Revert "[mlir][x86vector] AVX Convert/Broadcast BF16 to F32 instructions" #136781
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jplehr
requested review from
aartbik,
dcaballe and
nicolasvasilache
as code owners
|
@llvm/pr-subscribers-mlir-vector @llvm/pr-subscribers-mlir Author: Jan Patrick Lehr (jplehr) ChangesReverts llvm/llvm-project#135143 This broke multiple bots, see PR. Full diff: https://github.com/llvm/llvm-project/pull/136781.diff 8 Files Affected:
diff --git a/mlir/include/mlir/Dialect/X86Vector/X86Vector.td b/mlir/include/mlir/Dialect/X86Vector/X86Vector.td
index 126fa0e352656..5be0d92db4630 100644
--- a/mlir/include/mlir/Dialect/X86Vector/X86Vector.td
+++ b/mlir/include/mlir/Dialect/X86Vector/X86Vector.td
@@ -83,7 +83,7 @@ def MaskCompressOp : AVX512_Op<"mask.compress", [Pure,
}
}];
let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
+ SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&);
}];
}
@@ -404,127 +404,8 @@ def DotOp : AVX_LowOp<"dot", [Pure,
}
}];
let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
+ SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&);
}];
}
-
-//----------------------------------------------------------------------------//
-// AVX: Convert packed BF16 even-indexed/odd-indexed elements into packed F32
-//----------------------------------------------------------------------------//
-
-def CvtPackedEvenIndexedBF16ToF32Op : AVX_Op<"cvt.packed.even.indexed.bf16_to_f32", [MemoryEffects<[MemRead]>,
- DeclareOpInterfaceMethods<OneToOneIntrinsicOpInterface>]> {
- let summary = "AVX: Convert packed BF16 even-indexed elements into packed F32 Data.";
- let description = [{
- #### From the Intel Intrinsics Guide:
-
- Convert packed BF16 (16-bit) floating-point even-indexed elements stored at
- memory locations starting at location `__A` to packed single-precision
- (32-bit) floating-point elements, and store the results in `dst`.
-
- Example:
- ```mlir
- %dst = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- ```
- }];
- let arguments = (ins AnyMemRef:$a);
- let results = (outs VectorOfLengthAndType<[4, 8], [F32]>:$dst);
- let assemblyFormat =
- "$a attr-dict`:` type($a)`->` type($dst)";
-
- let extraClassDefinition = [{
- std::string $cppClass::getIntrinsicName() {
- std::string intr = "llvm.x86.vcvtneebf162ps";
- VectorType vecType = getDst().getType();
- unsigned elemBitWidth = vecType.getElementTypeBitWidth();
- unsigned opBitWidth = vecType.getShape()[0] * elemBitWidth;
- intr += std::to_string(opBitWidth);
- return intr;
- }
- }];
-
- let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
- }];
-}
-
-def CvtPackedOddIndexedBF16ToF32Op : AVX_Op<"cvt.packed.odd.indexed.bf16_to_f32", [MemoryEffects<[MemRead]>,
- DeclareOpInterfaceMethods<OneToOneIntrinsicOpInterface>]> {
- let summary = "AVX: Convert packed BF16 odd-indexed elements into packed F32 Data.";
- let description = [{
- #### From the Intel Intrinsics Guide:
-
- Convert packed BF16 (16-bit) floating-point odd-indexed elements stored at
- memory locations starting at location `__A` to packed single-precision
- (32-bit) floating-point elements, and store the results in `dst`.
-
- Example:
- ```mlir
- %dst = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- ```
- }];
- let arguments = (ins AnyMemRef:$a);
- let results = (outs VectorOfLengthAndType<[4, 8], [F32]>:$dst);
- let assemblyFormat =
- "$a attr-dict`:` type($a)`->` type($dst)";
-
- let extraClassDefinition = [{
- std::string $cppClass::getIntrinsicName() {
- std::string intr = "llvm.x86.vcvtneobf162ps";
- VectorType vecType = getDst().getType();
- unsigned elemBitWidth = vecType.getElementTypeBitWidth();
- unsigned opBitWidth = vecType.getShape()[0] * elemBitWidth;
- intr += std::to_string(opBitWidth);
- return intr;
- }
- }];
-
- let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
- }];
-}
-
-//----------------------------------------------------------------------------//
-// AVX: Convert BF16 to F32 and broadcast into packed F32
-//----------------------------------------------------------------------------//
-
-def BcstBF16ToPackedF32Op : AVX_Op<"bcst.bf16_to_f32.packed", [MemoryEffects<[MemRead]>,
- DeclareOpInterfaceMethods<OneToOneIntrinsicOpInterface>]> {
- let summary = "AVX: Broadcasts BF16 into packed F32 Data.";
- let description = [{
- #### From the Intel Intrinsics Guide:
-
- Convert scalar BF16 (16-bit) floating-point element stored at memory locations
- starting at location `__A` to a single-precision (32-bit) floating-point,
- broadcast it to packed single-precision (32-bit) floating-point elements,
- and store the results in `dst`.
