Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[X86][AVX10.2] Include changes for COMX and VGETEXP from rev. 2 #132824

Merged
merged 1 commit into from
Mar 25, 2025
Merged

[X86][AVX10.2] Include changes for COMX and VGETEXP from rev. 2 #132824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions llvm/lib/Target/X86/X86InstrAVX10.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1141,7 +1141,7 @@ defm VRSQRT : avx10_fp14_bf16<0x4E, "vrsqrt", X86rsqrt14, SchedWriteFRsqrt>,
defm VRCP : avx10_fp14_bf16<0x4C, "vrcp", X86rcp14, SchedWriteFRcp>,
T_MAP6, PS, EVEX_CD8<16, CD8VF>;
defm VGETEXP : avx10_fp14_bf16<0x42, "vgetexp", X86fgetexp, SchedWriteFRnd>,
T_MAP5, EVEX_CD8<16, CD8VF>;
T_MAP6, PS, EVEX_CD8<16, CD8VF>;

// VSCALEFBF16
multiclass avx10_fp_scalef_bf16<bits<8> opc, string OpcodeStr,
Expand Down Expand Up @@ -1338,31 +1338,31 @@ multiclass avx10_com_ef_int<bits<8> Opc, X86VectorVTInfo _, SDNode OpNode,
let Defs = [EFLAGS], Uses = [MXCSR], Predicates = [HasAVX10_2] in {
defm VUCOMXSDZ : avx10_com_ef<0x2e, FR64X, f64, X86ucomi512,
"vucomxsd", f64mem, loadf64, SSEPackedDouble>,
TB, XS, VEX_LIG, REX_W, EVEX_CD8<64, CD8VT1>;
TB, XD, VEX_LIG, REX_W, EVEX_CD8<64, CD8VT1>;
defm VUCOMXSHZ : avx10_com_ef<0x2e, FR16X, f16, X86ucomi512,
"vucomxsh", f16mem, loadf16, SSEPackedSingle>,
T_MAP5, XD, EVEX_CD8<16, CD8VT1>;
T_MAP5, XS, EVEX_CD8<16, CD8VT1>;
defm VUCOMXSSZ : avx10_com_ef<0x2e, FR32X, f32, X86ucomi512,
"vucomxss", f32mem, loadf32, SSEPackedSingle>,
TB, XD, VEX_LIG, EVEX_CD8<32, CD8VT1>;
TB, XS, VEX_LIG, EVEX_CD8<32, CD8VT1>;
defm VCOMXSDZ : avx10_com_ef_int<0x2f, v2f64x_info, X86comi512,
"vcomxsd", SSEPackedDouble>,
TB, XS, VEX_LIG, REX_W, EVEX_CD8<64, CD8VT1>;
TB, XD, VEX_LIG, REX_W, EVEX_CD8<64, CD8VT1>;
defm VCOMXSHZ : avx10_com_ef_int<0x2f, v8f16x_info, X86comi512,
"vcomxsh", SSEPackedSingle>,
T_MAP5, XD, EVEX_CD8<16, CD8VT1>;
T_MAP5, XS, EVEX_CD8<16, CD8VT1>;
defm VCOMXSSZ : avx10_com_ef_int<0x2f, v4f32x_info, X86comi512,
"vcomxss", SSEPackedSingle>,
TB, XD, VEX_LIG, EVEX_CD8<32, CD8VT1>;
TB, XS, VEX_LIG, EVEX_CD8<32, CD8VT1>;
defm VUCOMXSDZ : avx10_com_ef_int<0x2e, v2f64x_info, X86ucomi512,
"vucomxsd", SSEPackedDouble>,
TB, XS, VEX_LIG, REX_W, EVEX_CD8<64, CD8VT1>;
TB, XD, VEX_LIG, REX_W, EVEX_CD8<64, CD8VT1>;
defm VUCOMXSHZ : avx10_com_ef_int<0x2e, v8f16x_info, X86ucomi512,
"vucomxsh", SSEPackedSingle>,
T_MAP5, XD, EVEX_CD8<16, CD8VT1>;
T_MAP5, XS, EVEX_CD8<16, CD8VT1>;
defm VUCOMXSSZ : avx10_com_ef_int<0x2e, v4f32x_info, X86ucomi512,
"vucomxss", SSEPackedSingle>,
TB, XD, VEX_LIG, EVEX_CD8<32, CD8VT1>;
TB, XS, VEX_LIG, EVEX_CD8<32, CD8VT1>;
}

