cross posting: gpu - Compute and Data transfer not happening concurrently in cuda Streams on Iteration 2 - Stack Overflow
it may be this: Persistent Kernel does not work properly on some GPUs - #5 by Robert_Crovella
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Concurrent Kernel executions & Data Transfers | 3 | 658 | March 8, 2023 | |
| Unknown concurrency issue in CUDA/C++ program | 1 | 627 | September 10, 2021 | |
| How to Overlap Data Transfers in CUDA C/C++ | 23 | 2293 | January 18, 2023 | |
| Cuda stream question regarding transfer, kernel execution concurrency | 1 | 391 | December 19, 2022 | |
| Concurrent execution problem Try to understand how to achieve the data and execution concurrency | 4 | 1505 | July 9, 2010 | |
| Time intervals and non-concurrent in multi streaming | 6 | 607 | April 6, 2023 | |
| Combination of "Overlap of Data Transfer" and "Concurrent Kernel Execution" | 1 | 1318 | September 14, 2011 | |
| Using streams... Howto? | 0 | 1114 | July 25, 2008 | |
| Can I use streaming to overlap kernels and data transfers in this scenario? | 13 | 381 | July 5, 2024 | |
| How to Overlap Data Transfers in CUDA Fortran | 0 | 411 | August 25, 2020 |