I had a look at the implementations that come with the SDK, but I wondered if there is somewhere an off-the-shelf solution that works for matrix dimensions of arbitrary size?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Fast matrix transpose of any size library/implementation? | 0 | 341 | July 3, 2020 | |
| SDK Transpose revisited ... yet again! | 3 | 4856 | May 16, 2008 | |
| CUDA-LAPACK Availability/Field of Application | 0 | 2130 | August 27, 2008 | |
| Transpose example performance problem | 0 | 1956 | May 12, 2009 | |
| Matrix Multiplication with Shared Memory | 0 | 1349 | September 28, 2009 | |
| Matrix to be sort Code optimization | 0 | 2985 | February 15, 2008 | |
| rectangular matrix transpose | 3 | 7688 | April 30, 2008 | |
| Optimize problem regarding problem size | 4 | 6136 | May 25, 2011 | |
| approach to take for multiple small matrices | 0 | 2088 | March 30, 2007 | |
| Matrix types & functions | 0 | 587 | December 13, 2012 |