|
|
@@ -782,9 +782,11 @@ only be executed by the CPUs, but also by a CUDA device.
|
|
|
@node Definition of the CUDA Kernel
|
|
|
@subsection Definition of the CUDA Kernel
|
|
|
|
|
|
-The CUDA implementation can be written as follows. It needs to be
|
|
|
-compiled with a CUDA compiler such as nvcc, the NVIDIA CUDA compiler
|
|
|
-driver.
|
|
|
+The CUDA implementation can be written as follows. It needs to be compiled with
|
|
|
+a CUDA compiler such as nvcc, the NVIDIA CUDA compiler driver. It must be noted
|
|
|
+that the vector pointer returned by STARPU_VECTOR_GET_PTR is here a pointer in GPU
|
|
|
+memory, so that it can be passed as such to the @code{vector_mult_cuda} kernel
|
|
|
+call.
|
|
|
|
|
|
@cartouche
|
|
|
@smallexample
|
|
|
@@ -834,6 +836,9 @@ __kernel void vector_mult_opencl(__global float* val, int nx, float factor)
|
|
|
@end smallexample
|
|
|
@end cartouche
|
|
|
|
|
|
+Similarly to CUDA, the pointer returned by @code{STARPU_VECTOR_GET_PTR} is here
|
|
|
+a device pointer, so that it is passed as such to the OpenCL kernel.
|
|
|
+
|
|
|
@cartouche
|
|
|
@smallexample
|
|
|
#include <starpu.h>
|
