Displaying 2 results from an estimated 2 matches for "cudamemcpydevicetohost".
2012 Feb 23
0
[LLVMdev] Clang support for CUDA
...gt;
__global__ void kernfunc(int *a)
{
*a=threadIdx.x+blockIdx.x*blockDim.x;
}
int main()
{
int *h_a,*d_a,n;
n=sizeof(int);
h_a=(int*)malloc(n);
*h_a=5;
cudaMalloc((void*)&d_a,n);
cudaMemcpy(d_a,h_a,n,cudaMemcpyHostToDevice);
kernelfunc<<<1,1>>>(d_a);
cudaMemcpy(h_a,d_a,n,cudaMemcpyDeviceToHost);
printf("%d",*h_a);
return 0;
}
What additional header files should be included? What part of the code is
currently not supported by clang 3.0?
Thank you:)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/atta...
2012 Jul 21
3
Use GPU in R with .Call
...t_copy,cout,alloc_size,cudaMemcpyHostToDevice);
/*Step 1) Execute kernel.*/
VecAdd<<<(len+THREAD_PER_BLOCK-1)/THREAD_PER_BLOCK,THREAD_PER_BLOCK>>>(a_copy,b_copy,cout_copy,len);
/*Step 2) Copy result back to host.*/
cudaMemcpy(cout,cout_copy,alloc_size,cudaMemcpyDeviceToHost);
/*Step 3) Deallocate memory for device copies.*/
cudaFree(a_copy);
cudaFree(b_copy);
cudaFree(cout_copy);
/*Step 4) Get rid of the cuda context,necessary to avoid segfault when R
exits.*/
cudaThreadExit();
}
(c) Lastly, I wrote a R wrapper function called "VecAdd_cu...