|
MLIR 22.0.0git
|
Builder for gpu::BlockIdOps used to map scf.forall to blocks. More...
#include "mlir/Dialect/GPU/TransformOps/Utils.h"
Public Member Functions | |
| GpuBlockIdBuilder (MLIRContext *ctx, bool useLinearMapping=false, DeviceMaskingAttrInterface mask=nullptr) | |
| Public Member Functions inherited from mlir::transform::gpu::GpuIdBuilder | |
| GpuIdBuilder ()=default | |
| GpuIdBuilder (MLIRContext *ctx, bool useLinearMapping, const MappingIdBuilderFnType &builder) | |
Additional Inherited Members | |
| Public Types inherited from mlir::transform::gpu::GpuIdBuilder | |
| using | MappingIdBuilderFnType |
| Public Attributes inherited from mlir::transform::gpu::GpuIdBuilder | |
| SmallVector< DeviceMappingAttrInterface > | mappingAttributes |
| The mapping attributes targeted by this generator. | |
| GpuIdBuilderFnType | idBuilder |
| The constructor that builds the concrete IR for mapping ids. | |
Builder for gpu::BlockIdOps used to map scf.forall to blocks.
If useLinearMapping is false, the idBuilder method returns 3D values used for indexing rewrites as well as 3D sizes for predicate generation. If useLinearMapping is true, the idBuilder method returns nD values used for indexing rewrites as well as 1D sizes for predicate generation. If mask is provided, it will be used to filter the active blocks.
| mlir::transform::gpu::GpuBlockIdBuilder::GpuBlockIdBuilder | ( | MLIRContext * | ctx, |
| bool | useLinearMapping = false, | ||
| DeviceMaskingAttrInterface | mask = nullptr ) |
Definition at line 296 of file Utils.cpp.
References mlir::transform::gpu::GpuIdBuilder::GpuIdBuilder().