ComputationKernel Class Reference
HiCR
|
HiCR::backend::opencl::ComputationKernel Class Referencefinal
#include <computationKernel.hpp>
Inheritance diagram for HiCR::backend::opencl::ComputationKernel:

Public Member Functions | |
ComputationKernel (const std::shared_ptr< cl::Kernel > &kernel, const std::vector< std::shared_ptr< HiCR::LocalMemorySlot > > &args, const cl::NDRange offset, const cl::NDRange global, const cl::NDRange local) | |
~ComputationKernel ()=default | |
__INLINE__ void | start (const cl::CommandQueue *queue) override |
![]() | |
__INLINE__ | Kernel ()=default |
__INLINE__ | ~Kernel ()=default |
Detailed Description
This class represents a replicable Computation Kernel for the OpenCL backend. A Computation Kernel enables the kernel execution in the HiCR runtime, and in particular enables the concatenation of kernel execution and memcpy operations in a common queue of operations.
Constructor & Destructor Documentation
◆ ComputationKernel()
|
inline |
Constructor for the Computation Kernel unit class of the OpenCL backend. Set the kernel arguments.
- Parameters
-
kernel OpenCL kernel args kernel arguments offset offset range global global range local local range
◆ ~ComputationKernel()
|
default |
Default destructor
Member Function Documentation
◆ start()
|
inlineoverridevirtual |
Start the kernel using the given OpenCL queue
- Parameters
-
queue the OpenCL queue on which the kernel is to be executed
Implements HiCR::backend::opencl::Kernel.
The documentation for this class was generated from the following file:
- /home/runner/work/HiCR/HiCR/include/hicr/backends/opencl/computationKernel.hpp
Generated by