![]() Generally code is forwards compatible, but not backwards compatible. The older generation on the training nodes are Tesla K40s with compute capability of 3.5. Artemis has NVIDA Tesla V100s with a compute capability of 7.0. ![]() We will be using the Artemis Training accounts today (instructions detailed below.)Īll the data/scripts used in this course is location on Artemis at /project/Training/GPUtraining (which you can access through the training accounts) or you can download the data directly from here GPU RequirementsĪn CUDA capable GPU card. If you only want to follow along using Artemis, all you need is an SSH client, as described below. If you want to follow along and complete the exercises on your local machine use these setup instructions. ![]() Introduction to GPU computing on HPC: GPU and SSH setup
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |