Support Intel AVX-IFMA

x86: Support Intel AVX-IFMA

Intel AVX IFMA instructions are marked with CpuVEX_PREFIX, which is
cleared by default.  Without {vex} pseudo prefix, Intel IFMA instructions
are encoded with EVEX prefix.  {vex} pseudo prefix will turn on VEX
encoding for Intel IFMA instructions.

gas/

	* NEWS: Support Intel AVX-IFMA.
	* config/tc-i386.c (cpu_arch): Add avx_ifma.
	* doc/c-i386.texi: Document .avx_ifma.
	* testsuite/gas/i386/avx-ifma.d: New file.
	* testsuite/gas/i386/avx-ifma-intel.d: Likewise.
	* testsuite/gas/i386/avx-ifma.s: Likewise.
	* testsuite/gas/i386/x86-64-avx-ifma.d: Likewise.
	* testsuite/gas/i386/x86-64-avx-ifma-intel.d: Likewise.
	* testsuite/gas/i386/x86-64-avx-ifma.s: Likewise.
	* testsuite/gas/i386/i386.exp: Run AVX IFMA tests.

opcodes/

	* i386-dis.c (PREFIX_VEX_0F38B4): New.
	(PREFIX_VEX_0F38B5): Likewise.
	(VEX_W_0F38B4_P_2): Likewise.
	(VEX_W_0F38B5_P_2): Likewise.
	(prefix_table): Add PREFIX_VEX_0F38B4 and PREFIX_VEX_0F38B5.
	(vex_table): Add VEX_W_0F38B4_P_2 and VEX_W_0F38B5_P_2.
	* i386-dis-evex.h: Fold AVX512IFMA entries to AVX-IFMA.
	* i386-gen.c (cpu_flag_init): Clear the CpuAVX_IFMA bit in
	CPU_UNKNOWN_FLAGS. Add CPU_AVX_IFMA_FLGAS and
	CPU_ANY_AVX_IFMA_FLAGS. Add CpuAVX_IFMA to CPU_AVX2_FLAGS.
	(cpu_flags): Add CpuAVX_IFMA.
	* i386-opc.h (CpuAVX_IFMA): New.
	(i386_cpu_flags): Add cpuavx_ifma.
	* i386-opc.tbl: Add Intel AVX IFMA instructions.
	* i386-init.h: Regenerated.
	* i386-tbl.h: Likewise.

Co-authored-by: Haochen Jiang <haochen.jiang@intel.com>
This commit is contained in:
Hongyu Wang 2022-11-01 10:49:29 +08:00 committed by Cui,Lili
parent e8572cd6aa
commit 4321af3e4d
22 changed files with 4476 additions and 4160 deletions

View file

@ -1,5 +1,7 @@
-*- text -*-
* Add support for Intel AVX-IFMA instructions.
* Add support for Intel PREFETCHI instructions.
* Add support for Intel AMX-FP16 instructions.

View file

@ -1096,6 +1096,7 @@ static const arch_entry cpu_arch[] =
SUBARCH (hreset, HRESET, ANY_HRESET, false),
SUBARCH (avx512_fp16, AVX512_FP16, ANY_AVX512_FP16, false),
SUBARCH (prefetchi, PREFETCHI, PREFETCHI, false),
SUBARCH (avx_ifma, AVX_IFMA, ANY_AVX_IFMA, false),
};
#undef SUBARCH

