From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH v2 41/67] target/arm: Convert SQADD, SQSUB, UQADD, UQSUB to decodetree
Date: Fri, 24 May 2024 16:20:55 -0700 [thread overview]
Message-ID: <20240524232121.284515-42-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240524232121.284515-1-richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/tcg/a64.decode | 11 ++++
target/arm/tcg/translate-a64.c | 100 +++++++++++++++++++--------------
2 files changed, 68 insertions(+), 43 deletions(-)
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index f48adef5bb..19010af03b 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -44,6 +44,7 @@
@rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1
@rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd
@rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd
+@rrr_e ........ esz:2 . rm:5 ...... rn:5 rd:5 &rrr_e
@rrx_h ........ .. .. rm:4 .... . . rn:5 rd:5 &rrx_e esz=1 idx=%hlm
@rrx_s ........ .. . rm:5 .... . . rn:5 rd:5 &rrx_e esz=2 idx=%hl
@@ -744,6 +745,11 @@ FRECPS_s 0101 1110 0.1 ..... 11111 1 ..... ..... @rrr_sd
FRSQRTS_s 0101 1110 110 ..... 00111 1 ..... ..... @rrr_h
FRSQRTS_s 0101 1110 1.1 ..... 11111 1 ..... ..... @rrr_sd
+SQADD_s 0101 1110 ..1 ..... 00001 1 ..... ..... @rrr_e
+UQADD_s 0111 1110 ..1 ..... 00001 1 ..... ..... @rrr_e
+SQSUB_s 0101 1110 ..1 ..... 00101 1 ..... ..... @rrr_e
+UQSUB_s 0111 1110 ..1 ..... 00101 1 ..... ..... @rrr_e
+
### Advanced SIMD scalar pairwise
FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h
@@ -857,6 +863,11 @@ BSL_v 0.10 1110 011 ..... 00011 1 ..... ..... @qrrr_b
BIT_v 0.10 1110 101 ..... 00011 1 ..... ..... @qrrr_b
BIF_v 0.10 1110 111 ..... 00011 1 ..... ..... @qrrr_b
+SQADD_v 0.00 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e
+UQADD_v 0.10 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e
+SQSUB_v 0.00 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e
+UQSUB_v 0.10 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e
+
### Advanced SIMD scalar x indexed element
FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index ca7ba6b1e8..2f7298811d 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5060,6 +5060,43 @@ static const FPScalar f_scalar_frsqrts = {
};
TRANS(FRSQRTS_s, do_fp3_scalar, a, &f_scalar_frsqrts)
+static bool do_satacc_s(DisasContext *s, arg_rrr_e *a,
+ MemOp sgn_n, MemOp sgn_m,
+ void (*gen_bhs)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp),
+ void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64))
+{
+ TCGv_i64 t0, t1, t2, qc;
+ MemOp esz = a->esz;
+
+ if (!fp_access_check(s)) {
+ return true;
+ }
+
+ t0 = tcg_temp_new_i64();
+ t1 = tcg_temp_new_i64();
+ t2 = tcg_temp_new_i64();
+ qc = tcg_temp_new_i64();
+ read_vec_element(s, t1, a->rn, 0, esz | sgn_n);
+ read_vec_element(s, t2, a->rm, 0, esz | sgn_m);
+ tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
+
+ if (esz == MO_64) {
+ gen_d(t0, qc, t1, t2);
+ } else {
+ gen_bhs(t0, qc, t1, t2, esz);
+ tcg_gen_ext_i64(t0, t0, esz);
+ }
+
+ write_fp_dreg(s, a->rd, t0);
+ tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
+ return true;
+}
+
+TRANS(SQADD_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqadd_bhs, gen_sqadd_d)
+TRANS(SQSUB_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqsub_bhs, gen_sqsub_d)
+TRANS(UQADD_s, do_satacc_s, a, 0, 0, gen_uqadd_bhs, gen_uqadd_d)
+TRANS(UQSUB_s, do_satacc_s, a, 0, 0, gen_uqsub_bhs, gen_uqsub_d)
+
static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a,
gen_helper_gvec_3_ptr * const fns[3])
{
@@ -5298,6 +5335,11 @@ TRANS(BSL_v, do_bitsel, a->q, a->rd, a->rd, a->rn, a->rm)
TRANS(BIT_v, do_bitsel, a->q, a->rd, a->rm, a->rn, a->rd)
TRANS(BIF_v, do_bitsel, a->q, a->rd, a->rm, a->rd, a->rn)
+TRANS(SQADD_v, do_gvec_fn3, a, gen_gvec_sqadd_qc)
+TRANS(UQADD_v, do_gvec_fn3, a, gen_gvec_uqadd_qc)
+TRANS(SQSUB_v, do_gvec_fn3, a, gen_gvec_sqsub_qc)
+TRANS(UQSUB_v, do_gvec_fn3, a, gen_gvec_uqsub_qc)
+
/*
* Advanced SIMD scalar/vector x indexed element
*/
@@ -9291,29 +9333,8 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
* or scalar-three-reg-same groups.
