[PATCH v2 0/4] target/arm: Misc cleanups

[PATCH v2 0/4] target/arm: Misc cleanups

[Richard Henderson]

Version 2 adds a fix to a just merged patch.


r~


Richard Henderson (4):
  target/arm: Use tcg_gen_gvec_5_ptr for sve FMLA/FCMLA
  target/arm: Use tcg_gen_gvec_mov for clear_vec_high
  target/arm: Use clear_vec_high more effectively
  target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)

 target/arm/helper-sve.h    |  45 +++++++----
 target/arm/sve_helper.c    | 157 ++++++++++++++-----------------------
 target/arm/translate-a64.c |  69 ++++++++--------
 target/arm/translate-sve.c |  76 +++++++-----------
 4 files changed, 157 insertions(+), 190 deletions(-)

-- 
2.20.1

[PATCH v2 1/4] target/arm: Use tcg_gen_gvec_5_ptr for sve FMLA/FCMLA

[Richard Henderson]

Now that we can pass 7 parameters, do not encode register
operands within simd_data.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Taylor Simpson <tsimpson@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Remove gen_helper_sve_fmla typedef (phil).
---
 target/arm/helper-sve.h    |  45 +++++++----
 target/arm/sve_helper.c    | 157 ++++++++++++++-----------------------
 target/arm/translate-sve.c |  70 ++++++-----------
 3 files changed, 114 insertions(+), 158 deletions(-)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 2f47279155..7a200755ac 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -1099,25 +1099,40 @@ DEF_HELPER_FLAGS_6(sve_fcadd_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_6(sve_fcadd_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
-DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
-DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index fdfa652094..33b5a54a47 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -3372,23 +3372,11 @@ DO_ZPZ_FP(sve_ucvt_dd, uint64_t,     , uint64_to_float64)
 
 #undef DO_ZPZ_FP
 
-/* 4-operand predicated multiply-add.  This requires 7 operands to pass
- * "properly", so we need to encode some of the registers into DESC.
- */
-QEMU_BUILD_BUG_ON(SIMD_DATA_SHIFT + 20 > 32);
-
-static void do_fmla_zpzzz_h(CPUARMState *env, void *vg, uint32_t desc,
+static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg,
+                            float_status *status, uint32_t desc,
                             uint16_t neg1, uint16_t neg3)
 {
     intptr_t i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     do {
@@ -3401,45 +3389,42 @@ static void do_fmla_zpzzz_h(CPUARMState *env, void *vg, uint32_t desc,
                 e1 = *(uint16_t *)(vn + H1_2(i)) ^ neg1;
                 e2 = *(uint16_t *)(vm + H1_2(i));
                 e3 = *(uint16_t *)(va + H1_2(i)) ^ neg3;
-                r = float16_muladd(e1, e2, e3, 0, &env->vfp.fp_status_f16);
+                r = float16_muladd(e1, e2, e3, 0, status);
                 *(uint16_t *)(vd + H1_2(i)) = r;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0, 0);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0, 0);
 }
 
-void HELPER(sve_fmls_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmls_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0x8000, 0);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0x8000, 0);
 }
 
-void HELPER(sve_fnmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0x8000, 0x8000);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0x8000, 0x8000);
 }
 
-void HELPER(sve_fnmls_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmls_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_h(env, vg, desc, 0, 0x8000);
+    do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0, 0x8000);
 }
 
-static void do_fmla_zpzzz_s(CPUARMState *env, void *vg, uint32_t desc,
+static void do_fmla_zpzzz_s(void *vd, void *vn, void *vm, void *va, void *vg,
+                            float_status *status, uint32_t desc,
                             uint32_t neg1, uint32_t neg3)
 {
     intptr_t i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     do {
@@ -3452,45 +3437,42 @@ static void do_fmla_zpzzz_s(CPUARMState *env, void *vg, uint32_t desc,
                 e1 = *(uint32_t *)(vn + H1_4(i)) ^ neg1;
                 e2 = *(uint32_t *)(vm + H1_4(i));
                 e3 = *(uint32_t *)(va + H1_4(i)) ^ neg3;
-                r = float32_muladd(e1, e2, e3, 0, &env->vfp.fp_status);
+                r = float32_muladd(e1, e2, e3, 0, status);
                 *(uint32_t *)(vd + H1_4(i)) = r;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0, 0);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0, 0);
 }
 
-void HELPER(sve_fmls_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmls_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0x80000000, 0);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0x80000000, 0);
 }
 
-void HELPER(sve_fnmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0x80000000, 0x80000000);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0x80000000, 0x80000000);
 }
 
-void HELPER(sve_fnmls_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmls_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_s(env, vg, desc, 0, 0x80000000);
+    do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0, 0x80000000);
 }
 
-static void do_fmla_zpzzz_d(CPUARMState *env, void *vg, uint32_t desc,
+static void do_fmla_zpzzz_d(void *vd, void *vn, void *vm, void *va, void *vg,
+                            float_status *status, uint32_t desc,
                             uint64_t neg1, uint64_t neg3)
 {
     intptr_t i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     do {
@@ -3503,31 +3485,35 @@ static void do_fmla_zpzzz_d(CPUARMState *env, void *vg, uint32_t desc,
                 e1 = *(uint64_t *)(vn + i) ^ neg1;
                 e2 = *(uint64_t *)(vm + i);
                 e3 = *(uint64_t *)(va + i) ^ neg3;
-                r = float64_muladd(e1, e2, e3, 0, &env->vfp.fp_status);
+                r = float64_muladd(e1, e2, e3, 0, status);
                 *(uint64_t *)(vd + i) = r;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, 0, 0);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, 0, 0);
 }
 
-void HELPER(sve_fmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                              void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, INT64_MIN, 0);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, INT64_MIN, 0);
 }
 
-void HELPER(sve_fnmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, INT64_MIN, INT64_MIN);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, INT64_MIN, INT64_MIN);
 }
 
-void HELPER(sve_fnmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fnmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
-    do_fmla_zpzzz_d(env, vg, desc, 0, INT64_MIN);
+    do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, 0, INT64_MIN);
 }
 
 /* Two operand floating-point comparison controlled by a predicate.
@@ -3809,22 +3795,13 @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg,
  * FP Complex Multiply
  */
 
-QEMU_BUILD_BUG_ON(SIMD_DATA_SHIFT + 22 > 32);
-
-void HELPER(sve_fcmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fcmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
     intptr_t j, i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2);
+    unsigned rot = simd_data(desc);
     bool flip = rot & 1;
     float16 neg_imag, neg_real;
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     neg_imag = float16_set_sign(0, (rot & 2) != 0);
@@ -3851,32 +3828,25 @@ void HELPER(sve_fcmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc)
 
             if (likely((pg >> (i & 63)) & 1)) {
                 d = *(float16 *)(va + H1_2(i));
-                d = float16_muladd(e2, e1, d, 0, &env->vfp.fp_status_f16);
+                d = float16_muladd(e2, e1, d, 0, status);
                 *(float16 *)(vd + H1_2(i)) = d;
             }
             if (likely((pg >> (j & 63)) & 1)) {
                 d = *(float16 *)(va + H1_2(j));
-                d = float16_muladd(e4, e3, d, 0, &env->vfp.fp_status_f16);
+                d = float16_muladd(e4, e3, d, 0, status);
                 *(float16 *)(vd + H1_2(j)) = d;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fcmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fcmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
     intptr_t j, i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2);
+    unsigned rot = simd_data(desc);
     bool flip = rot & 1;
     float32 neg_imag, neg_real;
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     neg_imag = float32_set_sign(0, (rot & 2) != 0);
@@ -3903,32 +3873,25 @@ void HELPER(sve_fcmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc)
 
             if (likely((pg >> (i & 63)) & 1)) {
                 d = *(float32 *)(va + H1_2(i));
-                d = float32_muladd(e2, e1, d, 0, &env->vfp.fp_status);
+                d = float32_muladd(e2, e1, d, 0, status);
                 *(float32 *)(vd + H1_2(i)) = d;
             }
             if (likely((pg >> (j & 63)) & 1)) {
                 d = *(float32 *)(va + H1_2(j));
-                d = float32_muladd(e4, e3, d, 0, &env->vfp.fp_status);
+                d = float32_muladd(e4, e3, d, 0, status);
                 *(float32 *)(vd + H1_2(j)) = d;
             }
         } while (i & 63);
     } while (i != 0);
 }
 
-void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
+void HELPER(sve_fcmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va,
+                               void *vg, void *status, uint32_t desc)
 {
     intptr_t j, i = simd_oprsz(desc);
-    unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5);
-    unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5);
-    unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5);
-    unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5);
-    unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2);
+    unsigned rot = simd_data(desc);
     bool flip = rot & 1;
     float64 neg_imag, neg_real;
-    void *vd = &env->vfp.zregs[rd];
-    void *vn = &env->vfp.zregs[rn];
-    void *vm = &env->vfp.zregs[rm];
-    void *va = &env->vfp.zregs[ra];
     uint64_t *g = vg;
 
     neg_imag = float64_set_sign(0, (rot & 2) != 0);
@@ -3955,12 +3918,12 @@ void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc)
 
             if (likely((pg >> (i & 63)) & 1)) {
                 d = *(float64 *)(va + H1_2(i));
-                d = float64_muladd(e2, e1, d, 0, &env->vfp.fp_status);
+                d = float64_muladd(e2, e1, d, 0, status);
                 *(float64 *)(vd + H1_2(i)) = d;
             }
             if (likely((pg >> (j & 63)) & 1)) {
                 d = *(float64 *)(va + H1_2(j));
-                d = float64_muladd(e4, e3, d, 0, &env->vfp.fp_status);
+                d = float64_muladd(e4, e3, d, 0, status);
                 *(float64 *)(vd + H1_2(j)) = d;
             }
         } while (i & 63);
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 6c8bda4e4c..c8649283be 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3946,42 +3946,30 @@ static bool trans_FCADD(DisasContext *s, arg_FCADD *a)
     return true;
 }
 
-typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32);
-
-static bool do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla *fn)
+static bool do_fmla(DisasContext *s, arg_rprrr_esz *a,
+                    gen_helper_gvec_5_ptr *fn)
 {
-    if (fn == NULL) {
+    if (a->esz == 0) {
         return false;
     }
-    if (!sve_access_check(s)) {
-        return true;
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16);
+        tcg_gen_gvec_5_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           pred_full_reg_offset(s, a->pg),
+                           status, vsz, vsz, 0, fn);
+        tcg_temp_free_ptr(status);
     }
-
-    unsigned vsz = vec_full_reg_size(s);
-    unsigned desc;
-    TCGv_i32 t_desc;
-    TCGv_ptr pg = tcg_temp_new_ptr();
-
-    /* We would need 7 operands to pass these arguments "properly".
-     * So we encode all the register numbers into the descriptor.
-     */
-    desc = deposit32(a->rd, 5, 5, a->rn);
-    desc = deposit32(desc, 10, 5, a->rm);
-    desc = deposit32(desc, 15, 5, a->ra);
-    desc = simd_desc(vsz, vsz, desc);
-
-    t_desc = tcg_const_i32(desc);
-    tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg));
-    fn(cpu_env, pg, t_desc);
-    tcg_temp_free_i32(t_desc);
-    tcg_temp_free_ptr(pg);
     return true;
 }
 
 #define DO_FMLA(NAME, name) \
 static bool trans_##NAME(DisasContext *s, arg_rprrr_esz *a)          \
 {                                                                    \
-    static gen_helper_sve_fmla * const fns[4] = {                    \
+    static gen_helper_gvec_5_ptr * const fns[4] = {                  \
         NULL, gen_helper_sve_##name##_h,                             \
         gen_helper_sve_##name##_s, gen_helper_sve_##name##_d         \
     };                                                               \
@@ -3997,7 +3985,8 @@ DO_FMLA(FNMLS_zpzzz, fnmls_zpzzz)
 
