[llvm] [X86][AVX10.2] Include changes for COMX and VGETEXP from rev. 2 (PR #132824)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Mar 24 13:31:38 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mc
@llvm/pr-subscribers-backend-x86
Author: Evgenii Kudriashov (e-kud)
<details>
<summary>Changes</summary>
Address missing changes:
- V[,U]COMXSD need to have XD (F3.0F –> F2.0F)
- V[,U]COMXS[S,H] need to have XS (F2.[0F,MAP5] -> F3.[OF,MAP5])
- VGETEXP needs to have T_MAP6 and NP (66.MAP5 -> NP.MAP6)
Ref.: https://cdrdv2.intel.com/v1/dl/getContent/828965
---
Patch is 106.53 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/132824.diff
15 Files Affected:
- (modified) llvm/lib/Target/X86/X86InstrAVX10.td (+10-10)
- (modified) llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll (+2-2)
- (modified) llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll (+10-10)
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt (+27-27)
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt (+27-27)
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-com-ef-32.txt (+48-48)
- (modified) llvm/test/MC/Disassembler/X86/avx10.2-com-ef-64.txt (+48-48)
- (modified) llvm/test/MC/X86/avx10.2-bf16-32-att.s (+27-27)
- (modified) llvm/test/MC/X86/avx10.2-bf16-32-intel.s (+27-27)
- (modified) llvm/test/MC/X86/avx10.2-bf16-64-att.s (+27-27)
- (modified) llvm/test/MC/X86/avx10.2-bf16-64-intel.s (+27-27)
- (modified) llvm/test/MC/X86/avx10.2-com-ef-32-att.s (+48-48)
- (modified) llvm/test/MC/X86/avx10.2-com-ef-32-intel.s (+48-48)
- (modified) llvm/test/MC/X86/avx10.2-com-ef-64-att.s (+48-48)
- (modified) llvm/test/MC/X86/avx10.2-com-ef-64-intel.s (+48-48)
``````````diff
diff --git a/llvm/lib/Target/X86/X86InstrAVX10.td b/llvm/lib/Target/X86/X86InstrAVX10.td
index 7cbdcbc939eec..2d2bf1f6c725e 100644
--- a/llvm/lib/Target/X86/X86InstrAVX10.td
+++ b/llvm/lib/Target/X86/X86InstrAVX10.td
@@ -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,
@@ -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>;
}
//-------------------------------------------------
diff --git a/llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll b/llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll
index da17b995afedf..cbac76e9de273 100644
--- a/llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx10_2_512bf16-intrinsics.ll
@@ -164,7 +164,7 @@ 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]
@@ -172,7 +172,7 @@ define <32 x bfloat>@test_int_x86_avx512_mask_getexp_bf16_512(<32 x bfloat> %x0,
; 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]
diff --git a/llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll b/llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll
index 06875dbe7cd23..ba32b2adc7999 100644
--- a/llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll
+++ b/llvm/test/CodeGen/X86/avx10_2bf16-intrinsics.ll
@@ -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
@@ -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)
@@ -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
@@ -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
@@ -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)
@@ -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
diff --git a/llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt b/llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt
index a32e55e20e6b7..0db70d290e565 100644
--- a/llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt
+++ b/llvm/test/MC/Disassembler/X86/avx10.2-bf16-32.txt
@@ -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
diff --git a/llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt b/llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt
index 1319c5cbd0362..197415e5ba329 100644
--- a/llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt
+++ b/llvm/test/MC/Disassembler/X86/avx10.2-bf16-64.txt
@@ -1719,111 +1719,111 @@
# ATT: vgetexpbf16 %xmm23, %xmm22
# INTEL: vgetexpbf16 xmm22, xmm23
-0x62,0xa5,0x7d,0x08,0x42,0xf7
+0x62,0xa6,0x7c,0x08,0x42,0xf7
# ATT: vgetexpbf16 %xmm23, %xmm22 {%k7}
# INTEL: vgetexpbf16 xmm22 {k7}, xmm23
-0x62,0xa5,0x7d,0x0f,0x42,0xf7
+0x62,0xa6,0x7c,0x0f,0x42,0xf7
# ATT: vgetexpbf16 %xmm23, %xmm22 {%k7} {z}
# INTEL: vgetexpbf16 xmm22 {k7} {z}, xmm23
-0x62,0xa5,0x7d,0x8f,0x42,0xf7
+0x62,0xa6,0x7c,0x8f,0x42,0xf7
# ATT: vgetexpbf16 %zmm23, %zmm22
# INTEL: vgetexpbf16 zmm22, zmm23
-0x62,0xa5,0x7d,0x48,0x42,0xf7
+0x62,0xa6,0x7c,0x48,0x42,0xf7
# ATT: vgetexpbf16 %zmm23, %zmm22 {%k7}
# INTEL: vgetexpbf16 zmm22 {k7}, zmm23
-0x62,0xa5,0x7d,0x4f,0x42,0xf7
+0x62,0xa6,0x7c,0x4f,0x42,0xf7
# ATT: vgetexpbf16 %zmm23, %zmm22 {%k7} {z}
# INTEL: vgetexpbf16 zmm22 {k7} {z}, zmm23
-0x62,0xa5,0x7d,0xcf,0x42,0xf7
+0x62,0xa6,0x7c,0xcf,0x42,0xf7
# ATT: vgetexpbf16 %ymm23, %ymm22
# INTEL: vgetexpbf16 ymm22, ymm23
-0x62,0xa5,0x7d,0x28,0x42,0xf7
+0x62,0xa6,0x7c,0x28,0x42,0xf7
# ATT: vgetexpbf16 %ymm23, %ymm22 {%k7}
# INTEL: vgetexpbf16 ymm22 {k7}, ymm23
-0x62,0xa5,0x7d,0x2f,0x42,0xf7
+0x62,0xa6,0x7c,0x2f,0x42,0xf7
# ATT: vgetexpbf16 %ymm23, %ymm22 {%k7} {z}
# INTEL: vgetexpbf16 ymm22 {k7} {z}, ymm23
-0x62,0xa5,0x7d,0xaf,0x42,0xf7
+0x62,0xa6,0x7c,0xaf,0x42,0xf7
# ATT: vgetexpbf16 268435456(%rbp,%r14,8), %xmm22
# INTEL: vgetexpbf16 xmm22, xmmword ptr [rbp + 8*r14 + 268435456]
-0x62,0xa5,0x7d,0x08,0x42,0xb4,0xf5,0x00,0x00,0x00,0x10
+0x62,0xa6,0x7c,0x08,0x42,0xb4,0xf5,0x00,0x00,0x00,0x10
# ATT: vgetexpbf16 291(%r8,%rax,4), %xmm22 {%k7}
# INTEL: vgetexpbf16 xmm22 {k7}, xmmword ptr [r8 + 4*rax + 291]
-0x62,0xc5,0x7d,0x0f,0x42,0xb4,0x80,0x23,0x01,0x00,0x00
+0x62,0xc6,0x7c,0x0f,0x42,0xb4,0x80,0x23,0x01,0x00,0x00
# ATT: vgetexpbf16 (%rip){1to8}, %xmm22
# INTEL: vgetexpbf16 xmm22, word ptr [rip]{1to8}
-0x62,0xe5,0x7d,0x18,0x42,0x35,0x00,0x00,0x00,0x00
+0x62,0xe6,0x7c,0x18,0x42,0x35,0x00,0x00,0x00,0x00
# ATT: vgetexpbf16 -512(,%rbp,2), %xmm22
# INTEL: vgetexpbf16 xmm22, xmmword ptr [2*rbp - 512]
-0x62,0xe5,0x7d,0x08,0x42,0x34,0x6d,0x00,0xfe,0xff,0xff
+0x62,0xe6,0x7c,0x08,0x42,0x34,0x6d,0x00,0xfe,0xff,0xff
# ATT: vgetexpbf16 2032(%rcx), %xmm22 {%k7} {z}
# INTEL: vgetexpbf16 xmm22 {k7} {z}, xmmword ptr [rcx + 2032]
-0x62,0xe5,0x7d,0x8f,0x42,0x71,0x7f
+0x62,0xe6,0x7c,0x8f,0x42,0x71,0x7f
# ATT: vgetexpbf16 -256(%rdx){1to8}, %xmm22 {%k7} {z}
# INTEL: vgetexpbf16 xmm22 {k7} {z}, word ptr [rdx - 256]{1to8}
-0x62,0xe5,0x7d,0x9f,0x42,0x72,0x80
+0x62,0xe6,0x7c,0x9f,0x42,0x72,0x80
# ATT: vgetexpbf16 268435456(%rbp,%r14,8), %ymm22
# INTEL: vgetexpbf16 ymm22, ymmword ptr [rbp + 8*r14 + 268435456]
-0x62,0xa5,0x7d,0x28,0x42,0xb4,0xf5,0x00,0x00,0x00,0x10
+0x62,0xa6,0x7c,0x28,0x42,0xb4,0xf5,0x00,0x00,0x00,0x10
# ATT: vgetexpbf16 291(%r8,%rax,4), %ymm22 {%k7}
# INTEL: vgetexpbf16 ymm22 {k7}, ymmword ptr [r8 + 4*rax + 291]
-0x62,0xc5,0x7d,0x2f,0x42,0xb4,0x80,0x23,0x01,0x00,0x00
+0x62,0xc6,0x7c,0x2f,0x42,0xb4,0x80,0x23,0x01,0x00,0x00
# ATT: vgetexpbf16 (%rip){1to16}, %ymm22
# INTEL: vgetexpbf16 ymm22, word ptr [rip]{1to16}
-0x62,0xe5,0x7d,0x38,0x42,0x35,0x00,0x00,0x00,0x00
+0x62,0xe6,0x7c,0x38,0x42,0x35,0x00,0x00,0x00,0x00
# ATT: vgetexpbf16 -1024(,%rbp,2), %ymm22
# INTEL: vgetexpbf16 ymm22, ymmword ptr [2*rbp - 1024]
-0x62,0xe5,0x7d,0x28,0x42,0x34,0x6d,0x00,0xfc,0xff,0xff
+0x62,0xe6,0x7c,0x28,0x42,0x34,0x6d,0x00,0xfc,0xff,0xff
# ATT: vgetexpbf16 4064(%rcx), %ymm22 {%k7} {z}
# INTEL: vgetexpbf16 ymm22 {k7} {z}, ymmword ptr [rcx + 4064]
-0x62,0xe5,0x7d,0xaf,0x42,0x71,0x7f
+0x62,0xe6,0x7c,0xaf,0x42,0x71,0x7f
# ATT: vgetexpbf16 -256(%rdx){1to16}, %ymm22 {%k7} {z}
# INTEL: vgetexpbf16 ymm22 {k7} {z}, word ptr [rd...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/132824
More information about the llvm-commits
mailing list