*/
TCGCond cond;
- TCGv_i64 qc;
switch (opcode) {
- case 0x1: /* SQADD */
- qc = tcg_temp_new_i64();
- tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
- if (u) {
- gen_uqadd_d(tcg_rd, qc, tcg_rn, tcg_rm);
- } else {
- gen_sqadd_d(tcg_rd, qc, tcg_rn, tcg_rm);
- }
- tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
- break;
- case 0x5: /* SQSUB */
- qc = tcg_temp_new_i64();
- tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
- if (u) {
- gen_uqsub_d(tcg_rd, qc, tcg_rn, tcg_rm);
- } else {
- gen_sqsub_d(tcg_rd, qc, tcg_rn, tcg_rm);
- }
- tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
- break;
case 0x6: /* CMGT, CMHI */
cond = u ? TCG_COND_GTU : TCG_COND_GT;
do_cmop:
@@ -9366,6 +9387,8 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
}
break;
default:
+ case 0x1: /* SQADD / UQADD */
+ case 0x5: /* SQSUB / UQSUB */
g_assert_not_reached();
}
}
@@ -9387,8 +9410,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
TCGv_i64 tcg_rd;
switch (opcode) {
- case 0x1: /* SQADD, UQADD */
- case 0x5: /* SQSUB, UQSUB */
case 0x9: /* SQSHL, UQSHL */
case 0xb: /* SQRSHL, UQRSHL */
break;
@@ -9410,6 +9431,8 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
}
break;
default:
+ case 0x1: /* SQADD, UQADD */
+ case 0x5: /* SQSUB, UQSUB */
unallocated_encoding(s);
return;
}
@@ -9436,12 +9459,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL;
switch (opcode) {
- case 0x1: /* SQADD, UQADD */
- genfn = u ? gen_uqadd_bhs : gen_sqadd_bhs;
- break;
- case 0x5: /* SQSUB, UQSUB */
- genfn = u ? gen_uqsub_bhs : gen_sqsub_bhs;
- break;
case 0x9: /* SQSHL, UQSHL */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -9473,6 +9490,8 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
break;
}
default:
+ case 0x1: /* SQADD, UQADD */
+ case 0x5: /* SQSUB, UQSUB */
g_assert_not_reached();
}
@@ -10933,6 +10952,11 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
return;
}
break;
+
+ case 0x01: /* SQADD, UQADD */
+ case 0x05: /* SQSUB, UQSUB */
+ unallocated_encoding(s);
+ return;
}
if (!fp_access_check(s)) {
@@ -10940,20 +10964,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
}
switch (opcode) {
- case 0x01: /* SQADD, UQADD */
- if (u) {
- gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqadd_qc, size);
- } else {
- gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqadd_qc, size);
- }
- return;
- case 0x05: /* SQSUB, UQSUB */
- if (u) {
- gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqsub_qc, size);
- } else {
- gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqsub_qc, size);
- }
- return;
case 0x08: /* SSHL, USHL */
if (u) {
gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_ushl, size);
@@ -11038,6 +11048,10 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
vec_full_reg_offset(s, rm),
is_q ? 16 : 8, vec_full_reg_size(s));
return;
+
+ case 0x01: /* SQADD, UQADD */
+ case 0x05: /* SQSUB, UQSUB */
+ g_assert_not_reached();
}
if (size == 3) {
--
2.34.1
next prev parent reply other threads:[~2024-05-24 23:33 UTC|newest]
Thread overview: 114+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-24 23:20 [PATCH v2 00/67] target/arm: Convert a64 advsimd to decodetree (part 1) Richard Henderson
2024-05-24 23:20 ` [PATCH v2 01/67] target/arm: Add neoverse-n1 to qemu-arm (DO NOT MERGE) Richard Henderson
2024-05-24 23:20 ` [PATCH v2 02/67] target/arm: Use PLD, PLDW, PLI not NOP for t32 Richard Henderson
2024-05-28 13:13 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 03/67] target/arm: Reject incorrect operands to PLD, PLDW, PLI Richard Henderson
2024-05-28 13:18 ` Peter Maydell
2024-05-28 17:36 ` Richard Henderson
2024-05-29 13:32 ` Peter Maydell
2024-05-29 17:39 ` Richard Henderson
2024-05-24 23:20 ` [PATCH v2 04/67] target/arm: Zero-extend writeback for fp16 FCVTZS (scalar, integer) Richard Henderson
2024-05-28 12:48 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 05/67] target/arm: Fix decode of FMOV (hp) vs MOVI Richard Henderson
