parallel.gpu.CUDAKernel
Kernel executable on GPU
Description
A CUDAKernel
object represents a CUDA kernel that can execute on
a GPU. You create the kernel from CU and PTX files. For an example of how to create and use a
CUDAKernel
object, see Run CUDA or PTX Code on GPU.
Note
You cannot save
or load
CUDAKernel
objects.
Creation
Syntax
Description
creates a kern
= parallel.gpu.CUDAKernel(ptxFile
,cuFile
)CUDAKernel
object using the PTX code
ptxFile
and the CUDA® source file cuFile
. The PTX file must contain only a
single entry point.
Use feval
with kern
as an
input to execute the CUDA kernel on the GPU. For information on executing your kernel object, see
Run a CUDAKernel.
Input Arguments
Properties
Object Functions
feval | Evaluate kernel on GPU |
setConstantMemory | Set some constant memory on GPU |
existsOnGPU | Determine if gpuArray or CUDAKernel is available on GPU |
Examples
Version History
Introduced in R2010b