View file

@ -195,6 +195,7 @@ accept various extension mnemonics. For example,
@code{avx_vnni},
@code{avx512_fp16},
@code{prefetchi},
@code{avx_ifma},
@code{amx_int8},
@code{amx_bf16},
@code{amx_fp16},
@ -828,9 +829,9 @@ prefix which generates REX prefix unconditionally.
@samp{@{nooptimize@}} -- disable instruction size optimization.
@end itemize
Mnemonics of Intel VNNI instructions are encoded with the EVEX prefix
Mnemonics of Intel VNNI/IFMA instructions are encoded with the EVEX prefix
by default. The pseudo @samp{@{vex@}} prefix can be used to encode
mnemonics of Intel VNNI instructions with the VEX prefix.
mnemonics of Intel VNNI/IFMA instructions with the VEX prefix.
@cindex conversion instructions, i386
@cindex i386 conversion instructions
@ -1488,7 +1489,7 @@ supported on the CPU specified. The choices for @var{cpu_type} are:
@item @samp{.avx512_bitalg} @tab @samp{.avx512_bf16} @tab @samp{.avx512_vp2intersect}
@item @samp{.tdx} @tab @samp{.avx_vnni} @tab @samp{.avx512_fp16}
@item @samp{.clwb} @tab @samp{.rdpid} @tab @samp{.ptwrite} @tab @samp{.ibt}
@item @samp{.prefetchi}
@item @samp{.prefetchi} @tab @samp{.avx_ifma}
@item @samp{.wbnoinvd} @tab @samp{.pconfig} @tab @samp{.waitpkg} @tab @samp{.cldemote}
@item @samp{.shstk} @tab @samp{.gfni} @tab @samp{.vaes} @tab @samp{.vpclmulqdq}
@item @samp{.movdiri} @tab @samp{.movdir64b} @tab @samp{.enqcmd} @tab @samp{.tsxldtrk}

View file

@ -0,0 +1,37 @@
#as:
#objdump: -dw -Mintel
#name: i386 AVX IFMA insns (Intel disassembly)
#source: avx-ifma.s
.*: +file format .*
Disassembly of section .text:
0+ <_start>:
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b5 d2[ ]*vpmadd52huq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b5 d2[ ]*vpmadd52huq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b5 d2[ ]*\{vex\} vpmadd52huq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b5 11[ ]*\{vex\} vpmadd52huq xmm2,xmm4,XMMWORD PTR \[ecx\]
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b5 d2[ ]*vpmadd52huq ymm2,ymm4,ymm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b5 d2[ ]*vpmadd52huq ymm2,ymm4,ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b5 d2[ ]*\{vex\} vpmadd52huq ymm2,ymm4,ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b5 11[ ]*\{vex\} vpmadd52huq ymm2,ymm4,YMMWORD PTR \[ecx\]
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b4 d2[ ]*vpmadd52luq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b4 d2[ ]*vpmadd52luq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b4 d2[ ]*\{vex\} vpmadd52luq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b4 11[ ]*\{vex\} vpmadd52luq xmm2,xmm4,XMMWORD PTR \[ecx\]
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b4 d2[ ]*vpmadd52luq ymm2,ymm4,ymm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b4 d2[ ]*vpmadd52luq ymm2,ymm4,ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b4 d2[ ]*\{vex\} vpmadd52luq ymm2,ymm4,ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b4 11[ ]*\{vex\} vpmadd52luq ymm2,ymm4,YMMWORD PTR \[ecx\]
[ ]*[a-f0-9]+:[ ]*62 f2 fd 48 b5 c0[ ]*vpmadd52huq zmm0,zmm0,zmm0
[ ]*[a-f0-9]+:[ ]*c4 e2 fd b5 c0[ ]*\{vex\} vpmadd52huq ymm0,ymm0,ymm0
[ ]*[a-f0-9]+:[ ]*c4 e2 f9 b5 c0[ ]*\{vex\} vpmadd52huq xmm0,xmm0,xmm0
[ ]*[a-f0-9]+:[ ]*c4 e2 fd b5 c0[ ]*\{vex\} vpmadd52huq ymm0,ymm0,ymm0
[ ]*[a-f0-9]+:[ ]*c4 e2 f9 b5 c0[ ]*\{vex\} vpmadd52huq xmm0,xmm0,xmm0
[ ]*[a-f0-9]+:[ ]*c4 e2 fd b5 c0[ ]*\{vex\} vpmadd52huq ymm0,ymm0,ymm0
[ ]*[a-f0-9]+:[ ]*c4 e2 f9 b5 c0[ ]*\{vex\} vpmadd52huq xmm0,xmm0,xmm0
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b5 d2[ ]*vpmadd52huq xmm2,xmm4,xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b5 d2[ ]*vpmadd52huq ymm2,ymm4,ymm2
#pass

View file

@ -0,0 +1,3 @@
.* Assembler messages:
.*:6: Error: unsupported .* `vpmadd52huq'
.*:7: Error: operand .* `vpmadd52huq'

View file

@ -0,0 +1,7 @@
# Check illegal in AVXIFMA instructions
.text
.arch .noavx512ifma
_start:
vpmadd52huq %xmm2, %xmm4, %xmm2{%k6}
vpmadd52huq %zmm2, %zmm4, %zmm2

View file

@ -0,0 +1,37 @@
#as:
#objdump: -dw
#name: i386 AVX IFMA insns
#source: avx-ifma.s
.*: +file format .*
Disassembly of section .text:
0+ <_start>:
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b5 d2[ ]*vpmadd52huq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b5 d2[ ]*vpmadd52huq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b5 d2[ ]*\{vex\} vpmadd52huq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b5 11[ ]*\{vex\} vpmadd52huq \(%ecx\),%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b5 d2[ ]*vpmadd52huq %ymm2,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b5 d2[ ]*vpmadd52huq %ymm2,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b5 d2[ ]*\{vex\} vpmadd52huq %ymm2,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b5 11[ ]*\{vex\} vpmadd52huq \(%ecx\),%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b4 d2[ ]*vpmadd52luq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b4 d2[ ]*vpmadd52luq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b4 d2[ ]*\{vex\} vpmadd52luq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b4 11[ ]*\{vex\} vpmadd52luq \(%ecx\),%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b4 d2[ ]*vpmadd52luq %ymm2,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b4 d2[ ]*vpmadd52luq %ymm2,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b4 d2[ ]*\{vex\} vpmadd52luq %ymm2,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b4 11[ ]*\{vex\} vpmadd52luq \(%ecx\),%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 f2 fd 48 b5 c0[ ]*vpmadd52huq %zmm0,%zmm0,%zmm0
[ ]*[a-f0-9]+:[ ]*c4 e2 fd b5 c0[ ]*\{vex\} vpmadd52huq %ymm0,%ymm0,%ymm0
[ ]*[a-f0-9]+:[ ]*c4 e2 f9 b5 c0[ ]*\{vex\} vpmadd52huq %xmm0,%xmm0,%xmm0
[ ]*[a-f0-9]+:[ ]*c4 e2 fd b5 c0[ ]*\{vex\} vpmadd52huq %ymm0,%ymm0,%ymm0
[ ]*[a-f0-9]+:[ ]*c4 e2 f9 b5 c0[ ]*\{vex\} vpmadd52huq %xmm0,%xmm0,%xmm0
[ ]*[a-f0-9]+:[ ]*c4 e2 fd b5 c0[ ]*\{vex\} vpmadd52huq %ymm0,%ymm0,%ymm0
[ ]*[a-f0-9]+:[ ]*c4 e2 f9 b5 c0[ ]*\{vex\} vpmadd52huq %xmm0,%xmm0,%xmm0
[ ]*[a-f0-9]+:[ ]*62 f2 dd 08 b5 d2[ ]*vpmadd52huq %xmm2,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 f2 dd 28 b5 d2[ ]*vpmadd52huq %ymm2,%ymm4,%ymm2
#pass

View file

@ -0,0 +1,40 @@
.allow_index_reg
.macro test_insn mnemonic
\mnemonic %xmm2, %xmm4, %xmm2
{evex} \mnemonic %xmm2, %xmm4, %xmm2
{vex} \mnemonic %xmm2, %xmm4, %xmm2
{vex} \mnemonic (%ecx), %xmm4, %xmm2
\mnemonic %ymm2, %ymm4, %ymm2
{evex} \mnemonic %ymm2, %ymm4, %ymm2
{vex} \mnemonic %ymm2, %ymm4, %ymm2
{vex} \mnemonic (%ecx), %ymm4, %ymm2
.endm
.text
_start:
test_insn vpmadd52huq
test_insn vpmadd52luq
.arch .noavx512vl
vpmadd52huq %zmm0, %zmm0, %zmm0
vpmadd52huq %ymm0, %ymm0, %ymm0
vpmadd52huq %xmm0, %xmm0, %xmm0
.arch default
.arch .noavx512ifma
vpmadd52huq %ymm0, %ymm0, %ymm0
vpmadd52huq %xmm0, %xmm0, %xmm0
.arch default
.arch .noavx512f
vpmadd52huq %ymm0, %ymm0, %ymm0
vpmadd52huq %xmm0, %xmm0, %xmm0
.arch default
.arch .avx_ifma
vpmadd52huq %xmm2, %xmm4, %xmm2
vpmadd52huq %ymm2, %ymm4, %ymm2

View file

@ -474,6 +474,9 @@ if [gas_32_check] then {
run_list_test "avx512_bf16_vl-inval"
run_dump_test "avx-vnni"
run_list_test "avx-vnni-inval"
run_dump_test "avx-ifma"
run_dump_test "avx-ifma-intel"
run_list_test "avx-ifma-inval"
run_list_test "sg"
run_dump_test "clzero"
run_dump_test "invlpgb"
@ -1142,6 +1145,9 @@ if [gas_64_check] then {
run_dump_test "x86-64-amx-fp16"
run_dump_test "x86-64-amx-fp16-intel"
run_dump_test "x86-64-amx-fp16-bad"
run_dump_test "x86-64-avx-ifma"
run_dump_test "x86-64-avx-ifma-intel"
run_list_test "x86-64-avx-ifma-inval"
run_dump_test "x86-64-clzero"
run_dump_test "x86-64-mwaitx-bdver4"
run_list_test "x86-64-mwaitx-reg"

View file

@ -37,9 +37,9 @@
.*:120: Error: .*not supported.*
.*:121: Error: .*not supported.*
.*:122: Error: .*not supported.*
.*:126: Error: .*not supported.*
.*:127: Error: .*not supported.*
.*:128: Error: .*not supported.*
.*:126: Error: .*operand .*
.*:127: Error: .*unsupported .*
.*:128: Error: .*unsupported .*
.*:135: Error: .*operand size mismatch.*
.*:136: Error: .*unsupported masking.*
.*:137: Error: .*unsupported masking.*
@ -50,9 +50,9 @@
.*:142: Error: .*not supported.*
.*:143: Error: .*not supported.*
.*:144: Error: .*not supported.*
.*:148: Error: .*not supported.*
.*:149: Error: .*not supported.*
.*:150: Error: .*not supported.*
.*:148: Error: .*operand .*
.*:149: Error: .*unsupported .*
.*:150: Error: .*unsupported .*
.*:151: Error: .*not supported.*
.*:157: Error: .*operand size mismatch.*
.*:158: Error: .*unsupported masking.*
@ -64,9 +64,9 @@
.*:164: Error: .*not supported.*
.*:165: Error: .*not supported.*
.*:166: Error: .*not supported.*
.*:170: Error: .*not supported.*
.*:171: Error: .*not supported.*
.*:172: Error: .*not supported.*
.*:170: Error: .*operand .*
.*:171: Error: .*unsupported .*
.*:172: Error: .*unsupported .*
.*:173: Error: .*not supported.*
.*:174: Error: .*not supported.*
.*:175: Error: .*not supported.*
@ -84,9 +84,9 @@
.*:189: Error: .*bad register name.*
.*:190: Error: .*unknown vector operation.*
.*:191: Error: .*unknown vector operation.*
.*:192: Error: .*not supported.*
.*:193: Error: .*not supported.*
.*:194: Error: .*not supported.*
.*:192: Error: .*bad register name.*
.*:193: Error: .*unknown vector operation.*
.*:194: Error: .*unknown vector operation.*
.*:195: Error: .*not supported.*
.*:196: Error: .*not supported.*
.*:197: Error: .*not supported.*