//-------------------------------------------------
Expand Down
4 changes: 2 additions & 2 deletions llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,15 +164,15 @@ define <32 x bfloat>@test_int_x86_avx512_mask_getexp_bf16_512(<32 x bfloat> %x0,
; X64-LABEL: test_int_x86_avx512_mask_getexp_bf16_512:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vgetexpbf16 %zmm0, %zmm0 # encoding: [0x62,0xf5,0x7d,0x48,0x42,0xc0]
; X64-NEXT: vgetexpbf16 %zmm0, %zmm0 # encoding: [0x62,0xf6,0x7c,0x48,0x42,0xc0]
; X64-NEXT: vmovdqu16 %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf1,0xff,0x49,0x6f,0xc8]
; X64-NEXT: vaddbf16 %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf5,0x75,0x48,0x58,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
;
; X86-LABEL: test_int_x86_avx512_mask_getexp_bf16_512:
; X86: # %bb.0:
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vgetexpbf16 %zmm0, %zmm0 # encoding: [0x62,0xf5,0x7d,0x48,0x42,0xc0]
; X86-NEXT: vgetexpbf16 %zmm0, %zmm0 # encoding: [0x62,0xf6,0x7c,0x48,0x42,0xc0]
; X86-NEXT: vmovdqu16 %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf1,0xff,0x49,0x6f,0xc8]
; X86-NEXT: vaddbf16 %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf5,0x75,0x48,0x58,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
Expand Down
20 changes: 10 additions & 10 deletions llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -333,7 +333,7 @@ declare <16 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.256(<16 x bfloat>, <16 x
define <8 x bfloat>@test_int_x86_avx512_getexp_bf16_128(<8 x bfloat> %x0) {
; CHECK-LABEL: test_int_x86_avx512_getexp_bf16_128:
; CHECK: # %bb.0:
; CHECK-NEXT: vgetexpbf16 %xmm0, %xmm0 # encoding: [0x62,0xf5,0x7d,0x08,0x42,0xc0]
; CHECK-NEXT: vgetexpbf16 %xmm0, %xmm0 # encoding: [0x62,0xf6,0x7c,0x08,0x42,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.128(<8 x bfloat> %x0, <8 x bfloat> zeroinitializer, i8 -1)
ret <8 x bfloat> %res
Expand All @@ -343,14 +343,14 @@ define <8 x bfloat>@test_int_x86_avx512_mask_getexp_bf16_128(<8 x bfloat> %x0, <
; X64-LABEL: test_int_x86_avx512_mask_getexp_bf16_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vgetexpbf16 %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf5,0x7d,0x09,0x42,0xc8]
; X64-NEXT: vgetexpbf16 %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf6,0x7c,0x09,0x42,0xc8]
; X64-NEXT: vmovaps %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf8,0x28,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
;
; X86-LABEL: test_int_x86_avx512_mask_getexp_bf16_128:
; X86: # %bb.0:
; X86-NEXT: kmovb {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vgetexpbf16 %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf5,0x7d,0x09,0x42,0xc8]
; X86-NEXT: vgetexpbf16 %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf6,0x7c,0x09,0x42,0xc8]
; X86-NEXT: vmovaps %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf8,0x28,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
%res = call <8 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.128(<8 x bfloat> %x0, <8 x bfloat> %x1, i8 %x2)
Expand All @@ -361,13 +361,13 @@ define <8 x bfloat>@test_int_x86_avx512_maskz_getexp_bf16_128(<8 x bfloat> %x0,
; X64-LABEL: test_int_x86_avx512_maskz_getexp_bf16_128:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vgetexpbf16 %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf5,0x7d,0x89,0x42,0xc0]
; X64-NEXT: vgetexpbf16 %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf6,0x7c,0x89,0x42,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
;
; X86-LABEL: test_int_x86_avx512_maskz_getexp_bf16_128:
; X86: # %bb.0:
; X86-NEXT: kmovb {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT: vgetexpbf16 %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf5,0x7d,0x89,0x42,0xc0]
; X86-NEXT: vgetexpbf16 %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf6,0x7c,0x89,0x42,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
%res = call <8 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.128(<8 x bfloat> %x0, <8 x bfloat> zeroinitializer, i8 %x2)
ret <8 x bfloat> %res
Expand All @@ -376,7 +376,7 @@ define <8 x bfloat>@test_int_x86_avx512_maskz_getexp_bf16_128(<8 x bfloat> %x0,
define <16 x bfloat>@test_int_x86_avx512_getexp_bf16_256(<16 x bfloat> %x0) {
; CHECK-LABEL: test_int_x86_avx512_getexp_bf16_256:
; CHECK: # %bb.0:
; CHECK-NEXT: vgetexpbf16 %ymm0, %ymm0 # encoding: [0x62,0xf5,0x7d,0x28,0x42,0xc0]
; CHECK-NEXT: vgetexpbf16 %ymm0, %ymm0 # encoding: [0x62,0xf6,0x7c,0x28,0x42,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.256(<16 x bfloat> %x0, <16 x bfloat> zeroinitializer, i16 -1)
ret <16 x bfloat> %res
Expand All @@ -386,14 +386,14 @@ define <16 x bfloat>@test_int_x86_avx512_mask_getexp_bf16_256(<16 x bfloat> %x0,
; X64-LABEL: test_int_x86_avx512_mask_getexp_bf16_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vgetexpbf16 %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf5,0x7d,0x29,0x42,0xc8]
; X64-NEXT: vgetexpbf16 %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf6,0x7c,0x29,0x42,0xc8]
; X64-NEXT: vmovaps %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfc,0x28,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
;
; X86-LABEL: test_int_x86_avx512_mask_getexp_bf16_256:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vgetexpbf16 %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf5,0x7d,0x29,0x42,0xc8]
; X86-NEXT: vgetexpbf16 %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf6,0x7c,0x29,0x42,0xc8]
; X86-NEXT: vmovaps %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfc,0x28,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
%res = call <16 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.256(<16 x bfloat> %x0, <16 x bfloat> %x1, i16 %x2)
Expand All @@ -404,13 +404,13 @@ define <16 x bfloat>@test_int_x86_avx512_maskz_getexp_bf16_256(<16 x bfloat> %x0
; X64-LABEL: test_int_x86_avx512_maskz_getexp_bf16_256:
; X64: # %bb.0:
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT: vgetexpbf16 %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf5,0x7d,0xa9,0x42,0xc0]
; X64-NEXT: vgetexpbf16 %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf6,0x7c,0xa9,0x42,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
;
; X86-LABEL: test_int_x86_avx512_maskz_getexp_bf16_256:
; X86: # %bb.0:
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT: vgetexpbf16 %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf5,0x7d,0xa9,0x42,0xc0]
; X86-NEXT: vgetexpbf16 %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf6,0x7c,0xa9,0x42,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
%res = call <16 x bfloat> @llvm.x86.avx10.mask.getexp.bf16.256(<16 x bfloat> %x0, <16 x bfloat> zeroinitializer, i16 %x2)
ret <16 x bfloat> %res
Expand Down
54 changes: 27 additions & 27 deletions llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1719,111 +1719,111 @@