 static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a)
 {
-    static gen_helper_sve_fmla * const fns[3] = {
+    static gen_helper_gvec_5_ptr * const fns[4] = {
+        NULL,
         gen_helper_sve_fcmla_zpzzz_h,
         gen_helper_sve_fcmla_zpzzz_s,
         gen_helper_sve_fcmla_zpzzz_d,
@@ -4008,25 +3997,14 @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a)
     }
     if (sve_access_check(s)) {
         unsigned vsz = vec_full_reg_size(s);
-        unsigned desc;
-        TCGv_i32 t_desc;
-        TCGv_ptr pg = tcg_temp_new_ptr();
-
-        /* We would need 7 operands to pass these arguments "properly".
-         * So we encode all the register numbers into the descriptor.
-         */
-        desc = deposit32(a->rd, 5, 5, a->rn);
-        desc = deposit32(desc, 10, 5, a->rm);
-        desc = deposit32(desc, 15, 5, a->ra);
-        desc = deposit32(desc, 20, 2, a->rot);
-        desc = sextract32(desc, 0, 22);
-        desc = simd_desc(vsz, vsz, desc);
-
-        t_desc = tcg_const_i32(desc);
-        tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg));
-        fns[a->esz - 1](cpu_env, pg, t_desc);
-        tcg_temp_free_i32(t_desc);
-        tcg_temp_free_ptr(pg);
+        TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16);
+        tcg_gen_gvec_5_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           pred_full_reg_offset(s, a->pg),
+                           status, vsz, vsz, a->rot, fns[a->esz]);
+        tcg_temp_free_ptr(status);
     }
     return true;
 }
-- 
2.20.1

[PATCH v2 2/4] target/arm: Use tcg_gen_gvec_mov for clear_vec_high

[Richard Henderson]

The 8-byte store for the end a !is_q operation can be
merged with the other stores.  Use a no-op vector move
to trigger the expand_clr portion of tcg_gen_gvec_mov.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-a64.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 62e5729904..b6feb2b9dc 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -496,14 +496,8 @@ static void clear_vec_high(DisasContext *s, bool is_q, int rd)
     unsigned ofs = fp_reg_offset(s, rd, MO_64);
     unsigned vsz = vec_full_reg_size(s);
 
-    if (!is_q) {
-        TCGv_i64 tcg_zero = tcg_const_i64(0);
-        tcg_gen_st_i64(tcg_zero, cpu_env, ofs + 8);
-        tcg_temp_free_i64(tcg_zero);
-    }
-    if (vsz > 16) {
-        tcg_gen_gvec_dup_imm(MO_64, ofs + 16, vsz - 16, vsz - 16, 0);
-    }
+    /* Nop move, with side effect of clearing the tail. */
+    tcg_gen_gvec_mov(MO_64, ofs, ofs, is_q ? 16 : 8, vsz);
 }
 
 void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v)
-- 
2.20.1

[PATCH v2 3/4] target/arm: Use clear_vec_high more effectively

[Richard Henderson]

Do not explicitly store zero to the NEON high part
when we can pass !is_q to clear_vec_high.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-a64.c | 59 +++++++++++++++++++++++---------------
 1 file changed, 36 insertions(+), 23 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index b6feb2b9dc..0947eaee05 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -939,11 +939,10 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
 {
     /* This always zero-extends and writes to a full 128 bit wide vector */
     TCGv_i64 tmplo = tcg_temp_new_i64();
-    TCGv_i64 tmphi;
+    TCGv_i64 tmphi = NULL;
 
     if (size < 4) {
         MemOp memop = s->be_data + size;
-        tmphi = tcg_const_i64(0);
         tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
     } else {
         bool be = s->be_data == MO_BE;
@@ -961,12 +960,13 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
     }
 
     tcg_gen_st_i64(tmplo, cpu_env, fp_reg_offset(s, destidx, MO_64));
-    tcg_gen_st_i64(tmphi, cpu_env, fp_reg_hi_offset(s, destidx));
-
     tcg_temp_free_i64(tmplo);
-    tcg_temp_free_i64(tmphi);
 
-    clear_vec_high(s, true, destidx);
+    if (tmphi) {
+        tcg_gen_st_i64(tmphi, cpu_env, fp_reg_hi_offset(s, destidx));
+        tcg_temp_free_i64(tmphi);
+    }
+    clear_vec_high(s, tmphi != NULL, destidx);
 }
 