View file

@ -0,0 +1,34 @@
#as:
#objdump: -dw -Mintel
#name: x86-64 AVX IFMA insns (Intel disassembly)
#source: x86-64-avx-ifma.s
.*: +file format .*
Disassembly of section .text:
0+ <_start>:
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b5 d4[ ]*vpmadd52huq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b5 d4[ ]*vpmadd52huq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*c4 c2 d9 b5 d4[ ]*\{vex\} vpmadd52huq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b5 11[ ]*\{vex\} vpmadd52huq xmm2,xmm4,XMMWORD PTR \[rcx\]
[ ]*[a-f0-9]+:[ ]*62 b2 dd 08 b5 d6[ ]*vpmadd52huq xmm2,xmm4,xmm22
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b5 d4[ ]*vpmadd52huq ymm2,ymm4,ymm12
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b5 d4[ ]*vpmadd52huq ymm2,ymm4,ymm12
[ ]*[a-f0-9]+:[ ]*c4 c2 dd b5 d4[ ]*\{vex\} vpmadd52huq ymm2,ymm4,ymm12
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b5 11[ ]*\{vex\} vpmadd52huq ymm2,ymm4,YMMWORD PTR \[rcx\]
[ ]*[a-f0-9]+:[ ]*62 b2 dd 28 b5 d6[ ]*vpmadd52huq ymm2,ymm4,ymm22
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b4 d4[ ]*vpmadd52luq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b4 d4[ ]*vpmadd52luq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*c4 c2 d9 b4 d4[ ]*\{vex\} vpmadd52luq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b4 11[ ]*\{vex\} vpmadd52luq xmm2,xmm4,XMMWORD PTR \[rcx\]
[ ]*[a-f0-9]+:[ ]*62 b2 dd 08 b4 d6[ ]*vpmadd52luq xmm2,xmm4,xmm22
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b4 d4[ ]*vpmadd52luq ymm2,ymm4,ymm12
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b4 d4[ ]*vpmadd52luq ymm2,ymm4,ymm12
[ ]*[a-f0-9]+:[ ]*c4 c2 dd b4 d4[ ]*\{vex\} vpmadd52luq ymm2,ymm4,ymm12
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b4 11[ ]*\{vex\} vpmadd52luq ymm2,ymm4,YMMWORD PTR \[rcx\]
[ ]*[a-f0-9]+:[ ]*62 b2 dd 28 b4 d6[ ]*vpmadd52luq ymm2,ymm4,ymm22
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b5 d4[ ]*vpmadd52huq xmm2,xmm4,xmm12
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b5 d4[ ]*vpmadd52huq ymm2,ymm4,ymm12
#pass

View file

@ -0,0 +1,4 @@
.* Assembler messages:
.*:6: Error: unsupported .* `vpmadd52huq'
.*:7: Error: unsupported .* `vpmadd52huq'
.*:8: Error: operand .* `vpmadd52huq'

View file

@ -0,0 +1,8 @@
# Check illegal in AVXIFMA instructions
.text
.arch .noavx512ifma
_start:
vpmadd52huq %xmm2, %xmm4, %xmm2{%k6}
vpmadd52huq %xmm22, %xmm4, %xmm2{%k1}
vpmadd52huq %zmm2, %zmm4, %zmm2

View file

@ -0,0 +1,34 @@
#as:
#objdump: -dw
#name: x86-64 AVX IFMA insns
#source: x86-64-avx-ifma.s
.*: +file format .*
Disassembly of section .text:
0+ <_start>:
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b5 d4[ ]*vpmadd52huq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b5 d4[ ]*vpmadd52huq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 c2 d9 b5 d4[ ]*\{vex\} vpmadd52huq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b5 11[ ]*\{vex\} vpmadd52huq \(%rcx\),%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 b2 dd 08 b5 d6[ ]*vpmadd52huq %xmm22,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b5 d4[ ]*vpmadd52huq %ymm12,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b5 d4[ ]*vpmadd52huq %ymm12,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 c2 dd b5 d4[ ]*\{vex\} vpmadd52huq %ymm12,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b5 11[ ]*\{vex\} vpmadd52huq \(%rcx\),%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 b2 dd 28 b5 d6[ ]*vpmadd52huq %ymm22,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b4 d4[ ]*vpmadd52luq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b4 d4[ ]*vpmadd52luq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 c2 d9 b4 d4[ ]*\{vex\} vpmadd52luq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*c4 e2 d9 b4 11[ ]*\{vex\} vpmadd52luq \(%rcx\),%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 b2 dd 08 b4 d6[ ]*vpmadd52luq %xmm22,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b4 d4[ ]*vpmadd52luq %ymm12,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b4 d4[ ]*vpmadd52luq %ymm12,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 c2 dd b4 d4[ ]*\{vex\} vpmadd52luq %ymm12,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*c4 e2 dd b4 11[ ]*\{vex\} vpmadd52luq \(%rcx\),%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 b2 dd 28 b4 d6[ ]*vpmadd52luq %ymm22,%ymm4,%ymm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 08 b5 d4[ ]*vpmadd52huq %xmm12,%xmm4,%xmm2
[ ]*[a-f0-9]+:[ ]*62 d2 dd 28 b5 d4[ ]*vpmadd52huq %ymm12,%ymm4,%ymm2
#pass

