mlir::GPUDynamicSharedMemoryOpLowering Struct Reference
Lowering for gpu.dynamic.shared.memory to LLVM dialect. More...
#include "Conversion/GPUCommon/GPUOpsLowering.h"
Inheritance diagram for mlir::GPUDynamicSharedMemoryOpLowering:
Public Member Functions | |
| GPUDynamicSharedMemoryOpLowering (const LLVMTypeConverter &converter, unsigned alignmentBit=0, PatternBenefit benefit=1) | |
| LogicalResult | matchAndRewrite (gpu::DynamicSharedMemoryOp op, OpAdaptor adaptor, ConversionPatternRewriter &rewriter) const override |
| Public Member Functions inherited from mlir::ConvertOpToLLVMPattern< gpu::DynamicSharedMemoryOp > | |
| ConvertOpToLLVMPattern (const LLVMTypeConverter &typeConverter, PatternBenefit benefit=1) | |
| LogicalResult | matchAndRewrite (Operation *op, ArrayRef< Value > operands, ConversionPatternRewriter &rewriter) const final |
| Wrappers around the RewritePattern methods that pass the derived op type. | |
| Public Member Functions inherited from mlir::ConvertToLLVMPattern | |
| ConvertToLLVMPattern (StringRef rootOpName, MLIRContext *context, const LLVMTypeConverter &typeConverter, PatternBenefit benefit=1) | |
Additional Inherited Members | |
| Public Types inherited from mlir::ConvertOpToLLVMPattern< gpu::DynamicSharedMemoryOp > | |
| using | OpAdaptor |
| using | OneToNOpAdaptor |
| Protected Member Functions inherited from mlir::ConvertToLLVMPattern | |
| LLVM::LLVMDialect & | getDialect () const |
| Returns the LLVM dialect. | |
| const LLVMTypeConverter * | getTypeConverter () const |
| Type | getIndexType () const |
| Gets the MLIR type wrapping the LLVM integer type whose bit width is defined by the used type converter. | |
| Type | getIntPtrType (unsigned addressSpace=0) const |
| Gets the MLIR type wrapping the LLVM integer type whose bit width corresponds to that of a LLVM pointer type. | |
| Type | getVoidType () const |
| Gets the MLIR type wrapping the LLVM void type. | |
| Type | getVoidPtrType () const |
| Get the MLIR type wrapping the LLVM i8* type. | |
| Type | getPtrType (unsigned addressSpace=0) const |
| Get the MLIR type wrapping the LLVM ptr type. | |
| Value | getStridedElementPtr (ConversionPatternRewriter &rewriter, Location loc, MemRefType type, Value memRefDesc, ValueRange indices, LLVM::GEPNoWrapFlags noWrapFlags=LLVM::GEPNoWrapFlags::none) const |
| Convenience wrapper for the corresponding helper utility. | |
| bool | isConvertibleAndHasIdentityMaps (MemRefType type) const |
| Returns if the given memref type is convertible to LLVM and has an identity layout map. | |
| Type | getElementPtrType (MemRefType type) const |
| Returns the type of a pointer to an element of the memref. | |
| void | getMemRefDescriptorSizes (Location loc, MemRefType memRefType, ValueRange dynamicSizes, ConversionPatternRewriter &rewriter, SmallVectorImpl< Value > &sizes, SmallVectorImpl< Value > &strides, Value &size, bool sizeInBytes=true) const |
| Computes sizes, strides and buffer size of memRefType with identity layout. | |
| Value | getSizeInBytes (Location loc, Type type, ConversionPatternRewriter &rewriter) const |
| Computes the size of type in bytes. | |
| Value | getNumElements (Location loc, MemRefType memRefType, ValueRange dynamicSizes, ConversionPatternRewriter &rewriter) const |
| Computes total number of elements for the given MemRef and dynamicSizes. | |
| MemRefDescriptor | createMemRefDescriptor (Location loc, MemRefType memRefType, Value allocatedPtr, Value alignedPtr, ArrayRef< Value > sizes, ArrayRef< Value > strides, ConversionPatternRewriter &rewriter) const |
| Creates and populates a canonical memref descriptor struct. | |
| Value | copyUnrankedDescriptor (OpBuilder &builder, Location loc, UnrankedMemRefType memRefType, Value operand, bool toDynamic) const |
| Copies the given unranked memory descriptor to heap-allocated memory (if toDynamic is true) or to stack-allocated memory (otherwise) and returns the new descriptor. | |
| LogicalResult | copyUnrankedDescriptors (OpBuilder &builder, Location loc, TypeRange origTypes, SmallVectorImpl< Value > &operands, bool toDynamic) const |
| Copies the memory descriptor for any operands that were unranked descriptors originally to heap-allocated memory (if toDynamic is true) or to stack-allocated memory (otherwise). | |
| Static Protected Member Functions inherited from mlir::ConvertToLLVMPattern | |
| static Value | createIndexAttrConstant (OpBuilder &builder, Location loc, Type resultType, int64_t value) |
| Create a constant Op producing a value of resultType from an index-typed integer attribute. | |
Detailed Description
Lowering for gpu.dynamic.shared.memory to LLVM dialect.
The pattern first create a 0-sized global array symbol similar as LLVM expects. It constructs a memref descriptor with these values and return it.
Definition at line 45 of file GPUOpsLowering.h.
Constructor & Destructor Documentation
◆ GPUDynamicSharedMemoryOpLowering()
|
inline |
Definition at line 49 of file GPUOpsLowering.h.
References mlir::ConvertOpToLLVMPattern< gpu::DynamicSharedMemoryOp >::ConvertOpToLLVMPattern().
Member Function Documentation
◆ matchAndRewrite()
|
override |
Definition at line 721 of file GPUOpsLowering.cpp.
References mlir::ConvertToLLVMPattern::createMemRefDescriptor(), getDynamicSharedMemorySymbol(), mlir::ConvertToLLVMPattern::getMemRefDescriptorSizes(), mlir::ConvertToLLVMPattern::getTypeConverter(), and success().
The documentation for this struct was generated from the following files:
- lib/Conversion/GPUCommon/GPUOpsLowering.h
- lib/Conversion/GPUCommon/GPUOpsLowering.cpp
Generated on for MLIR by
1.14.0