x86/APX: extend SSE2AVX coverage

Legacy encoded SIMD insns are converted to AVX ones in that mode. When
eGPR-s are in use, i.e. with APX, convert to AVX10 insns (where
available; there are quite a few which can't be converted).

Note that LDDQU is represented as VMOVDQU32 (and the prior use of the
sse3 template there needs dropping, to get the order right).

Note further that in a few cases, due to the use of templates, AVX512VL
is used when AVX512F would suffice. Since AVX10 is the main reference,
this shouldn't be too much of a problem.
This commit is contained in:
Jan Beulich 2024-05-03 09:26:25 +02:00
parent d125c4bbce
commit 24187fb9c0
9 changed files with 2615 additions and 671 deletions

View file

@ -4133,7 +4133,7 @@ build_evex_prefix (void)
/* Check the REX.W bit and VEXW. */
if (i.tm.opcode_modifier.vexw == VEXWIG)
w = (evexwig == evexw1 || (i.rex & REX_W)) ? 1 : 0;
else if (i.tm.opcode_modifier.vexw)
else if (i.tm.opcode_modifier.vexw && !(i.rex & REX_W))
w = i.tm.opcode_modifier.vexw == VEXW1 ? 1 : 0;
else
w = (flag_code == CODE_64BIT ? i.rex & REX_W : evexwig == evexw1) ? 1 : 0;
@ -8281,7 +8281,12 @@ check_VecOperands (const insn_template *t)
if ((is_cpu (t, CpuXOP) && t->operands == 5)
|| (t->opcode_space == SPACE_0F3A
&& (t->base_opcode | 3) == 0x0b
&& is_cpu (t, CpuAPX_F)))
&& (is_cpu (t, CpuAPX_F)
|| (t->opcode_modifier.sse2avx && t->opcode_modifier.evex
&& (!t->opcode_modifier.vex
|| (i.encoding != encoding_default
&& i.encoding != encoding_vex
&& i.encoding != encoding_vex3))))))
{
if (i.op[0].imms->X_op != O_constant
|| !fits_in_imm4 (i.op[0].imms->X_add_number))

View file

@ -312,7 +312,9 @@ when respective checks fail.
@cindex @samp{-msse2avx} option, x86-64
@item -msse2avx
This option specifies that the assembler should encode SSE instructions
with VEX prefix.
with VEX prefix, requiring AVX to be available. SSE instructions using
extended GPRs will be encoded with EVEX prefix, requiring AVX512 or AVX10 to
be available.
@cindex @samp{-muse-unaligned-vector-move} option, i386
@cindex @samp{-muse-unaligned-vector-move} option, x86-64

View file

@ -0,0 +1,261 @@
#as: -msse2avx
#objdump: -dw
#name: x86-64 SSE+ with APX encoding
.*: file format .*
Disassembly of section .text:
0+ <sse2avx>:
[ ]*[a-f0-9]+: 62 f9 7c 08 5b 60 01 vcvtdq2ps 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 ff 08 e6 60 01 vcvtpd2dqx 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 5a 60 01 vcvtpd2psx 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7d 08 5b 60 01 vcvtps2dq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 e6 60 01 vcvttpd2dqx 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 5b 60 01 vcvttps2dq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 6f 60 01 vmovdqu32 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 28 60 01 vmovapd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7c 08 28 60 01 vmovaps 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7d 08 6f 60 01 vmovdqa32 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 6f 60 01 vmovdqu32 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 2a 60 01 vmovntdqa 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 16 60 01 vmovshdup 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 12 60 01 vmovsldup 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 10 60 01 vmovupd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7c 08 10 60 01 vmovups 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 1c 60 01 vpabsb 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 1d 60 01 vpabsw 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 1e 60 01 vpabsd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 4c 60 01 vrcp14ps 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 4e 60 01 vrsqrt14ps 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 51 60 01 vsqrtpd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7c 08 51 60 01 vsqrtps 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 29 60 01 vmovapd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7c 08 29 60 01 vmovaps %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7d 08 7f 60 01 vmovdqa32 %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7e 08 7f 60 01 vmovdqu32 %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7d 08 e7 60 01 vmovntdq %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 fd 08 2b 60 01 vmovntpd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7c 08 2b 60 01 vmovntps %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 fd 08 11 60 01 vmovupd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7c 08 11 60 01 vmovups %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 cd 08 58 70 01 vaddpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 58 70 01 vaddps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 dc 70 01 vaesenc 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 dd 70 01 vaesenclast 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 de 70 01 vaesdec 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 df 70 01 vaesdeclast 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 55 70 01 vandnpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 55 70 01 vandnps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 54 70 01 vandpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 54 70 01 vandps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 5e 70 01 vdivpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 5e 70 01 vdivps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 cf 70 01 vgf2p8mulb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 5f 70 01 vmaxpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 5f 70 01 vmaxps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 5d 70 01 vminpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 5d 70 01 vminps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 59 70 01 vmulpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 59 70 01 vmulps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 56 70 01 vorpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 56 70 01 vorps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 63 70 01 vpacksswb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 6b 70 01 vpackssdw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 67 70 01 vpackuswb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 2b 70 01 vpackusdw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 fc 70 01 vpaddb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 fd 70 01 vpaddw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 fe 70 01 vpaddd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 d4 70 01 vpaddq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 ec 70 01 vpaddsb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 ed 70 01 vpaddsw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 dc 70 01 vpaddusb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 dd 70 01 vpaddusw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 db 70 01 vpandd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 df 70 01 vpandnd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e0 70 01 vpavgb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e3 70 01 vpavgw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 44 70 01 00 vpclmullqlqdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 44 70 01 01 vpclmulhqlqdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 44 70 01 10 vpclmullqhqdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 44 70 01 11 vpclmulhqhqdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 f5 70 01 vpmaddwd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 04 70 01 vpmaddubsw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 3c 70 01 vpmaxsb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 ee 70 01 vpmaxsw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 3d 70 01 vpmaxsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 de 70 01 vpmaxub 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 3e 70 01 vpmaxuw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 3f 70 01 vpmaxud 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 38 70 01 vpminsb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 ea 70 01 vpminsw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 39 70 01 vpminsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 da 70 01 vpminub 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 3a 70 01 vpminuw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 3b 70 01 vpminud 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa cd 08 28 70 01 vpmuldq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e4 70 01 vpmulhuw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 0b 70 01 vpmulhrsw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e5 70 01 vpmulhw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 d5 70 01 vpmullw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 40 70 01 vpmulld 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 f4 70 01 vpmuludq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 eb 70 01 vpord 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 f6 70 01 vpsadbw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 00 70 01 vpshufb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 f1 70 01 vpsllw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 f2 70 01 vpslld 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 f3 70 01 vpsllq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e1 70 01 vpsraw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e2 70 01 vpsrad 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 d1 70 01 vpsrlw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 d2 70 01 vpsrld 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 d3 70 01 vpsrlq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 f8 70 01 vpsubb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 f9 70 01 vpsubw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 fa 70 01 vpsubd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 fb 70 01 vpsubq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e8 70 01 vpsubsb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 e9 70 01 vpsubsw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 d8 70 01 vpsubusb 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 d9 70 01 vpsubusw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 68 70 01 vpunpckhbw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 69 70 01 vpunpckhwd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 6a 70 01 vpunpckhdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 6d 70 01 vpunpckhqdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 60 70 01 vpunpcklbw 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 61 70 01 vpunpcklwd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 62 70 01 vpunpckldq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 6c 70 01 vpunpcklqdq 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4d 08 ef 70 01 vpxord 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 5c 70 01 vsubpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 5c 70 01 vsubps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 15 70 01 vunpckhpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 15 70 01 vunpckhps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 14 70 01 vunpcklpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 14 70 01 vunpcklps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 57 70 01 vxorpd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 57 70 01 vxorps 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 7d 08 70 70 01 64 vpshufd \$0x64,0x10\(%r16\),%xmm6
[ ]*[a-f0-9]+: 62 f9 7e 08 70 70 01 64 vpshufhw \$0x64,0x10\(%r16\),%xmm6
[ ]*[a-f0-9]+: 62 f9 7f 08 70 70 01 64 vpshuflw \$0x64,0x10\(%r16\),%xmm6
[ ]*[a-f0-9]+: 62 fb fd 08 09 70 01 04 vrndscalepd \$(0x)?4,0x10\(%r16\),%xmm6
[ ]*[a-f0-9]+: 62 fb 7d 08 08 70 01 04 vrndscaleps \$(0x)?4,0x10\(%r16\),%xmm6
[ ]*[a-f0-9]+: 62 fb cd 08 ce 70 01 64 vgf2p8affineqb \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb cd 08 cf 70 01 64 vgf2p8affineinvqb \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 0f 70 01 64 vpalignr \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 44 70 01 64 vpclmulqdq \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cd 08 c6 70 01 64 vshufpd \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4c 08 c6 70 01 64 vshufps \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 fd 08 2f 60 02 vcomisd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 e6 60 02 vcvtdq2pd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 e6 60 02 vcvtdq2pd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7c 08 5a 60 02 vcvtps2pd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 ff 08 12 60 02 vmovddup 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 ff 08 10 60 02 vmovsd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 20 60 02 vpmovsxbw 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 23 60 02 vpmovsxwd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 25 60 02 vpmovsxdq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 30 60 02 vpmovzxbw 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 33 60 02 vpmovzxwd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 35 60 02 vpmovzxdq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 2e 60 02 vucomisd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 13 60 02 vmovlpd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7c 08 13 60 02 vmovlps %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 fd 08 17 60 02 vmovhpd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7c 08 17 60 02 vmovhps %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 ff 08 11 60 02 vmovsd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 dd 08 12 60 02 vmovlpd 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5c 08 12 60 02 vmovlps 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 dd 08 16 60 02 vmovhpd 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5c 08 16 60 02 vmovhps 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 7e e0 vmovq %xmm4,%r16
[ ]*[a-f0-9]+: 62 f9 fd 08 6e e0 vmovq %r16,%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 7e e0 vmovq %xmm4,%r16
[ ]*[a-f0-9]+: 62 f9 fd 08 6e e0 vmovq %r16,%xmm4
[ ]*[a-f0-9]+: 62 f9 fd 08 d6 60 02 vmovq %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 fe 08 7e 60 02 vmovq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 e1 7f 08 2d c4 vcvtsd2si %xmm4,%r16d
[ ]*[a-f0-9]+: 62 f9 7f 08 2d 48 02 vcvtsd2si 0x10\(%r16\),%ecx
[ ]*[a-f0-9]+: 62 e1 7f 08 2c c4 vcvttsd2si %xmm4,%r16d
[ ]*[a-f0-9]+: 62 f9 7f 08 2c 48 02 vcvttsd2si 0x10\(%r16\),%ecx
[ ]*[a-f0-9]+: 62 e1 ff 08 2d c4 vcvtsd2si %xmm4,%r16
[ ]*[a-f0-9]+: 62 f9 ff 08 2d 48 02 vcvtsd2si 0x10\(%r16\),%rcx
[ ]*[a-f0-9]+: 62 e1 ff 08 2c c4 vcvttsd2si %xmm4,%r16
[ ]*[a-f0-9]+: 62 f9 ff 08 2c 48 02 vcvttsd2si 0x10\(%r16\),%rcx
[ ]*[a-f0-9]+: 62 f9 df 08 2a e0 vcvtsi2sd %r16,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 df 08 2a 60 02 vcvtsi2sdq 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 de 08 2a e0 vcvtsi2ss %r16,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 de 08 2a 60 02 vcvtsi2ssq 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb dd 08 22 e0 64 vpinsrq \$0x64,%r16,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb dd 08 22 60 02 64 vpinsrq \$0x64,0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb fd 08 16 e0 64 vpextrq \$0x64,%xmm4,%r16
[ ]*[a-f0-9]+: 62 fb fd 08 16 60 02 64 vpextrq \$0x64,%xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 fb cd 08 0b 70 02 04 vrndscalesd \$(0x)?4,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 58 70 02 vaddsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 5a 70 02 vcvtsd2ss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 5e 70 02 vdivsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 5f 70 02 vmaxsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 5d 70 02 vminsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 59 70 02 vmulsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 51 70 02 vsqrtsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 cf 08 5c 70 02 vsubsd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 58 70 04 vaddss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 5a 70 04 vcvtss2sd 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 5e 70 04 vdivss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 5f 70 04 vmaxss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 5d 70 04 vminss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 59 70 04 vmulss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 4d 70 04 vrcp14ss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 4d 08 4f 70 04 vrsqrt14ss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 51 70 04 vsqrtss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 4e 08 5c 70 04 vsubss 0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 f9 7c 08 2f 60 04 vcomiss 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 10 60 04 vmovss 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 21 60 04 vpmovsxbd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 24 60 04 vpmovsxwq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 31 60 04 vpmovzxbd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 34 60 04 vpmovzxwq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7c 08 2e 60 04 vucomiss 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 f9 7e 08 11 60 04 vmovss %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7d 08 7e e0 vmovd %xmm4,%r16d
[ ]*[a-f0-9]+: 62 f9 7d 08 7e 60 04 vmovd %xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 7d 08 6e e0 vmovd %r16d,%xmm4
[ ]*[a-f0-9]+: 62 f9 7d 08 6e 60 04 vmovd 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 e1 7e 08 2d c4 vcvtss2si %xmm4,%r16d
[ ]*[a-f0-9]+: 62 f9 7e 08 2d 48 04 vcvtss2si 0x10\(%r16\),%ecx
[ ]*[a-f0-9]+: 62 e1 7e 08 2c c4 vcvttss2si %xmm4,%r16d
[ ]*[a-f0-9]+: 62 f9 7e 08 2c 48 04 vcvttss2si 0x10\(%r16\),%ecx
[ ]*[a-f0-9]+: 62 e1 fe 08 2d c4 vcvtss2si %xmm4,%r16
[ ]*[a-f0-9]+: 62 f9 fe 08 2d 48 04 vcvtss2si 0x10\(%r16\),%rcx
[ ]*[a-f0-9]+: 62 e1 fe 08 2c c4 vcvttss2si %xmm4,%r16
[ ]*[a-f0-9]+: 62 f9 fe 08 2c 48 04 vcvttss2si 0x10\(%r16\),%rcx
[ ]*[a-f0-9]+: 62 fb fd 08 17 e0 64 vextractps \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 fb 7d 08 16 e0 64 vpextrd \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 fb 7d 08 16 60 04 64 vpextrd \$0x64,%xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 fb 7d 08 17 e0 64 vextractps \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 fb 7d 08 17 60 04 64 vextractps \$0x64,%xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 fb 5d 08 22 e0 64 vpinsrd \$0x64,%r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb 5d 08 22 60 04 64 vpinsrd \$0x64,0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5f 08 2a e0 vcvtsi2sd %r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5f 08 2a 60 04 vcvtsi2sdl 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5e 08 2a e0 vcvtsi2ss %r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5e 08 2a 60 04 vcvtsi2ssl 0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb 4d 08 21 70 04 64 vinsertps \$0x64,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fb 4d 08 0a 70 04 04 vrndscaless \$(0x)?4,0x10\(%r16\),%xmm6,%xmm6
[ ]*[a-f0-9]+: 62 fa 7d 08 22 60 08 vpmovsxbq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 fa 7d 08 32 60 08 vpmovzxbq 0x10\(%r16\),%xmm4
[ ]*[a-f0-9]+: 62 e1 7d 08 c5 c4 64 vpextrw \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 e1 7d 08 c5 c4 64 vpextrw \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 fb 7d 08 15 60 08 64 vpextrw \$0x64,%xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 f9 5d 08 c4 e0 64 vpinsrw \$0x64,%r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5d 08 c4 e0 64 vpinsrw \$0x64,%r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 f9 5d 08 c4 60 08 64 vpinsrw \$0x64,0x10\(%r16\),%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb 7d 08 14 e0 64 vpextrb \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 fb 7d 08 14 e0 64 vpextrb \$0x64,%xmm4,%r16d
[ ]*[a-f0-9]+: 62 fb 7d 08 14 60 10 64 vpextrb \$0x64,%xmm4,0x10\(%r16\)
[ ]*[a-f0-9]+: 62 fb 5d 08 20 e0 64 vpinsrb \$0x64,%r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb 5d 08 20 e0 64 vpinsrb \$0x64,%r16d,%xmm4,%xmm4
[ ]*[a-f0-9]+: 62 fb 5d 08 20 60 10 64 vpinsrb \$0x64,0x10\(%r16\),%xmm4,%xmm4
#pass

