qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: paul@nowt.org, richard.henderson@linaro.org
Subject: [PATCH 27/35] target/i386: reimplement 0x0f 0xc2, 0xc4-0xc6, add AVX
Date: Thu, 13 Oct 2022 23:46:43 +0200	[thread overview]
Message-ID: <20221013214651.672114-28-pbonzini@redhat.com> (raw)
In-Reply-To: <20221013214651.672114-1-pbonzini@redhat.com>

Nothing special going on here, for once.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/tcg/decode-new.c.inc |  5 +++
 target/i386/tcg/emit.c.inc       | 75 ++++++++++++++++++++++++++++++++
 target/i386/tcg/translate.c      |  1 +
 3 files changed, 81 insertions(+)

diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.c.inc
index 6732720302..a5b4a98ba0 100644
--- a/target/i386/tcg/decode-new.c.inc
+++ b/target/i386/tcg/decode-new.c.inc
@@ -655,6 +655,11 @@ static const X86OpEntry opcodes_0F[256] = {
     [0x7e] = X86_OP_GROUP0(0F7E),
     [0x7f] = X86_OP_GROUP0(0F7F),
 
+    [0xc2] = X86_OP_ENTRY4(VCMP,       V,x, H,x, W,x,       vex2_rep3 p_00_66_f3_f2),
+    [0xc4] = X86_OP_ENTRY4(PINSRW,     V,dq,H,dq,E,w,       vex5 mmx p_00_66),
+    [0xc5] = X86_OP_ENTRY3(PEXTRW,     G,d, U,dq,I,b,       vex5 mmx p_00_66),
+    [0xc6] = X86_OP_ENTRY4(VSHUF,      V,x, H,x, W,x,       vex4 p_00_66),
+
     [0xd0] = X86_OP_ENTRY3(VADDSUB,   V,x, H,x, W,x,        vex2 cpuid(SSE3) p_66_f2),
     [0xd1] = X86_OP_ENTRY3(PSRLW_r,   V,x, H,x, W,x,        vex4 mmx avx2_256 p_00_66),
     [0xd2] = X86_OP_ENTRY3(PSRLD_r,   V,x, H,x, W,x,        vex4 mmx avx2_256 p_00_66),
diff --git a/target/i386/tcg/emit.c.inc b/target/i386/tcg/emit.c.inc
index 0c5e9d956a..d4534c3f39 100644
--- a/target/i386/tcg/emit.c.inc
+++ b/target/i386/tcg/emit.c.inc
@@ -1341,6 +1341,11 @@ static void gen_PINSRB(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode
     gen_pinsr(s, env, decode, MO_8);
 }
 
+static void gen_PINSRW(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
+{
+    gen_pinsr(s, env, decode, MO_16);
+}
+
 static void gen_PINSR(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 {
     gen_pinsr(s, env, decode, decode->op[2].ot);
@@ -1645,6 +1650,66 @@ static void gen_VAESIMC(DisasContext *s, CPUX86State *env, X86DecodedInsn *decod
     gen_helper_aesimc_xmm(cpu_env, OP_PTR0, OP_PTR2);
 }
 
+/*
+ * 00 = v*ps Vps, Hps, Wpd
+ * 66 = v*pd Vpd, Hpd, Wps
+ * f3 = v*ss Vss, Hss, Wps
+ * f2 = v*sd Vsd, Hsd, Wps
+ */
+#define SSE_CMP(x) { \
+    gen_helper_ ## x ## ps ## _xmm, gen_helper_ ## x ## pd ## _xmm, \
+    gen_helper_ ## x ## ss, gen_helper_ ## x ## sd, \
+    gen_helper_ ## x ## ps ## _ymm, gen_helper_ ## x ## pd ## _ymm}
+static const SSEFunc_0_eppp gen_helper_cmp_funcs[32][6] = {
+    SSE_CMP(cmpeq),
+    SSE_CMP(cmplt),
+    SSE_CMP(cmple),
+    SSE_CMP(cmpunord),
+    SSE_CMP(cmpneq),
+    SSE_CMP(cmpnlt),
+    SSE_CMP(cmpnle),
+    SSE_CMP(cmpord),
+
+    SSE_CMP(cmpequ),
+    SSE_CMP(cmpnge),
+    SSE_CMP(cmpngt),
+    SSE_CMP(cmpfalse),
+    SSE_CMP(cmpnequ),
+    SSE_CMP(cmpge),
+    SSE_CMP(cmpgt),
+    SSE_CMP(cmptrue),
+
+    SSE_CMP(cmpeqs),
+    SSE_CMP(cmpltq),
+    SSE_CMP(cmpleq),
+    SSE_CMP(cmpunords),
+    SSE_CMP(cmpneqq),
+    SSE_CMP(cmpnltq),
+    SSE_CMP(cmpnleq),
+    SSE_CMP(cmpords),
+
+    SSE_CMP(cmpequs),
+    SSE_CMP(cmpngeq),
+    SSE_CMP(cmpngtq),
+    SSE_CMP(cmpfalses),
+    SSE_CMP(cmpnequs),
+    SSE_CMP(cmpgeq),
+    SSE_CMP(cmpgtq),
+    SSE_CMP(cmptrues),
+};
+#undef SSE_CMP
+
+static void gen_VCMP(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
+{
+    int index = decode->immediate & (s->prefix & PREFIX_VEX ? 31 : 7);
+    int b =
+        s->prefix & PREFIX_REPZ  ? 2 /* ss */ :
+        s->prefix & PREFIX_REPNZ ? 3 /* sd */ :
+        !!(s->prefix & PREFIX_DATA) /* pd */ + (s->vex_l << 2);
+
+    gen_helper_cmp_funcs[index][b](cpu_env, OP_PTR0, OP_PTR1, OP_PTR2);
+}
+
 static void gen_VCVTfp2fp(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 {
     gen_unary_fp_sse(s, env, decode,
@@ -1790,6 +1855,16 @@ static void gen_VROUNDSS(DisasContext *s, CPUX86State *env, X86DecodedInsn *deco
     gen_helper_roundss_xmm(cpu_env, OP_PTR0, OP_PTR1, OP_PTR2, imm);
 }
 
+static void gen_VSHUF(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
+{
+    TCGv_i32 imm = tcg_constant_i32(decode->immediate);
+    SSEFunc_0_pppi ps, pd, fn;
+    ps = s->vex_l ? gen_helper_shufps_ymm : gen_helper_shufps_xmm;
+    pd = s->vex_l ? gen_helper_shufpd_ymm : gen_helper_shufpd_xmm;
+    fn = s->prefix & PREFIX_DATA ? pd : ps;
+    fn(OP_PTR0, OP_PTR1, OP_PTR2, imm);
+}
+
 static void gen_VZEROALL(DisasContext *s, CPUX86State *env, X86DecodedInsn *decode)
 {
     TCGv_ptr ptr = tcg_temp_new_ptr();
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 9cb567f02f..04b51d7477 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -4776,6 +4776,7 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         if (use_new &&
             (b == 0x138 || b == 0x13a ||
              (b >= 0x150 && b <= 0x17f) ||
+             b == 0x1c2 || (b >= 0x1c4 && b <= 0x1c6) ||
              (b >= 0x1d0 && b <= 0x1ff))) {
             disas_insn_new(s, cpu, b + 0x100);
             return s->pc;
-- 
2.37.3



