[X86][AVX10.2] Decouple AMX-AVX512 from AVX10.2

clang/include/clang/Basic/BuiltinsX86_64.td

@@ -290,13 +290,19 @@ let Features = "amx-complex,amx-transpose", Attributes = [NoThrow] in {
   def tconjtfp16_internal : X86Builtin<"_Vector<256, int>(unsigned short, unsigned short, _Vector<256, int>)">;
 }
 
-let Features = "amx-avx512,avx10.2-512", Attributes = [NoThrow] in {
+let Features = "amx-avx512", Attributes = [NoThrow] in {
   def tcvtrowd2ps_internal : X86Builtin<"_Vector<16, float>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
+  def tilemovrow_internal : X86Builtin<"_Vector<16, int>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
+}
+
+let Features = "amx-avx512,avx512bf16", Attributes = [NoThrow] in {
   def tcvtrowps2bf16h_internal : X86Builtin<"_Vector<32, __bf16>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
   def tcvtrowps2bf16l_internal : X86Builtin<"_Vector<32, __bf16>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
+}
+
+let Features = "amx-avx512,avx512fp16", Attributes = [NoThrow] in {
   def tcvtrowps2phh_internal : X86Builtin<"_Vector<32, _Float16>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
   def tcvtrowps2phl_internal : X86Builtin<"_Vector<32, _Float16>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
-  def tilemovrow_internal : X86Builtin<"_Vector<16, int>(unsigned short, unsigned short, _Vector<256, int>, unsigned int)">;
 }
 
 let Features = "amx-tf32", Attributes = [NoThrow] in {
@@ -382,13 +388,19 @@ let Features = "amx-complex,amx-transpose", Attributes = [NoThrow] in {
   def tconjtfp16 : X86Builtin<"void(_Constant unsigned char, _Constant unsigned char)">;
 }
 
-let Features = "amx-avx512,avx10.2-512", Attributes = [NoThrow] in {
+let Features = "amx-avx512", Attributes = [NoThrow] in {
   def tcvtrowd2ps : X86Builtin<"_Vector<16, float>(_Constant unsigned char, unsigned int)">;
+  def tilemovrow : X86Builtin<"_Vector<16, int>(_Constant unsigned char, unsigned int)">;
+}
+
+let Features = "amx-avx512,avx512bf16", Attributes = [NoThrow] in {
   def tcvtrowps2bf16h : X86Builtin<"_Vector<32, __bf16>(_Constant unsigned char, unsigned int)">;
   def tcvtrowps2bf16l : X86Builtin<"_Vector<32, __bf16>(_Constant unsigned char, unsigned int)">;
+}
+
+let Features = "amx-avx512,avx512fp16", Attributes = [NoThrow] in {
   def tcvtrowps2phh : X86Builtin<"_Vector<32, _Float16>(_Constant unsigned char, unsigned int)">;
   def tcvtrowps2phl : X86Builtin<"_Vector<32, _Float16>(_Constant unsigned char, unsigned int)">;
-  def tilemovrow : X86Builtin<"_Vector<16, int>(_Constant unsigned char, unsigned int)">;
 }
 
 let Features = "amx-fp16", Attributes = [NoThrow] in {

clang/lib/Headers/amxavx512intrin.h

@@ -16,7 +16,15 @@
 
 #define __DEFAULT_FN_ATTRS_AVX512                                              \
   __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("amx-avx512,avx10.2-512")))
+                 __target__("amx-avx512")))
+
+#define __DEFAULT_FN_ATTRS_AVX512BF16                                          \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("amx-avx512,avx512bf16")))
+
+#define __DEFAULT_FN_ATTRS_AVX512FP16                                          \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("amx-avx512,avx512fp16")))
 
 /// Moves a row from a tile register to a zmm destination register, converting
 ///    the int32 source elements to fp32. The row of the tile is selected by a
@@ -237,25 +245,27 @@ static __inline__ __m512 __DEFAULT_FN_ATTRS_AVX512 _tile_cvtrowd2ps_internal(
   return __builtin_ia32_tcvtrowd2ps_internal(m, n, src, u);
 }
 