View file

@ -0,0 +1,320 @@
.text
.sse_check warning
sse2avx:
# Tests for op mem128, xmm
cvtdq2ps 16(%r16),%xmm4
cvtpd2dq 16(%r16),%xmm4
cvtpd2ps 16(%r16),%xmm4
cvtps2dq 16(%r16),%xmm4
cvttpd2dq 16(%r16),%xmm4
cvttps2dq 16(%r16),%xmm4
lddqu 16(%r16),%xmm4
movapd 16(%r16),%xmm4
movaps 16(%r16),%xmm4
movdqa 16(%r16),%xmm4
movdqu 16(%r16),%xmm4
movntdqa 16(%r16),%xmm4
movshdup 16(%r16),%xmm4
movsldup 16(%r16),%xmm4
movupd 16(%r16),%xmm4
movups 16(%r16),%xmm4
pabsb 16(%r16),%xmm4
pabsw 16(%r16),%xmm4
pabsd 16(%r16),%xmm4
rcpps 16(%r16),%xmm4
rsqrtps 16(%r16),%xmm4
sqrtpd 16(%r16),%xmm4
sqrtps 16(%r16),%xmm4
# Tests for op xmm, mem128
movapd %xmm4,16(%r16)
movaps %xmm4,16(%r16)
movdqa %xmm4,16(%r16)
movdqu %xmm4,16(%r16)
movntdq %xmm4,16(%r16)
movntpd %xmm4,16(%r16)
movntps %xmm4,16(%r16)
movupd %xmm4,16(%r16)
movups %xmm4,16(%r16)
# Tests for op mem128, xmm[, xmm]
addpd 16(%r16),%xmm6
addps 16(%r16),%xmm6
aesenc 16(%r16),%xmm6
aesenclast 16(%r16),%xmm6
aesdec 16(%r16),%xmm6
aesdeclast 16(%r16),%xmm6
andnpd 16(%r16),%xmm6
andnps 16(%r16),%xmm6
andpd 16(%r16),%xmm6
andps 16(%r16),%xmm6
divpd 16(%r16),%xmm6
divps 16(%r16),%xmm6
gf2p8mulb 16(%r16),%xmm6
maxpd 16(%r16),%xmm6
maxps 16(%r16),%xmm6
minpd 16(%r16),%xmm6
minps 16(%r16),%xmm6
mulpd 16(%r16),%xmm6
mulps 16(%r16),%xmm6
orpd 16(%r16),%xmm6
orps 16(%r16),%xmm6
packsswb 16(%r16),%xmm6
packssdw 16(%r16),%xmm6
packuswb 16(%r16),%xmm6
packusdw 16(%r16),%xmm6
paddb 16(%r16),%xmm6
paddw 16(%r16),%xmm6
paddd 16(%r16),%xmm6
paddq 16(%r16),%xmm6
paddsb 16(%r16),%xmm6
paddsw 16(%r16),%xmm6
paddusb 16(%r16),%xmm6
paddusw 16(%r16),%xmm6
pand 16(%r16),%xmm6
pandn 16(%r16),%xmm6
pavgb 16(%r16),%xmm6
pavgw 16(%r16),%xmm6
pclmullqlqdq 16(%r16),%xmm6
pclmulhqlqdq 16(%r16),%xmm6
pclmullqhqdq 16(%r16),%xmm6
pclmulhqhqdq 16(%r16),%xmm6
pmaddwd 16(%r16),%xmm6
pmaddubsw 16(%r16),%xmm6
pmaxsb 16(%r16),%xmm6
pmaxsw 16(%r16),%xmm6
pmaxsd 16(%r16),%xmm6
pmaxub 16(%r16),%xmm6
pmaxuw 16(%r16),%xmm6
pmaxud 16(%r16),%xmm6
pminsb 16(%r16),%xmm6
pminsw 16(%r16),%xmm6
pminsd 16(%r16),%xmm6
pminub 16(%r16),%xmm6
pminuw 16(%r16),%xmm6
pminud 16(%r16),%xmm6
pmuldq 16(%r16),%xmm6
pmulhuw 16(%r16),%xmm6
pmulhrsw 16(%r16),%xmm6
pmulhw 16(%r16),%xmm6
pmullw 16(%r16),%xmm6
pmulld 16(%r16),%xmm6
pmuludq 16(%r16),%xmm6
por 16(%r16),%xmm6
psadbw 16(%r16),%xmm6
pshufb 16(%r16),%xmm6
psllw 16(%r16),%xmm6
pslld 16(%r16),%xmm6
psllq 16(%r16),%xmm6
psraw 16(%r16),%xmm6
psrad 16(%r16),%xmm6
psrlw 16(%r16),%xmm6
psrld 16(%r16),%xmm6
psrlq 16(%r16),%xmm6
psubb 16(%r16),%xmm6
psubw 16(%r16),%xmm6
psubd 16(%r16),%xmm6
psubq 16(%r16),%xmm6
psubsb 16(%r16),%xmm6
psubsw 16(%r16),%xmm6
psubusb 16(%r16),%xmm6
psubusw 16(%r16),%xmm6
punpckhbw 16(%r16),%xmm6
punpckhwd 16(%r16),%xmm6
punpckhdq 16(%r16),%xmm6
punpckhqdq 16(%r16),%xmm6
punpcklbw 16(%r16),%xmm6
punpcklwd 16(%r16),%xmm6
punpckldq 16(%r16),%xmm6
punpcklqdq 16(%r16),%xmm6
pxor 16(%r16),%xmm6
subpd 16(%r16),%xmm6
subps 16(%r16),%xmm6
unpckhpd 16(%r16),%xmm6
unpckhps 16(%r16),%xmm6
unpcklpd 16(%r16),%xmm6
unpcklps 16(%r16),%xmm6
xorpd 16(%r16),%xmm6
xorps 16(%r16),%xmm6
# Tests for op imm8, mem128, xmm
pshufd $100,16(%r16),%xmm6
pshufhw $100,16(%r16),%xmm6
pshuflw $100,16(%r16),%xmm6
roundpd $4,16(%r16),%xmm6
roundps $4,16(%r16),%xmm6
# Tests for op imm8, mem128, xmm[, xmm]
gf2p8affineqb $100,16(%r16),%xmm6
gf2p8affineinvqb $100,16(%r16),%xmm6
palignr $100,16(%r16),%xmm6
pclmulqdq $100,16(%r16),%xmm6
shufpd $100,16(%r16),%xmm6
shufps $100,16(%r16),%xmm6
# Tests for op mem64, xmm
comisd 16(%r16),%xmm4
cvtdq2pd 16(%r16),%xmm4
cvtpi2pd 16(%r16),%xmm4
cvtps2pd 16(%r16),%xmm4
movddup 16(%r16),%xmm4
movsd 16(%r16),%xmm4
pmovsxbw 16(%r16),%xmm4
pmovsxwd 16(%r16),%xmm4
pmovsxdq 16(%r16),%xmm4
pmovzxbw 16(%r16),%xmm4
pmovzxwd 16(%r16),%xmm4
pmovzxdq 16(%r16),%xmm4
ucomisd 16(%r16),%xmm4
# Tests for op xmm, mem64
movlpd %xmm4,16(%r16)
movlps %xmm4,16(%r16)
movhpd %xmm4,16(%r16)
movhps %xmm4,16(%r16)
movsd %xmm4,16(%r16)
# Tests for op mem64, xmm[, xmm]
movlpd 16(%r16),%xmm4
movlps 16(%r16),%xmm4
movhpd 16(%r16),%xmm4
movhps 16(%r16),%xmm4
# Tests for op xmm, regq/mem64
# Tests for op regq/mem64, xmm
movd %xmm4,%r16
movd %r16,%xmm4
movq %xmm4,%r16
movq %r16,%xmm4
movq %xmm4,16(%r16)
movq 16(%r16),%xmm4
# Tests for op xmm/mem64, regl
cvtsd2si %xmm4,%r16d
cvtsd2si 16(%r16),%ecx
cvttsd2si %xmm4,%r16d
cvttsd2si 16(%r16),%ecx
# Tests for op xmm/mem64, regq
cvtsd2si %xmm4,%r16
cvtsd2si 16(%r16),%rcx
cvttsd2si %xmm4,%r16
cvttsd2si 16(%r16),%rcx
# Tests for op regq/mem64, xmm[, xmm]
cvtsi2sdq %r16,%xmm4
cvtsi2sdq 16(%r16),%xmm4
cvtsi2ssq %r16,%xmm4
cvtsi2ssq 16(%r16),%xmm4
# Tests for op imm8, regq/mem64, xmm[, xmm]
pinsrq $100,%r16,%xmm4
pinsrq $100,16(%r16),%xmm4
# Tests for op imm8, xmm, regq/mem64
pextrq $100,%xmm4,%r16
pextrq $100,%xmm4,16(%r16)
# Tests for op imm8, mem64, xmm[, xmm]
roundsd $4,16(%r16),%xmm6
# Tests for op mem64, xmm[, xmm]
addsd 16(%r16),%xmm6
cvtsd2ss 16(%r16),%xmm6
divsd 16(%r16),%xmm6
maxsd 16(%r16),%xmm6
minsd 16(%r16),%xmm6
mulsd 16(%r16),%xmm6
sqrtsd 16(%r16),%xmm6
subsd 16(%r16),%xmm6
# Tests for op mem32, xmm[, xmm]
addss 16(%r16),%xmm6
cvtss2sd 16(%r16),%xmm6
divss 16(%r16),%xmm6
maxss 16(%r16),%xmm6
minss 16(%r16),%xmm6
mulss 16(%r16),%xmm6
rcpss 16(%r16),%xmm6
rsqrtss 16(%r16),%xmm6
sqrtss 16(%r16),%xmm6
subss 16(%r16),%xmm6
# Tests for op mem32, xmm
comiss 16(%r16),%xmm4
movss 16(%r16),%xmm4
pmovsxbd 16(%r16),%xmm4
pmovsxwq 16(%r16),%xmm4
pmovzxbd 16(%r16),%xmm4
pmovzxwq 16(%r16),%xmm4
ucomiss 16(%r16),%xmm4
# Tests for op xmm, mem32
movss %xmm4,16(%r16)
# Tests for op xmm, regl/mem32
# Tests for op regl/mem32, xmm
movd %xmm4,%r16d
movd %xmm4,16(%r16)
movd %r16d,%xmm4
movd 16(%r16),%xmm4
# Tests for op xmm/mem32, regl
cvtss2si %xmm4,%r16d
cvtss2si 16(%r16),%ecx
cvttss2si %xmm4,%r16d
cvttss2si 16(%r16),%ecx
# Tests for op xmm/mem32, regq
cvtss2si %xmm4,%r16
cvtss2si 16(%r16),%rcx
cvttss2si %xmm4,%r16
cvttss2si 16(%r16),%rcx
# Tests for op imm8, xmm, regq/mem32
extractps $100,%xmm4,%r16
# Tests for op imm8, xmm, regl/mem32
pextrd $100,%xmm4,%r16d
pextrd $100,%xmm4,16(%r16)
extractps $100,%xmm4,%r16d
extractps $100,%xmm4,16(%r16)
# Tests for op imm8, regl/mem32, xmm[, xmm]
pinsrd $100,%r16d,%xmm4
pinsrd $100,16(%r16),%xmm4
# Tests for op regl/mem32, xmm[, xmm]
cvtsi2sd %r16d,%xmm4
cvtsi2sd 16(%r16),%xmm4
cvtsi2ss %r16d,%xmm4
cvtsi2ss 16(%r16),%xmm4
# Tests for op imm8, mem32, xmm[, xmm]
insertps $100,16(%r16),%xmm6
roundss $4,16(%r16),%xmm6
# Tests for op mem16, xmm
pmovsxbq 16(%r16),%xmm4
pmovzxbq 16(%r16),%xmm4
# Tests for op imm8, xmm, regl/mem16
pextrw $100,%xmm4,%r16d
pextrw $100,%xmm4,%r16
pextrw $100,%xmm4,16(%r16)
# Tests for op imm8, regl/mem16, xmm[, xmm]
pinsrw $100,%r16d,%xmm4
pinsrw $100,%r16,%xmm4
pinsrw $100,16(%r16),%xmm4
# Tests for op imm8, xmm, regl/mem8
pextrb $100,%xmm4,%r16d
pextrb $100,%xmm4,%r16
pextrb $100,%xmm4,16(%r16)
# Tests for op imm8, regl/mem8, xmm[, xmm]
pinsrb $100,%r16d,%xmm4
pinsrb $100,%r16,%xmm4
pinsrb $100,16(%r16),%xmm4

