Has anyone benchmarked running a Tesla or a GeForce GPU on a VM either in the cloud or on their own machine? I am curious if there is a latency hit for launching kernels or pulling the data on and off. I assume most people running in public clouds don’t care about this and I couldn’t find any information on it. I’m also assuming something like Nvidia-Docker wouldn’t have any latency issues since it simply maps /dev.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Tesla K80 poor performance on Azure | 1 | 880 | June 5, 2019 | |
| Latency when I launch a program on Tesla S2050 | 0 | 2938 | January 9, 2012 | |
| Performance difference between Tesla and system where Cuda GPU is used as display device | 8 | 6119 | September 2, 2009 | |
| Is there any instruction on running the Nvidia containers inside a VM ? | 2 | 614 | May 30, 2019 | |
| reduces kernel launch latency? | 6 | 13067 | July 6, 2008 | |
| Memory copy latency and kernel launch overhead | 3 | 7531 | May 17, 2011 | |
| host-device latencies? | 2 | 932 | March 1, 2019 | |
| Any way to measure the latency of a kernel launch? | 13 | 8157 | July 22, 2022 | |
| Measuring Kernel Latencies | 0 | 345 | May 5, 2021 | |
| Kernel operation delays when gpu is idle | 10 | 659 | March 20, 2024 |