sdfg::data_flow::AtomicScalarOpGPUImpl Class Reference

Shared base for the GPU implementations (CUDA and ROCm). More...

#include <sdfg/data_flow/library_nodes/atomic_op_node.h>

Inheritance diagram for sdfg::data_flow::AtomicScalarOpGPUImpl:

Protected Member Functions
	AtomicScalarOpImpl (const AtomicScalarOpImpl &)=delete
	AtomicScalarOpImpl ()
Protected Member Functions inherited from sdfg::data_flow::AtomicScalarOpImpl
	AtomicScalarOpImpl ()

Additional Inherited Members
Public Member Functions inherited from sdfg::data_flow::AtomicScalarOpImpl
virtual	~AtomicScalarOpImpl ()=default
	AtomicScalarOpImpl (const AtomicScalarOpImpl &)=delete
AtomicScalarOpImpl &	operator= (const AtomicScalarOpImpl &)=delete
virtual std::string_view	type_name () const =0
ImplementationType	implementation_type () const
	The implementation type this impl corresponds to.
virtual bool	supports (types::PrimitiveType data_type, AtomicOpType op) const =0
	Whether this implementation supports the given (data type, op) combination.

Detailed Description

Shared base for the GPU implementations (CUDA and ROCm).

Their code generation is currently identical; only the supported (data type, op) combinations differ, which the concrete subclasses provide.

Member Function Documentation

AtomicScalarOpImpl() [1/2]

sdfg::data_flow::AtomicScalarOpImpl::AtomicScalarOpImpl ( )

inlineprotected

AtomicScalarOpImpl() [2/2]

sdfg::data_flow::AtomicScalarOpImpl::AtomicScalarOpImpl ( const AtomicScalarOpImpl & )

protecteddelete

---

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

• sdfg/include/sdfg/data_flow/library_nodes/atomic_op_node.h