MLIR  19.0.0git
Public Member Functions | List of all members
mlir::sparse_tensor::SparsificationAndBufferizationPass Class Reference

A pass that lowers tensor ops to memref ops, regardless of whether they are dense or sparse. More...

+ Inheritance diagram for mlir::sparse_tensor::SparsificationAndBufferizationPass:

Public Member Functions

 SparsificationAndBufferizationPass (const bufferization::OneShotBufferizationOptions &bufferizationOptions, const SparsificationOptions &sparsificationOptions, bool createSparseDeallocs, bool enableRuntimeLibrary, bool enableBufferInitialization, unsigned vectorLength, bool enableVLAVectorization, bool enableSIMDIndex32, bool enableGPULibgen)
 
LogicalResult runDenseBufferization ()
 Bufferize all dense ops. More...
 
void runOnOperation () override
 

Detailed Description

A pass that lowers tensor ops to memref ops, regardless of whether they are dense or sparse.

One-Shot Analysis is used to detect RaW conflicts and to insert buffer copies of the tensor level (insertTensorCopies). Afterwards, the lowering of tensor ops to memref ops follows a different code path depending on whether the op is sparse or dense:

Definition at line 59 of file SparsificationAndBufferizationPass.cpp.

Constructor & Destructor Documentation

◆ SparsificationAndBufferizationPass()

mlir::sparse_tensor::SparsificationAndBufferizationPass::SparsificationAndBufferizationPass ( const bufferization::OneShotBufferizationOptions bufferizationOptions,
const SparsificationOptions sparsificationOptions,
bool  createSparseDeallocs,
bool  enableRuntimeLibrary,
bool  enableBufferInitialization,
unsigned  vectorLength,
bool  enableVLAVectorization,
bool  enableSIMDIndex32,
bool  enableGPULibgen 
)
inline

Definition at line 63 of file SparsificationAndBufferizationPass.cpp.

Member Function Documentation

◆ runDenseBufferization()

LogicalResult mlir::sparse_tensor::SparsificationAndBufferizationPass::runDenseBufferization ( )
inline

Bufferize all dense ops.

This assumes that no further analysis is needed and that all required buffer copies were already inserted by insertTensorCopies in the form of bufferization.alloc_tensor ops.

Definition at line 82 of file SparsificationAndBufferizationPass.cpp.

References mlir::bufferization::OpFilter::denyOperation(), and mlir::bufferization::BufferizationOptions::opFilter.

Referenced by runOnOperation().

◆ runOnOperation()

void mlir::sparse_tensor::SparsificationAndBufferizationPass::runOnOperation ( )
inlineoverride

The documentation for this class was generated from the following file: