MLIR  19.0.0git
Classes | Namespaces | Functions
VectorUtils.h File Reference
#include "mlir/Dialect/MemRef/IR/MemRef.h"
#include "mlir/Dialect/Tensor/IR/Tensor.h"
#include "mlir/Dialect/Utils/IndexingUtils.h"
#include "mlir/Dialect/Vector/IR/VectorOps.h"
#include "mlir/IR/BuiltinAttributes.h"
#include "mlir/Support/LLVM.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/TypeSwitch.h"

Go to the source code of this file.


struct  mlir::vector::MaskableOpRewritePattern< SourceOp >
 A pattern for ops that implement MaskableOpInterface and that might be masked (i.e. More...


 Include the generated interface declarations.


Value mlir::vector::createOrFoldDimOp (OpBuilder &b, Location loc, Value source, int64_t dim)
 Helper function that creates a memref::DimOp or tensor::DimOp depending on the type of source. More...
FailureOr< std::pair< int, int > > mlir::vector::isTranspose2DSlice (vector::TransposeOp op)
 Returns two dims that are greater than one if the transposition is applied on a 2D slice. More...
bool mlir::vector::isContiguousSlice (MemRefType memrefType, VectorType vectorType)
 Return true if vectorType is a contiguous slice of memrefType. More...
std::optional< StaticTileOffsetRangemlir::vector::createUnrollIterator (VectorType vType, int64_t targetRank=1)
 Returns an iterator for all positions in the leading dimensions of vType up to the targetRank. More...
SmallVector< OpFoldResultmlir::vector::getMixedSizesXfer (bool hasTensorSemantics, Operation *xfer, RewriterBase &rewriter)
 A wrapper for getMixedSizes for vector.transfer_read and vector.transfer_write Ops (for source and destination, respectively). More...
bool mlir::vector::isLinearizableVector (VectorType type)
 Returns true if the input Vector type can be linearized. More...
Value mlir::vector::createReadOrMaskedRead (OpBuilder &builder, Location loc, Value source, ArrayRef< int64_t > readShape, Value padValue, bool useInBoundsInsteadOfMasking)
 Create a TransferReadOp from source with static shape readShape. More...
LogicalResult mlir::vector::isValidMaskedInputVector (ArrayRef< int64_t > shape, ArrayRef< int64_t > inputVectorSizes)
 Returns success if inputVectorSizes is a valid masking configuraion for given shape, i.e., it meets: More...