[clang] 979d876 - [X86][AMX] enable amx cast intrinsics in FE.
via cfe-commits
cfe-commits at lists.llvm.org
Fri Apr 1 23:04:14 PDT 2022
Author: Luo, Yuanke
Date: 2022-04-02T14:02:35+08:00
New Revision: 979d876bb4e93db1be50360a4941b83319d4e114
URL: https://github.com/llvm/llvm-project/commit/979d876bb4e93db1be50360a4941b83319d4e114
DIFF: https://github.com/llvm/llvm-project/commit/979d876bb4e93db1be50360a4941b83319d4e114.diff
LOG: [X86][AMX] enable amx cast intrinsics in FE.
We have some discission in D99152 and llvm-dev and finially come up with
a solution to add amx specific cast intrinsics. We've support the
intrinsics in llvm IR. This patch is to replace bitcast with amx cast
intrinsics in code emitting in FE.
Differential Revision: https://reviews.llvm.org/D122567
Added:
Modified:
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/X86/amx_api.c
Removed:
################################################################################
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index ffba93846958e..8ca4b2d0bf15d 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -5411,7 +5411,13 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
assert(PTy->canLosslesslyBitCastTo(FTy->getParamType(i)) &&
"Must be able to losslessly bit cast to param");
- ArgValue = Builder.CreateBitCast(ArgValue, PTy);
+ // Cast vector type (e.g., v256i32) to x86_amx, this only happen
+ // in amx intrinsics.
+ if (PTy->isX86_AMXTy())
+ ArgValue = Builder.CreateIntrinsic(Intrinsic::x86_cast_vector_to_tile,
+ {ArgValue->getType()}, {ArgValue});
+ else
+ ArgValue = Builder.CreateBitCast(ArgValue, PTy);
}
Args.push_back(ArgValue);
@@ -5435,7 +5441,13 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
assert(V->getType()->canLosslesslyBitCastTo(RetTy) &&
"Must be able to losslessly bit cast result type");
- V = Builder.CreateBitCast(V, RetTy);
+ // Cast x86_amx to vector type (e.g., v256i32), this only happen
+ // in amx intrinsics.
+ if (V->getType()->isX86_AMXTy())
+ V = Builder.CreateIntrinsic(Intrinsic::x86_cast_tile_to_vector, {RetTy},
+ {V});
+ else
+ V = Builder.CreateBitCast(V, RetTy);
}
return RValue::get(V);
diff --git a/clang/test/CodeGen/X86/amx_api.c b/clang/test/CodeGen/X86/amx_api.c
index fda6d6e8ee4f2..e5927f189fb78 100644
--- a/clang/test/CodeGen/X86/amx_api.c
+++ b/clang/test/CodeGen/X86/amx_api.c
@@ -11,9 +11,11 @@ char buf2[1024];
// This is an example code and integration test.
void test_api(int cond, short row, short col) {
//CHECK-LABEL: @test_api
- //CHECK: call x86_amx @llvm.x86.tileloadd64.internal
- //CHECK: call x86_amx @llvm.x86.tdpbssd.internal
- //CHECK: call void @llvm.x86.tilestored64.internal
+ //CHECK-DAG: call x86_amx @llvm.x86.tileloadd64.internal
+ //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.tdpbssd.internal
+ //CHECK-DAG: call void @llvm.x86.tilestored64.internal
__tile1024i a = {row, 8};
__tile1024i b = {8, col};
__tile1024i c = {row, col};
@@ -33,65 +35,70 @@ void test_api(int cond, short row, short col) {
void test_tile_loadd(short row, short col) {
//CHECK-LABEL: @test_tile_loadd
- //CHECK: call x86_amx @llvm.x86.tileloadd64.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //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: call x86_amx @llvm.x86.tileloaddt164.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //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: call x86_amx @llvm.x86.tdpbssd.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.tdpbssd.internal
+ //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
__tile_dpbssd(&c, a, b);
}
void test_tile_dpbsud(__tile1024i a, __tile1024i b, __tile1024i c) {
//CHECK-LABEL: @test_tile_dpbsud
- //CHECK: call x86_amx @llvm.x86.tdpbsud.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.tdpbsud.internal
+ //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
__tile_dpbsud(&c, a, b);
}
void test_tile_dpbusd(__tile1024i a, __tile1024i b, __tile1024i c) {
//CHECK-LABEL: @test_tile_dpbusd
- //CHECK: call x86_amx @llvm.x86.tdpbusd.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.tdpbusd.internal
+ //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
__tile_dpbusd(&c, a, b);
}
void test_tile_dpbuud(__tile1024i a, __tile1024i b, __tile1024i c) {
//CHECK-LABEL: @test_tile_dpbuud
- //CHECK: call x86_amx @llvm.x86.tdpbuud.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.tdpbuud.internal
+ //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
__tile_dpbuud(&c, a, b);
}
void test_tile_stored(__tile1024i c) {
//CHECK-LABEL: @test_tile_stored
- //CHECK: {{%.*}} = bitcast <256 x i32> {{%.*}} to x86_amx
- //CHECK-NEXT: call void @llvm.x86.tilestored64.internal
+ //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: call x86_amx @llvm.x86.tilezero.internal
- //CHECK-NEXT bitcast x86_amx {{%.*}} to <256 x i32>
+ //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: call x86_amx @llvm.x86.tdpbf16ps.internal
- //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
+ //CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
+ //CHECK-DAG: call x86_amx @llvm.x86.tdpbf16ps.internal
+ //CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
__tile_dpbf16ps(&a, b, c);
}
More information about the cfe-commits
mailing list