View file

@ -746,9 +746,19 @@ Disassembly of section .text:
[ ]*[a-f0-9]+: c5 79 7e c8 vmovd %xmm9,%eax
[ ]*[a-f0-9]+: c4 a1 79 7e c8 vmovd %xmm1,%eax
[ ]*[a-f0-9]+: c4 e1 f9 7e c8 vmovq %xmm1,%rax
[ ]*[a-f0-9]+: 62 f1 7d 08 7e c8 \{evex\} vmovd %xmm1,%eax
[ ]*[a-f0-9]+: c5 f9 7e c8 vmovd %xmm1,%eax
[ ]*[a-f0-9]+: c5 f9 7e c8 vmovd %xmm1,%eax
[ ]*[a-f0-9]+: c4 e1 79 7e c8 vmovd %xmm1,%eax
[ ]*[a-f0-9]+: 62 f9 7d 08 7e c8 vmovd %xmm1,%r16d
[ ]*[a-f0-9]+: 62 f9 7d 08 7e c8 vmovd %xmm1,%r16d
[ ]*[a-f0-9]+: 62 d9 7d 08 7e c8 vmovd %xmm1,%r24d
[ ]*[a-f0-9]+: 62 79 7d 08 7e c8 vmovd %xmm9,%r16d
[ ]*[a-f0-9]+: 62 b9 7d 08 7e c8 vmovd %xmm1,%r16d
[ ]*[a-f0-9]+: 62 f9 fd 08 7e c8 vmovq %xmm1,%r16
[ ]*[a-f0-9]+: 62 f9 7d 08 7e c8 vmovd %xmm1,%r16d
[ ]*[a-f0-9]+: 62 f9 7d 08 7e c8 vmovd %xmm1,%r16d
[ ]*[a-f0-9]+: 62 f9 7d 08 7e c8 vmovd %xmm1,%r16d
[ ]*[a-f0-9]+: c5 f8 ae 11 vldmxcsr \(%rcx\)
[ ]*[a-f0-9]+: c5 f8 ae 19 vstmxcsr \(%rcx\)
[ ]*[a-f0-9]+: c5 f8 5b f4 vcvtdq2ps %xmm4,%xmm6

View file

@ -847,10 +847,21 @@ _start:
rex.r movd %xmm1, %eax
rex.x movd %xmm1, %eax
rex.w movd %xmm1, %eax
{evex} movd %xmm1, %eax
{rex} movd %xmm1, %eax
{rex2} movd %xmm1, %eax
{vex3} movd %xmm1, %eax
movd %xmm1, %r16d
rex movd %xmm1, %r16d
rex.b movd %xmm1, %r16d
rex.r movd %xmm1, %r16d
rex.x movd %xmm1, %r16d
rex.w movd %xmm1, %r16d
{evex} movd %xmm1, %r16d
{rex} movd %xmm1, %r16d
{rex2} movd %xmm1, %r16d
.intel_syntax noprefix
# Tests for op mem64
ldmxcsr DWORD PTR [rcx]

View file

@ -390,6 +390,7 @@ run_dump_test "x86-64-apx-jmpabs-inval"
run_dump_test "x86-64-apx-nf"
run_dump_test "x86-64-apx-nf-intel"
run_dump_test "x86-64-apx_f-evex"
run_dump_test "sse2avx-apx"
run_dump_test "x86-64-avx512f-rcigrz-intel"
run_dump_test "x86-64-avx512f-rcigrz"
run_dump_test "x86-64-clwb"

