MLIR
20.0.0git
|
Classes | |
struct | ShapeMappingValue |
ShapeMappingValue works as the value of ShapeMappingAnalysis table, where funcSymbol is the symbol of mapping function, and inputs are the actual parameters for the function. More... | |
struct | ShapeMappingAnalysis |
ShapeMappingAnalysis is used together with OutlineShapeComputationPass to preserve Value and corresponding shape function / arguments mapping information. More... | |
Functions | |
RankedTensorType | getExtentTensorType (MLIRContext *ctx, int64_t rank=ShapedType::kDynamic) |
Alias type for extent tensors. More... | |
bool | isExtentTensorType (Type) |
LogicalResult | getShapeVec (Value input, SmallVectorImpl< int64_t > &shapeValues) |
void | registerBufferizableOpInterfaceExternalModels (DialectRegistry ®istry) |
RankedTensorType mlir::shape::getExtentTensorType | ( | MLIRContext * | ctx, |
int64_t | rank = ShapedType::kDynamic |
||
) |
LogicalResult mlir::shape::getShapeVec | ( | Value | input, |
SmallVectorImpl< int64_t > & | shapeValues | ||
) |
Definition at line 50 of file Shape.cpp.
References mlir::Value::getDefiningOp(), mlir::m_Constant(), and mlir::matchPattern().
void mlir::shape::registerBufferizableOpInterfaceExternalModels | ( | DialectRegistry & | registry | ) |
Definition at line 138 of file BufferizableOpInterfaceImpl.cpp.
References mlir::DialectRegistry::addExtension().
Referenced by mlir::registerAllDialects().