[Headers][X86] amxintrin.h - fix attributes according to Intel SDM (#122204)

`tileloadd`, `tileloaddt1` and `tilestored` are part of `amx-tile`
feature.

The problem is observed if `__tile_loadd` intrinsic is invoked,
`_tile_loadd_internal` requiring `amx-int8` is inlined into
`__tile_loadd` that has only `amx-tile`.

Author: e-kud

clang/lib/Headers/amxintrin.h

@@ -234,15 +234,15 @@ typedef int _tile1024i_1024a
     __attribute__((__vector_size__(1024), __aligned__(1024)));
 
 /// This is internal intrinsic. C/C++ user should avoid calling it directly.
-static __inline__ _tile1024i __DEFAULT_FN_ATTRS_INT8
+static __inline__ _tile1024i __DEFAULT_FN_ATTRS_TILE
 _tile_loadd_internal(unsigned short m, unsigned short n, const void *base,
                      __SIZE_TYPE__ stride) {
   return __builtin_ia32_tileloadd64_internal(m, n, base,
                                              (__SIZE_TYPE__)(stride));
 }
 
 /// This is internal intrinsic. C/C++ user should avoid calling it directly.
-static __inline__ _tile1024i __DEFAULT_FN_ATTRS_INT8
+static __inline__ _tile1024i __DEFAULT_FN_ATTRS_TILE
 _tile_loaddt1_internal(unsigned short m, unsigned short n, const void *base,
                        __SIZE_TYPE__ stride) {
   return __builtin_ia32_tileloaddt164_internal(m, n, base,
@@ -278,7 +278,7 @@ _tile_dpbuud_internal(unsigned short m, unsigned short n, unsigned short k,
 }
 
 /// This is internal intrinsic. C/C++ user should avoid calling it directly.
-static __inline__ void __DEFAULT_FN_ATTRS_INT8
+static __inline__ void __DEFAULT_FN_ATTRS_TILE
 _tile_stored_internal(unsigned short m, unsigned short n, void *base,
                       __SIZE_TYPE__ stride, _tile1024i tile) {
   return __builtin_ia32_tilestored64_internal(m, n, base,

clang/test/CodeGen/X86/amx_api.c

@@ -33,22 +33,6 @@ void test_api(int cond, short row, short col) {
   __tile_stored(buf, STRIDE, c);
 }
 
-void test_tile_loadd(short row, short col) {
-  //CHECK-LABEL: @test_tile_loadd
-  //CHECK-DAG: call x86_amx @llvm.x86.tileloadd64.internal
-  //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
-  __tile1024i a = {row, col};
-  __tile_loadd(&a, buf, STRIDE);
-}
-
-void test_tile_stream_loadd(short row, short col) {
-  //CHECK-LABEL: @test_tile_stream_loadd
-  //CHECK-DAG: call x86_amx @llvm.x86.tileloaddt164.internal
-  //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
-  __tile1024i a = {row, col};
-  __tile_stream_loadd(&a, buf, STRIDE);
-}
-
 void test_tile_dpbssd(__tile1024i a, __tile1024i b, __tile1024i c) {
   //CHECK-LABEL: @test_tile_dpbssd
   //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
@@ -81,20 +65,6 @@ void test_tile_dpbuud(__tile1024i a, __tile1024i b, __tile1024i c) {
   __tile_dpbuud(&c, a, b);
 }
 
-void test_tile_stored(__tile1024i c) {
-  //CHECK-LABEL: @test_tile_stored
-  //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
-  //CHECK-DAG: call void @llvm.x86.tilestored64.internal
-  __tile_stored(buf, STRIDE, c);
-}
-
-void test_tile_zero(__tile1024i c) {
-  //CHECK-LABEL: @test_tile_zero
-  //CHECK-DAG: call x86_amx @llvm.x86.tilezero.internal
-  //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
-  __tile_zero(&c);
-}
-
 void test_tile_dpbf16ps(__tile1024i a, __tile1024i b, __tile1024i c) {
   //CHECK-LABEL: @test_tile_dpbf16ps
   //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})

clang/test/CodeGen/X86/amx_tile.c

@@ -0,0 +1,37 @@
+// RUN: %clang_cc1 %s -flax-vector-conversions=none -ffreestanding -triple=x86_64-unknown-unknown  -target-feature +amx-tile  \
+// RUN: -emit-llvm -o - -Werror -pedantic | FileCheck %s --check-prefixes=CHECK
+
+#include <immintrin.h>
+
+char buf[1024];
+#define STRIDE 32
+
+void test_tile_loadd(short row, short col) {
+  //CHECK-LABEL: @test_tile_loadd
+  //CHECK-DAG: call x86_amx @llvm.x86.tileloadd64.internal
+  //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
+  __tile1024i a = {row, col};
+  __tile_loadd(&a, buf, STRIDE);
+}
+
+void test_tile_stream_loadd(short row, short col) {
+  //CHECK-LABEL: @test_tile_stream_loadd
+  //CHECK-DAG: call x86_amx @llvm.x86.tileloaddt164.internal
+  //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
+  __tile1024i a = {row, col};
+  __tile_stream_loadd(&a, buf, STRIDE);
+}
+
+void test_tile_stored(__tile1024i c) {
+  //CHECK-LABEL: @test_tile_stored
+  //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+  //CHECK-DAG: call void @llvm.x86.tilestored64.internal
+  __tile_stored(buf, STRIDE, c);
+}
+
+void test_tile_zero(__tile1024i c) {
+  //CHECK-LABEL: @test_tile_zero
+  //CHECK-DAG: call x86_amx @llvm.x86.tilezero.internal
+  //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
+  __tile_zero(&c);
+}