I run yolov3 on CUDA 10.0 faster than CUDA 10.0 + cudnn 7.4. Is it that the optimization of cudnn is slower than that of cuda?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Cudnn 7.3 has poor performance on GeForce RTX 2080 | 0 | 903 | October 12, 2018 | |
| Low performance for convolution in cuDNN on Tesla V100 | 5 | 2221 | August 2, 2018 | |
| Cudnn convolution is significantly slow | 3 | 1264 | April 19, 2022 | |
| some questions about cudnn7.2? | 0 | 642 | August 17, 2018 | |
| Darknet YOLO slowing down when using Jetpack4.4's cuDNN(8.0.0) on Jetson Xavier NX and Jetson Nano | 4 | 2722 | March 10, 2021 | |
| I want to know about compatibility of CUDA, cudnn and tensorflow | 0 | 669 | September 12, 2020 | |
| cuDNN 5.1 delivers 2.7x Faster Training of Networks with 3x3 Convolutions | 0 | 2120 | August 12, 2016 | |
| Why is 2-D convolution slower than the matrix product? | 17 | 7075 | April 18, 2015 | |
| Darknet slower using Jetpack 4.4 (cuDNN 8.0.0 / CUDA 10.2) than Jetpack 4.3 (cuDNN 7.6.3 / CUDA 10.0) | 34 | 9973 | August 4, 2021 | |
| Pytorch 1.2 cuda 10.0 vs. pytorch 1.9 cuda 11.1 significant slowdown | 3 | 1042 | July 8, 2021 |