2024-05-28 12:34 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 06/67] target/arm: Verify sz=0 for Advanced SIMD scalar pairwise (fp16) Richard Henderson
2024-05-28 12:25 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 07/67] target/arm: Split out gengvec.c Richard Henderson
2024-05-24 23:20 ` [PATCH v2 08/67] target/arm: Split out gengvec64.c Richard Henderson
2024-05-24 23:20 ` [PATCH v2 09/67] target/arm: Convert Cryptographic AES to decodetree Richard Henderson
2024-05-24 23:20 ` [PATCH v2 10/67] target/arm: Convert Cryptographic 3-register SHA " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 11/67] target/arm: Convert Cryptographic 2-register " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 12/67] target/arm: Convert Cryptographic 3-register SHA512 " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 13/67] target/arm: Convert Cryptographic 2-register " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 14/67] target/arm: Convert Cryptographic 4-register " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 15/67] target/arm: Convert Cryptographic 3-register, imm2 " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 16/67] target/arm: Convert XAR " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 17/67] target/arm: Convert Advanced SIMD copy " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 18/67] target/arm: Convert FMULX " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 19/67] target/arm: Convert FADD, FSUB, FDIV, FMUL " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 20/67] target/arm: Convert FMAX, FMIN, FMAXNM, FMINNM " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 21/67] target/arm: Introduce vfp_load_reg16 Richard Henderson
2024-05-28 12:22 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 22/67] target/arm: Expand vfp neg and abs inline Richard Henderson
2024-05-24 23:20 ` [PATCH v2 23/67] target/arm: Convert FNMUL to decodetree Richard Henderson
2024-05-24 23:20 ` [PATCH v2 24/67] target/arm: Convert FMLA, FMLS " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 25/67] target/arm: Convert FCMEQ, FCMGE, FCMGT, FACGE, FACGT " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 26/67] target/arm: Convert FABD " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 27/67] target/arm: Convert FRECPS, FRSQRTS " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 28/67] target/arm: Convert FADDP " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 29/67] target/arm: Convert FMAXP, FMINP, FMAXNMP, FMINNMP " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 30/67] target/arm: Use gvec for neon faddp, fmaxp, fminp Richard Henderson
2024-05-24 23:20 ` [PATCH v2 31/67] target/arm: Convert ADDP to decodetree Richard Henderson
2024-05-24 23:20 ` [PATCH v2 32/67] target/arm: Use gvec for neon padd Richard Henderson
2024-05-24 23:20 ` [PATCH v2 33/67] target/arm: Convert SMAXP, SMINP, UMAXP, UMINP to decodetree Richard Henderson
2024-05-24 23:20 ` [PATCH v2 34/67] target/arm: Use gvec for neon pmax, pmin Richard Henderson
2024-05-24 23:20 ` [PATCH v2 35/67] target/arm: Convert FMLAL, FMLSL to decodetree Richard Henderson
2024-05-24 23:20 ` [PATCH v2 36/67] target/arm: Convert disas_simd_3same_logic " Richard Henderson
2024-05-24 23:20 ` [PATCH v2 37/67] target/arm: Improve vector UQADD, UQSUB, SQADD, SQSUB Richard Henderson
2024-05-28 15:24 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 38/67] target/arm: Convert SUQADD and USQADD to gvec Richard Henderson
2024-05-28 15:37 ` Peter Maydell
2024-05-28 17:41 ` Richard Henderson
2024-05-24 23:20 ` [PATCH v2 39/67] target/arm: Inline scalar SUQADD and USQADD Richard Henderson
2024-05-28 15:40 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 40/67] target/arm: Inline scalar SQADD, UQADD, SQSUB, UQSUB Richard Henderson
2024-05-28 15:42 ` Peter Maydell
2024-05-24 23:20 ` Richard Henderson [this message]
2024-05-28 15:44 ` [PATCH v2 41/67] target/arm: Convert SQADD, SQSUB, UQADD, UQSUB to decodetree Peter Maydell
