I agree, one should not write a routine to predict what cudaMallocPitch will use as a pitch in a given circumstance. That said, the need to plan has not gone away. Currently I perform test allocations which I free, for no other purpose to than to work out the pitch for complex layouts. I would far rather there be a cudaCalculateMallocPitch which does the same calculation as cudaMallocPitch, but no
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| cudaMallocPitch is giving inconsistent result cudaMallocPitch is giving inconsistent r | 5 | 6321 | June 28, 2008 | |
| cudaMallocPitch returns wrong pitch | 2 | 2711 | May 8, 2012 | |
| How to determine the base adress alignment and pitch alignment used by 'cudaMallocPitch' ? | 4 | 2587 | June 9, 2016 | |
| cudaMallocPitch() | 1 | 6320 | December 26, 2009 | |
| Returned pitch in cudaMallocPitch | 4 | 2300 | October 11, 2014 | |
| cudaMallocPitch : pitch size Will the pitch be different for two arrays with same dimension ? | 0 | 749 | April 15, 2011 | |
| "Pitch" in cudaMallocPitch()? | 3 | 4579 | March 2, 2009 | |
| cudaMallocPitch seg fault I've probably missunderstood the docs but can't see where | 3 | 5544 | February 12, 2009 | |
| CudaMallocPitch and CudaMemcpy | 2 | 1001 | January 21, 2015 | |
| Problem with 2D memory copy using pitch | 6 | 6539 | November 20, 2011 |