-
- Example:
- ```mlir
- %dst = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- ```
- }];
- let arguments = (ins AnyMemRef:$a);
- let results = (outs VectorOfLengthAndType<[4, 8], [F32]>:$dst);
- let assemblyFormat =
- "$a attr-dict`:` type($a)`->` type($dst)";
-
- let extraClassDefinition = [{
- std::string $cppClass::getIntrinsicName() {
- std::string intr = "llvm.x86.vbcstnebf162ps";
- VectorType vecType = getDst().getType();
- unsigned elemBitWidth = vecType.getElementTypeBitWidth();
- unsigned opBitWidth = vecType.getShape()[0] * elemBitWidth;
- intr += std::to_string(opBitWidth);
- return intr;
- }
- }];
-
- let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
- }];
-
-}
-
#endif // X86VECTOR_OPS
diff --git a/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h b/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h
index 308adfa5b9021..7bcf4c69b0a6c 100644
--- a/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h
+++ b/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h
@@ -14,8 +14,6 @@
#define MLIR_DIALECT_X86VECTOR_X86VECTORDIALECT_H_
#include "mlir/Bytecode/BytecodeOpInterface.h"
-#include "mlir/Conversion/LLVMCommon/Pattern.h"
-#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
#include "mlir/IR/BuiltinTypes.h"
#include "mlir/IR/Dialect.h"
#include "mlir/IR/OpDefinition.h"
diff --git a/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td b/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td
index 5176f4a447b6e..98d5ca70b4a7d 100644
--- a/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td
+++ b/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td
@@ -58,7 +58,7 @@ def OneToOneIntrinsicOpInterface : OpInterface<"OneToOneIntrinsicOp"> {
}],
/*retType=*/"SmallVector<Value>",
/*methodName=*/"getIntrinsicOperands",
- /*args=*/(ins "::mlir::RewriterBase &":$rewriter, "const LLVMTypeConverter &":$typeConverter),
+ /*args=*/(ins "::mlir::RewriterBase &":$rewriter),
/*methodBody=*/"",
/*defaultImplementation=*/"return SmallVector<Value>($_op->getOperands());"
>,
diff --git a/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp b/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp
index f5e5070c74f8f..5bb4dcfd60d83 100644
--- a/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp
+++ b/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp
@@ -31,26 +31,6 @@ void x86vector::X86VectorDialect::initialize() {
>();
}
-static SmallVector<Value>
-getMemrefBuffPtr(Location loc, ::mlir::TypedValue<::mlir::MemRefType> memrefVal,
- RewriterBase &rewriter,
- const LLVMTypeConverter &typeConverter) {
- SmallVector<Value> operands;
- auto opType = memrefVal.getType();
-
- Type llvmStructType = typeConverter.convertType(opType);
- Value llvmStruct =
- rewriter
- .create<UnrealizedConversionCastOp>(loc, llvmStructType, memrefVal)
- .getResult(0);
- MemRefDescriptor memRefDescriptor(llvmStruct);
-
- Value ptr = memRefDescriptor.bufferPtr(rewriter, loc, typeConverter, opType);
- operands.push_back(ptr);
-
- return operands;
-}
-
LogicalResult x86vector::MaskCompressOp::verify() {
if (getSrc() && getConstantSrc())
return emitError("cannot use both src and constant_src");
@@ -65,8 +45,8 @@ LogicalResult x86vector::MaskCompressOp::verify() {
return success();
}
-SmallVector<Value> x86vector::MaskCompressOp::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
+SmallVector<Value>
+x86vector::MaskCompressOp::getIntrinsicOperands(RewriterBase &rewriter) {
auto loc = getLoc();
auto opType = getA().getType();
@@ -84,8 +64,7 @@ SmallVector<Value> x86vector::MaskCompressOp::getIntrinsicOperands(
}
SmallVector<Value>
-x86vector::DotOp::getIntrinsicOperands(RewriterBase &rewriter,
- const LLVMTypeConverter &typeConverter) {
+x86vector::DotOp::getIntrinsicOperands(RewriterBase &rewriter) {
SmallVector<Value> operands(getOperands());
// Dot product of all elements, broadcasted to all elements.