-static __inline__ __m512bh __DEFAULT_FN_ATTRS_AVX512
+static __inline__ __m512bh __DEFAULT_FN_ATTRS_AVX512BF16
 _tile_cvtrowps2bf16h_internal(unsigned short m, unsigned short n,
                               _tile1024i src, unsigned u) {
   return __builtin_ia32_tcvtrowps2bf16h_internal(m, n, src, u);
 }
 
-static __inline__ __m512bh __DEFAULT_FN_ATTRS_AVX512
+static __inline__ __m512bh __DEFAULT_FN_ATTRS_AVX512BF16
 _tile_cvtrowps2bf16l_internal(unsigned short m, unsigned short n,
                               _tile1024i src, unsigned u) {
   return __builtin_ia32_tcvtrowps2bf16l_internal(m, n, src, u);
 }
 
-static __inline__ __m512h __DEFAULT_FN_ATTRS_AVX512 _tile_cvtrowps2phh_internal(
-    unsigned short m, unsigned short n, _tile1024i src, unsigned u) {
+static __inline__ __m512h __DEFAULT_FN_ATTRS_AVX512FP16
+_tile_cvtrowps2phh_internal(unsigned short m, unsigned short n,
+                            _tile1024i src, unsigned u) {
   return __builtin_ia32_tcvtrowps2phh_internal(m, n, src, u);
 }
 
-static __inline__ __m512h __DEFAULT_FN_ATTRS_AVX512 _tile_cvtrowps2phl_internal(
-    unsigned short m, unsigned short n, _tile1024i src, unsigned u) {
+static __inline__ __m512h __DEFAULT_FN_ATTRS_AVX512FP16
+_tile_cvtrowps2phl_internal(unsigned short m, unsigned short n,
+                            _tile1024i src, unsigned u) {
   return __builtin_ia32_tcvtrowps2phl_internal(m, n, src, u);
 }
 
@@ -298,7 +308,7 @@ static __m512 __tile_cvtrowd2ps(__tile1024i src0, unsigned src1) {
 ///    The 2nd source r32. Size is 4 Bytes.
 /// \returns
 ///    The destination v32bf16 data. Size is 64 Bytes.
-__DEFAULT_FN_ATTRS_AVX512
+__DEFAULT_FN_ATTRS_AVX512BF16
 static __m512bh __tile_cvtrowps2bf16h(__tile1024i src0, unsigned src1) {
   return _tile_cvtrowps2bf16h_internal(src0.row, src0.col, src0.tile, src1);
 }
@@ -317,7 +327,7 @@ static __m512bh __tile_cvtrowps2bf16h(__tile1024i src0, unsigned src1) {
 ///    The 2nd source r32. Size is 4 Bytes.
 /// \returns
 ///    The destination v32bf16 data. Size is 64 Bytes.
-__DEFAULT_FN_ATTRS_AVX512
+__DEFAULT_FN_ATTRS_AVX512BF16
 static __m512bh __tile_cvtrowps2bf16l(__tile1024i src0, unsigned src1) {
   return _tile_cvtrowps2bf16l_internal(src0.row, src0.col, src0.tile, src1);
 }
@@ -336,7 +346,7 @@ static __m512bh __tile_cvtrowps2bf16l(__tile1024i src0, unsigned src1) {
 ///    The 2nd source r32. Size is 4 Bytes.
 /// \returns
 ///    The destination v32fp16 data. Size is 64 Bytes.
-__DEFAULT_FN_ATTRS_AVX512
+__DEFAULT_FN_ATTRS_AVX512FP16
 static __m512h __tile_cvtrowps2phh(__tile1024i src0, unsigned src1) {
   return _tile_cvtrowps2phh_internal(src0.row, src0.col, src0.tile, src1);
 }
@@ -355,7 +365,7 @@ static __m512h __tile_cvtrowps2phh(__tile1024i src0, unsigned src1) {
 ///    The 2nd source r32. Size is 4 Bytes.
 /// \returns
 ///    The destination v32fp16 data. Size is 64 Bytes.
-__DEFAULT_FN_ATTRS_AVX512
+__DEFAULT_FN_ATTRS_AVX512FP16
 static __m512h __tile_cvtrowps2phl(__tile1024i src0, unsigned src1) {
   return _tile_cvtrowps2phl_internal(src0.row, src0.col, src0.tile, src1);
 }

