13.07.2015 Views

CUDA Libraries and MPI+OpenMP+CUDA - Prace Training Portal

CUDA Libraries and MPI+OpenMP+CUDA - Prace Training Portal

CUDA Libraries and MPI+OpenMP+CUDA - Prace Training Portal

SHOW MORE
SHOW LESS
  • No tags were found...

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Performance Measurement <strong>and</strong> Metrics__global__ base(float *a, float *b) {int i;i = (blockIdx.x-1)*blockDim.x + threadIdx.x;a[i] = sin(b[i]);}__global__ memory(float *a, float *b) {int i;i = (blockIdx.-1)*blockDim.x + threadIdx.x;a[i] = b[i];}__global__ math(float *a, float b, int flag) {float v;int i;i = (blockIdx.-1)*blockDim.x + threadIdx.xv = sin(b);if (v*flag == 1) a[i] = v;}Smart trick to avoid compilerinterference at assembly levelCourtesy of M. FaticaFebruary 10, 2012 PRACE Winter School 201232

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!