qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: peter.maydell@linaro.org, "Alex Bennée" <alex.bennee@linaro.org>
Subject: [PULL 14/30] tcg/i386: Support avx512vbmi2 vector shift-double instructions
Date: Thu,  3 Mar 2022 10:59:28 -1000	[thread overview]
Message-ID: <20220303205944.469445-15-richard.henderson@linaro.org> (raw)
In-Reply-To: <20220303205944.469445-1-richard.henderson@linaro.org>

We will use VPSHLD, VPSHLDV and VPSHRDV for 16-bit rotates.

Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/i386/tcg-target-con-set.h |  1 +
 tcg/i386/tcg-target.opc.h     |  3 +++
 tcg/i386/tcg-target.c.inc     | 38 +++++++++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

diff --git a/tcg/i386/tcg-target-con-set.h b/tcg/i386/tcg-target-con-set.h
index 78774d1005..91ceb0e1da 100644
--- a/tcg/i386/tcg-target-con-set.h
+++ b/tcg/i386/tcg-target-con-set.h
@@ -45,6 +45,7 @@ C_O1_I2(r, r, rI)
 C_O1_I2(x, x, x)
 C_N1_I2(r, r, r)
 C_N1_I2(r, r, rW)
+C_O1_I3(x, 0, x, x)
 C_O1_I3(x, x, x, x)
 C_O1_I4(r, r, re, r, 0)
 C_O1_I4(r, r, r, ri, ri)
diff --git a/tcg/i386/tcg-target.opc.h b/tcg/i386/tcg-target.opc.h
index 1312941800..b5f403e35e 100644
--- a/tcg/i386/tcg-target.opc.h
+++ b/tcg/i386/tcg-target.opc.h
@@ -33,3 +33,6 @@ DEF(x86_psrldq_vec, 1, 1, 1, IMPLVEC)
 DEF(x86_vperm2i128_vec, 1, 2, 1, IMPLVEC)
 DEF(x86_punpckl_vec, 1, 2, 0, IMPLVEC)
 DEF(x86_punpckh_vec, 1, 2, 0, IMPLVEC)
+DEF(x86_vpshldi_vec, 1, 2, 1, IMPLVEC)
+DEF(x86_vpshldv_vec, 1, 3, 0, IMPLVEC)
+DEF(x86_vpshrdv_vec, 1, 3, 0, IMPLVEC)
diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 712ae3a168..a39f890a7d 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -424,6 +424,15 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
 #define OPC_VPROLVQ     (0x15 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
 #define OPC_VPRORVD     (0x14 | P_EXT38 | P_DATA16 | P_EVEX)
 #define OPC_VPRORVQ     (0x14 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
+#define OPC_VPSHLDW     (0x70 | P_EXT3A | P_DATA16 | P_VEXW | P_EVEX)
+#define OPC_VPSHLDD     (0x71 | P_EXT3A | P_DATA16 | P_EVEX)
+#define OPC_VPSHLDQ     (0x71 | P_EXT3A | P_DATA16 | P_VEXW | P_EVEX)
+#define OPC_VPSHLDVW    (0x70 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
+#define OPC_VPSHLDVD    (0x71 | P_EXT38 | P_DATA16 | P_EVEX)
+#define OPC_VPSHLDVQ    (0x71 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
+#define OPC_VPSHRDVW    (0x72 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
+#define OPC_VPSHRDVD    (0x73 | P_EXT38 | P_DATA16 | P_EVEX)
+#define OPC_VPSHRDVQ    (0x73 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
 #define OPC_VPSLLVW     (0x12 | P_EXT38 | P_DATA16 | P_VEXW | P_EVEX)
 #define OPC_VPSLLVD     (0x47 | P_EXT38 | P_DATA16)
 #define OPC_VPSLLVQ     (0x47 | P_EXT38 | P_DATA16 | P_VEXW)
@@ -2867,6 +2876,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static int const sars_insn[4] = {
         OPC_UD2, OPC_PSRAW, OPC_PSRAD, OPC_VPSRAQ
     };
+    static int const vpshldi_insn[4] = {
+        OPC_UD2, OPC_VPSHLDW, OPC_VPSHLDD, OPC_VPSHLDQ
+    };
+    static int const vpshldv_insn[4] = {
+        OPC_UD2, OPC_VPSHLDVW, OPC_VPSHLDVD, OPC_VPSHLDVQ
+    };
+    static int const vpshrdv_insn[4] = {
+        OPC_UD2, OPC_VPSHRDVW, OPC_VPSHRDVD, OPC_VPSHRDVQ
+    };
     static int const abs_insn[4] = {
         /* TODO: AVX512 adds support for MO_64.  */
         OPC_PABSB, OPC_PABSW, OPC_PABSD, OPC_UD2
@@ -2959,6 +2977,16 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_x86_packus_vec:
         insn = packus_insn[vece];
         goto gen_simd;
+    case INDEX_op_x86_vpshldv_vec:
+        insn = vpshldv_insn[vece];
+        a1 = a2;
+        a2 = args[3];
+        goto gen_simd;
+    case INDEX_op_x86_vpshrdv_vec:
+        insn = vpshrdv_insn[vece];
+        a1 = a2;
+        a2 = args[3];
+        goto gen_simd;
 #if TCG_TARGET_REG_BITS == 32
     case INDEX_op_dup2_vec:
         /* First merge the two 32-bit inputs to a single 64-bit element. */
@@ -3061,7 +3089,12 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         insn = OPC_VPERM2I128;
         sub = args[3];
         goto gen_simd_imm8;
+    case INDEX_op_x86_vpshldi_vec:
+        insn = vpshldi_insn[vece];
+        sub = args[3];
+        goto gen_simd_imm8;
     gen_simd_imm8:
+        tcg_debug_assert(insn != OPC_UD2);
         if (type == TCG_TYPE_V256) {
             insn |= P_VEXL;
         }
@@ -3305,6 +3338,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_x86_vperm2i128_vec:
     case INDEX_op_x86_punpckl_vec:
     case INDEX_op_x86_punpckh_vec:
+    case INDEX_op_x86_vpshldi_vec:
 #if TCG_TARGET_REG_BITS == 32
     case INDEX_op_dup2_vec:
 #endif
@@ -3319,6 +3353,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_x86_psrldq_vec:
         return C_O1_I1(x, x);
 