clang/test/CodeGen/X86/amx_avx512_api.c

@@ -1,6 +1,6 @@
 // RUN: %clang_cc1 %s -flax-vector-conversions=none -ffreestanding -triple=x86_64-unknown-unknown \
-// RUN: -target-feature +amx-avx512 -target-feature +avx10.2-512 \
-// RUN: -emit-llvm -o - -Werror -pedantic | FileCheck %s --check-prefixes=CHECK
+// RUN: -target-feature +amx-avx512 -emit-llvm -o - -Werror -pedantic | \
+// RUN: FileCheck %s --check-prefixes=CHECK
 
 #include <immintrin.h>
 
@@ -16,27 +16,31 @@ __m512 test_tile_cvtrowd2ps(__tile1024i a, unsigned b) {
  return __tile_cvtrowd2ps(a, b);
 }
 
+__attribute__((__target__("avx512bf16")))
 __m512bh test_tile_cvtrowps2bf16h(__tile1024i a, unsigned b) {
   //CHECK-LABEL: @test_tile_cvtrowps2bf16h
   //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
   //CHECK-DAG: call <32 x bfloat> @llvm.x86.tcvtrowps2bf16h.internal
  return __tile_cvtrowps2bf16h(a, b);
 }
 
+__attribute__((__target__("avx512bf16")))
 __m512bh test_tile_cvtrowps2bf16l(__tile1024i a, unsigned b) {
   //CHECK-LABEL: @test_tile_cvtrowps2bf16l
   //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
   //CHECK-DAG: call <32 x bfloat> @llvm.x86.tcvtrowps2bf16l.internal
  return __tile_cvtrowps2bf16l(a, b);
 }
 
+__attribute__((__target__("avx512fp16")))
 __m512h test_tile_cvtrowps2phh(__tile1024i a, unsigned b) {
   //CHECK-LABEL: @test_tile_cvtrowps2phh
   //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
   //CHECK-DAG: call <32 x half> @llvm.x86.tcvtrowps2phh.internal
  return __tile_cvtrowps2phh(a, b);
 }
 
+__attribute__((__target__("avx512fp16")))
 __m512h test_tile_cvtrowps2phl(__tile1024i a, unsigned b) {
   //CHECK-LABEL: @test_tile_cvtrowps2phl
   //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})

clang/test/CodeGen/X86/amxavx512-builtins.c

@@ -1,5 +1,5 @@
 // RUN: %clang_cc1 %s -ffreestanding -triple=x86_64-unknown-unknown -target-feature +amx-tile -target-feature +amx-avx512 \
-// RUN: -target-feature +avx10.2-512 -emit-llvm -o - -Wall -Werror -pedantic -Wno-gnu-statement-expression -flax-vector-conversions=none | FileCheck %s
+// RUN: -emit-llvm -o - -Wall -Werror -pedantic -Wno-gnu-statement-expression -flax-vector-conversions=none | FileCheck %s
 
 #include <immintrin.h>
 #include <stddef.h>
@@ -10,24 +10,28 @@ __m512 test_tile_cvtrowd2ps(unsigned int A) {
   return _tile_cvtrowd2ps(1, A);
 }
 
+__attribute__((__target__("avx512bf16")))
 __m512bh test_tile_cvtrowps2bf16h(unsigned int A) {
   // CHECK-LABEL: @test_tile_cvtrowps2bf16h(
   // CHECK: call <32 x bfloat> @llvm.x86.tcvtrowps2bf16h(i8 1, i32 %{{.*}})
   return _tile_cvtrowps2bf16h(1, A);
 }
 
+__attribute__((__target__("avx512bf16")))
 __m512bh test_tile_cvtrowps2bf16l(unsigned int A) {
   // CHECK-LABEL: @test_tile_cvtrowps2bf16l(
   // CHECK: call <32 x bfloat> @llvm.x86.tcvtrowps2bf16l(i8 1, i32 %{{.*}})
   return _tile_cvtrowps2bf16l(1, A);
 }
 
+__attribute__((__target__("avx512fp16")))
 __m512h test_tile_cvtrowps2phh(unsigned int A) {
   // CHECK-LABEL: @test_tile_cvtrowps2phh(
   // CHECK: call <32 x half> @llvm.x86.tcvtrowps2phh(i8 1, i32 %{{.*}})
   return _tile_cvtrowps2phh(1, A);
 }
 
+__attribute__((__target__("avx512fp16")))
 __m512h test_tile_cvtrowps2phl(unsigned int A) {
   // CHECK-LABEL: @test_tile_cvtrowps2phl(
   // CHECK: call <32 x half> @llvm.x86.tcvtrowps2phl(i8 1, i32 %{{.*}})

llvm/lib/Target/X86/X86.td

@@ -277,7 +277,8 @@ def FeatureAMXTRANSPOSE : SubtargetFeature<"amx-transpose", "HasAMXTRANSPOSE", "
 def FeatureAMXAVX512 : SubtargetFeature<"amx-avx512",
                                         "HasAMXAVX512", "true",
                                         "Support AMX-AVX512 instructions",
-                                        [FeatureAMXTILE]>;
+                                        [FeatureAMXTILE, FeatureAVX512,
+                                         FeatureEVEX512]>;
 def FeatureAMXTF32 : SubtargetFeature<"amx-tf32", "HasAMXTF32", "true",
                                       "Support AMX-TF32 instructions",
                                       [FeatureAMXTILE]>;

llvm/lib/Target/X86/X86InstrAMX.td

@@ -550,7 +550,7 @@ let Predicates = [HasAMXMOVRS, In64BitMode], SchedRW = [WriteSystem] in {
 } // HasAMXMOVRS, In64BitMode
 
 multiclass m_tcvtrowd2ps {
-  let Predicates = [HasAMXAVX512, HasAVX10_2_512, In64BitMode] in {
+  let Predicates = [HasAMXAVX512, In64BitMode] in {
     let SchedRW = [WriteSystem] in {
       def rri : Ii8<0x7, MRMSrcReg, (outs VR512:$dst),
                     (ins TILE:$src1, i32u8imm:$src2),
@@ -561,12 +561,12 @@ multiclass m_tcvtrowd2ps {
                   "tcvtrowd2ps\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                   []>, T8,XS, EVEX, VVVV, EVEX_V512;
     }
-  } // HasAMXAVX512, HasAVX10_2_512, In64BitMode
+  } // HasAMXAVX512, In64BitMode
 }
 
 defm TCVTROWD2PS : m_tcvtrowd2ps;
 
-let Predicates = [HasAMXAVX512, HasAVX10_2_512, In64BitMode] in {
+let Predicates = [HasAMXAVX512, In64BitMode] in {
   let SchedRW = [WriteSystem] in {
     let  usesCustomInserter = 1 in {
       def PTCVTROWD2PSrri : PseudoI<(outs VR512:$dst), (ins u8imm:$src1, i32u8imm:$src2),
@@ -630,7 +630,7 @@ let Predicates = [HasAMXAVX512, HasAVX10_2_512, In64BitMode] in {
 
 multiclass AMXAVX512_BASE<bits<8> Opcode1, bits<8> Opcode2, string Opstr,
                                 Prefix P1, Prefix P2> {
-  let Predicates = [HasAMXAVX512, HasAVX10_2_512, In64BitMode], SchedRW = [WriteSystem] in {
+  let Predicates = [HasAMXAVX512, In64BitMode], SchedRW = [WriteSystem] in {
     let OpPrefix = P1 in
       def rre : I<Opcode1, MRMSrcReg4VOp3, (outs VR512:$dst),
                   (ins TILE:$src1, GR32:$src2),
@@ -658,7 +658,7 @@ defm TCVTROWPS2BF16H : AMXAVX512_BASE<0x6d, 0x07, "tcvtrowps2bf16h", XD, XD>;
 defm TCVTROWPS2BF16L : AMXAVX512_BASE<0x6d, 0x77, "tcvtrowps2bf16l", XS, XS>;
 
