Options for analysis-enabled bufferization. More...
#include "mlir/Dialect/Bufferization/Transforms/OneShotAnalysis.h"
Inheritance diagram for mlir::bufferization::OneShotBufferizationOptions:
Public Types | |
| enum class | AnalysisHeuristic { BottomUp , TopDown , BottomUpFromTerminators , Fuzzer } |
| Public Types inherited from mlir::bufferization::BufferizationOptions | |
| using | AllocationFn = std::function< FailureOr< Value >(OpBuilder &, Location, MemRefType, ValueRange, unsigned int)> |
| Allocator function: Generate a memref allocation with the given type, dynamic extents and alignment. More... | |
| using | MemCpyFn = std::function< LogicalResult(OpBuilder &, Location, Value, Value)> |
| Memcpy function: Generate a memcpy between two buffers. More... | |
| using | AnalysisStateInitFn = std::function< void(AnalysisState &)> |
| Initializer function for analysis state. More... | |
| using | FunctionArgTypeConverterFn = std::function< BaseMemRefType(TensorType, Attribute memorySpace, func::FuncOp, const BufferizationOptions &)> |
| Tensor -> MemRef type converter. More... | |
| using | UnknownTypeConverterFn = std::function< BaseMemRefType(Value, Attribute memorySpace, const BufferizationOptions &)> |
| Tensor -> MemRef type converter. More... | |
| using | DefaultMemorySpaceFn = std::function< std::optional< Attribute >(TensorType t)> |
Public Member Functions | |
| OneShotBufferizationOptions ()=default | |
| Public Member Functions inherited from mlir::bufferization::BufferizationOptions | |
| BufferizationOptions () | |
| BufferizableOpInterface | dynCastBufferizableOp (Operation *op) const |
| Try to cast the given op to BufferizableOpInterface if the op is allow listed. More... | |
| BufferizableOpInterface | dynCastBufferizableOp (Value value) const |
| Try to cast the given value to BufferizableOpInterface if the op is allow listed. More... | |
| bool | isOpAllowed (Operation *op) const |
Return true if the given op should be bufferized. More... | |
| FailureOr< Value > | createAlloc (OpBuilder &b, Location loc, MemRefType type, ValueRange dynShape) const |
| Create a memref allocation with the given type and dynamic extents. More... | |
| LogicalResult | createMemCpy (OpBuilder &b, Location loc, Value from, Value to) const |
| Creates a memcpy between two given buffers. More... | |
| void | setFunctionBoundaryTypeConversion (LayoutMapOption layoutMapOption) |
| This function controls buffer types on function signatures. More... | |
Public Attributes | |
| bool | allowReturnAllocsFromLoops = false |
| Specifies whether returning newly allocated memrefs from loops should be allowed. More... | |
| bool | dumpAliasSets = false |
| Specifies whether the tensor IR should be annotated with alias sets. More... | |
| AnalysisHeuristic | analysisHeuristic = AnalysisHeuristic::BottomUp |
| The heuristic controls the order in which ops are traversed during the analysis. More... | |
| llvm::ArrayRef< std::string > | noAnalysisFuncFilter |
| Specify the functions that should not be analyzed. More... | |
| unsigned | analysisFuzzerSeed = 0 |
| Seed for the analysis fuzzer. More... | |
| Public Attributes inherited from mlir::bufferization::BufferizationOptions | |
| OpFilter | opFilter |
| A filter that specifies which ops should be bufferized and which ops should be ignored. More... | |
| std::optional< AllocationFn > | allocationFn |
| Helper functions for allocation and memory copying. More... | |
| std::optional< MemCpyFn > | memCpyFn |
| bool | allowUnknownOps = false |
| Specifies whether not bufferizable ops are allowed in the input. More... | |
| bool | bufferizeFunctionBoundaries = false |
| Specifies whether function boundaries (ops in the func dialect) should be bufferized or not. More... | |
| bool | checkParallelRegions = true |
| bool | enforceAliasingInvariants = true |
| Certain ops have aliasing OpOperand/OpResult invariants (e.g., scf.for). More... | |
| FunctionArgTypeConverterFn | functionArgTypeConverterFn = nullptr |
| Type converter from tensors to memrefs. More... | |
| bool | inferFunctionResultLayout = true |
| If true, function result types are inferred from the body of the function. More... | |
| UnknownTypeConverterFn | unknownTypeConverterFn = nullptr |
| Type converter from tensors to memrefs. More... | |
| DefaultMemorySpaceFn | defaultMemorySpaceFn |
| bool | copyBeforeWrite = false |
If set to true, the analysis is skipped. More... | |
| bool | testAnalysisOnly = false |
If set to true, does not modify the IR apart from adding attributes (for checking the results of the analysis) and post analysis steps. More... | |
| bool | printConflicts = false |
If set to true, the IR is annotated with details about RaW conflicts. More... | |
| unsigned int | bufferAlignment = 64 |
| Buffer alignment for new memory allocations. More... | |
| SmallVector< AnalysisStateInitFn > | stateInitializers |
| Initializer functions for analysis state. More... | |
Detailed Description
Options for analysis-enabled bufferization.
Definition at line 26 of file OneShotAnalysis.h.
Member Enumeration Documentation
◆ AnalysisHeuristic
| Enumerator | |
|---|---|
| BottomUp | |
| TopDown | |
| BottomUpFromTerminators | |
| Fuzzer | |
Definition at line 27 of file OneShotAnalysis.h.
Constructor & Destructor Documentation
◆ OneShotBufferizationOptions()
|
default |
Member Data Documentation
◆ allowReturnAllocsFromLoops
| bool mlir::bufferization::OneShotBufferizationOptions::allowReturnAllocsFromLoops = false |
Specifies whether returning newly allocated memrefs from loops should be allowed.
Otherwise, a pass failure is triggered.
Definition at line 38 of file OneShotAnalysis.h.
◆ analysisFuzzerSeed
| unsigned mlir::bufferization::OneShotBufferizationOptions::analysisFuzzerSeed = 0 |
Seed for the analysis fuzzer.
Used only if the heuristic is set to AnalysisHeuristic::Fuzzer. The fuzzer should be used only with testAnalysisOnly = true.
Definition at line 54 of file OneShotAnalysis.h.
◆ analysisHeuristic
| AnalysisHeuristic mlir::bufferization::OneShotBufferizationOptions::analysisHeuristic = AnalysisHeuristic::BottomUp |
The heuristic controls the order in which ops are traversed during the analysis.
Definition at line 45 of file OneShotAnalysis.h.
Referenced by mlir::bufferization::OneShotAnalysisState::analyzeOp().
◆ dumpAliasSets
| bool mlir::bufferization::OneShotBufferizationOptions::dumpAliasSets = false |
Specifies whether the tensor IR should be annotated with alias sets.
Definition at line 41 of file OneShotAnalysis.h.
◆ noAnalysisFuncFilter
| llvm::ArrayRef<std::string> mlir::bufferization::OneShotBufferizationOptions::noAnalysisFuncFilter |
Specify the functions that should not be analyzed.
copyBeforeWrite will be set to true when bufferizing them.
Definition at line 49 of file OneShotAnalysis.h.
The documentation for this struct was generated from the following file:
- include/mlir/Dialect/Bufferization/Transforms/OneShotAnalysis.h