View file

@ -1004,10 +1004,40 @@ pause, 0xf390, i186, NoSuf, {}
$avx:AVX:66:Vex128|VexVVVV|VexW0|SSE2AVX:RegXMM:Xmmword, +
$sse:SSE2:66::RegXMM:Xmmword, +
$mmx:MMX:::RegMMX:Qword>
// As above, but also allowing AVX512 (EVEX) encoding, to transform
// in particular insns using eGPR-s.
<MMX:cpu:pfx:attr:reg:mem, +
$avx:AVX|AVX512VL:66:Vex128|EVex128|VexVVVV|VexW0|Disp8MemShift=4|SSE2AVX:RegXMM:Xmmword, +
$sse:SSE2:66::RegXMM:Xmmword, +
$mmx:MMX:::RegMMX:Qword>
<MMXdq:opc:cpu:pfx:attr:reg:mem, +
d:0:AVX|AVX512VL:66:Vex128|EVex128|VexVVVV|VexW0|Disp8MemShift=4|SSE2AVX:RegXMM:Xmmword, +
d:0:SSE2:66::RegXMM:Xmmword, +
d:0:MMX:::RegMMX:Qword, +
q:1:AVX:66:Vex128|VexVVVV|VexW0|SSE2AVX:RegXMM:Xmmword, +
q:1:AVX512VL:66:EVex128|VexVVVV|VexW1|Disp8MemShift=4|SSE2AVX:RegXMM:Xmmword, +
q:1:SSE2:66::RegXMM:Xmmword, +
q:1:MMX:::RegMMX:Qword>
<MMXBW:cpu:pfx:attr:reg:mem, +
$avx:AVX:66:Vex128|VexVVVV|VexW0|SSE2AVX:RegXMM:Xmmword, +
$apx:AVX512BW&AVX512VL:66:EVex128|VexVVVV|VexW0|Disp8MemShift=4|SSE2AVX:RegXMM:Xmmword, +
$sse:SSE2:66::RegXMM:Xmmword, +
$mmx:MMX:::RegMMX:Qword>
<sse2:cpu:attr:scal:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexLIG|VexW0|SSE2AVX:VexVVVV, +
$sse:SSE2:::>
<SSE2BW:cpu:attr:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexVVVV, +
$apx:AVX512BW&AVX512VL:EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexVVVV, +
$sse:SSE2::>
<SSE2D:cpu:attr:scal:vvvv, +
$avx:AVX|AVX512VL:Vex128|EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexLIG|EVexLIG|VexW0|Disp8MemShift=2|SSE2AVX:VexVVVV, +
$sse:SSE2:::>
<SSE2Q:cpu:attr:scal:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexLIG|VexW0|SSE2AVX:VexVVVV, +
$apx:AVX512VL:EVex128|VexW1|Disp8MemShift=4|SSE2AVX:EVexLIG|VexW1|Disp8MemShift=3|SSE2AVX:VexVVVV, +
$sse:SSE2:::>
<bw:opc:vexw:elem:kcpu:kpfx:cpubmi, +
b:0:VexW0:Byte:AVX512DQ:66:AVX512VBMI, +
@ -1022,8 +1052,8 @@ emms, 0xf77, MMX, NoSuf, {}
// copying between Reg64/Mem64 and RegXMM/RegMMX, as is mandated by Intel's
// spec). AMD's spec, having been in existence for much longer, failed to
// recognize that and specified movd for 32- and 64-bit operations.
movd, 0x666e, AVX, D|Modrm|Vex128|Space0F|VexW0|NoSuf|SSE2AVX, { Reg32|Unspecified|BaseIndex, RegXMM }
movd, 0x666e, AVX&x64, D|Modrm|Vex=1|Space0F|VexW1|NoSuf|Size64|SSE2AVX, { Reg64|BaseIndex, RegXMM }
movd, 0x666e, AVX|AVX512F, D|Modrm|Vex128|EVex128|Space0F|VexW0|Disp8MemShift=2|NoSuf|SSE2AVX, { Reg32|Unspecified|BaseIndex, RegXMM }
movd, 0x666e, x64&(AVX|AVX512F), D|Modrm|Vex128|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf|Size64|SSE2AVX, { Reg64|BaseIndex, RegXMM }
movd, 0x660f6e, SSE2, D|Modrm|IgnoreSize|NoSuf, { Reg32|Unspecified|BaseIndex, RegXMM }
movd, 0x660f6e, SSE2&x64, D|Modrm|NoSuf|Size64, { Reg64|BaseIndex, RegXMM }
// The MMX templates have to remain after at least the SSE2AVX ones.
@ -1031,247 +1061,280 @@ movd, 0xf6e, MMX, D|Modrm|IgnoreSize|NoSuf, { Reg32|Unspecified|BaseIndex, RegMM
movd, 0xf6e, MMX&x64, D|Modrm|NoSuf|Size64, { Reg64|BaseIndex, RegMMX }
movq, 0xf37e, AVX, Load|Modrm|Vex128|Space0F|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movq, 0x66d6, AVX, Modrm|Vex128|Space0F|VexW0|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
movq, 0x666e, AVX&x64, D|Modrm|Vex=1|Space0F|VexW1|NoSuf|Size64|SSE2AVX, { Reg64|Unspecified|BaseIndex, RegXMM }
movq, 0xf37e, AVX512F, Load|Modrm|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movq, 0x66d6, AVX512F, Modrm|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex|RegXMM }
movq, 0x666e, x64&(AVX|AVX512F), D|Modrm|Vex128|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf|Size64|SSE2AVX, { Reg64|Unspecified|BaseIndex, RegXMM }
movq, 0xf30f7e, SSE2, Load|Modrm|NoSuf, { Unspecified|Qword|BaseIndex|RegXMM, RegXMM }
movq, 0x660fd6, SSE2, Modrm|NoSuf, { RegXMM, Unspecified|Qword|BaseIndex|RegXMM }
movq, 0x660f6e, SSE2&x64, D|Modrm|NoSuf|Size64, { Reg64|Unspecified|BaseIndex, RegXMM }
// The MMX templates have to remain after at least the SSE2AVX ones.
movq, 0xf6f, MMX, D|Modrm|NoSuf, { Unspecified|Qword|BaseIndex|RegMMX, RegMMX }
movq, 0xf6e, MMX&x64, D|Modrm|NoSuf|Size64, { Reg64|Unspecified|BaseIndex, RegMMX }
packssdw<mmx>, 0x<mmx:pfx>0f6b, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
packsswb<mmx>, 0x<mmx:pfx>0f63, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
packuswb<mmx>, 0x<mmx:pfx>0f67, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
padd<bw><mmx>, 0x<mmx:pfx>0ffc | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
paddd<mmx>, 0x<mmx:pfx>0ffe, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
paddq<sse2>, 0x660fd4, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
packssdw<MMXBW>, 0x<MMXBW:pfx>0f6b, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
packsswb<MMXBW>, 0x<MMXBW:pfx>0f63, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
packuswb<MMXBW>, 0x<MMXBW:pfx>0f67, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
padd<bw><MMXBW>, 0x<MMXBW:pfx>0ffc | <bw:opc>, <MMXBW:cpu>, Modrm|<MMXBW:attr>|C|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
paddd<MMX>, 0x<MMX:pfx>0ffe, <MMX:cpu>, Modrm|<MMX:attr>|C|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
paddq<SSE2Q>, 0x660fd4, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
paddq, 0xfd4, SSE2, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
padds<bw><mmx>, 0x<mmx:pfx>0fec | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
paddus<bw><mmx>, 0x<mmx:pfx>0fdc | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pand<mmx>, 0x<mmx:pfx>0fdb, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pandn<mmx>, 0x<mmx:pfx>0fdf, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
padds<bw><MMXBW>, 0x<MMXBW:pfx>0fec | <bw:opc>, <MMXBW:cpu>, Modrm|<MMXBW:attr>|C|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
paddus<bw><MMXBW>, 0x<MMXBW:pfx>0fdc | <bw:opc>, <MMXBW:cpu>, Modrm|<MMXBW:attr>|C|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
pand<MMX>, 0x<MMX:pfx>0fdb, <MMX:cpu>, Modrm|<MMX:attr>|C|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
pandn<MMX>, 0x<MMX:pfx>0fdf, <MMX:cpu>, Modrm|<MMX:attr>|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
pcmpeq<bw><mmx>, 0x<mmx:pfx>0f74 | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pcmpeqd<mmx>, 0x<mmx:pfx>0f76, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pcmpgt<bw><mmx>, 0x<mmx:pfx>0f64 | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf|Optimize, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pcmpgtd<mmx>, 0x<mmx:pfx>0f66, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf|Optimize, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pmaddwd<mmx>, 0x<mmx:pfx>0ff5, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pmulhw<mmx>, 0x<mmx:pfx>0fe5, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pmullw<mmx>, 0x<mmx:pfx>0fd5, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
por<mmx>, 0x<mmx:pfx>0feb, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psllw<mmx>, 0x<mmx:pfx>0ff1, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psllw<mmx>, 0x<mmx:pfx>0f71/6, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { Imm8, <mmx:reg> }
psll<dq><mmx>, 0x<mmx:pfx>0ff2 | <dq:opc>, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psll<dq><mmx>, 0x<mmx:pfx>0f72 | <dq:opc>/6, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { Imm8, <mmx:reg> }
psraw<mmx>, 0x<mmx:pfx>0fe1, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psraw<mmx>, 0x<mmx:pfx>0f71/4, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { Imm8, <mmx:reg> }
psrad<mmx>, 0x<mmx:pfx>0fe2, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psrad<mmx>, 0x<mmx:pfx>0f72/4, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { Imm8, <mmx:reg> }
psrlw<mmx>, 0x<mmx:pfx>0fd1, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psrlw<mmx>, 0x<mmx:pfx>0f71/2, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { Imm8, <mmx:reg> }
psrl<dq><mmx>, 0x<mmx:pfx>0fd2 | <dq:opc>, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psrl<dq><mmx>, 0x<mmx:pfx>0f72 | <dq:opc>/2, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { Imm8, <mmx:reg> }
psub<bw><mmx>, 0x<mmx:pfx>0ff8 | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psubd<mmx>, 0x<mmx:pfx>0ffa, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psubq<sse2>, 0x660ffb, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaddwd<MMXBW>, 0x<MMXBW:pfx>0ff5, <MMXBW:cpu>, Modrm|<MMXBW:attr>|C|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
pmulhw<MMXBW>, 0x<MMXBW:pfx>0fe5, <MMXBW:cpu>, Modrm|<MMXBW:attr>|C|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
pmullw<MMXBW>, 0x<MMXBW:pfx>0fd5, <MMXBW:cpu>, Modrm|<MMXBW:attr>|C|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
por<MMX>, 0x<MMX:pfx>0feb, <MMX:cpu>, Modrm|<MMX:attr>|C|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
psllw<MMXBW>, 0x<MMXBW:pfx>0ff1, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
psllw<MMXBW>, 0x<MMXBW:pfx>0f71/6, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { Imm8, <MMXBW:reg> }
psll<MMXdq>, 0x<MMXdq:pfx>0ff2 | <MMXdq:opc>, <MMXdq:cpu>, Modrm|<MMXdq:attr>|NoSuf, { <MMXdq:reg>|<MMXdq:mem>|Unspecified|BaseIndex, <MMXdq:reg> }
psll<MMXdq>, 0x<MMXdq:pfx>0f72 | <MMXdq:opc>/6, <MMXdq:cpu>, Modrm|<MMXdq:attr>|NoSuf, { Imm8, <MMXdq:reg> }
psraw<MMXBW>, 0x<MMXBW:pfx>0fe1, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
psraw<MMXBW>, 0x<MMXBW:pfx>0f71/4, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { Imm8, <MMXBW:reg> }
psrad<MMX>, 0x<MMX:pfx>0fe2, <MMX:cpu>, Modrm|<MMX:attr>|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
psrad<MMX>, 0x<MMX:pfx>0f72/4, <MMX:cpu>, Modrm|<MMX:attr>|NoSuf, { Imm8, <MMX:reg> }
psrlw<MMXBW>, 0x<MMXBW:pfx>0fd1, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
psrlw<MMXBW>, 0x<MMXBW:pfx>0f71/2, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { Imm8, <MMXBW:reg> }
psrl<MMXdq>, 0x<MMXdq:pfx>0fd2 | <MMXdq:opc>, <MMXdq:cpu>, Modrm|<MMXdq:attr>|NoSuf, { <MMXdq:reg>|<MMXdq:mem>|Unspecified|BaseIndex, <MMXdq:reg> }
psrl<MMXdq>, 0x<MMXdq:pfx>0f72 | <MMXdq:opc>/2, <MMXdq:cpu>, Modrm|<MMXdq:attr>|NoSuf, { Imm8, <MMXdq:reg> }
psub<bw><MMXBW>, 0x<MMXBW:pfx>0ff8 | <bw:opc>, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
psubd<MMX>, 0x<MMX:pfx>0ffa, <MMX:cpu>, Modrm|<MMX:attr>|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
psubq<SSE2Q>, 0x660ffb, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
psubq, 0xffb, SSE2, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
psubs<bw><mmx>, 0x<mmx:pfx>0fe8 | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
psubus<bw><mmx>, 0x<mmx:pfx>0fd8 | <bw:opc>, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
punpckhbw<mmx>, 0x<mmx:pfx>0f68, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
punpckhwd<mmx>, 0x<mmx:pfx>0f69, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
punpckhdq<mmx>, 0x<mmx:pfx>0f6a, <mmx:cpu>, Modrm|<mmx:attr>|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
punpcklbw<sse2>, 0x660f60, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
psubs<bw><MMXBW>, 0x<MMXBW:pfx>0fe8 | <bw:opc>, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
psubus<bw><MMXBW>, 0x<MMXBW:pfx>0fd8 | <bw:opc>, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
punpckhbw<MMXBW>, 0x<MMXBW:pfx>0f68, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
punpckhwd<MMXBW>, 0x<MMXBW:pfx>0f69, <MMXBW:cpu>, Modrm|<MMXBW:attr>|NoSuf, { <MMXBW:reg>|<MMXBW:mem>|Unspecified|BaseIndex, <MMXBW:reg> }
punpckhdq<MMX>, 0x<MMX:pfx>0f6a, <MMX:cpu>, Modrm|<MMX:attr>|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
punpcklbw<SSE2BW>, 0x660f60, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpcklbw, 0xf60, MMX, Modrm|NoSuf, { Dword|Unspecified|BaseIndex|RegMMX, RegMMX }
punpcklwd<sse2>, 0x660f61, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpcklwd<SSE2BW>, 0x660f61, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpcklwd, 0xf61, MMX, Modrm|NoSuf, { Dword|Unspecified|BaseIndex|RegMMX, RegMMX }
