|
MLIR 24.0.0git
|
Go to the source code of this file.
Namespaces | |
| namespace | mlir |
| Include the generated interface declarations. | |
Macros | |
| #define | GEN_PASS_DECL_CONVERTVECTORTONVGPUPASS |
Functions | |
| std::unique_ptr<::mlir::Pass > | mlir::createConvertVectorToNVGPUPass () |
| void | mlir::populatePrepareVectorToNVMMAPatterns (RewritePatternSet &patterns) |
| Populate patterns that prepare vector operations for lowering to nvgpu.mma.sync operations. | |
| LogicalResult | mlir::convertVectorToNVVMCompatibleMMASync (RewriterBase &rewriter, Operation *rootOp) |
| Convert vector ops nested under rootOp to vector and GPU operations compatible with the nvvm.mma.sync lowering path. | |
| #define GEN_PASS_DECL_CONVERTVECTORTONVGPUPASS |
Definition at line 20 of file VectorToNVGPU.h.