# ATT: vgetexpbf16 %xmm3, %xmm2
# INTEL: vgetexpbf16 xmm2, xmm3
0x62,0xf5,0x7d,0x08,0x42,0xd3
0x62,0xf6,0x7c,0x08,0x42,0xd3

# ATT: vgetexpbf16 %xmm3, %xmm2 {%k7}
# INTEL: vgetexpbf16 xmm2 {k7}, xmm3
0x62,0xf5,0x7d,0x0f,0x42,0xd3
0x62,0xf6,0x7c,0x0f,0x42,0xd3

# ATT: vgetexpbf16 %xmm3, %xmm2 {%k7} {z}
# INTEL: vgetexpbf16 xmm2 {k7} {z}, xmm3
0x62,0xf5,0x7d,0x8f,0x42,0xd3
0x62,0xf6,0x7c,0x8f,0x42,0xd3

# ATT: vgetexpbf16 %zmm3, %zmm2
# INTEL: vgetexpbf16 zmm2, zmm3
0x62,0xf5,0x7d,0x48,0x42,0xd3
0x62,0xf6,0x7c,0x48,0x42,0xd3

# ATT: vgetexpbf16 %zmm3, %zmm2 {%k7}
# INTEL: vgetexpbf16 zmm2 {k7}, zmm3
0x62,0xf5,0x7d,0x4f,0x42,0xd3
0x62,0xf6,0x7c,0x4f,0x42,0xd3

# ATT: vgetexpbf16 %zmm3, %zmm2 {%k7} {z}
# INTEL: vgetexpbf16 zmm2 {k7} {z}, zmm3
0x62,0xf5,0x7d,0xcf,0x42,0xd3
0x62,0xf6,0x7c,0xcf,0x42,0xd3

# ATT: vgetexpbf16 %ymm3, %ymm2
# INTEL: vgetexpbf16 ymm2, ymm3
0x62,0xf5,0x7d,0x28,0x42,0xd3
0x62,0xf6,0x7c,0x28,0x42,0xd3

# ATT: vgetexpbf16 %ymm3, %ymm2 {%k7}
# INTEL: vgetexpbf16 ymm2 {k7}, ymm3
0x62,0xf5,0x7d,0x2f,0x42,0xd3
0x62,0xf6,0x7c,0x2f,0x42,0xd3

# ATT: vgetexpbf16 %ymm3, %ymm2 {%k7} {z}
# INTEL: vgetexpbf16 ymm2 {k7} {z}, ymm3
0x62,0xf5,0x7d,0xaf,0x42,0xd3
0x62,0xf6,0x7c,0xaf,0x42,0xd3

# ATT: vgetexpbf16 268435456(%esp,%esi,8), %xmm2
# INTEL: vgetexpbf16 xmm2, xmmword ptr [esp + 8*esi + 268435456]
0x62,0xf5,0x7d,0x08,0x42,0x94,0xf4,0x00,0x00,0x00,0x10
0x62,0xf6,0x7c,0x08,0x42,0x94,0xf4,0x00,0x00,0x00,0x10

# ATT: vgetexpbf16 291(%edi,%eax,4), %xmm2 {%k7}
# INTEL: vgetexpbf16 xmm2 {k7}, xmmword ptr [edi + 4*eax + 291]
0x62,0xf5,0x7d,0x0f,0x42,0x94,0x87,0x23,0x01,0x00,0x00
0x62,0xf6,0x7c,0x0f,0x42,0x94,0x87,0x23,0x01,0x00,0x00

# ATT: vgetexpbf16 (%eax){1to8}, %xmm2
# INTEL: vgetexpbf16 xmm2, word ptr [eax]{1to8}
0x62,0xf5,0x7d,0x18,0x42,0x10
0x62,0xf6,0x7c,0x18,0x42,0x10

# ATT: vgetexpbf16 -512(,%ebp,2), %xmm2
# INTEL: vgetexpbf16 xmm2, xmmword ptr [2*ebp - 512]
0x62,0xf5,0x7d,0x08,0x42,0x14,0x6d,0x00,0xfe,0xff,0xff
0x62,0xf6,0x7c,0x08,0x42,0x14,0x6d,0x00,0xfe,0xff,0xff

# ATT: vgetexpbf16 2032(%ecx), %xmm2 {%k7} {z}
# INTEL: vgetexpbf16 xmm2 {k7} {z}, xmmword ptr [ecx + 2032]
0x62,0xf5,0x7d,0x8f,0x42,0x51,0x7f
0x62,0xf6,0x7c,0x8f,0x42,0x51,0x7f

# ATT: vgetexpbf16 -256(%edx){1to8}, %xmm2 {%k7} {z}
# INTEL: vgetexpbf16 xmm2 {k7} {z}, word ptr [edx - 256]{1to8}
0x62,0xf5,0x7d,0x9f,0x42,0x52,0x80
0x62,0xf6,0x7c,0x9f,0x42,0x52,0x80

# ATT: vgetexpbf16 268435456(%esp,%esi,8), %ymm2
# INTEL: vgetexpbf16 ymm2, ymmword ptr [esp + 8*esi + 268435456]
0x62,0xf5,0x7d,0x28,0x42,0x94,0xf4,0x00,0x00,0x00,0x10
0x62,0xf6,0x7c,0x28,0x42,0x94,0xf4,0x00,0x00,0x00,0x10