punpckldq<sse2>, 0x660f62, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpckldq<SSE2D>, 0x660f62, <SSE2D:cpu>, Modrm|<SSE2D:attr>|<SSE2D:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpckldq, 0xf62, MMX, Modrm|NoSuf, { Dword|Unspecified|BaseIndex|RegMMX, RegMMX }
pxor<mmx>, 0x<mmx:pfx>0fef, <mmx:cpu>, Modrm|<mmx:attr>|C|NoSuf, { <mmx:reg>|<mmx:mem>|Unspecified|BaseIndex, <mmx:reg> }
pxor<MMX>, 0x<MMX:pfx>0fef, <MMX:cpu>, Modrm|<MMX:attr>|C|NoSuf, { <MMX:reg>|<MMX:mem>|Unspecified|BaseIndex, <MMX:reg> }
// SSE instructions.
<sse:cpu:attr:scal:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexLIG|VexW0|SSE2AVX:VexVVVV, +
$sse:SSE:::>
<SSE:cpu:attr:scal:vvvv, +
$avx:AVX|AVX512VL:Vex128|EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexLIG|EVexLIG|VexW0|Disp8MemShift=2|SSE2AVX:VexVVVV, +
$sse:SSE:::>
<SSEDQ:cpu:attr, +
$avx:AVX:Vex128|VexW0|VexVVVV|SSE2AVX, +
$apx:AVX512DQ&AVX512VL:EVex128|VexW0|VexVVVV|Disp8MemShift=4|SSE2AVX, +
$sse:SSE:>
<SSERP:recip:rsqrt:cpu:attr, +
$avx:0x0f53:0x0f52:AVX:Vex128|VexW0|SSE2AVX, +
$apx:0x660f384c:0x660f384e:AVX512VL:EVex128|VexW0|Disp8MemShift=4|SSE2AVX, +
$sse:0x0f53:0x0f52:SSE:::>
<SSERS:recip:rsqrt:cpu:attr, +
$avx:0xf30f53:0xf30f52:AVX:VexLIG|VexW0|VexVVVV|SSE2AVX, +
$apx:0x660f384d:0x660f384f:AVX512F:EVexLIG|VexW0|VexVVVV|Disp8MemShift=2|SSE2AVX, +
$sse:0xf30f53:0xf30f52:SSE:::>
<frel:imm:comm, eq:0:C, lt:1:, le:2:, unord:3:C, neq:4:C, nlt:5:, nle:6:, ord:7:C>
addps<sse>, 0x0f58, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
addss<sse>, 0xf30f58, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
andnps<sse>, 0x0f55, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
andps<sse>, 0x0f54, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
addps<SSE>, 0x0f58, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
addss<SSE>, 0xf30f58, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
andnps<SSEDQ>, 0x0f55, <SSEDQ:cpu>, Modrm|<SSEDQ:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
andps<SSEDQ>, 0x0f54, <SSEDQ:cpu>, Modrm|<SSEDQ:attr>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cmp<frel>ps<sse>, 0x0fc2/<frel:imm>, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|<frel:comm>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
cmp<frel>ss<sse>, 0xf30fc2/<frel:imm>, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|<frel:comm>|NoSuf|ImmExt, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
cmpps<sse>, 0x0fc2, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
cmpss<sse>, 0xf30fc2, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Imm8, Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
comiss<sse>, 0x0f2f, <sse:cpu>, Modrm|<sse:scal>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
comiss<SSE>, 0x0f2f, <SSE:cpu>, Modrm|<SSE:scal>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtpi2ps, 0xf2a, SSE, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegXMM }
cvtps2pi, 0xf2d, SSE, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegMMX }
cvtsi2ss<sse>, 0xf30f2a, <sse:cpu>&No64, Modrm|<sse:scal>|<sse:vvvv>|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|No_qSuf, { Reg32|Unspecified|BaseIndex, RegXMM }
cvtsi2ss, 0xf32a, AVX&x64, Modrm|Vex=3|Space0F|VexVVVV|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|ATTSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2ss, 0xf32a, AVX&x64, Modrm|Vex=3|Space0F|VexVVVV|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|IntelSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2ss, 0xf32a, x64&(AVX|AVX512F), Modrm|VexLIG|EVexLIG|Space0F|VexVVVV|IgnoreSize|Disp8ShiftVL|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|ATTSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2ss, 0xf32a, x64&(AVX|AVX512F), Modrm|VexLIG|EVexLIG|Space0F|VexVVVV|Disp8ShiftVL|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|IntelSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2ss, 0xf30f2a, SSE&x64, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|ATTSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2ss, 0xf30f2a, SSE&x64, Modrm|No_bSuf|No_wSuf|No_sSuf|IntelSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtss2si, 0xf32d, AVX, Modrm|VexLIG|Space0F|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Dword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvtss2si, 0xf32d, AVX|AVX512F, Modrm|VexLIG|EVexLIG|Space0F|Disp8MemShift=2|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Dword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvtss2si, 0xf30f2d, SSE, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Dword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvttps2pi, 0xf2c, SSE, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegMMX }
cvttss2si, 0xf32c, AVX, Modrm|VexLIG|Space0F|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Dword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvttss2si, 0xf32c, AVX|AVX512F, Modrm|VexLIG|EVexLIG|Space0F|Disp8MemShift=2|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Dword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvttss2si, 0xf30f2c, SSE, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Dword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
divps<sse>, 0x0f5e, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
divss<sse>, 0xf30f5e, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
divps<SSE>, 0x0f5e, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
divss<SSE>, 0xf30f5e, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
ldmxcsr<sse>, 0x0fae/2, <sse:cpu>, Modrm|<sse:attr>|NoSuf, { Dword|Unspecified|BaseIndex }
maskmovq, 0xff7, SSE|3dnowA, Modrm|NoSuf, { RegMMX, RegMMX }
maxps<sse>, 0x0f5f, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
maxss<sse>, 0xf30f5f, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
minps<sse>, 0x0f5d, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
minss<sse>, 0xf30f5d, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
movaps<sse>, 0x0f28, <sse:cpu>, D|Modrm|<sse:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
maxps<SSE>, 0x0f5f, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
maxss<SSE>, 0xf30f5f, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
minps<SSE>, 0x0f5d, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
minss<SSE>, 0xf30f5d, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
movaps<SSE>, 0x0f28, <SSE:cpu>, D|Modrm|<SSE:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movhlps<sse>, 0x0f12, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM, RegXMM }
movhps, 0x16, AVX, Modrm|Vex|Space0F|VexVVVV|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movhps, 0x17, AVX, Modrm|Vex|Space0F|VexW0|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movhps, 0x16, AVX|AVX512F, Modrm|Vex128|EVex128|Space0F|VexVVVV|VexW0|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movhps, 0x17, AVX|AVX512F, Modrm|Vex128|EVex128|Space0F|VexW0|Disp8MemShift=3|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movhps, 0xf16, SSE, D|Modrm|NoSuf, { Qword|Unspecified|BaseIndex, RegXMM }
movlhps<sse>, 0x0f16, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM, RegXMM }
movlps, 0x12, AVX, Modrm|Vex|Space0F|VexVVVV|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movlps, 0x13, AVX, Modrm|Vex|Space0F|VexW0|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movlps, 0x12, AVX|AVX512F, Modrm|Vex128|EVex128|Space0F|VexVVVV|VexW0|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movlps, 0x13, AVX|AVX512F, Modrm|Vex128|EVex128|Space0F|VexW0|Disp8MemShift=3|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movlps, 0xf12, SSE, D|Modrm|NoSuf, { Qword|Unspecified|BaseIndex, RegXMM }
movmskps<sse>, 0x0f50, <sse:cpu>, Modrm|<sse:attr>|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|NoRex64, { RegXMM, Reg32|Reg64 }
movntps<sse>, 0x0f2b, <sse:cpu>, Modrm|<sse:attr>|NoSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
movntps<SSE>, 0x0f2b, <SSE:cpu>, Modrm|<SSE:attr>|NoSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
movntq, 0xfe7, SSE|3dnowA, Modrm|NoSuf, { RegMMX, Qword|Unspecified|BaseIndex }
movntdq<sse2>, 0x660fe7, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
movss, 0xf310, AVX, D|Modrm|VexLIG|Space0F|VexW0|NoSuf|SSE2AVX, { Dword|Unspecified|BaseIndex, RegXMM }
movntdq<SSE2D>, 0x660fe7, <SSE2D:cpu>, Modrm|<SSE2D:attr>|NoSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
movss, 0xf310, AVX|AVX512F, D|Modrm|VexLIG|EVexLIG|Space0F|VexW0|Disp8MemShift=2|NoSuf|SSE2AVX, { Dword|Unspecified|BaseIndex, RegXMM }
movss, 0xf310, AVX, D|Modrm|VexLIG|Space0F|VexVVVV|VexW0|NoSuf|SSE2AVX, { RegXMM, RegXMM }
movss, 0xf30f10, SSE, D|Modrm|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
movups<sse>, 0x0f10, <sse:cpu>, D|Modrm|<sse:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulps<sse>, 0x0f59, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulss<sse>, 0xf30f59, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
orps<sse>, 0x0f56, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movups<SSE>, 0x0f10, <SSE:cpu>, D|Modrm|<SSE:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulps<SSE>, 0x0f59, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulss<SSE>, 0xf30f59, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
orps<SSEDQ>, 0x0f56, <SSEDQ:cpu>, Modrm|<SSEDQ:attr>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pavg<bw>, 0xfe0 | (3 * <bw:opc>), SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
pavg<bw><sse2>, 0x660fe0 | (3 * <bw:opc>), <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pextrw<sse2>, 0x660fc5, <sse2:cpu>, Load|Modrm|<sse2:attr>|No_bSuf|No_wSuf|No_sSuf|IgnoreSize|NoRex64, { Imm8, RegXMM, Reg32|Reg64 }
pavg<bw><SSE2BW>, 0x660fe0 | (3 * <bw:opc>), <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pextrw<SSE2D>, 0x660fc5, <SSE2D:cpu>, Load|Modrm|<SSE2D:attr>|No_bSuf|No_wSuf|No_sSuf|IgnoreSize|NoRex64, { Imm8, RegXMM, Reg32|Reg64 }
pextrw, 0xfc5, SSE|3dnowA, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|NoRex64, { Imm8, RegMMX, Reg32|Reg64 }
pinsrw<sse2>, 0x660fc4, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|No_bSuf|No_wSuf|No_sSuf|IgnoreSize|NoRex64, { Imm8, Reg32|Reg64, RegXMM }
pinsrw<sse2>, 0x660fc4, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { Imm8, Word|Unspecified|BaseIndex, RegXMM }
pinsrw<SSE2D>, 0x660fc4, <SSE2D:cpu>, Modrm|<SSE2D:attr>|<SSE2D:vvvv>|No_bSuf|No_wSuf|No_sSuf|IgnoreSize|NoRex64, { Imm8, Reg32|Reg64, RegXMM }
pinsrw<SSE2D>, 0x660fc4, <SSE2D:cpu>, Modrm|<SSE2D:attr>|<SSE2D:vvvv>|Disp8MemShift|NoSuf, { Imm8, Word|Unspecified|BaseIndex, RegXMM }
pinsrw, 0xfc4, SSE|3dnowA, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|NoRex64, { Imm8, Reg32|Reg64, RegMMX }
pinsrw, 0xfc4, SSE|3dnowA, Modrm|NoSuf, { Imm8, Word|Unspecified|BaseIndex, RegMMX }
pmaxsw<sse2>, 0x660fee, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxsw<SSE2BW>, 0x660fee, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxsw, 0xfee, SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
pmaxub<sse2>, 0x660fde, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxub<SSE2BW>, 0x660fde, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxub, 0xfde, SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
pminsw<sse2>, 0x660fea, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminsw<SSE2BW>, 0x660fea, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminsw, 0xfea, SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
pminub<sse2>, 0x660fda, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminub<SSE2BW>, 0x660fda, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminub, 0xfda, SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
pmovmskb<sse2>, 0x660fd7, <sse2:cpu>, Modrm|<sse2:attr>|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|NoRex64, { RegXMM, Reg32|Reg64 }
pmovmskb, 0xfd7, SSE|3dnowA, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|NoRex64, { RegMMX, Reg32|Reg64 }
pmulhuw<sse2>, 0x660fe4, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmulhuw<SSE2BW>, 0x660fe4, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmulhuw, 0xfe4, SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
