sdfg::passes::TensorAllocationSizeInference Class Reference

Records the byte size of pointer containers in their StorageType::allocation_size, derived from the Tensor-typed memlets connecting them to library nodes. More...

#include <sdfg/passes/memory/tensor_allocation_size_inference.h>

Inheritance diagram for sdfg::passes::TensorAllocationSizeInference:

Public Member Functions
std::string	name () override
bool	run_pass (builder::StructuredSDFGBuilder &builder, analysis::AnalysisManager &analysis_manager) override
Public Member Functions inherited from sdfg::passes::Pass
	Pass ()=default
	Pass (const Options &options)
virtual	~Pass ()=default
virtual std::vector< OptionSpec >	options ()
bool	run (builder::SDFGBuilder &builder, bool create_report=false)
bool	run (builder::StructuredSDFGBuilder &builder, analysis::AnalysisManager &analysis_manager, bool create_report=false)
virtual bool	run_pass (builder::SDFGBuilder &builder)
virtual void	invalidates (analysis::AnalysisManager &analysis_manager, bool applied)

Additional Inherited Members
Protected Member Functions inherited from sdfg::passes::Pass
template<class T>
T	option (const OptionKey< T > &key, T fallback=T{}) const

Detailed Description

Records the byte size of pointer containers in their StorageType::allocation_size, derived from the Tensor-typed memlets connecting them to library nodes.

Must run before library node expansion, which drops the tensor layouts. The size is the memory span of the layout (including gaps of non-contiguous layouts); multiple uses are combined with max. Containers are skipped if any use depends on non-argument symbols, and managed allocations are left untouched.

Member Function Documentation

name()

std::string sdfg::passes::TensorAllocationSizeInference::name ( )

inlineoverridevirtual

Implements sdfg::passes::Pass.

run_pass()

bool sdfg::passes::TensorAllocationSizeInference::run_pass ( builder::StructuredSDFGBuilder & builder, analysis::AnalysisManager & analysis_manager )

overridevirtual

Reimplemented from sdfg::passes::Pass.

---

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

• sdfg/include/sdfg/passes/memory/tensor_allocation_size_inference.h