+    case INDEX_op_x86_vpshldv_vec:
+    case INDEX_op_x86_vpshrdv_vec:
+        return C_O1_I3(x, 0, x, x);
+
     case INDEX_op_x86_vpblendvb_vec:
         return C_O1_I3(x, x, x, x);
 
-- 
2.25.1



  parent reply	other threads:[~2022-03-03 21:16 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-03-03 20:59 [PULL 00/30] tcg patch queue Richard Henderson
2022-03-03 20:59 ` [PULL 01/30] tcg/optimize: only read val after const check Richard Henderson
2022-03-03 20:59 ` [PULL 02/30] tcg: Set MAX_OPC_PARAM_IARGS to 7 Richard Henderson
2022-03-03 20:59 ` [PULL 03/30] tcg: Add opcodes for vector nand, nor, eqv Richard Henderson
2022-03-03 20:59 ` [PULL 04/30] tcg/ppc: Implement vector NAND, NOR, EQV Richard Henderson
2022-03-03 20:59 ` [PULL 05/30] tcg/s390x: " Richard Henderson
2022-03-03 20:59 ` [PULL 06/30] tcg/i386: Detect AVX512 Richard Henderson
2022-03-03 20:59 ` [PULL 07/30] tcg/i386: Add tcg_out_evex_opc Richard Henderson
2022-03-03 20:59 ` [PULL 08/30] tcg/i386: Use tcg_can_emit_vec_op in expand_vec_cmp_noinv Richard Henderson
2022-03-03 20:59 ` [PULL 09/30] tcg/i386: Implement avx512 variable shifts Richard Henderson
2022-03-03 20:59 ` [PULL 10/30] tcg/i386: Implement avx512 scalar shift Richard Henderson
2022-03-03 20:59 ` [PULL 11/30] tcg/i386: Implement avx512 immediate sari shift Richard Henderson
2022-03-03 20:59 ` [PULL 12/30] tcg/i386: Implement avx512 immediate rotate Richard Henderson
2022-03-03 20:59 ` [PULL 13/30] tcg/i386: Implement avx512 variable rotate Richard Henderson
2022-03-03 20:59 ` Richard Henderson [this message]
2022-03-03 20:59 ` [PULL 15/30] tcg/i386: Expand vector word rotate as avx512vbmi2 shift-double Richard Henderson
2022-03-03 20:59 ` [PULL 16/30] tcg/i386: Remove rotls_vec from tcg_target_op_def Richard Henderson
2022-03-03 20:59 ` [PULL 17/30] tcg/i386: Expand scalar rotate with avx512 insns Richard Henderson
2022-03-03 20:59 ` [PULL 18/30] tcg/i386: Implement avx512 min/max/abs Richard Henderson
2022-03-03 20:59 ` [PULL 19/30] tcg/i386: Implement avx512 multiply Richard Henderson
2022-03-03 20:59 ` [PULL 20/30] tcg/i386: Implement more logical operations for avx512 Richard Henderson
2022-03-03 20:59 ` [PULL 21/30] tcg/i386: Implement bitsel " Richard Henderson
2022-03-03 20:59 ` [PULL 22/30] tcg: Add TCG_TARGET_SIGNED_ADDR32 Richard Henderson
2022-03-03 20:59 ` [PULL 23/30] accel/tcg: Split out g2h_tlbe Richard Henderson
2022-03-03 20:59 ` [PULL 24/30] accel/tcg: Support TCG_TARGET_SIGNED_ADDR32 for softmmu Richard Henderson
2022-03-03 20:59 ` [PULL 25/30] accel/tcg: Add guest_base_signed_addr32 for user-only Richard Henderson
2022-03-03 20:59 ` [PULL 26/30] linux-user: Support TCG_TARGET_SIGNED_ADDR32 Richard Henderson
2022-03-03 20:59 ` [PULL 27/30] tcg/aarch64: " Richard Henderson
2022-03-03 20:59 ` [PULL 28/30] tcg/mips: " Richard Henderson
2022-03-03 20:59 ` [PULL 29/30] tcg/riscv: " Richard Henderson
2022-03-03 20:59 ` [PULL 30/30] tcg/loongarch64: " Richard Henderson
2022-03-04 15:22 ` [PULL 00/30] tcg patch queue Peter Maydell
2022-03-04 18:47   ` Richard Henderson

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=20220303205944.469445-15-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=alex.bennee@linaro.org \
    --cc=peter.maydell@linaro.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).