 multiclass m_tilemovrow {
-  let Predicates = [HasAMXAVX512, HasAVX10_2_512, In64BitMode] in {
+  let Predicates = [HasAMXAVX512, In64BitMode] in {
     let SchedRW = [WriteSystem] in {
       def rri : Ii8<0x7, MRMSrcReg, (outs VR512:$dst),
                     (ins TILE:$src1, u8imm:$src2),
@@ -669,12 +669,12 @@ multiclass m_tilemovrow {
                   "tilemovrow\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                   []>, T8,PD, EVEX, VVVV, EVEX_V512;
     }
-  } // HasAMXAVX512, HasAVX10_2_512, In64BitMode
+  } // HasAMXAVX512, In64BitMode
 }
 
 defm TILEMOVROW : m_tilemovrow;
 
-let Predicates = [HasAMXAVX512, HasAVX10_2_512, In64BitMode] in {
+let Predicates = [HasAMXAVX512, In64BitMode] in {
   let SchedRW = [WriteSystem] in {
     let  usesCustomInserter = 1 in {
       def PTILEMOVROWrri : PseudoI<(outs VR512:$dst), (ins u8imm:$src1, i32u8imm:$src2),

llvm/lib/TargetParser/X86TargetParser.cpp

@@ -616,7 +616,7 @@ constexpr FeatureBitset ImpliedFeaturesAMX_FP8 = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesAMX_TRANSPOSE = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesAMX_MOVRS = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesAMX_AVX512 =
-    FeatureAMX_TILE | FeatureAVX10_2_512;
+    FeatureAMX_TILE | FeatureAVX512F | FeatureEVEX512;
 constexpr FeatureBitset ImpliedFeaturesAMX_TF32 = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesHRESET = {};
 

llvm/test/CodeGen/X86/amx-across-func-tilemovrow.ll

@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx10.2-512 -mattr=+amx-avx512 -verify-machineinstrs | FileCheck %s
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx10.2-512 -mattr=+amx-avx512 -verify-machineinstrs -enable-ipra | FileCheck -check-prefix=IPRA %s
-; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx10.2-512 -mattr=+amx-avx512 -verify-machineinstrs | FileCheck -check-prefix=O0 %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8,+amx-avx512 -verify-machineinstrs | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8,+amx-avx512 -verify-machineinstrs -enable-ipra | FileCheck -check-prefix=IPRA %s
+; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+amx-int8,+amx-avx512 -verify-machineinstrs | FileCheck -check-prefix=O0 %s
 
 @buf = dso_local global [3072 x i8] zeroinitializer, align 64
 
@@ -95,7 +95,7 @@ define dso_local <16 x i32> @test_api(i16 signext %0, i16 signext %1) nounwind {
 ; O0-NEXT:    movq %rsp, %rbp
 ; O0-NEXT:    andq $-1024, %rsp # imm = 0xFC00
 ; O0-NEXT:    subq $4096, %rsp # imm = 0x1000
-; O0-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; O0-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; O0-NEXT:    vmovups %zmm0, {{[0-9]+}}(%rsp)
 ; O0-NEXT:    movb $1, {{[0-9]+}}(%rsp)
 ; O0-NEXT:    movw %si, %cx

llvm/test/CodeGen/X86/amx-avx512-intrinsics.ll

@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=x86_64-unknown-unknown --show-mc-encoding -mattr=+amx-tile,+amx-avx512,+avx10.2-512 | FileCheck %s
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=x86_64-unknown-unknown --show-mc-encoding -mattr=+amx-tile,+amx-avx512 | FileCheck %s
 
 define <16 x float> @test_tcvtrowd2ps(i32 %A) {
 ; CHECK-LABEL: test_tcvtrowd2ps:
@@ -20,7 +20,7 @@ define <16 x float> @test_tcvtrowd2psi() {
 }
 declare <16 x float> @llvm.x86.tcvtrowd2ps(i8 %A, i32 %B)
 
-define <32 x bfloat> @test_tcvtrowps2bf16h(i32 %A) {
+define <32 x bfloat> @test_tcvtrowps2bf16h(i32 %A) "target-features"="+avx512bf16" {
 ; CHECK-LABEL: test_tcvtrowps2bf16h:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2bf16h %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x47,0x48,0x6d,0xc1]
@@ -29,7 +29,7 @@ define <32 x bfloat> @test_tcvtrowps2bf16h(i32 %A) {
   ret <32 x bfloat> %ret
 }
 