2024-05-24 23:20 ` [PATCH v2 42/67] target/arm: Convert SUQADD, USQADD " Richard Henderson
2024-05-28 15:44 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 43/67] target/arm: Convert SSHL, USHL " Richard Henderson
2024-05-28 15:46 ` Peter Maydell
2024-05-24 23:20 ` [PATCH v2 44/67] target/arm: Convert SRSHL and URSHL (register) to gvec Richard Henderson
2024-05-28 15:51 ` Peter Maydell
2024-05-28 17:30 ` Richard Henderson
2024-05-24 23:20 ` [PATCH v2 45/67] target/arm: Convert SRSHL, URSHL to decodetree Richard Henderson
2024-05-28 15:51 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 46/67] target/arm: Convert SQSHL and UQSHL (register) to gvec Richard Henderson
2024-05-28 15:53 ` Peter Maydell
2024-05-28 17:31 ` Richard Henderson
2024-05-24 23:21 ` [PATCH v2 47/67] target/arm: Convert SQSHL, UQSHL to decodetree Richard Henderson
2024-05-28 15:53 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 48/67] target/arm: Convert SQRSHL and UQRSHL (register) to gvec Richard Henderson
2024-05-28 15:54 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 49/67] target/arm: Convert SQRSHL, UQRSHL to decodetree Richard Henderson
2024-05-28 15:55 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 50/67] target/arm: Convert ADD, SUB (vector) " Richard Henderson
2024-05-28 15:56 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 51/67] target/arm: Convert CMGT, CMHI, CMGE, CMHS, CMTST, CMEQ " Richard Henderson
2024-05-28 15:57 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 52/67] target/arm: Use TCG_COND_TSTNE in gen_cmtst_{i32, i64} Richard Henderson
2024-05-28 15:58 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 53/67] target/arm: Use TCG_COND_TSTNE in gen_cmtst_vec Richard Henderson
2024-05-28 15:59 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 54/67] target/arm: Convert SHADD, UHADD to gvec Richard Henderson
2024-05-28 16:01 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 55/67] target/arm: Convert SHADD, UHADD to decodetree Richard Henderson
2024-05-28 16:01 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 56/67] target/arm: Convert SHSUB, UHSUB to gvec Richard Henderson
2024-05-28 16:02 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 57/67] target/arm: Convert SHSUB, UHSUB to decodetree Richard Henderson
2024-05-28 16:02 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 58/67] target/arm: Convert SRHADD, URHADD to gvec Richard Henderson
2024-05-28 16:03 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 59/67] target/arm: Convert SRHADD, URHADD to decodetree Richard Henderson
2024-05-28 16:04 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 60/67] target/arm: Convert SMAX, SMIN, UMAX, UMIN " Richard Henderson
2024-05-28 16:04 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 61/67] target/arm: Convert SABA, SABD, UABA, UABD " Richard Henderson
2024-05-28 16:05 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 62/67] target/arm: Convert MUL, PMUL " Richard Henderson
2024-05-28 16:06 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 63/67] target/arm: Convert MLA, MLS " Richard Henderson
2024-05-28 16:07 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 64/67] target/arm: Tidy SQDMULH, SQRDMULH (vector) Richard Henderson
2024-05-28 16:08 ` Peter Maydell
2024-05-24 23:21 ` [PATCH v2 65/67] target/arm: Convert SQDMULH, SQRDMULH to decodetree Richard Henderson
2024-05-28 16:10 ` Peter Maydell
2024-05-28 17:27 ` Richard Henderson
2024-05-24 23:21 ` [PATCH v2 66/67] target/arm: Convert FMADD, FMSUB, FNMADD, FNMSUB " Richard Henderson
2024-05-28 16:15 ` Peter Maydell
2024-05-28 17:31 ` Richard Henderson
2024-05-24 23:21 ` [PATCH v2 67/67] target/arm: Convert FCSEL " Richard Henderson
2024-05-28 16:16 ` Peter Maydell
2024-05-28 16:20 ` [PATCH v2 00/67] target/arm: Convert a64 advsimd to decodetree (part 1) Peter Maydell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240524232121.284515-42-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).