View file

@ -0,0 +1,23 @@
.allow_index_reg
.macro test_insn mnemonic
\mnemonic %xmm12, %xmm4, %xmm2
{evex} \mnemonic %xmm12, %xmm4, %xmm2
{vex} \mnemonic %xmm12, %xmm4, %xmm2
{vex} \mnemonic (%rcx), %xmm4, %xmm2
\mnemonic %xmm22, %xmm4, %xmm2
\mnemonic %ymm12, %ymm4, %ymm2
{evex} \mnemonic %ymm12, %ymm4, %ymm2
{vex} \mnemonic %ymm12, %ymm4, %ymm2
{vex} \mnemonic (%rcx), %ymm4, %ymm2
\mnemonic %ymm22, %ymm4, %ymm2
.endm
.text
_start:
test_insn vpmadd52huq
test_insn vpmadd52luq
.arch .avx_ifma
vpmadd52huq %xmm12, %xmm4, %xmm2
vpmadd52huq %ymm12, %ymm4, %ymm2

View file

@ -495,8 +495,8 @@ static const struct dis386 evex_table[][256] = {
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ "vpmadd52luq", { XM, Vex, EXx }, PREFIX_DATA },
{ "vpmadd52huq", { XM, Vex, EXx }, PREFIX_DATA },
{ VEX_W_TABLE (VEX_W_0F38B4) },
{ VEX_W_TABLE (VEX_W_0F38B5) },
{ "%XEvfmaddsub231p%XW", { XM, Vex, EXx, EXxEVexR }, PREFIX_DATA },
{ "%XEvfmsubadd231p%XW", { XM, Vex, EXx, EXxEVexR }, PREFIX_DATA },
/* B8 */

View file

@ -1536,6 +1536,8 @@ enum
VEX_W_0F385E_X86_64_P_3,
VEX_W_0F3878,
VEX_W_0F3879,
VEX_W_0F38B4,
VEX_W_0F38B5,
VEX_W_0F38CF,
VEX_W_0F3A00_L_1,
VEX_W_0F3A01_L_1,
@ -6334,8 +6336,8 @@ static const struct dis386 vex_table[][256] = {
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ Bad_Opcode },
{ VEX_W_TABLE (VEX_W_0F38B4) },
{ VEX_W_TABLE (VEX_W_0F38B5) },
{ "vfmaddsub231p%XW", { XM, Vex, EXx }, PREFIX_DATA },
{ "vfmsubadd231p%XW", { XM, Vex, EXx }, PREFIX_DATA },
/* b8 */
@ -7649,6 +7651,16 @@ static const struct dis386 vex_w_table[][2] = {
/* VEX_W_0F3879 */
{ "%XEvpbroadcastw", { XM, EXw }, PREFIX_DATA },
},
{
/* VEX_W_0F38B4 */
{ Bad_Opcode },
{ "%XVvpmadd52luq", { XM, Vex, EXx }, PREFIX_DATA },
},
{
/* VEX_W_0F38B5 */
{ Bad_Opcode },
{ "%XVvpmadd52huq", { XM, Vex, EXx }, PREFIX_DATA },
},
{
/* VEX_W_0F38CF */
{ "%XEvgf2p8mulb", { XM, Vex, EXx }, PREFIX_DATA },