Value scale =
@@ -95,22 +74,5 @@ x86vector::DotOp::getIntrinsicOperands(RewriterBase &rewriter,
return operands;
}
-SmallVector<Value> x86vector::BcstBF16ToPackedF32Op::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
- return getMemrefBuffPtr(getLoc(), getA(), rewriter, typeConverter);
-}
-
-SmallVector<Value>
-x86vector::CvtPackedOddIndexedBF16ToF32Op::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
- return getMemrefBuffPtr(getLoc(), getA(), rewriter, typeConverter);
-}
-
-SmallVector<Value>
-x86vector::CvtPackedEvenIndexedBF16ToF32Op::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
- return getMemrefBuffPtr(getLoc(), getA(), rewriter, typeConverter);
-}
-
#define GET_OP_CLASSES
#include "mlir/Dialect/X86Vector/X86Vector.cpp.inc"
diff --git a/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp b/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp
index d2297554a1012..c0c7f61f55f88 100644
--- a/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp
+++ b/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp
@@ -96,8 +96,8 @@ struct OneToOneIntrinsicOpConversion
LogicalResult matchAndRewrite(x86vector::OneToOneIntrinsicOp op,
PatternRewriter &rewriter) const override {
return intrinsicRewrite(op, rewriter.getStringAttr(op.getIntrinsicName()),
- op.getIntrinsicOperands(rewriter, typeConverter),
- typeConverter, rewriter);
+ op.getIntrinsicOperands(rewriter), typeConverter,
+ rewriter);
}
private:
@@ -114,8 +114,7 @@ void mlir::populateX86VectorLegalizeForLLVMExportPatterns(
void mlir::configureX86VectorLegalizeForExportTarget(
LLVMConversionTarget &target) {
- target.addIllegalOp<
- MaskCompressOp, MaskRndScaleOp, MaskScaleFOp, Vp2IntersectOp, DotBF16Op,
- CvtPackedF32ToBF16Op, CvtPackedEvenIndexedBF16ToF32Op,
- CvtPackedOddIndexedBF16ToF32Op, BcstBF16ToPackedF32Op, RsqrtOp, DotOp>();
+ target.addIllegalOp<MaskCompressOp, MaskRndScaleOp, MaskScaleFOp,
+ Vp2IntersectOp, DotBF16Op, CvtPackedF32ToBF16Op, RsqrtOp,
+ DotOp>();
}
diff --git a/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir b/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir
index 93b304c44de8e..df0be7bce83be 100644
--- a/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir
+++ b/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir
@@ -95,60 +95,6 @@ func.func @avx512bf16_cvt_packed_f32_to_bf16_512(
return %0 : vector<16xbf16>
}
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneebf162ps128"
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneebf162ps256"
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneobf162ps128"
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneobf162ps256"
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bsct_bf16_to_f32_packed_128
-func.func @avxbf16_bsct_bf16_to_f32_packed_128(
- %a: memref<1xbf16>) -> vector<4xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vbcstnebf162ps128"
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bsct_bf16_to_f32_packed_256
-func.func @avxbf16_bsct_bf16_to_f32_packed_256(
- %a: memref<1xbf16>) -> vector<8xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vbcstnebf162ps256"
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
// CHECK-LABEL: func @avx_rsqrt
func.func @avx_rsqrt(%a: vector<8xf32>) -> (vector<8xf32>)
{
diff --git a/mlir/test/Dialect/X86Vector/roundtrip.mlir b/mlir/test/Dialect/X86Vector/roundtrip.mlir
index b783cc869b981..0d00448c63da8 100644
--- a/mlir/test/Dialect/X86Vector/roundtrip.mlir
+++ b/mlir/test/Dialect/X86Vector/roundtrip.mlir
@@ -94,66 +94,6 @@ func.func @avx512bf16_cvt_packed_f32_to_bf16_512(
return %0 : vector<16xbf16>
}
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<8xbf16> -> vector<4xf32>
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<16xbf16> -> vector<8xf32>
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<8xbf16> -> vector<4xf32>
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<16xbf16> -> vector<8xf32>
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bcst_bf16_to_f32_128
-func.func @avxbf16_bcst_bf16_to_f32_128(
- %a: memref<1xbf16>) -> vector<4xf32>
-{
- // CHECK: x86vector.avx.bcst.bf16_to_f32.packed {{.*}} :
- // CHECK-SAME: memref<1xbf16> -> vector<4xf32>
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bcst_bf16_to_f32_256
-func.func @avxbf16_bcst_bf16_to_f32_256(
