qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH v2 62/67] target/arm: Convert MUL, PMUL to decodetree
Date: Fri, 24 May 2024 16:21:16 -0700	[thread overview]
Message-ID: <20240524232121.284515-63-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      |  5 ++++
 target/arm/tcg/translate-a64.c | 51 +++++++++++++---------------------
 2 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 07b604ec30..3ea0643370 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -926,6 +926,8 @@ SABD_v          0.00 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e
 UABD_v          0.10 1110 ..1 ..... 01110 1 ..... ..... @qrrr_e
 SABA_v          0.00 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e
 UABA_v          0.10 1110 ..1 ..... 01111 1 ..... ..... @qrrr_e
+MUL_v           0.00 1110 ..1 ..... 10011 1 ..... ..... @qrrr_e
+PMUL_v          0.10 1110 001 ..... 10011 1 ..... ..... @qrrr_b
 
 ### Advanced SIMD scalar x indexed element
 
@@ -967,3 +969,6 @@ FMLAL_vi        0.00 1111 10 .. .... 0000 . 0 ..... .....   @qrrx_h
 FMLSL_vi        0.00 1111 10 .. .... 0100 . 0 ..... .....   @qrrx_h
 FMLAL2_vi       0.10 1111 10 .. .... 1000 . 0 ..... .....   @qrrx_h
 FMLSL2_vi       0.10 1111 10 .. .... 1100 . 0 ..... .....   @qrrx_h
+
+MUL_vi          0.00 1111 01 .. .... 1000 . 0 ..... .....   @qrrx_h
+MUL_vi          0.00 1111 10 . ..... 1000 . 0 ..... .....   @qrrx_s
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 61afbc434f..1909d1426c 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5468,6 +5468,8 @@ TRANS(SABA_v, do_gvec_fn3_no64, a, gen_gvec_saba)
 TRANS(UABA_v, do_gvec_fn3_no64, a, gen_gvec_uaba)
 TRANS(SABD_v, do_gvec_fn3_no64, a, gen_gvec_sabd)
 TRANS(UABD_v, do_gvec_fn3_no64, a, gen_gvec_uabd)
+TRANS(MUL_v, do_gvec_fn3_no64, a, tcg_gen_gvec_mul)
+TRANS(PMUL_v, do_gvec_op3_ool, a, 0, gen_helper_gvec_pmul_b)
 
 static bool do_cmop_v(DisasContext *s, arg_qrrr_e *a, TCGCond cond)
 {
@@ -5694,6 +5696,22 @@ TRANS_FEAT(FMLSL_vi, aa64_fhm, do_fmlal_idx, a, true, false)
 TRANS_FEAT(FMLAL2_vi, aa64_fhm, do_fmlal_idx, a, false, true)
 TRANS_FEAT(FMLSL2_vi, aa64_fhm, do_fmlal_idx, a, true, true)
 
+static bool do_int3_vector_idx(DisasContext *s, arg_qrrx_e *a,
+                               gen_helper_gvec_3 * const fns[2])
+{
+    assert(a->esz == MO_16 || a->esz == MO_32);
+    if (fp_access_check(s)) {
+        gen_gvec_op3_ool(s, a->q, a->rd, a->rn, a->rm, a->idx, fns[a->esz - 1]);
+    }
+    return true;
+}
+
+static gen_helper_gvec_3 * const f_vector_idx_mul[2] = {
+    gen_helper_gvec_mul_idx_h,
+    gen_helper_gvec_mul_idx_s,
+};
+TRANS(MUL_vi, do_int3_vector_idx, a, f_vector_idx_mul)
+
 /*
  * Advanced SIMD scalar pairwise
  */
@@ -10927,12 +10945,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     int rd = extract32(insn, 0, 5);
 
     switch (opcode) {
-    case 0x13: /* MUL, PMUL */
-        if (u && size != 0) {
-            unallocated_encoding(s);
-            return;
-        }
-        /* fall through */
     case 0x12: /* MLA, MLS */
         if (size == 3) {
             unallocated_encoding(s);
@@ -10969,6 +10981,7 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     case 0x0f: /* SABA, UABA */
     case 0x10: /* ADD, SUB */
     case 0x11: /* CMTST, CMEQ */
+    case 0x13: /* MUL, PMUL */
         unallocated_encoding(s);
         return;
     }
@@ -10978,13 +10991,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x13: /* MUL, PMUL */
-        if (!u) { /* MUL */
-            gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size);
-        } else {  /* PMUL */
-            gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, gen_helper_gvec_pmul_b);
-        }
-        return;
     case 0x12: /* MLA, MLS */
         if (u) {
             gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size);
@@ -12198,7 +12204,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     TCGv_ptr fpst;
 
     switch (16 * u + opcode) {
-    case 0x08: /* MUL */
     case 0x10: /* MLA */
     case 0x14: /* MLS */
         if (is_scalar) {
@@ -12285,6 +12290,7 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
     case 0x01: /* FMLA */
     case 0x04: /* FMLSL */
     case 0x05: /* FMLS */
+    case 0x08: /* MUL */
     case 0x09: /* FMUL */
     case 0x18: /* FMLAL2 */
     case 0x19: /* FMULX */
@@ -12407,22 +12413,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
         }
         return;
 
-    case 0x08: /* MUL */
-        if (!is_long && !is_scalar) {
-            static gen_helper_gvec_3 * const fns[3] = {
-                gen_helper_gvec_mul_idx_h,
-                gen_helper_gvec_mul_idx_s,
-                gen_helper_gvec_mul_idx_d,
-            };
-            tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd),
-                               vec_full_reg_offset(s, rn),
-                               vec_full_reg_offset(s, rm),
-                               is_q ? 16 : 8, vec_full_reg_size(s),
-                               index, fns[size - 1]);
-            return;
-        }
-        break;
-
     case 0x10: /* MLA */
         if (!is_long && !is_scalar) {
             static gen_helper_gvec_4 * const fns[3] = {
@@ -12491,7 +12481,6 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32);
 
             switch (16 * u + opcode) {
-            case 0x08: /* MUL */
             case 0x10: /* MLA */
             case 0x14: /* MLS */
             {
-- 
2.34.1



  parent reply	other threads:[~2024-05-24 23:30 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 ` [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 ` Richard Henderson [this message]
2024-05-28 16:06   ` [PATCH v2 62/67] target/arm: Convert MUL, PMUL " 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=20240524232121.284515-63-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).