# ATT: vgetexpbf16 291(%edi,%eax,4), %ymm2 {%k7}
# INTEL: vgetexpbf16 ymm2 {k7}, ymmword ptr [edi + 4*eax + 291]
0x62,0xf5,0x7d,0x2f,0x42,0x94,0x87,0x23,0x01,0x00,0x00
0x62,0xf6,0x7c,0x2f,0x42,0x94,0x87,0x23,0x01,0x00,0x00

# ATT: vgetexpbf16 (%eax){1to16}, %ymm2
# INTEL: vgetexpbf16 ymm2, word ptr [eax]{1to16}
0x62,0xf5,0x7d,0x38,0x42,0x10
0x62,0xf6,0x7c,0x38,0x42,0x10

# ATT: vgetexpbf16 -1024(,%ebp,2), %ymm2
# INTEL: vgetexpbf16 ymm2, ymmword ptr [2*ebp - 1024]
0x62,0xf5,0x7d,0x28,0x42,0x14,0x6d,0x00,0xfc,0xff,0xff
0x62,0xf6,0x7c,0x28,0x42,0x14,0x6d,0x00,0xfc,0xff,0xff

# ATT: vgetexpbf16 4064(%ecx), %ymm2 {%k7} {z}
# INTEL: vgetexpbf16 ymm2 {k7} {z}, ymmword ptr [ecx + 4064]
0x62,0xf5,0x7d,0xaf,0x42,0x51,0x7f
0x62,0xf6,0x7c,0xaf,0x42,0x51,0x7f

# ATT: vgetexpbf16 -256(%edx){1to16}, %ymm2 {%k7} {z}
# INTEL: vgetexpbf16 ymm2 {k7} {z}, word ptr [edx - 256]{1to16}
0x62,0xf5,0x7d,0xbf,0x42,0x52,0x80
0x62,0xf6,0x7c,0xbf,0x42,0x52,0x80

# ATT: vgetexpbf16 268435456(%esp,%esi,8), %zmm2
# INTEL: vgetexpbf16 zmm2, zmmword ptr [esp + 8*esi + 268435456]
0x62,0xf5,0x7d,0x48,0x42,0x94,0xf4,0x00,0x00,0x00,0x10
0x62,0xf6,0x7c,0x48,0x42,0x94,0xf4,0x00,0x00,0x00,0x10

# ATT: vgetexpbf16 291(%edi,%eax,4), %zmm2 {%k7}
# INTEL: vgetexpbf16 zmm2 {k7}, zmmword ptr [edi + 4*eax + 291]
0x62,0xf5,0x7d,0x4f,0x42,0x94,0x87,0x23,0x01,0x00,0x00
0x62,0xf6,0x7c,0x4f,0x42,0x94,0x87,0x23,0x01,0x00,0x00

# ATT: vgetexpbf16 (%eax){1to32}, %zmm2
# INTEL: vgetexpbf16 zmm2, word ptr [eax]{1to32}
0x62,0xf5,0x7d,0x58,0x42,0x10
0x62,0xf6,0x7c,0x58,0x42,0x10

# ATT: vgetexpbf16 -2048(,%ebp,2), %zmm2
# INTEL: vgetexpbf16 zmm2, zmmword ptr [2*ebp - 2048]
0x62,0xf5,0x7d,0x48,0x42,0x14,0x6d,0x00,0xf8,0xff,0xff
0x62,0xf6,0x7c,0x48,0x42,0x14,0x6d,0x00,0xf8,0xff,0xff

# ATT: vgetexpbf16 8128(%ecx), %zmm2 {%k7} {z}
# INTEL: vgetexpbf16 zmm2 {k7} {z}, zmmword ptr [ecx + 8128]
0x62,0xf5,0x7d,0xcf,0x42,0x51,0x7f
0x62,0xf6,0x7c,0xcf,0x42,0x51,0x7f

# ATT: vgetexpbf16 -256(%edx){1to32}, %zmm2 {%k7} {z}
# INTEL: vgetexpbf16 zmm2 {k7} {z}, word ptr [edx - 256]{1to32}
0x62,0xf5,0x7d,0xdf,0x42,0x52,0x80
0x62,0xf6,0x7c,0xdf,0x42,0x52,0x80

# ATT: vgetmantbf16 $123, %zmm3, %zmm2
# INTEL: vgetmantbf16 zmm2, zmm3, 123
Expand Down
Loading