- %a: memref<1xbf16>) -> vector<8xf32>
-{
- // CHECK: x86vector.avx.bcst.bf16_to_f32.packed {{.*}} :
- // CHECK-SAME: memref<1xbf16> -> vector<8xf32>
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
// CHECK-LABEL: func @avx_rsqrt
func.func @avx_rsqrt(%a: vector<8xf32>) -> (vector<8xf32>)
{
diff --git a/mlir/test/Target/LLVMIR/x86vector.mlir b/mlir/test/Target/LLVMIR/x86vector.mlir
index a8bc180d1d0ac..85dad36334b1d 100644
--- a/mlir/test/Target/LLVMIR/x86vector.mlir
+++ b/mlir/test/Target/LLVMIR/x86vector.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s --convert-vector-to-llvm="enable-x86vector" --convert-to-llvm -reconcile-unrealized-casts \
+// RUN: mlir-opt %s --convert-vector-to-llvm="enable-x86vector" --convert-to-llvm \
// RUN: | mlir-translate --mlir-to-llvmir \
// RUN: | FileCheck %s
@@ -109,60 +109,6 @@ func.func @LLVM_x86_avx512bf16_cvtneps2bf16_512(
return %0 : vector<16xbf16>
}
-// CHECK-LABEL: define <4 x float> @LLVM_x86_avxbf16_vcvtneebf162ps128
-func.func @LLVM_x86_avxbf16_vcvtneebf162ps128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: call <4 x float> @llvm.x86.vcvtneebf162ps128(
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: define <8 x float> @LLVM_x86_avxbf16_vcvtneebf162ps256
-func.func @LLVM_x86_avxbf16_vcvtneebf162ps256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: call <8 x float> @llvm.x86.vcvtneebf162ps256(
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: define <4 x float> @LLVM_x86_avxbf16_vcvtneobf162ps128
-func.func @LLVM_x86_avxbf16_vcvtneobf162ps128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: call <4 x float> @llvm.x86.vcvtneobf162ps128(
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: define <8 x float> @LLVM_x86_avxbf16_vcvtneobf162ps256
-func.func @LLVM_x86_avxbf16_vcvtneobf162ps256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: call <8 x float> @llvm.x86.vcvtneobf162ps256(
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: define <4 x float> @LLVM_x86_avxbf16_vbcstnebf162ps128
-func.func @LLVM_x86_avxbf16_vbcstnebf162ps128(
- %a: memref<1xbf16>) -> vector<4xf32>
-{
- // CHECK: call <4 x float> @llvm.x86.vbcstnebf162ps128(
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: define <8 x float> @LLVM_x86_avxbf16_vbcstnebf162ps256
-func.func @LLVM_x86_avxbf16_vbcstnebf162ps256(
- %a: memref<1xbf16>) -> vector<8xf32>
-{
- // CHECK: call <8 x float> @llvm.x86.vbcstnebf162ps256(
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
// CHECK-LABEL: define <8 x float> @LLVM_x86_avx_rsqrt_ps_256
func.func @LLVM_x86_avx_rsqrt_ps_256(%a: vector <8xf32>) -> vector<8xf32>
{
|
|
@llvm/pr-subscribers-mlir-llvm Author: Jan Patrick Lehr (jplehr) ChangesReverts llvm/llvm-project#135143 This broke multiple bots, see PR. Full diff: https://github.com/llvm/llvm-project/pull/136781.diff 8 Files Affected:
diff --git a/mlir/include/mlir/Dialect/X86Vector/X86Vector.td b/mlir/include/mlir/Dialect/X86Vector/X86Vector.td
index 126fa0e352656..5be0d92db4630 100644
--- a/mlir/include/mlir/Dialect/X86Vector/X86Vector.td
+++ b/mlir/include/mlir/Dialect/X86Vector/X86Vector.td
@@ -83,7 +83,7 @@ def MaskCompressOp : AVX512_Op<"mask.compress", [Pure,
}
}];
let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
+ SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&);
}];
}
@@ -404,127 +404,8 @@ def DotOp : AVX_LowOp<"dot", [Pure,
}
}];
let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
+ SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&);
}];
}
-
-//----------------------------------------------------------------------------//
-// AVX: Convert packed BF16 even-indexed/odd-indexed elements into packed F32
-//----------------------------------------------------------------------------//
-
-def CvtPackedEvenIndexedBF16ToF32Op : AVX_Op<"cvt.packed.even.indexed.bf16_to_f32", [MemoryEffects<[MemRead]>,
- DeclareOpInterfaceMethods<OneToOneIntrinsicOpInterface>]> {
- let summary = "AVX: Convert packed BF16 even-indexed elements into packed F32 Data.";
- let description = [{
- #### From the Intel Intrinsics Guide:
-
- Convert packed BF16 (16-bit) floating-point even-indexed elements stored at
- memory locations starting at location `__A` to packed single-precision
- (32-bit) floating-point elements, and store the results in `dst`.