View file

@ -247,6 +247,8 @@ static initializer cpu_flag_init[] =
"CPU_AVX512BW_FLAGS|CpuAVX512_FP16" },
{ "CPU_PREFETCHI_FLAGS",
"CpuPREFETCHI"},
{ "CPU_AVX_IFMA_FLAGS",
"CPU_AVX2_FLAGS|CpuAVX_IFMA" },
{ "CPU_IAMCU_FLAGS",
"Cpu186|Cpu286|Cpu386|Cpu486|Cpu586|CpuIAMCU" },
{ "CPU_ADX_FLAGS",
@ -374,7 +376,7 @@ static initializer cpu_flag_init[] =
{ "CPU_ANY_AVX_FLAGS",
"CPU_ANY_AVX2_FLAGS|CpuF16C|CpuFMA|CpuFMA4|CpuXOP|CpuAVX" },
{ "CPU_ANY_AVX2_FLAGS",
"CPU_ANY_AVX512F_FLAGS|CpuAVX2|CpuAVX_VNNI" },
"CPU_ANY_AVX512F_FLAGS|CpuAVX2|CpuAVX_VNNI|CpuAVX_IFMA" },
{ "CPU_ANY_AVX512F_FLAGS",
"CpuAVX512F|CpuAVX512CD|CpuAVX512ER|CpuAVX512PF|CpuAVX512DQ|CPU_ANY_AVX512BW_FLAGS|CpuAVX512VL|CpuAVX512IFMA|CpuAVX512VBMI|CpuAVX512_4FMAPS|CpuAVX512_4VNNIW|CpuAVX512_VPOPCNTDQ|CpuAVX512_VBMI2|CpuAVX512_VNNI|CpuAVX512_BITALG|CpuAVX512_BF16|CpuAVX512_VP2INTERSECT" },
{ "CPU_ANY_AVX512CD_FLAGS",
@ -443,6 +445,8 @@ static initializer cpu_flag_init[] =
"CpuHRESET" },
{ "CPU_ANY_AVX512_FP16_FLAGS",
"CpuAVX512_FP16" },
{ "CPU_ANY_AVX_IFMA_FLAGS",
"CpuAVX_IFMA" },
};
static initializer operand_type_init[] =
@ -643,6 +647,7 @@ static bitfield cpu_flags[] =
BITFIELD (CpuAVX_VNNI),
BITFIELD (CpuAVX512_FP16),
BITFIELD (CpuPREFETCHI),
BITFIELD (CpuAVX_IFMA),
BITFIELD (CpuMWAITX),
BITFIELD (CpuCLZERO),
BITFIELD (CpuOSPKE),

File diff suppressed because it is too large Load diff

View file

@ -211,6 +211,8 @@ enum
CpuAVX512_FP16,
/* PREFETCHI instruction required */
CpuPREFETCHI,
/* Intel AVX IFMA Instructions support required. */
CpuAVX_IFMA,
/* mwaitx instruction required */
CpuMWAITX,
/* Clzero instruction required */
@ -393,6 +395,7 @@ typedef union i386_cpu_flags
unsigned int cpuavx_vnni:1;
unsigned int cpuavx512_fp16:1;
unsigned int cpuprefetchi:1;
unsigned int cpuavx_ifma:1;
unsigned int cpumwaitx:1;
unsigned int cpuclzero:1;
unsigned int cpuospke:1;

View file

@ -2811,6 +2811,13 @@ vpmadd52luq, 0x66B4, None, CpuAVX512IFMA, Modrm|Masking=3|Space0F38|VexVVVV=1|Ve
// AVX512IFMA instructions end
// AVX-IFMA instructions.
vpmadd52huq, 0x66B5, None, CpuAVX_IFMA, Modrm|Vex|Space0F38|VexVVVV|VexW1|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
vpmadd52luq, 0x66B4, None, CpuAVX_IFMA, Modrm|Vex|Space0F38|VexVVVV|VexW1|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|Unspecified|BaseIndex, RegXMM|RegYMM, RegXMM|RegYMM }
// AVX-IFMA instructions end.
// AVX512VBMI instructions
vpmultishiftqb, 0x6683, None, CpuAVX512VBMI, Modrm|Masking=3|Space0F38|VexVVVV=1|VexW=2|Broadcast|Disp8ShiftVL|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }

File diff suppressed because it is too large Load diff