On three different machines I found my Cuda code significantly slower for Cuda 10.2 compared to Cuda 9.2. In fact it is a factor of 6 times slowed for a Nvidia 2080 Ti card machine. I use single graphics card on all three. Has there been some significant change that might explain this? It is a simple function doing a convolution and uses cudaMalloc, etc code. I can upload it if that would help.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Much worse performance after updating cuda toolkit from 10.2 to 11.4 | 3 | 587 | January 20, 2022 | |
| Is cuda 2.0 faster than the previous versions? | 3 | 3375 | July 25, 2008 | |
| Extremely slow cudaMalloc call on GTX 1080 with CUDA8RC | 0 | 582 | July 27, 2016 | |
| Strange performance across CUDA versions | 3 | 427 | October 12, 2021 | |
| CUDA 11.1 vs CUDA 10.0 significant slowdown | 1 | 756 | July 7, 2021 | |
| CUDA slower than CPU Help me please... | 0 | 2832 | February 4, 2010 | |
| CUDA on WIN7 is much slower than on WIN XP same computer, two OSs, two different run times | 2 | 15653 | November 11, 2009 | |
| Graphic driver of low version causes wrong cuda program result | 3 | 445 | April 23, 2019 | |
| unexpected slow performance | 0 | 368 | February 29, 2020 | |
| Why my CUDA code is slower than CPU code? | 6 | 3293 | July 20, 2011 |