-
- Example:
- ```mlir
- %dst = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- ```
- }];
- let arguments = (ins AnyMemRef:$a);
- let results = (outs VectorOfLengthAndType<[4, 8], [F32]>:$dst);
- let assemblyFormat =
- "$a attr-dict`:` type($a)`->` type($dst)";
-
- let extraClassDefinition = [{
- std::string $cppClass::getIntrinsicName() {
- std::string intr = "llvm.x86.vcvtneebf162ps";
- VectorType vecType = getDst().getType();
- unsigned elemBitWidth = vecType.getElementTypeBitWidth();
- unsigned opBitWidth = vecType.getShape()[0] * elemBitWidth;
- intr += std::to_string(opBitWidth);
- return intr;
- }
- }];
-
- let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
- }];
-}
-
-def CvtPackedOddIndexedBF16ToF32Op : AVX_Op<"cvt.packed.odd.indexed.bf16_to_f32", [MemoryEffects<[MemRead]>,
- DeclareOpInterfaceMethods<OneToOneIntrinsicOpInterface>]> {
- let summary = "AVX: Convert packed BF16 odd-indexed elements into packed F32 Data.";
- let description = [{
- #### From the Intel Intrinsics Guide:
-
- Convert packed BF16 (16-bit) floating-point odd-indexed elements stored at
- memory locations starting at location `__A` to packed single-precision
- (32-bit) floating-point elements, and store the results in `dst`.
-
- Example:
- ```mlir
- %dst = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- ```
- }];
- let arguments = (ins AnyMemRef:$a);
- let results = (outs VectorOfLengthAndType<[4, 8], [F32]>:$dst);
- let assemblyFormat =
- "$a attr-dict`:` type($a)`->` type($dst)";
-
- let extraClassDefinition = [{
- std::string $cppClass::getIntrinsicName() {
- std::string intr = "llvm.x86.vcvtneobf162ps";
- VectorType vecType = getDst().getType();
- unsigned elemBitWidth = vecType.getElementTypeBitWidth();
- unsigned opBitWidth = vecType.getShape()[0] * elemBitWidth;
- intr += std::to_string(opBitWidth);
- return intr;
- }
- }];
-
- let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
- }];
-}
-
-//----------------------------------------------------------------------------//
-// AVX: Convert BF16 to F32 and broadcast into packed F32
-//----------------------------------------------------------------------------//
-
-def BcstBF16ToPackedF32Op : AVX_Op<"bcst.bf16_to_f32.packed", [MemoryEffects<[MemRead]>,
- DeclareOpInterfaceMethods<OneToOneIntrinsicOpInterface>]> {
- let summary = "AVX: Broadcasts BF16 into packed F32 Data.";
- let description = [{
- #### From the Intel Intrinsics Guide:
-
- Convert scalar BF16 (16-bit) floating-point element stored at memory locations
- starting at location `__A` to a single-precision (32-bit) floating-point,
- broadcast it to packed single-precision (32-bit) floating-point elements,
- and store the results in `dst`.
-
- Example:
- ```mlir
- %dst = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- ```
- }];
- let arguments = (ins AnyMemRef:$a);
- let results = (outs VectorOfLengthAndType<[4, 8], [F32]>:$dst);
- let assemblyFormat =
- "$a attr-dict`:` type($a)`->` type($dst)";
-
- let extraClassDefinition = [{
- std::string $cppClass::getIntrinsicName() {
- std::string intr = "llvm.x86.vbcstnebf162ps";
- VectorType vecType = getDst().getType();
- unsigned elemBitWidth = vecType.getElementTypeBitWidth();
- unsigned opBitWidth = vecType.getShape()[0] * elemBitWidth;
- intr += std::to_string(opBitWidth);
- return intr;
- }
- }];
-
- let extraClassDeclaration = [{
- SmallVector<Value> getIntrinsicOperands(::mlir::RewriterBase&, const LLVMTypeConverter&);
- }];
-
-}
-
#endif // X86VECTOR_OPS
diff --git a/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h b/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h
index 308adfa5b9021..7bcf4c69b0a6c 100644
--- a/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h
+++ b/mlir/include/mlir/Dialect/X86Vector/X86VectorDialect.h
@@ -14,8 +14,6 @@
#define MLIR_DIALECT_X86VECTOR_X86VECTORDIALECT_H_
#include "mlir/Bytecode/BytecodeOpInterface.h"
-#include "mlir/Conversion/LLVMCommon/Pattern.h"
-#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
#include "mlir/IR/BuiltinTypes.h"
#include "mlir/IR/Dialect.h"
#include "mlir/IR/OpDefinition.h"
diff --git a/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td b/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td
index 5176f4a447b6e..98d5ca70b4a7d 100644
--- a/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td
+++ b/mlir/include/mlir/Dialect/X86Vector/X86VectorInterfaces.td
@@ -58,7 +58,7 @@ def OneToOneIntrinsicOpInterface : OpInterface<"OneToOneIntrinsicOp"> {
}],
/*retType=*/"SmallVector<Value>",
/*methodName=*/"getIntrinsicOperands",
- /*args=*/(ins "::mlir::RewriterBase &":$rewriter, "const LLVMTypeConverter &":$typeConverter),
+ /*args=*/(ins "::mlir::RewriterBase &":$rewriter),
/*methodBody=*/"",
/*defaultImplementation=*/"return SmallVector<Value>($_op->getOperands());"
>,
diff --git a/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp b/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp
index f5e5070c74f8f..5bb4dcfd60d83 100644
--- a/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp
+++ b/mlir/lib/Dialect/X86Vector/IR/X86VectorDialect.cpp
@@ -31,26 +31,6 @@ void x86vector::X86VectorDialect::initialize() {
>();
}
-static SmallVector<Value>
-getMemrefBuffPtr(Location loc, ::mlir::TypedValue<::mlir::MemRefType> memrefVal,
- RewriterBase &rewriter,
- const LLVMTypeConverter &typeConverter) {
- SmallVector<Value> operands;
- auto opType = memrefVal.getType();
-
- Type llvmStructType = typeConverter.convertType(opType);
- Value llvmStruct =
- rewriter
- .create<UnrealizedConversionCastOp>(loc, llvmStructType, memrefVal)
- .getResult(0);
- MemRefDescriptor memRefDescriptor(llvmStruct);
-
- Value ptr = memRefDescriptor.bufferPtr(rewriter, loc, typeConverter, opType);
- operands.push_back(ptr);
-
- return operands;
-}
-
LogicalResult x86vector::MaskCompressOp::verify() {
if (getSrc() && getConstantSrc())
return emitError("cannot use both src and constant_src");
@@ -65,8 +45,8 @@ LogicalResult x86vector::MaskCompressOp::verify() {
return success();
}
-SmallVector<Value> x86vector::MaskCompressOp::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
+SmallVector<Value>
+x86vector::MaskCompressOp::getIntrinsicOperands(RewriterBase &rewriter) {
auto loc = getLoc();
auto opType = getA().getType();
@@ -84,8 +64,7 @@ SmallVector<Value> x86vector::MaskCompressOp::getIntrinsicOperands(
}
SmallVector<Value>
-x86vector::DotOp::getIntrinsicOperands(RewriterBase &rewriter,
- const LLVMTypeConverter &typeConverter) {
+x86vector::DotOp::getIntrinsicOperands(RewriterBase &rewriter) {
SmallVector<Value> operands(getOperands());
// Dot product of all elements, broadcasted to all elements.
