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 42/67] target/arm: Convert SUQADD, USQADD to decodetree
Date: Fri, 24 May 2024 16:20:56 -0700	[thread overview]
Message-ID: <20240524232121.284515-43-richard.henderson@linaro.org> (raw)
In-Reply-To: <20240524232121.284515-1-richard.henderson@linaro.org>

These are faux 2-operand instructions, reading from rd.
Sort them next to the other three-operand same insns for clarity.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/a64.decode      |  8 +++++
 target/arm/tcg/translate-a64.c | 64 ++++------------------------------
 2 files changed, 14 insertions(+), 58 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 19010af03b..7c350ba833 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -45,6 +45,7 @@
 @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
+@r2r_e          ........ esz:2 . ..... ...... rm:5 rd:5 &rrr_e rn=%rd
 
 @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
@@ -60,6 +61,7 @@
 @qrrr_h         . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=1
 @qrrr_sd        . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=%esz_sd
 @qrrr_e         . q:1 ...... esz:2 . rm:5 ...... rn:5 rd:5  &qrrr_e
+@qr2r_e         . q:1 ...... esz:2 . ..... ...... rm:5 rd:5 &qrrr_e rn=%rd
 
 @qrrx_h         . q:1 .. .... .. .. rm:4 .... . . rn:5 rd:5 \
                 &qrrx_e esz=1 idx=%hlm
@@ -750,6 +752,9 @@ 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
 
+SUQADD_s        0101 1110 ..1 00000 00111 0 ..... ..... @r2r_e
+USQADD_s        0111 1110 ..1 00000 00111 0 ..... ..... @r2r_e
+
 ### Advanced SIMD scalar pairwise
 
 FADDP_s         0101 1110 0011 0000 1101 10 ..... ..... @rr_h
@@ -868,6 +873,9 @@ 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
 
+SUQADD_v        0.00 1110 ..1 00000 00111 0 ..... ..... @qr2r_e
+USQADD_v        0.10 1110 ..1 00000 00111 0 ..... ..... @qr2r_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 2f7298811d..fbcf18f92a 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5096,6 +5096,8 @@ 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)
+TRANS(SUQADD_s, do_satacc_s, a, MO_SIGN, 0, gen_suqadd_bhs, gen_suqadd_d)
+TRANS(USQADD_s, do_satacc_s, a, 0, MO_SIGN, gen_usqadd_bhs, gen_usqadd_d)
 
 static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a,
                           gen_helper_gvec_3_ptr * const fns[3])
@@ -5339,6 +5341,8 @@ 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)
+TRANS(SUQADD_v, do_gvec_fn3, a, gen_gvec_suqadd_qc)
+TRANS(USQADD_v, do_gvec_fn3, a, gen_gvec_usqadd_qc)
 
 /*
  * Advanced SIMD scalar/vector x indexed element
@@ -10009,48 +10013,6 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar,
     clear_vec_high(s, is_q, rd);
 }
 
-/* Remaining saturating accumulating ops */
-static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u,
-                                bool is_q, unsigned size, int rn, int rd)
-{
-    TCGv_i64 res, qc, a, b;
-
-    if (!is_scalar) {
-        gen_gvec_fn3(s, is_q, rd, rd, rn,
-                     is_u ? gen_gvec_usqadd_qc : gen_gvec_suqadd_qc, size);
-        return;
-    }
-
-    res = tcg_temp_new_i64();
-    qc = tcg_temp_new_i64();
-    a = tcg_temp_new_i64();
-    b = tcg_temp_new_i64();
-
-    /* Read and extend scalar inputs to 64-bits. */
-    read_vec_element(s, a, rd, 0, size | (is_u ? 0 : MO_SIGN));
-    read_vec_element(s, b, rn, 0, size | (is_u ? MO_SIGN : 0));
-    tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
-
-    if (size == MO_64) {
-        if (is_u) {
-            gen_usqadd_d(res, qc, a, b);
-        } else {
-            gen_suqadd_d(res, qc, a, b);
-        }
-    } else {
-        if (is_u) {
-            gen_usqadd_bhs(res, qc, a, b, size);
-        } else {
-            gen_suqadd_bhs(res, qc, a, b, size);
-            /* Truncate signed 64-bit result for writeback. */
-            tcg_gen_ext_i64(res, res, size);
-        }
-    }
-
-    write_fp_dreg(s, rd, res);
-    tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
-}
-
 /* AdvSIMD scalar two reg misc
  *  31 30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
  * +-----+---+-----------+------+-----------+--------+-----+------+------+
@@ -10070,12 +10032,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
     TCGv_ptr tcg_fpstatus;
 
     switch (opcode) {
-    case 0x3: /* USQADD / SUQADD*/
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_2misc_satacc(s, true, u, false, size, rn, rd);
-        return;
     case 0x7: /* SQABS / SQNEG */
         break;
     case 0xa: /* CMLT */
@@ -10175,6 +10131,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
         }
         break;
     default:
+    case 0x3: /* USQADD / SUQADD */
         unallocated_encoding(s);
         return;
     }
@@ -11666,16 +11623,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             return;
         }
         break;
-    case 0x3: /* SUQADD, USQADD */
-        if (size == 3 && !is_q) {
-            unallocated_encoding(s);
-            return;
-        }
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_2misc_satacc(s, false, u, is_q, size, rn, rd);
-        return;
     case 0x7: /* SQABS, SQNEG */
         if (size == 3 && !is_q) {
             unallocated_encoding(s);
@@ -11850,6 +11797,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
         break;
     }
     default:
+    case 0x3: /* SUQADD, USQADD */
         unallocated_encoding(s);
         return;
     }
-- 
2.34.1



  parent reply	other threads:[~2024-05-24 23:28 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 ` Richard Henderson [this message]
2024-05-28 15:44   ` [PATCH v2 42/67] target/arm: Convert SUQADD, USQADD " 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=20240524232121.284515-43-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).