16, x11, vlx2 // tile predicate (N dimension)
+ b.first .Loop_N
+
+ add x3, x3, x22, lsl #3 // a_base += 2*SVLs*lda FP32 elms [Bytes]
+ add x5, x5, x23, lsl #3 // c_base += 2*SVLs*ldc FP32 elms [Bytes]
+ incw x12, all, mul #2 // M loop counter += 2* SVLs
+ whilelt pn8.s, x12, x0, vlx2 // tiles predicate (M dimension)
+ b.first .Loop_M
+
+ smstop
+
+ ldp x23, x24, [sp, #32]
+ ldp x21, x22, [sp, #16]
+ ldp x19, x20, [sp], #48
+
+ ret
+ .cfi_endproc
+ .size matmul_asm_impl, .-matmul_asm_impl
--
2.43.0
^ permalink raw reply related [flat|nested] 172+ messages in thread