Value scale =
@@ -95,22 +74,5 @@ x86vector::DotOp::getIntrinsicOperands(RewriterBase &rewriter,
return operands;
}
-SmallVector<Value> x86vector::BcstBF16ToPackedF32Op::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
- return getMemrefBuffPtr(getLoc(), getA(), rewriter, typeConverter);
-}
-
-SmallVector<Value>
-x86vector::CvtPackedOddIndexedBF16ToF32Op::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
- return getMemrefBuffPtr(getLoc(), getA(), rewriter, typeConverter);
-}
-
-SmallVector<Value>
-x86vector::CvtPackedEvenIndexedBF16ToF32Op::getIntrinsicOperands(
- RewriterBase &rewriter, const LLVMTypeConverter &typeConverter) {
- return getMemrefBuffPtr(getLoc(), getA(), rewriter, typeConverter);
-}
-
#define GET_OP_CLASSES
#include "mlir/Dialect/X86Vector/X86Vector.cpp.inc"
diff --git a/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp b/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp
index d2297554a1012..c0c7f61f55f88 100644
--- a/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp
+++ b/mlir/lib/Dialect/X86Vector/Transforms/LegalizeForLLVMExport.cpp
@@ -96,8 +96,8 @@ struct OneToOneIntrinsicOpConversion
LogicalResult matchAndRewrite(x86vector::OneToOneIntrinsicOp op,
PatternRewriter &rewriter) const override {
return intrinsicRewrite(op, rewriter.getStringAttr(op.getIntrinsicName()),
- op.getIntrinsicOperands(rewriter, typeConverter),
- typeConverter, rewriter);
+ op.getIntrinsicOperands(rewriter), typeConverter,
+ rewriter);
}
private:
@@ -114,8 +114,7 @@ void mlir::populateX86VectorLegalizeForLLVMExportPatterns(
void mlir::configureX86VectorLegalizeForExportTarget(
LLVMConversionTarget &target) {
- target.addIllegalOp<
- MaskCompressOp, MaskRndScaleOp, MaskScaleFOp, Vp2IntersectOp, DotBF16Op,
- CvtPackedF32ToBF16Op, CvtPackedEvenIndexedBF16ToF32Op,
- CvtPackedOddIndexedBF16ToF32Op, BcstBF16ToPackedF32Op, RsqrtOp, DotOp>();
+ target.addIllegalOp<MaskCompressOp, MaskRndScaleOp, MaskScaleFOp,
+ Vp2IntersectOp, DotBF16Op, CvtPackedF32ToBF16Op, RsqrtOp,
+ DotOp>();
}
diff --git a/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir b/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir
index 93b304c44de8e..df0be7bce83be 100644
--- a/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir
+++ b/mlir/test/Dialect/X86Vector/legalize-for-llvm.mlir
@@ -95,60 +95,6 @@ func.func @avx512bf16_cvt_packed_f32_to_bf16_512(
return %0 : vector<16xbf16>
}
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneebf162ps128"
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneebf162ps256"
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneobf162ps128"
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vcvtneobf162ps256"
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bsct_bf16_to_f32_packed_128
-func.func @avxbf16_bsct_bf16_to_f32_packed_128(
- %a: memref<1xbf16>) -> vector<4xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vbcstnebf162ps128"
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bsct_bf16_to_f32_packed_256
-func.func @avxbf16_bsct_bf16_to_f32_packed_256(
- %a: memref<1xbf16>) -> vector<8xf32>
-{
- // CHECK: llvm.call_intrinsic "llvm.x86.vbcstnebf162ps256"
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
// CHECK-LABEL: func @avx_rsqrt
func.func @avx_rsqrt(%a: vector<8xf32>) -> (vector<8xf32>)
{
diff --git a/mlir/test/Dialect/X86Vector/roundtrip.mlir b/mlir/test/Dialect/X86Vector/roundtrip.mlir
index b783cc869b981..0d00448c63da8 100644
--- a/mlir/test/Dialect/X86Vector/roundtrip.mlir
+++ b/mlir/test/Dialect/X86Vector/roundtrip.mlir
@@ -94,66 +94,6 @@ func.func @avx512bf16_cvt_packed_f32_to_bf16_512(
return %0 : vector<16xbf16>
}
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<8xbf16> -> vector<4xf32>
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_even_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<16xbf16> -> vector<8xf32>
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<8xbf16> -> vector<4xf32>
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256
-func.func @avxbf16_cvt_packed_odd_indexed_bf16_to_f32_256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 {{.*}} :
- // CHECK-SAME: memref<16xbf16> -> vector<8xf32>
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bcst_bf16_to_f32_128
-func.func @avxbf16_bcst_bf16_to_f32_128(
- %a: memref<1xbf16>) -> vector<4xf32>
-{
- // CHECK: x86vector.avx.bcst.bf16_to_f32.packed {{.*}} :
- // CHECK-SAME: memref<1xbf16> -> vector<4xf32>
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: func @avxbf16_bcst_bf16_to_f32_256
-func.func @avxbf16_bcst_bf16_to_f32_256(
- %a: memref<1xbf16>) -> vector<8xf32>
-{
- // CHECK: x86vector.avx.bcst.bf16_to_f32.packed {{.*}} :
- // CHECK-SAME: memref<1xbf16> -> vector<8xf32>
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
// CHECK-LABEL: func @avx_rsqrt
func.func @avx_rsqrt(%a: vector<8xf32>) -> (vector<8xf32>)
{
diff --git a/mlir/test/Target/LLVMIR/x86vector.mlir b/mlir/test/Target/LLVMIR/x86vector.mlir
index a8bc180d1d0ac..85dad36334b1d 100644
--- a/mlir/test/Target/LLVMIR/x86vector.mlir
+++ b/mlir/test/Target/LLVMIR/x86vector.mlir
@@ -1,4 +1,4 @@
-// RUN: mlir-opt %s --convert-vector-to-llvm="enable-x86vector" --convert-to-llvm -reconcile-unrealized-casts \
+// RUN: mlir-opt %s --convert-vector-to-llvm="enable-x86vector" --convert-to-llvm \
// RUN: | mlir-translate --mlir-to-llvmir \
// RUN: | FileCheck %s
@@ -109,60 +109,6 @@ func.func @LLVM_x86_avx512bf16_cvtneps2bf16_512(
return %0 : vector<16xbf16>
}
-// CHECK-LABEL: define <4 x float> @LLVM_x86_avxbf16_vcvtneebf162ps128
-func.func @LLVM_x86_avxbf16_vcvtneebf162ps128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: call <4 x float> @llvm.x86.vcvtneebf162ps128(
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: define <8 x float> @LLVM_x86_avxbf16_vcvtneebf162ps256
-func.func @LLVM_x86_avxbf16_vcvtneebf162ps256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: call <8 x float> @llvm.x86.vcvtneebf162ps256(
- %0 = x86vector.avx.cvt.packed.even.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: define <4 x float> @LLVM_x86_avxbf16_vcvtneobf162ps128
-func.func @LLVM_x86_avxbf16_vcvtneobf162ps128(
- %a: memref<8xbf16>) -> vector<4xf32>
-{
- // CHECK: call <4 x float> @llvm.x86.vcvtneobf162ps128(
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<8xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: define <8 x float> @LLVM_x86_avxbf16_vcvtneobf162ps256
-func.func @LLVM_x86_avxbf16_vcvtneobf162ps256(
- %a: memref<16xbf16>) -> vector<8xf32>
-{
- // CHECK: call <8 x float> @llvm.x86.vcvtneobf162ps256(
- %0 = x86vector.avx.cvt.packed.odd.indexed.bf16_to_f32 %a : memref<16xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
-// CHECK-LABEL: define <4 x float> @LLVM_x86_avxbf16_vbcstnebf162ps128
-func.func @LLVM_x86_avxbf16_vbcstnebf162ps128(
- %a: memref<1xbf16>) -> vector<4xf32>
-{
- // CHECK: call <4 x float> @llvm.x86.vbcstnebf162ps128(
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<4xf32>
- return %0 : vector<4xf32>
-}
-
-// CHECK-LABEL: define <8 x float> @LLVM_x86_avxbf16_vbcstnebf162ps256
-func.func @LLVM_x86_avxbf16_vbcstnebf162ps256(
- %a: memref<1xbf16>) -> vector<8xf32>
-{
- // CHECK: call <8 x float> @llvm.x86.vbcstnebf162ps256(
- %0 = x86vector.avx.bcst.bf16_to_f32.packed %a : memref<1xbf16> -> vector<8xf32>
- return %0 : vector<8xf32>
-}
-
// CHECK-LABEL: define <8 x float> @LLVM_x86_avx_rsqrt_ps_256
func.func @LLVM_x86_avx_rsqrt_ps_256(%a: vector <8xf32>) -> vector<8xf32>
{
|
IanWood1
pushed a commit
to IanWood1/llvm-project
that referenced
this pull request
May 6, 2025
…ons" (llvm#136781) Reverts llvm#135143 This broke multiple bots, see PR.
IanWood1
pushed a commit
to IanWood1/llvm-project
that referenced
this pull request
May 6, 2025
…ons" (llvm#136781) Reverts llvm#135143 This broke multiple bots, see PR.
IanWood1
pushed a commit
to IanWood1/llvm-project
that referenced
this pull request
May 6, 2025
…ons" (llvm#136781) Reverts llvm#135143 This broke multiple bots, see PR.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Reverts #135143
This broke multiple bots, see PR.