I’d maybe be able to tell you something if you’d pasted both versions of your code.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| about shared memory's contribution to performance when global memory access is coalesced | 0 | 625 | July 12, 2011 | |
| about shared memory's contribution to performance when global memory access is coalesced | 3 | 3571 | July 12, 2011 | |
| No performance inprovement shared mem x global mem | 5 | 1246 | April 26, 2013 | |
| Local memory performance Using more than 4kb kills it.. why? | 24 | 5347 | September 6, 2008 | |
| Non coalesced read/write in global vs shared | 12 | 4643 | May 12, 2015 | |
| Please help with __shared__ memory different usage than in samples | 30 | 3576 | January 10, 2010 | |
| Why is the performance more? Refering to Dr Dobbs article | 10 | 2749 | April 23, 2010 | |
| Shared memory question | 27 | 7632 | June 23, 2008 | |
| shared memory Computation become slower when using the shared memory | 8 | 1915 | August 20, 2010 | |
| write data from global to shared memory strange thing in SDK sample oclMatrixMul | 4 | 1759 | February 4, 2010 |