 /*
@@ -6960,8 +6960,8 @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
         return;
     }
 
-    tcg_resh = tcg_temp_new_i64();
     tcg_resl = tcg_temp_new_i64();
+    tcg_resh = NULL;
 
     /* Vd gets bits starting at pos bits into Vm:Vn. This is
      * either extracting 128 bits from a 128:128 concatenation, or
@@ -6973,7 +6973,6 @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
             read_vec_element(s, tcg_resh, rm, 0, MO_64);
             do_ext64(s, tcg_resh, tcg_resl, pos);
         }
-        tcg_gen_movi_i64(tcg_resh, 0);
     } else {
         TCGv_i64 tcg_hh;
         typedef struct {
@@ -6988,6 +6987,7 @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
             pos -= 64;
         }
 
+        tcg_resh = tcg_temp_new_i64();
         read_vec_element(s, tcg_resl, elt->reg, elt->elt, MO_64);
         elt++;
         read_vec_element(s, tcg_resh, elt->reg, elt->elt, MO_64);
@@ -7003,9 +7003,12 @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
 
     write_vec_element(s, tcg_resl, rd, 0, MO_64);
     tcg_temp_free_i64(tcg_resl);
-    write_vec_element(s, tcg_resh, rd, 1, MO_64);
-    tcg_temp_free_i64(tcg_resh);
-    clear_vec_high(s, true, rd);
+
+    if (is_q) {
+        write_vec_element(s, tcg_resh, rd, 1, MO_64);
+        tcg_temp_free_i64(tcg_resh);
+    }
+    clear_vec_high(s, is_q, rd);
 }
 
 /* TBL/TBX
@@ -7042,17 +7045,21 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn)
      * the input.
      */
     tcg_resl = tcg_temp_new_i64();
-    tcg_resh = tcg_temp_new_i64();
+    tcg_resh = NULL;
 
     if (is_tblx) {
         read_vec_element(s, tcg_resl, rd, 0, MO_64);
     } else {
         tcg_gen_movi_i64(tcg_resl, 0);
     }
-    if (is_tblx && is_q) {
-        read_vec_element(s, tcg_resh, rd, 1, MO_64);
-    } else {
-        tcg_gen_movi_i64(tcg_resh, 0);
+
+    if (is_q) {
+        tcg_resh = tcg_temp_new_i64();
+        if (is_tblx) {
+            read_vec_element(s, tcg_resh, rd, 1, MO_64);
+        } else {
+            tcg_gen_movi_i64(tcg_resh, 0);
+        }
     }
 
     tcg_idx = tcg_temp_new_i64();
@@ -7072,9 +7079,12 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn)
 
     write_vec_element(s, tcg_resl, rd, 0, MO_64);
     tcg_temp_free_i64(tcg_resl);
-    write_vec_element(s, tcg_resh, rd, 1, MO_64);
-    tcg_temp_free_i64(tcg_resh);
-    clear_vec_high(s, true, rd);
+
+    if (is_q) {
+        write_vec_element(s, tcg_resh, rd, 1, MO_64);
+        tcg_temp_free_i64(tcg_resh);
+    }
+    clear_vec_high(s, is_q, rd);
 }
 
 /* ZIP/UZP/TRN
@@ -7111,7 +7121,7 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
     }
 
     tcg_resl = tcg_const_i64(0);
-    tcg_resh = tcg_const_i64(0);
+    tcg_resh = is_q ? tcg_const_i64(0) : NULL;
     tcg_res = tcg_temp_new_i64();
 
     for (i = 0; i < elements; i++) {
@@ -7162,9 +7172,12 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
 
     write_vec_element(s, tcg_resl, rd, 0, MO_64);
     tcg_temp_free_i64(tcg_resl);
-    write_vec_element(s, tcg_resh, rd, 1, MO_64);
-    tcg_temp_free_i64(tcg_resh);
-    clear_vec_high(s, true, rd);
+
+    if (is_q) {
+        write_vec_element(s, tcg_resh, rd, 1, MO_64);
+        tcg_temp_free_i64(tcg_resh);
+    }
+    clear_vec_high(s, is_q, rd);
 }
 
 /*
-- 
2.20.1

[PATCH v2 4/4] target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)

[Richard Henderson]

DUP (indexed) can duplicate 128-bit elements, so using esz
unconditionally can assert in tcg_gen_gvec_dup_imm.

Fixes: 8711e71f9cbb
Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-sve.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index c8649283be..83614e9e70 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -2044,7 +2044,11 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
             unsigned nofs = vec_reg_offset(s, a->rn, index, esz);
             tcg_gen_gvec_dup_mem(esz, dofs, nofs, vsz, vsz);
         } else {
-            tcg_gen_gvec_dup_imm(esz, dofs, vsz, vsz, 0);
+            /*
+             * While dup_mem handles 128-bit elements, dup_imm does not.
+             * Thankfully element size doesn't matter for splatting zero.
+             */
+            tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0);
         }
     }
     return true;
-- 
2.20.1

Re: [PATCH v2 4/4] target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)

[Laurent Desnogues]

On Thu, May 7, 2020 at 7:23 PM Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> DUP (indexed) can duplicate 128-bit elements, so using esz
> unconditionally can assert in tcg_gen_gvec_dup_imm.
>
> Fixes: 8711e71f9cbb
> Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com>

I had the same fix locally.

Thanks,

Laurent


> ---
>  target/arm/translate-sve.c | 6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
> index c8649283be..83614e9e70 100644
> --- a/target/arm/translate-sve.c
> +++ b/target/arm/translate-sve.c
> @@ -2044,7 +2044,11 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
>              unsigned nofs = vec_reg_offset(s, a->rn, index, esz);
>              tcg_gen_gvec_dup_mem(esz, dofs, nofs, vsz, vsz);
>          } else {
> -            tcg_gen_gvec_dup_imm(esz, dofs, vsz, vsz, 0);
> +            /*
> +             * While dup_mem handles 128-bit elements, dup_imm does not.
> +             * Thankfully element size doesn't matter for splatting zero.
> +             */
> +            tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0);
>          }
>      }
>      return true;
> --
> 2.20.1
>

Re: [PATCH v2 0/4] target/arm: Misc cleanups

[Richard Henderson]

On 5/7/20 10:23 AM, Richard Henderson wrote:
> Version 2 adds a fix to a just merged patch.

Ho hum.  This is actually v4.  Sigh.


r~

Re: [PATCH v2 0/4] target/arm: Misc cleanups

[Peter Maydell]

On Thu, 7 May 2020 at 18:23, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Version 2 adds a fix to a just merged patch.
>
>
> r~
>
>
> Richard Henderson (4):
>   target/arm: Use tcg_gen_gvec_5_ptr for sve FMLA/FCMLA
>   target/arm: Use tcg_gen_gvec_mov for clear_vec_high
>   target/arm: Use clear_vec_high more effectively
>   target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)



Applied to target-arm.next, thanks.

-- PMM

Re: [PATCH v2 0/4] target/arm: Misc cleanups

[Peter Maydell]

On Mon, 11 May 2020 at 12:00, Peter Maydell <peter.maydell@linaro.org> wrote:
>
> On Thu, 7 May 2020 at 18:23, Richard Henderson
> <richard.henderson@linaro.org> wrote:
> >
> > Version 2 adds a fix to a just merged patch.
> >
> >
> > r~
> >
> >
> > Richard Henderson (4):
> >   target/arm: Use tcg_gen_gvec_5_ptr for sve FMLA/FCMLA
> >   target/arm: Use tcg_gen_gvec_mov for clear_vec_high
> >   target/arm: Use clear_vec_high more effectively
> >   target/arm: Fix tcg_gen_gvec_dup_imm vs DUP (indexed)

> Applied to target-arm.next, thanks.

The 'use clear_vec_high more effectively' patch seems
to cause the 'check-acceptance' test
tests/acceptance/boot_linux.py:BootLinuxAarch64.test_virt_tcg
to time out. It looks like that happens with or without
the other clear_vec_high patch, but since they're kind
of related I've dropped both from target-arm.next (but
am keeping patches 1 and 4).

thanks
-- PMM