-define <32 x bfloat> @test_tcvtrowps2bf16hi() {
+define <32 x bfloat> @test_tcvtrowps2bf16hi() "target-features"="+avx512bf16" {
 ; CHECK-LABEL: test_tcvtrowps2bf16hi:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2bf16h $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7f,0x48,0x07,0xc1,0x7f]
@@ -39,7 +39,7 @@ define <32 x bfloat> @test_tcvtrowps2bf16hi() {
 }
 declare <32 x bfloat> @llvm.x86.tcvtrowps2bf16h(i8 %A, i32 %B)
 
-define <32 x bfloat> @test_tcvtrowps2bf16l(i32 %A) {
+define <32 x bfloat> @test_tcvtrowps2bf16l(i32 %A) "target-features"="+avx512bf16" {
 ; CHECK-LABEL: test_tcvtrowps2bf16l:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2bf16l %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x46,0x48,0x6d,0xc1]
@@ -48,7 +48,7 @@ define <32 x bfloat> @test_tcvtrowps2bf16l(i32 %A) {
   ret <32 x bfloat> %ret
 }
 
-define <32 x bfloat> @test_tcvtrowps2bf16li() {
+define <32 x bfloat> @test_tcvtrowps2bf16li() "target-features"="+avx512bf16" {
 ; CHECK-LABEL: test_tcvtrowps2bf16li:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2bf16l $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7e,0x48,0x77,0xc1,0x7f]
@@ -58,7 +58,7 @@ define <32 x bfloat> @test_tcvtrowps2bf16li() {
 }
 declare <32 x bfloat> @llvm.x86.tcvtrowps2bf16l(i8 %A, i32 %B)
 
-define <32 x half> @test_tcvtrowps2phh(i32 %A) {
+define <32 x half> @test_tcvtrowps2phh(i32 %A) "target-features"="+avx512fp16" {
 ; CHECK-LABEL: test_tcvtrowps2phh:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2phh %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x44,0x48,0x6d,0xc1]
@@ -67,7 +67,7 @@ define <32 x half> @test_tcvtrowps2phh(i32 %A) {
   ret <32 x half> %ret
 }
 
-define <32 x half> @test_tcvtrowps2phhi() {
+define <32 x half> @test_tcvtrowps2phhi() "target-features"="+avx512fp16" {
 ; CHECK-LABEL: test_tcvtrowps2phhi:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2phh $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7c,0x48,0x07,0xc1,0x7f]
@@ -77,7 +77,7 @@ define <32 x half> @test_tcvtrowps2phhi() {
 }
 declare <32 x half> @llvm.x86.tcvtrowps2phh(i8 %A, i32 %B)
 
-define <32 x half> @test_tcvtrowps2phl(i32 %A) {
+define <32 x half> @test_tcvtrowps2phl(i32 %A) "target-features"="+avx512fp16" {
 ; CHECK-LABEL: test_tcvtrowps2phl:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2phl %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x45,0x48,0x6d,0xc1]
@@ -86,7 +86,7 @@ define <32 x half> @test_tcvtrowps2phl(i32 %A) {
   ret <32 x half> %ret
 }
 
-define <32 x half> @test_tcvtrowps2phli() {
+define <32 x half> @test_tcvtrowps2phli() "target-features"="+avx512fp16" {
 ; CHECK-LABEL: test_tcvtrowps2phli:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    tcvtrowps2phl $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7f,0x48,0x77,0xc1,0x7f]

llvm/test/CodeGen/X86/amx-tile-avx512-internals.ll

@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-tile,+amx-bf16,+avx10.2-512, \
-; RUN: -mattr=+amx-avx512 -verify-machineinstrs | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-tile,+amx-bf16,+amx-avx512,avx512fp16,+avx512bf16 \
+; RUN: -verify-machineinstrs | FileCheck %s
 
 define void @test_amx(i8* %pointer, i8* %base, i32 %index, i64 %stride) {
 ; CHECK-LABEL: test_amx: