An implementation of a subclass of kernel_t for kernels compiled together with the host-side program. More...

#include "../kernel.hpp"
#include <cuda_runtime.h>
#include <type_traits>

Include dependency graph for apriori_compiled.hpp:

This graph shows which files directly or indirectly include this file:

Classes
struct	cuda::kernel::apriori_compiled::attributes_t
	a wrapper around `cudaFuncAttributes`, offering a few convenience member functions. More...

class	cuda::kernel::apriori_compiled_t
	A subclass of the kernel_t interface for kernels being functions marked as global in source files and compiled apriori. More...

Namespaces
	cuda
	Definitions and functionality wrapping CUDA APIs.

Functions

template<typename KernelFunctionPtr >
apriori_compiled_t	cuda::kernel::get (const device_t &device, KernelFunctionPtr function_ptr)
	Choose an association of a `__global__` kernel function with a context (or a device's primary context), and produce a proxy object for that association with which the library can more readily act. More...

template<typename KernelFunctionPtr >
apriori_compiled_t	cuda::kernel::get (context_t context, KernelFunctionPtr function_ptr)

Detailed Description

An implementation of a subclass of kernel_t for kernels compiled together with the host-side program.

Function Documentation

◆ get() [1/2]

template<typename KernelFunctionPtr >

apriori_compiled_t cuda::kernel::get	(	const device_t &	device,
		KernelFunctionPtr	function_ptr
	)

Choose an association of a __global__ kernel function with a context (or a device's primary context), and produce a proxy object for that association with which the library can more readily act.

Obtain a wrapped kernel object corresponding to a "raw" kernel function.

Note: The returned kernel proxy object will keep the device's primary

Parameters

device The device with whose primary context to construct an associated kernel object

Note: Kernel objects are device (and context) specific;' but kernels built from functions in program sources are used (only?) with the primary context of a device; The returned kernel proxy object will keep the device's primary context active while the kernel exists.

◆ get() [2/2]

template<typename KernelFunctionPtr >

apriori_compiled_t cuda::kernel::get	(	context_t	context,
		KernelFunctionPtr	function_ptr
	)

Parameters

context The context for which to construct an associated kernel object

Classes

Namespaces

Functions

Detailed Description

Function Documentation

◆ get() [1/2]

◆ get() [2/2]