From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH v2 47/67] target/arm: Convert SQSHL, UQSHL to decodetree
Date: Fri, 24 May 2024 16:21:01 -0700 [thread overview]
Message-ID: <20240524232121.284515-48-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 | 4 ++
target/arm/tcg/translate-a64.c | 74 ++++++++++++++++++++++------------
2 files changed, 53 insertions(+), 25 deletions(-)
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 9e02776036..85caf37948 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -760,6 +760,8 @@ SSHL_s 0101 1110 111 ..... 01000 1 ..... ..... @rrr_d
USHL_s 0111 1110 111 ..... 01000 1 ..... ..... @rrr_d
SRSHL_s 0101 1110 111 ..... 01010 1 ..... ..... @rrr_d
URSHL_s 0111 1110 111 ..... 01010 1 ..... ..... @rrr_d
+SQSHL_s 0101 1110 ..1 ..... 01001 1 ..... ..... @rrr_e
+UQSHL_s 0111 1110 ..1 ..... 01001 1 ..... ..... @rrr_e
### Advanced SIMD scalar pairwise
@@ -886,6 +888,8 @@ SSHL_v 0.00 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e
USHL_v 0.10 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e
SRSHL_v 0.00 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e
URSHL_v 0.10 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e
+SQSHL_v 0.00 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e
+UQSHL_v 0.10 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e
### Advanced SIMD scalar x indexed element
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 50b653bb4d..f8d2760bea 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5119,6 +5119,49 @@ TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64)
TRANS(SRSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_s64)
TRANS(URSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_u64)
+typedef struct ENVScalar2 {
+ NeonGenTwoOpEnvFn *gen_bhs[3];
+ NeonGenTwo64OpEnvFn *gen_d;
+} ENVScalar2;
+
+static bool do_env_scalar2(DisasContext *s, arg_rrr_e *a, const ENVScalar2 *f)
+{
+ if (!fp_access_check(s)) {
+ return true;
+ }
+ if (a->esz == MO_64) {
+ TCGv_i64 t0 = read_fp_dreg(s, a->rn);
+ TCGv_i64 t1 = read_fp_dreg(s, a->rm);
+ f->gen_d(t0, tcg_env, t0, t1);
+ write_fp_dreg(s, a->rd, t0);
+ } else {
+ TCGv_i32 t0 = tcg_temp_new_i32();
+ TCGv_i32 t1 = tcg_temp_new_i32();
+
+ read_vec_element_i32(s, t0, a->rn, 0, a->esz);
+ read_vec_element_i32(s, t1, a->rm, 0, a->esz);
+ f->gen_bhs[a->esz](t0, tcg_env, t0, t1);
+ write_fp_sreg(s, a->rd, t0);
+ }
+ return true;
+}
+
+static const ENVScalar2 f_scalar_sqshl = {
+ { gen_helper_neon_qshl_s8,
+ gen_helper_neon_qshl_s16,
+ gen_helper_neon_qshl_s32 },
+ gen_helper_neon_qshl_s64,
+};
+TRANS(SQSHL_s, do_env_scalar2, a, &f_scalar_sqshl)
+
+static const ENVScalar2 f_scalar_uqshl = {
+ { gen_helper_neon_qshl_u8,
+ gen_helper_neon_qshl_u16,
+ gen_helper_neon_qshl_u32 },
+ gen_helper_neon_qshl_u64,
+};
+TRANS(UQSHL_s, do_env_scalar2, a, &f_scalar_uqshl)
+
static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a,
gen_helper_gvec_3_ptr * const fns[3])
{
@@ -5368,6 +5411,8 @@ TRANS(SSHL_v, do_gvec_fn3, a, gen_gvec_sshl)
TRANS(USHL_v, do_gvec_fn3, a, gen_gvec_ushl)
TRANS(SRSHL_v, do_gvec_fn3, a, gen_gvec_srshl)
TRANS(URSHL_v, do_gvec_fn3, a, gen_gvec_urshl)
+TRANS(SQSHL_v, do_gvec_fn3, a, gen_neon_sqshl)
+TRANS(UQSHL_v, do_gvec_fn3, a, gen_neon_uqshl)
/*
@@ -9381,13 +9426,6 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
}
gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm);
break;
- case 0x9: /* SQSHL, UQSHL */
- if (u) {
- gen_helper_neon_qshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
- } else {
- gen_helper_neon_qshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
- }
- break;
case 0xb: /* SQRSHL, UQRSHL */
if (u) {
gen_helper_neon_qrshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
@@ -9406,6 +9444,7 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
case 0x1: /* SQADD / UQADD */
case 0x5: /* SQSUB / UQSUB */
case 0x8: /* SSHL, USHL */
+ case 0x9: /* SQSHL, UQSHL */
case 0xa: /* SRSHL, URSHL */
g_assert_not_reached();
}
@@ -9428,7 +9467,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
TCGv_i64 tcg_rd;
switch (opcode) {
- case 0x9: /* SQSHL, UQSHL */
case 0xb: /* SQRSHL, UQRSHL */
break;
case 0x6: /* CMGT, CMHI */
@@ -9450,6 +9488,7 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
case 0x1: /* SQADD, UQADD */
case 0x5: /* SQSUB, UQSUB */
case 0x8: /* SSHL, USHL */
+ case 0x9: /* SQSHL, UQSHL */
case 0xa: /* SRSHL, URSHL */
unallocated_encoding(s);
return;
@@ -9477,16 +9516,6 @@ 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 0x9: /* SQSHL, UQSHL */
- {
- static NeonGenTwoOpEnvFn * const fns[3][2] = {
- { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
- { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
- { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
- };
- genenvfn = fns[size][u];
- break;
- }
case 0xb: /* SQRSHL, UQRSHL */
{
static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -9510,6 +9539,7 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
default:
case 0x1: /* SQADD, UQADD */
case 0x5: /* SQSUB, UQSUB */
+ case 0x9: /* SQSHL, UQSHL */
g_assert_not_reached();
}
@@ -10935,13 +10965,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
}
switch (opcode) {
- case 0x09: /* SQSHL, UQSHL */
- if (u) {
- gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqshl, size);
- } else {
- gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqshl, size);
- }
- return;
case 0x0c: /* SMAX, UMAX */
if (u) {
gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size);
@@ -11023,6 +11046,7 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
case 0x01: /* SQADD, UQADD */
case 0x05: /* SQSUB, UQSUB */
case 0x08: /* SSHL, USHL */
+ case 0x09: /* SQSHL, UQSHL */
case 0x0a: /* SRSHL, URSHL */
g_assert_not_reached();
}
--
2.34.1
next prev parent reply other threads:[~2024-05-24 23:32 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 ` [PATCH v2 41/67] target/arm: Convert SQADD, SQSUB, UQADD, UQSUB to decodetree Richard Henderson
2024-05-28 15:44 ` 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 ` Richard Henderson [this message]
2024-05-28 15:53 ` [PATCH v2 47/67] target/arm: Convert SQSHL, UQSHL to decodetree 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=20240524232121.284515-48-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).