prefetchnta, 0xf18/0, SSE|3dnowA, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex }
prefetcht0, 0xf18/1, SSE|3dnowA, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex }
prefetcht1, 0xf18/2, SSE|3dnowA, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex }
prefetcht2, 0xf18/3, SSE|3dnowA, Modrm|Anysize|IgnoreSize|NoSuf, { BaseIndex }
psadbw, 0xff6, SSE|3dnowA, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
psadbw<sse2>, 0x660ff6, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
psadbw<SSE2BW>, 0x660ff6, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|<SSE2BW:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pshufw, 0xf70, SSE|3dnowA, Modrm|NoSuf, { Imm8|Imm8S, Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
rcpps<sse>, 0x0f53, <sse:cpu>, Modrm|<sse:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
rcpss<sse>, 0xf30f53, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
rsqrtps<sse>, 0x0f52, <sse:cpu>, Modrm|<sse:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
rsqrtss<sse>, 0xf30f52, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
rcpps<SSERP>, <SSERP:recip>, <SSERP:cpu>, Modrm|<SSERP:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
rcpss<SSERS>, <SSERS:recip>, <SSERS:cpu>, Modrm|<SSERS:attr>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
rsqrtps<SSERP>, <SSERP:rsqrt>, <SSERP:cpu>, Modrm|<SSERP:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
rsqrtss<SSERS>, <SSERS:rsqrt>, <SSERS:cpu>, Modrm|<SSERS:attr>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
sfence, 0xfaef8, SSE|3dnowA, NoSuf, {}
shufps<sse>, 0x0fc6, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtps<sse>, 0x0f51, <sse:cpu>, Modrm|<sse:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtss<sse>, 0xf30f51, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
shufps<SSE>, 0x0fc6, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtps<SSE>, 0x0f51, <SSE:cpu>, Modrm|<SSE:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtss<SSE>, 0xf30f51, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
stmxcsr<sse>, 0x0fae/3, <sse:cpu>, Modrm|<sse:attr>|NoSuf, { Dword|Unspecified|BaseIndex }
subps<sse>, 0x0f5c, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
subss<sse>, 0xf30f5c, <sse:cpu>, Modrm|<sse:scal>|<sse:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
ucomiss<sse>, 0x0f2e, <sse:cpu>, Modrm|<sse:scal>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
unpckhps<sse>, 0x0f15, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
unpcklps<sse>, 0x0f14, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
xorps<sse>, 0x0f57, <sse:cpu>, Modrm|<sse:attr>|<sse:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
subps<SSE>, 0x0f5c, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
subss<SSE>, 0xf30f5c, <SSE:cpu>, Modrm|<SSE:scal>|<SSE:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
ucomiss<SSE>, 0x0f2e, <SSE:cpu>, Modrm|<SSE:scal>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
unpckhps<SSE>, 0x0f15, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
unpcklps<SSE>, 0x0f14, <SSE:cpu>, Modrm|<SSE:attr>|<SSE:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
xorps<SSEDQ>, 0x0f57, <SSEDQ:cpu>, Modrm|<SSEDQ:attr>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
// SSE2 instructions.
addpd<sse2>, 0x660f58, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
addsd<sse2>, 0xf20f58, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
andnpd<sse2>, 0x660f55, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
andpd<sse2>, 0x660f54, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
<SSE2DQ:cpu:attr, +
$avx:AVX:Vex128|VexW0|VexVVVV|SSE2AVX, +
$apx:AVX512DQ&AVX512VL:EVex128|VexW1|VexVVVV|Disp8MemShift=4|SSE2AVX, +
$sse:SSE2:>
addpd<SSE2Q>, 0x660f58, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
addsd<SSE2Q>, 0xf20f58, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
andnpd<SSE2DQ>, 0x660f55, <SSE2DQ:cpu>, Modrm|<SSE2DQ:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
andpd<SSE2DQ>, 0x660f54, <SSE2DQ:cpu>, Modrm|<SSE2DQ:attr>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cmp<frel>pd<sse2>, 0x660fc2/<frel:imm>, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|<frel:comm>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
cmp<frel>sd<sse2>, 0xf20fc2/<frel:imm>, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|<frel:comm>|NoSuf|ImmExt, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
cmppd<sse2>, 0x660fc2, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
cmpsd<sse2>, 0xf20fc2, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Imm8, Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
comisd<sse2>, 0x660f2f, <sse2:cpu>, Modrm|<sse2:scal>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
comisd<SSE2Q>, 0x660f2f, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtpi2pd, 0x660f2a, SSE2, Modrm|NoSuf, { RegMMX, RegXMM }
cvtpi2pd, 0xf3e6, AVX, Modrm|Vex|Space0F|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
cvtpi2pd, 0xf3e6, AVX|AVX512VL, Modrm|Vex128|EVex128|Space0F|VexW0|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
cvtpi2pd, 0x660f2a, SSE2, Modrm|NoSuf, { Qword|Unspecified|BaseIndex, RegXMM }
cvtsi2sd<sse2>, 0xf20f2a, <sse2:cpu>&No64, Modrm|IgnoreSize|<sse2:scal>|<sse2:vvvv>|No_bSuf|No_wSuf|No_sSuf|No_qSuf, { Reg32|Unspecified|BaseIndex, RegXMM }
cvtsi2sd, 0xf22a, AVX&x64, Modrm|Vex=3|Space0F|VexVVVV|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|ATTSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2sd, 0xf22a, AVX&x64, Modrm|Vex=3|Space0F|VexVVVV|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|IntelSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2sd, 0xf22a, x64&(AVX|AVX512F), Modrm|VexLIG|EVexLIG|Space0F|VexVVVV|Disp8ShiftVL|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|ATTSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2sd, 0xf22a, x64&(AVX|AVX512F), Modrm|VexLIG|EVexLIG|Space0F|VexVVVV|Disp8ShiftVL|No_bSuf|No_wSuf|No_sSuf|SSE2AVX|IntelSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2sd, 0xf20f2a, SSE2&x64, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|ATTSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
cvtsi2sd, 0xf20f2a, SSE2&x64, Modrm|No_bSuf|No_wSuf|No_sSuf|IntelSyntax, { Reg32|Reg64|Unspecified|BaseIndex, RegXMM }
divpd<sse2>, 0x660f5e, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
divsd<sse2>, 0xf20f5e, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
maxpd<sse2>, 0x660f5f, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
maxsd<sse2>, 0xf20f5f, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
minpd<sse2>, 0x660f5d, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
minsd<sse2>, 0xf20f5d, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movapd<sse2>, 0x660f28, <sse2:cpu>, D|Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
divpd<SSE2Q>, 0x660f5e, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
divsd<SSE2Q>, 0xf20f5e, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
maxpd<SSE2Q>, 0x660f5f, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
maxsd<SSE2Q>, 0xf20f5f, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
minpd<SSE2Q>, 0x660f5d, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
minsd<SSE2Q>, 0xf20f5d, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movapd<SSE2Q>, 0x660f28, <SSE2Q:cpu>, D|Modrm|<SSE2Q:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movhpd, 0x6616, AVX, Modrm|Vex|Space0F|VexVVVV|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movhpd, 0x6616, AVX512F, Modrm|EVex128|Space0F|VexVVVV|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movhpd, 0x6617, AVX, Modrm|Vex|Space0F|VexW0|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movhpd, 0x6617, AVX512F, Modrm|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movhpd, 0x660f16, SSE2, D|Modrm|NoSuf, { Qword|Unspecified|BaseIndex, RegXMM }
movlpd, 0x6612, AVX, Modrm|Vex|Space0F|VexVVVV|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movlpd, 0x6612, AVX512F, Modrm|EVex128|Space0F|VexVVVV|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movlpd, 0x6613, AVX, Modrm|Vex|Space0F|VexW0|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movlpd, 0x6613, AVX512F, Modrm|EVex128|Space0F|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { RegXMM, Qword|Unspecified|BaseIndex }
movlpd, 0x660f12, SSE2, D|Modrm|NoSuf, { Qword|Unspecified|BaseIndex, RegXMM }
movmskpd<sse2>, 0x660f50, <sse2:cpu>, Modrm|<sse2:attr>|IgnoreSize|No_bSuf|No_wSuf|No_sSuf|NoRex64, { RegXMM, Reg32|Reg64 }
movntpd<sse2>, 0x660f2b, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
movntpd<SSE2Q>, 0x660f2b, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|NoSuf, { RegXMM, Xmmword|Unspecified|BaseIndex }
movsd, 0xf210, AVX, D|Modrm|VexLIG|Space0F|VexW0|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movsd, 0xf210, AVX512F, D|Modrm|EVexLIG|Space0F|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { Qword|Unspecified|BaseIndex, RegXMM }
movsd, 0xf210, AVX, D|Modrm|VexLIG|Space0F|VexVVVV|VexW0|NoSuf|SSE2AVX, { RegXMM, RegXMM }
movsd, 0xf20f10, SSE2, D|Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movupd<sse2>, 0x660f10, <sse2:cpu>, D|Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulpd<sse2>, 0x660f59, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulsd<sse2>, 0xf20f59, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
orpd<sse2>, 0x660f56, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
shufpd<sse2>, 0x660fc6, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtpd<sse2>, 0x660f51, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtsd<sse2>, 0xf20f51, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
subpd<sse2>, 0x660f5c, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
subsd<sse2>, 0xf20f5c, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
ucomisd<sse2>, 0x660f2e, <sse2:cpu>, Modrm|<sse2:scal>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
unpckhpd<sse2>, 0x660f15, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
unpcklpd<sse2>, 0x660f14, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
xorpd<sse2>, 0x660f57, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtdq2pd<sse2>, 0xf30fe6, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtpd2dq<sse2>, 0xf20fe6, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtdq2ps<sse2>, 0x0f5b, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movupd<SSE2Q>, 0x660f10, <SSE2Q:cpu>, D|Modrm|<SSE2Q:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulpd<SSE2Q>, 0x660f59, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
mulsd<SSE2Q>, 0xf20f59, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
orpd<SSE2DQ>, 0x660f56, <SSE2DQ:cpu>, Modrm|<SSE2DQ:attr>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
shufpd<SSE2Q>, 0x660fc6, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtpd<SSE2Q>, 0x660f51, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
sqrtsd<SSE2Q>, 0xf20f51, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
subpd<SSE2Q>, 0x660f5c, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
subsd<SSE2Q>, 0xf20f5c, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
ucomisd<SSE2Q>, 0x660f2e, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
unpckhpd<SSE2Q>, 0x660f15, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
unpcklpd<SSE2Q>, 0x660f14, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
xorpd<SSE2DQ>, 0x660f57, <SSE2DQ:cpu>, Modrm|<SSE2DQ:attr>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtdq2pd<SSE2D>, 0xf30fe6, <SSE2D:cpu>, Modrm|<SSE2D:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtpd2dq<SSE2Q>, 0xf20fe6, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtdq2ps<SSE2D>, 0x0f5b, <SSE2D:cpu>, Modrm|<SSE2D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtpd2pi, 0x660f2d, SSE2, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegMMX }
cvtpd2ps<sse2>, 0x660f5a, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtps2pd<sse2>, 0x0f5a, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtps2dq<sse2>, 0x660f5b, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtsd2si, 0xf22d, AVX, Modrm|VexLIG|Space0F|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvtpd2ps<SSE2Q>, 0x660f5a, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtps2pd<SSE2D>, 0x0f5a, <SSE2D:cpu>, Modrm|<SSE2D:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtps2dq<SSE2D>, 0x660f5b, <SSE2D:cpu>, Modrm|<SSE2D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvtsd2si, 0xf22d, AVX|AVX512F, Modrm|VexLIG|EVexLIG|Space0F|Disp8MemShift=3|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvtsd2si, 0xf20f2d, SSE2, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Qword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvtsd2ss<sse2>, 0xf20f5a, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtss2sd<sse2>, 0xf30f5a, <sse2:cpu>, Modrm|<sse2:scal>|<sse2:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtsd2ss<SSE2Q>, 0xf20f5a, <SSE2Q:cpu>, Modrm|<SSE2Q:scal>|<SSE2Q:vvvv>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvtss2sd<SSE2D>, 0xf30f5a, <SSE2D:cpu>, Modrm|<SSE2D:scal>|<SSE2D:vvvv>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
cvttpd2pi, 0x660f2c, SSE2, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegMMX }
cvttsd2si, 0xf22c, AVX, Modrm|VexLIG|Space0F|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvttsd2si, 0xf22c, AVX|AVX512F, Modrm|VexLIG|EVexLIG|Space0F|Disp8MemShift=3|No_bSuf|No_wSuf|No_sSuf|SSE2AVX, { Qword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvttsd2si, 0xf20f2c, SSE2, Modrm|IgnoreSize|No_bSuf|No_wSuf|No_sSuf, { Qword|Unspecified|BaseIndex|RegXMM, Reg32|Reg64 }
cvttpd2dq<sse2>, 0x660fe6, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvttps2dq<sse2>, 0xf30f5b, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvttpd2dq<SSE2Q>, 0x660fe6, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
cvttps2dq<SSE2D>, 0xf30f5b, <SSE2D:cpu>, Modrm|<SSE2D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
maskmovdqu<sse2>, 0x660ff7, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { RegXMM, RegXMM }
movdqa<sse2>, 0x660f6f, <sse2:cpu>, D|Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movdqu<sse2>, 0xf30f6f, <sse2:cpu>, D|Modrm|<sse2:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movdqa<SSE2D>, 0x660f6f, <SSE2D:cpu>, D|Modrm|<SSE2D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movdqu<SSE2D>, 0xf30f6f, <SSE2D:cpu>, D|Modrm|<SSE2D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movdq2q, 0xf20fd6, SSE2, Modrm|NoSuf, { RegXMM, RegMMX }
movq2dq, 0xf30fd6, SSE2, Modrm|NoSuf, { RegMMX, RegXMM }
pmuludq<sse2>, 0x660ff4, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmuludq<SSE2Q>, 0x660ff4, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|C|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmuludq, 0xff4, SSE2, Modrm|NoSuf, { Qword|Unspecified|BaseIndex|RegMMX, RegMMX }
pshufd<sse2>, 0x660f70, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pshufhw<sse2>, 0xf30f70, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pshuflw<sse2>, 0xf20f70, <sse2:cpu>, Modrm|<sse2:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pshufd<SSE2D>, 0x660f70, <SSE2D:cpu>, Modrm|<SSE2D:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pshufhw<SSE2BW>, 0xf30f70, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pshuflw<SSE2BW>, 0xf20f70, <SSE2BW:cpu>, Modrm|<SSE2BW:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pslldq<sse2>, 0x660f73/7, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { Imm8, RegXMM }
psrldq<sse2>, 0x660f73/3, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { Imm8, RegXMM }
punpckhqdq<sse2>, 0x660f6d, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpcklqdq<sse2>, 0x660f6c, <sse2:cpu>, Modrm|<sse2:attr>|<sse2:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpckhqdq<SSE2Q>, 0x660f6d, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
punpcklqdq<SSE2Q>, 0x660f6c, <SSE2Q:cpu>, Modrm|<SSE2Q:attr>|<SSE2Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
<frel>
// SSE3 instructions.
<sse3:cpu:attr:vvvv, $avx:AVX:Vex128|VexW0|SSE2AVX:VexVVVV, $sse:SSE3::>
<SSE3D:cpu:attr, +
$avx:AVX|AVX512VL:Vex128|EVex128|VexW0|Disp8MemShift=4|SSE2AVX, +
$sse:SSE3:>
<SSE3Q:cpu:attr, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexVVVV, +
$apx:AVX512VL:EVex128|VexW1|Disp8MemShift=3|SSE2AVX, +
$sse:SSE3:>
addsubpd<sse3>, 0x660fd0, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
addsubps<sse3>, 0xf20fd0, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
@ -1279,10 +1342,13 @@ haddpd<sse3>, 0x660f7c, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|NoSuf, { RegXM
haddps<sse3>, 0xf20f7c, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
hsubpd<sse3>, 0x660f7d, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
hsubps<sse3>, 0xf20f7d, <sse3:cpu>, Modrm|<sse3:attr>|<sse3:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
lddqu<sse3>, 0xf20ff0, <sse3:cpu>, Modrm|<sse3:attr>|NoSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
movddup<sse3>, 0xf20f12, <sse3:cpu>, Modrm|<sse3:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movshdup<sse3>, 0xf30f16, <sse3:cpu>, Modrm|<sse3:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movsldup<sse3>, 0xf30f12, <sse3:cpu>, Modrm|<sse3:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
lddqu, 0xf20ff0, AVX, Modrm|Vex128|VexW0|SSE2AVX|NoSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
// For use with eGPR-s in the memory operand, utilize VMOVDQU32.
lddqu, 0xf30f6f, AVX512VL, Modrm|EVex128|VexW0|Disp8MemShift=4|SSE2AVX|NoSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
lddqu, 0xf20ff0, SSE3, Modrm|NoSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
movddup<SSE3Q>, 0xf20f12, <SSE3Q:cpu>, Modrm|<SSE3Q:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
movshdup<SSE3D>, 0xf30f16, <SSE3D:cpu>, Modrm|<SSE3D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
movsldup<SSE3D>, 0xf30f12, <SSE3D:cpu>, Modrm|<SSE3D:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
// FPU instructions also covered by SSE3 CPUID flag.
@ -1352,6 +1418,15 @@ invpcid, 0xf3f2, INVPCID&APX_F, Modrm|NoSuf|EVexMap4|VexWIG, { Oword|Unspecified
$avx:AVX:66:Vex128|VexW0|SSE2AVX:VexVVVV:RegXMM:Xmmword, +
$sse:SSSE3:66:::RegXMM:Xmmword, +
$mmx:SSSE3::::RegMMX:Qword>
<SSSE3BW:cpu:pfx:attr:vvvv:reg:mem, +
$avx:AVX:66:Vex128|VexW0|SSE2AVX:VexVVVV:RegXMM:Xmmword, +
$apx:AVX512BW&AVX512VL:66:EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexVVVV:RegXMM:Xmmword, +
$sse:SSSE3:66:::RegXMM:Xmmword, +
$mmx:SSSE3::::RegMMX:Qword>
<SSSE3D:cpu:pfx:attr:reg:mem, +
$avx:AVX|AVX512VL:66:Vex128|EVex128|VexW0|Disp8MemShift=4|SSE2AVX:RegXMM:Xmmword, +
$sse:SSSE3:66::RegXMM:Xmmword, +
$mmx:SSSE3:::RegMMX:Qword>
phaddw<ssse3>, 0x<ssse3:pfx>0f3801, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
phaddd<ssse3>, 0x<ssse3:pfx>0f3802, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
@ -1359,18 +1434,34 @@ phaddsw<ssse3>, 0x<ssse3:pfx>0f3803, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv
phsubw<ssse3>, 0x<ssse3:pfx>0f3805, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
phsubd<ssse3>, 0x<ssse3:pfx>0f3806, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
phsubsw<ssse3>, 0x<ssse3:pfx>0f3807, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
pmaddubsw<ssse3>, 0x<ssse3:pfx>0f3804, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
pmulhrsw<ssse3>, 0x<ssse3:pfx>0f380b, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
pshufb<ssse3>, 0x<ssse3:pfx>0f3800, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
pmaddubsw<SSSE3BW>, 0x<SSSE3BW:pfx>0f3804, <SSSE3BW:cpu>, Modrm|<SSSE3BW:attr>|<SSSE3BW:vvvv>|NoSuf, { <SSSE3BW:reg>|<SSSE3BW:mem>|Unspecified|BaseIndex, <SSSE3BW:reg> }
pmulhrsw<SSSE3BW>, 0x<SSSE3BW:pfx>0f380b, <SSSE3BW:cpu>, Modrm|<SSSE3BW:attr>|<SSSE3BW:vvvv>|NoSuf, { <SSSE3BW:reg>|<SSSE3BW:mem>|Unspecified|BaseIndex, <SSSE3BW:reg> }
pshufb<SSSE3BW>, 0x<SSSE3BW:pfx>0f3800, <SSSE3BW:cpu>, Modrm|<SSSE3BW:attr>|<SSSE3BW:vvvv>|NoSuf, { <SSSE3BW:reg>|<SSSE3BW:mem>|Unspecified|BaseIndex, <SSSE3BW:reg> }
psign<bw><ssse3>, 0x<ssse3:pfx>0f3808 | <bw:opc>, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
psignd<ssse3>, 0x<ssse3:pfx>0f380a, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
palignr<ssse3>, 0x<ssse3:pfx>0f3a0f, <ssse3:cpu>, Modrm|<ssse3:attr>|<ssse3:vvvv>|NoSuf, { Imm8, <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
pabs<bw><ssse3>, 0x<ssse3:pfx>0f381c | <bw:opc>, <ssse3:cpu>, Modrm|<ssse3:attr>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
pabsd<ssse3>, 0x<ssse3:pfx>0f381e, <ssse3:cpu>, Modrm|<ssse3:attr>|NoSuf, { <ssse3:reg>|<ssse3:mem>|Unspecified|BaseIndex, <ssse3:reg> }
palignr<SSSE3BW>, 0x<SSSE3BW:pfx>0f3a0f, <SSSE3BW:cpu>, Modrm|<SSSE3BW:attr>|<SSSE3BW:vvvv>|NoSuf, { Imm8, <SSSE3BW:reg>|<SSSE3BW:mem>|Unspecified|BaseIndex, <SSSE3BW:reg> }
pabs<bw><SSSE3BW>, 0x<SSSE3BW:pfx>0f381c | <bw:opc>, <SSSE3BW:cpu>, Modrm|<SSSE3BW:attr>|NoSuf, { <SSSE3BW:reg>|<SSSE3BW:mem>|Unspecified|BaseIndex, <SSSE3BW:reg> }
pabsd<SSSE3D>, 0x<SSSE3D:pfx>0f381e, <SSSE3D:cpu>, Modrm|<SSSE3D:attr>|NoSuf, { <SSSE3D:reg>|<SSSE3D:mem>|Unspecified|BaseIndex, <SSSE3D:reg> }
// SSE4.1 instructions.
<sse41:cpu:attr:scal:vvvv, $avx:AVX:Vex128|VexW0|SSE2AVX:VexLIG|VexW0|SSE2AVX:VexVVVV, $sse:SSE4_1:::>
<SSE41BW:cpu:attr:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexVVVV, +
$apx:AVX512BW&AVX512VL:EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexVVVV, +
$sse:SSE4_1::>
<SSE41DQ:cpu:attr:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexVVVV, +
$apx:AVX512DQ&AVX512VL:EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexVVVV, +
$sse:SSE4_1::>
<SSE41D:cpu:attr:scal:vvvv, +
$avx:AVX|AVX512VL:Vex128|EVex128|VexW0|Disp8MemShift=4|SSE2AVX:VexLIG|EVexLIG|VexW0|Disp8MemShift=2|SSE2AVX:VexVVVV, +
$sse:SSE4_1:::>
<SSE41Q:cpu:attr:scal:vvvv, +
$avx:AVX:Vex128|VexW0|SSE2AVX:VexLIG|VexW0|SSE2AVX:VexVVVV, +
$apx:AVX512VL:EVex128|VexW1|Disp8MemShift=4|SSE2AVX:EVexLIG|VexW1|Disp8MemShift=3|SSE2AVX:VexVVVV, +
$sse:SSE4_1:::>
<sd:ppfx:spfx:opc:vexw:elem, s::f3:0:VexW0:Dword, d:66:f2:1:VexW1:Qword>
blendp<sd><sse41>, 0x660f3a0c | <sd:opc>, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
@ -1379,56 +1470,60 @@ blendvp<sd>, 0x664a | <sd:opc>, AVX, Modrm|Vex128|Space0F3A|VexVVVV|VexW0|NoSuf|
blendvp<sd>, 0x660f3814 | <sd:opc>, SSE4_1, Modrm|NoSuf, { Acc|Xmmword, RegXMM|Unspecified|BaseIndex, RegXMM }
blendvp<sd>, 0x660f3814 | <sd:opc>, SSE4_1, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
dpp<sd><sse41>, 0x660f3a40 | <sd:opc>, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
extractps, 0x6617, AVX, Modrm|Vex128|Space0F3A|VexW0|NoSuf|SSE2AVX, { Imm8, RegXMM, Reg32|Unspecified|BaseIndex }
extractps, 0x6617, AVX&x64, RegMem|Vex128|Space0F3A|VexW1|NoSuf|SSE2AVX, { Imm8, RegXMM, Reg64 }
extractps, 0x6617, AVX|AVX512F, Modrm|Vex128|EVex128|Space0F3A|VexW0|Disp8MemShift=2|NoSuf|SSE2AVX, { Imm8, RegXMM, Reg32|Unspecified|BaseIndex }
extractps, 0x6617, x64&(AVX|AVX512F), RegMem|Vex128|EVex128|Space0F3A|VexW1|NoSuf|SSE2AVX, { Imm8, RegXMM, Reg64 }
extractps, 0x660f3a17, SSE4_1, Modrm|IgnoreSize|NoSuf, { Imm8, RegXMM, Reg32|Unspecified|BaseIndex }
extractps, 0x660f3a17, SSE4_1&x64, RegMem|NoSuf|NoRex64, { Imm8, RegXMM, Reg64 }
insertps<sse41>, 0x660f3a21, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { Imm8, Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
movntdqa<sse41>, 0x660f382a, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
insertps<SSE41D>, 0x660f3a21, <SSE41D:cpu>, Modrm|<SSE41D:attr>|<SSE41D:vvvv>|Disp8MemShift|NoSuf, { Imm8, Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
movntdqa<SSE41D>, 0x660f382a, <SSE41D:cpu>, Modrm|<SSE41D:attr>|NoSuf, { Xmmword|Unspecified|BaseIndex, RegXMM }
mpsadbw<sse41>, 0x660f3a42, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
packusdw<sse41>, 0x660f382b, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
packusdw<SSE41BW>, 0x660f382b, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pblendvb, 0x664c, AVX, Modrm|Vex128|Space0F3A|VexVVVV|VexW0|NoSuf|SSE2AVX, { Acc|Xmmword, RegXMM|Unspecified|BaseIndex, RegXMM }
pblendvb, 0x664c, AVX, Modrm|Vex128|Space0F3A|VexVVVV|VexW0|NoSuf|Implicit1stXmm0|SSE2AVX, { RegXMM|Unspecified|BaseIndex, RegXMM }
pblendvb, 0x660f3810, SSE4_1, Modrm|NoSuf, { Acc|Xmmword, RegXMM|Unspecified|BaseIndex, RegXMM }
pblendvb, 0x660f3810, SSE4_1, Modrm|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pblendw<sse41>, 0x660f3a0e, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pcmpeqq<sse41>, 0x660f3829, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf|Optimize, { RegXMM|Unspecified|BaseIndex, RegXMM }
pextr<bw><sse41>, 0x660f3a14 | <bw:opc>, <sse41:cpu>, RegMem|<sse41:attr>|NoSuf|IgnoreSize|NoRex64, { Imm8, RegXMM, Reg32|Reg64 }
pextr<bw><sse41>, 0x660f3a14 | <bw:opc>, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Imm8, RegXMM, <bw:elem>|Unspecified|BaseIndex }
pextrd<sse41>, 0x660f3a16, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf|IgnoreSize, { Imm8, RegXMM, Reg32|Unspecified|BaseIndex }
pextr<bw><SSE41BW>, 0x660f3a14 | <bw:opc>, <SSE41BW:cpu>, RegMem|<SSE41BW:attr>|NoSuf|IgnoreSize|NoRex64, { Imm8, RegXMM, Reg32|Reg64 }
pextr<bw><SSE41BW>, 0x660f3a14 | <bw:opc>, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|Disp8MemShift|NoSuf, { Imm8, RegXMM, <bw:elem>|Unspecified|BaseIndex }
pextrd<SSE41DQ>, 0x660f3a16, <SSE41DQ:cpu>, Modrm|<SSE41DQ:attr>|Disp8MemShift|NoSuf|IgnoreSize, { Imm8, RegXMM, Reg32|Unspecified|BaseIndex }
pextrq, 0x6616, AVX&x64, Modrm|Vex|Space0F3A|VexW1|NoSuf|SSE2AVX, { Imm8, RegXMM, Reg64|Unspecified|BaseIndex }
pextrq, 0x6616, AVX512DQ&AVX512VL&x64, Modrm|EVex128|Space0F3A|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { Imm8, RegXMM, Reg64|Unspecified|BaseIndex }
pextrq, 0x660f3a16, SSE4_1&x64, Modrm|Size64|NoSuf, { Imm8, RegXMM, Reg64|Unspecified|BaseIndex }
phminposuw<sse41>, 0x660f3841, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pinsrb<sse41>, 0x660f3a20, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf|IgnoreSize|NoRex64, { Imm8, Reg32|Reg64, RegXMM }
pinsrb<sse41>, 0x660f3a20, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { Imm8, Byte|Unspecified|BaseIndex, RegXMM }
pinsrd<sse41>, 0x660f3a22, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf|IgnoreSize, { Imm8, Reg32|Unspecified|BaseIndex, RegXMM }
pinsrb<SSE41BW>, 0x660f3a20, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|NoSuf|IgnoreSize|NoRex64, { Imm8, Reg32|Reg64, RegXMM }
pinsrb<SSE41BW>, 0x660f3a20, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|Disp8MemShift|NoSuf, { Imm8, Byte|Unspecified|BaseIndex, RegXMM }
pinsrd<SSE41DQ>, 0x660f3a22, <SSE41DQ:cpu>, Modrm|<SSE41DQ:attr>|<SSE41DQ:vvvv>|Disp8MemShift|NoSuf|IgnoreSize, { Imm8, Reg32|Unspecified|BaseIndex, RegXMM }
pinsrq, 0x6622, AVX&x64, Modrm|Vex|Space0F3A|VexVVVV|VexW1|NoSuf|SSE2AVX, { Imm8, Reg64|Unspecified|BaseIndex, RegXMM }
pinsrq, 0x6622, AVX512DQ&AVX512VL&AVX&x64, Modrm|EVex128|Space0F3A|VexVVVV|VexW1|Disp8MemShift=3|NoSuf|SSE2AVX, { Imm8, Reg64|Unspecified|BaseIndex, RegXMM }
pinsrq, 0x660f3a22, SSE4_1&x64, Modrm|Size64|NoSuf, { Imm8, Reg64|Unspecified|BaseIndex, RegXMM }
pmaxsb<sse41>, 0x660f383c, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxsd<sse41>, 0x660f383d, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxud<sse41>, 0x660f383f, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxuw<sse41>, 0x660f383e, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminsb<sse41>, 0x660f3838, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminsd<sse41>, 0x660f3839, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminud<sse41>, 0x660f383b, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminuw<sse41>, 0x660f383a, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmovsxbw<sse41>, 0x660f3820, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxbd<sse41>, 0x660f3821, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxbq<sse41>, 0x660f3822, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Word|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxwd<sse41>, 0x660f3823, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxwq<sse41>, 0x660f3824, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxdq<sse41>, 0x660f3825, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxbw<sse41>, 0x660f3830, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxbd<sse41>, 0x660f3831, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxbq<sse41>, 0x660f3832, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Word|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxwd<sse41>, 0x660f3833, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxwq<sse41>, 0x660f3834, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxdq<sse41>, 0x660f3835, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmuldq<sse41>, 0x660f3828, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmulld<sse41>, 0x660f3840, <sse41:cpu>, Modrm|<sse41:attr>|<sse41:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxsb<SSE41BW>, 0x660f383c, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxsd<SSE41D>, 0x660f383d, <SSE41D:cpu>, Modrm|<SSE41D:attr>|<SSE41D:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxud<SSE41D>, 0x660f383f, <SSE41D:cpu>, Modrm|<SSE41D:attr>|<SSE41D:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmaxuw<SSE41BW>, 0x660f383e, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminsb<SSE41BW>, 0x660f3838, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminsd<SSE41D>, 0x660f3839, <SSE41D:cpu>, Modrm|<SSE41D:attr>|<SSE41D:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminud<SSE41D>, 0x660f383b, <SSE41D:cpu>, Modrm|<SSE41D:attr>|<SSE41D:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pminuw<SSE41BW>, 0x660f383a, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|<SSE41BW:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmovsxbw<SSE41BW>, 0x660f3820, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxbd<SSE41D>, 0x660f3821, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxbq<SSE41D>, 0x660f3822, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Word|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxwd<SSE41D>, 0x660f3823, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxwq<SSE41D>, 0x660f3824, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovsxdq<SSE41D>, 0x660f3825, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxbw<SSE41BW>, 0x660f3830, <SSE41BW:cpu>, Modrm|<SSE41BW:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxbd<SSE41D>, 0x660f3831, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxbq<SSE41D>, 0x660f3832, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Word|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxwd<SSE41D>, 0x660f3833, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxwq<SSE41D>, 0x660f3834, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmovzxdq<SSE41D>, 0x660f3835, <SSE41D:cpu>, Modrm|<SSE41D:attr>|Disp8MemShift|NoSuf, { Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
pmuldq<SSE41Q>, 0x660f3828, <SSE41Q:cpu>, Modrm|<SSE41Q:attr>|<SSE41Q:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
pmulld<SSE41D>, 0x660f3840, <SSE41D:cpu>, Modrm|<SSE41D:attr>|<SSE41D:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
ptest<sse41>, 0x660f3817, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
roundp<sd><sse41>, 0x660f3a08 | <sd:opc>, <sse41:cpu>, Modrm|<sse41:attr>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
rounds<sd><sse41>, 0x660f3a0a | <sd:opc>, <sse41:cpu>, Modrm|<sse41:scal>|<sse41:vvvv>|NoSuf, { Imm8, <sd:elem>|Unspecified|BaseIndex|RegXMM, RegXMM }
roundpd<SSE41Q>, 0x660f3a09, <SSE41Q:cpu>, Modrm|<SSE41Q:attr>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
roundps<SSE41D>, 0x660f3a08, <SSE41D:cpu>, Modrm|<SSE41D:attr>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
roundsd<SSE41Q>, 0x660f3a0b, <SSE41Q:cpu>, Modrm|<SSE41Q:scal>|<SSE41Q:vvvv>|NoSuf, { Imm8, Qword|Unspecified|BaseIndex|RegXMM, RegXMM }
roundss<SSE41D>, 0x660f3a0a, <SSE41D:cpu>, Modrm|<SSE41D:scal>|<SSE41D:vvvv>|NoSuf, { Imm8, Dword|Unspecified|BaseIndex|RegXMM, RegXMM }
// SSE4.2 instructions.
@ -1465,31 +1560,38 @@ xsaveopt64, 0xfae/6, Xsaveopt&x64, Modrm|NoSuf|Size64|NoEgpr, { Unspecified|Base
// AES instructions.
<aes:cpu:attr:vvvv, $avx:AVX&:Vex128|VexW0|SSE2AVX:VexVVVV, $sse:::>
<AES:cpu:attr, +
$avx:&(AVX|AVX512VL):Vex128|EVex128|VexW0|VexVVVV|Disp8MemShift=4|SSE2AVX, +
$sse::>
aesdec<aes>, 0x660f38de, <aes:cpu>AES, Modrm|<aes:attr>|<aes:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesdeclast<aes>, 0x660f38df, <aes:cpu>AES, Modrm|<aes:attr>|<aes:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesenc<aes>, 0x660f38dc, <aes:cpu>AES, Modrm|<aes:attr>|<aes:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesenclast<aes>, 0x660f38dd, <aes:cpu>AES, Modrm|<aes:attr>|<aes:vvvv>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesdec<AES>, 0x660f38de, AES<AES:cpu>, Modrm|<AES:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesdeclast<AES>, 0x660f38df, AES<AES:cpu>, Modrm|<AES:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesenc<AES>, 0x660f38dc, AES<AES:cpu>, Modrm|<AES:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesenclast<AES>, 0x660f38dd, AES<AES:cpu>, Modrm|<AES:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aesimc<aes>, 0x660f38db, <aes:cpu>AES, Modrm|<aes:attr>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
aeskeygenassist<aes>, 0x660f3adf, <aes:cpu>AES, Modrm|<aes:attr>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
// PCLMULQDQ
<pclmul:cpu:attr, $avx:AVX&:Vex128|VexW0|SSE2AVX|VexVVVV, $sse::>
<pclmul:cpu:attr, +
$avx:&(AVX|AVX512VL):Vex128|EVex128|VexW0|VexVVVV|Disp8MemShift=4|SSE2AVX, +
$sse::>
pclmulqdq<pclmul>, 0x660f3a44, <pclmul:cpu>PCLMULQDQ, Modrm|<pclmul:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pclmullqlqdq<pclmul>, 0x660f3a44/0x00, <pclmul:cpu>PCLMULQDQ, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmulhqlqdq<pclmul>, 0x660f3a44/0x01, <pclmul:cpu>PCLMULQDQ, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmullqhqdq<pclmul>, 0x660f3a44/0x10, <pclmul:cpu>PCLMULQDQ, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmulhqhqdq<pclmul>, 0x660f3a44/0x11, <pclmul:cpu>PCLMULQDQ, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmulqdq<pclmul>, 0x660f3a44, PCLMULQDQ<pclmul:cpu>, Modrm|<pclmul:attr>|NoSuf, { Imm8|Imm8S, RegXMM|Unspecified|BaseIndex, RegXMM }
pclmullqlqdq<pclmul>, 0x660f3a44/0x00, PCLMULQDQ<pclmul:cpu>, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmulhqlqdq<pclmul>, 0x660f3a44/0x01, PCLMULQDQ<pclmul:cpu>, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmullqhqdq<pclmul>, 0x660f3a44/0x10, PCLMULQDQ<pclmul:cpu>, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
pclmulhqhqdq<pclmul>, 0x660f3a44/0x11, PCLMULQDQ<pclmul:cpu>, Modrm|<pclmul:attr>|NoSuf|ImmExt, { RegXMM|Unspecified|BaseIndex, RegXMM }
// GFNI
<gfni:cpu:w0:w1, $avx:AVX&:Vex128|VexW0|SSE2AVX|VexVVVV:Vex128|VexW1|SSE2AVX|VexVVVV, $sse:::>
<gfni:cpu:attr:vexw0:vexw1, +
$avx:&(AVX|AVX512VL):Vex128|EVex128|VexVVVV|Disp8MemShift=4|SSE2AVX:VexW0:VexW1, +
$sse::::>
gf2p8affineqb<gfni>, 0x660f3ace, <gfni:cpu>GFNI, Modrm|<gfni:w1>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
gf2p8affineinvqb<gfni>, 0x660f3acf, <gfni:cpu>GFNI, Modrm|<gfni:w1>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
gf2p8mulb<gfni>, 0x660f38cf, <gfni:cpu>GFNI, Modrm|<gfni:w0>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
gf2p8affineqb<gfni>, 0x660f3ace, GFNI<gfni:cpu>, Modrm|<gfni:attr>|<gfni:vexw1>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
gf2p8affineinvqb<gfni>, 0x660f3acf, GFNI<gfni:cpu>, Modrm|<gfni:attr>|<gfni:vexw1>|NoSuf, { Imm8, RegXMM|Unspecified|BaseIndex, RegXMM }
gf2p8mulb<gfni>, 0x660f38cf, GFNI<gfni:cpu>, Modrm|<gfni:attr>|<gfni:vexw0>|NoSuf, { RegXMM|Unspecified|BaseIndex, RegXMM }
// AVX instructions.

File diff suppressed because it is too large Load diff