  parent reply	other threads:[~2022-10-13 22:15 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-13 21:46 [PATCH v3 00/35] target/i386: new decoder + AVX implementation Paolo Bonzini
2022-10-13 21:46 ` [PATCH 01/35] target/i386: Define XMMReg and access macros, align ZMM registers Paolo Bonzini
2022-10-13 21:46 ` [PATCH 02/35] target/i386: make ldo/sto operations consistent with ldq Paolo Bonzini
2022-10-13 21:46 ` [PATCH 03/35] target/i386: add core of new i386 decoder Paolo Bonzini
2022-10-13 21:46 ` [PATCH 04/35] target/i386: add ALU load/writeback core Paolo Bonzini
2022-10-13 21:46 ` [PATCH 05/35] target/i386: add CPUID[EAX=7, ECX=0].ECX to DisasContext Paolo Bonzini
2022-10-13 21:46 ` [PATCH 06/35] target/i386: add CPUID feature checks to new decoder Paolo Bonzini
2022-10-13 21:46 ` [PATCH 07/35] target/i386: add AVX_EN hflag Paolo Bonzini
2022-10-13 21:46 ` [PATCH 08/35] target/i386: validate VEX prefixes via the instructions' exception classes Paolo Bonzini
2022-10-13 21:46 ` [PATCH 09/35] target/i386: validate SSE prefixes directly in the decoding table Paolo Bonzini
2022-10-13 21:46 ` [PATCH 10/35] target/i386: move scalar 0F 38 and 0F 3A instruction to new decoder Paolo Bonzini
2022-10-13 21:46 ` [PATCH 11/35] target/i386: Prepare ops_sse_header.h for 256 bit AVX Paolo Bonzini
2022-10-13 21:46 ` [PATCH 12/35] target/i386: extend helpers to support VEX.V 3- and 4- operand encodings Paolo Bonzini
2022-10-13 21:46 ` [PATCH 13/35] target/i386: support operand merging in binary scalar helpers Paolo Bonzini
2022-10-13 21:46 ` [PATCH 14/35] target/i386: provide 3-operand versions of unary " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 15/35] target/i386: implement additional AVX comparison operators Paolo Bonzini
2022-10-13 21:46 ` [PATCH 16/35] target/i386: Introduce 256-bit vector helpers Paolo Bonzini
2022-10-13 21:46 ` [PATCH 17/35] target/i386: reimplement 0x0f 0x60-0x6f, add AVX Paolo Bonzini
2022-10-13 21:46 ` [PATCH 18/35] target/i386: reimplement 0x0f 0xd8-0xdf, 0xe8-0xef, 0xf8-0xff, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 19/35] target/i386: reimplement 0x0f 0x50-0x5f, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 20/35] target/i386: reimplement 0x0f 0x78-0x7f, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 21/35] target/i386: reimplement 0x0f 0x70-0x77, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 22/35] target/i386: reimplement 0x0f 0xd0-0xd7, 0xe0-0xe7, 0xf0-0xf7, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 23/35] target/i386: clarify (un)signedness of immediates from 0F3Ah opcodes Paolo Bonzini
2022-10-13 21:46 ` [PATCH 24/35] target/i386: reimplement 0x0f 0x3a, add AVX Paolo Bonzini
2022-10-13 21:46 ` [PATCH 25/35] target/i386: Use tcg gvec ops for pmovmskb Paolo Bonzini
2022-10-13 21:46 ` [PATCH 26/35] target/i386: reimplement 0x0f 0x38, add AVX Paolo Bonzini
2022-10-13 21:46 ` Paolo Bonzini [this message]
2022-10-13 21:46 ` [PATCH 28/35] target/i386: reimplement 0x0f 0x10-0x17, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 29/35] target/i386: reimplement 0x0f 0x28-0x2f, " Paolo Bonzini
2022-10-13 21:46 ` [PATCH 30/35] target/i386: implement XSAVE and XRSTOR of AVX registers Paolo Bonzini
2022-10-13 21:46 ` [PATCH 31/35] target/i386: implement VLDMXCSR/VSTMXCSR Paolo Bonzini
2022-10-13 21:46 ` [PATCH 32/35] target/i386: Enable AVX cpuid bits when using TCG Paolo Bonzini
2022-10-13 21:46 ` [PATCH 33/35] tests/tcg: extend SSE tests to AVX Paolo Bonzini
2022-10-13 21:46 ` [PATCH 34/35] target/i386: move 3DNow to the new decoder Paolo Bonzini
2022-10-13 21:46 ` [PATCH 35/35] target/i386: remove old SSE decoder Paolo Bonzini

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=20221013214651.672114-28-pbonzini@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=paul@nowt.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.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).