[mlir][amdgpu] Sink op creation in scaled conversion intrinsics (NFC) #168542
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
Member
|
@llvm/pr-subscribers-mlir-gpu @llvm/pr-subscribers-mlir Author: Erick Ochoa Lopez (amd-eochoalo) ChangesWhere possible:
Full diff: https://github.com/llvm/llvm-project/pull/168542.diff 1 Files Affected:
diff --git a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
index edc6565f44f00..97487c727f999 100644
--- a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
+++ b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
@@ -1738,15 +1738,11 @@ LogicalResult ScaledExtPacked816OpLowering::matchAndRewrite(
auto sourceType = cast<VectorType>(op.getSource().getType());
auto srcElemType = cast<FloatType>(sourceType.getElementType());
unsigned bitWidth = srcElemType.getWidth();
- int32_t scaleSel =
- getScaleSel(blockSize, bitWidth, firstScaleLane, firstScaleByte);
auto targetType = cast<VectorType>(op.getResult().getType());
auto destElemType = cast<FloatType>(targetType.getElementType());
- IntegerType i32 = rewriter.getI32Type();
- Value castedScale =
- LLVM::BitcastOp::create(rewriter, loc, i32, adaptor.getScale());
+ IntegerType i32 = rewriter.getI32Type();
Value source = adaptor.getSource();
Type llvmResultType = typeConverter->convertType(op.getResult().getType());
Type packedType = nullptr;
@@ -1767,15 +1763,21 @@ LogicalResult ScaledExtPacked816OpLowering::matchAndRewrite(
return rewriter.notifyMatchFailure(op, "type conversion failed");
}
- Value castedSource =
- LLVM::BitcastOp::create(rewriter, loc, packedType, source);
-
std::optional<StringRef> maybeIntrinsic =
scaledExtPacked816ToIntrinsic(srcElemType, destElemType);
if (!maybeIntrinsic.has_value())
return op.emitOpError(
"no intrinsic matching packed scaled conversion on the given chipset");
+ int32_t scaleSel =
+ getScaleSel(blockSize, bitWidth, firstScaleLane, firstScaleByte);
+
+ Value castedScale =
+ LLVM::BitcastOp::create(rewriter, loc, i32, adaptor.getScale());
+
+ Value castedSource =
+ LLVM::BitcastOp::create(rewriter, loc, packedType, source);
+
OperationState loweredOp(loc, *maybeIntrinsic);
loweredOp.addTypes({llvmResultType});
loweredOp.addOperands({castedSource, castedScale});
|
Member
|
@llvm/pr-subscribers-backend-amdgpu Author: Erick Ochoa Lopez (amd-eochoalo) ChangesWhere possible:
Full diff: https://github.com/llvm/llvm-project/pull/168542.diff 1 Files Affected:
diff --git a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
index edc6565f44f00..97487c727f999 100644
--- a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
+++ b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
@@ -1738,15 +1738,11 @@ LogicalResult ScaledExtPacked816OpLowering::matchAndRewrite(
auto sourceType = cast<VectorType>(op.getSource().getType());
auto srcElemType = cast<FloatType>(sourceType.getElementType());
unsigned bitWidth = srcElemType.getWidth();
- int32_t scaleSel =
- getScaleSel(blockSize, bitWidth, firstScaleLane, firstScaleByte);
auto targetType = cast<VectorType>(op.getResult().getType());
auto destElemType = cast<FloatType>(targetType.getElementType());
- IntegerType i32 = rewriter.getI32Type();
- Value castedScale =
- LLVM::BitcastOp::create(rewriter, loc, i32, adaptor.getScale());
+ IntegerType i32 = rewriter.getI32Type();
Value source = adaptor.getSource();
Type llvmResultType = typeConverter->convertType(op.getResult().getType());
Type packedType = nullptr;
@@ -1767,15 +1763,21 @@ LogicalResult ScaledExtPacked816OpLowering::matchAndRewrite(
return rewriter.notifyMatchFailure(op, "type conversion failed");
}
- Value castedSource =
- LLVM::BitcastOp::create(rewriter, loc, packedType, source);
-
std::optional<StringRef> maybeIntrinsic =
scaledExtPacked816ToIntrinsic(srcElemType, destElemType);
if (!maybeIntrinsic.has_value())
return op.emitOpError(
"no intrinsic matching packed scaled conversion on the given chipset");
+ int32_t scaleSel =
+ getScaleSel(blockSize, bitWidth, firstScaleLane, firstScaleByte);
+
+ Value castedScale =
+ LLVM::BitcastOp::create(rewriter, loc, i32, adaptor.getScale());
+
+ Value castedSource =
+ LLVM::BitcastOp::create(rewriter, loc, packedType, source);
+
OperationState loweredOp(loc, *maybeIntrinsic);
loweredOp.addTypes({llvmResultType});
loweredOp.addOperands({castedSource, castedScale});
|
🐧 Linux x64 Test Results
|
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Where possible: