- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Intel MPI ( version 2019.3.199) is underperforming in our InfiniBand FDR cluster. Bandwidth is a little more than half it should be with a benchmark MPI code. The Pingpong IMB also shows a significant decrease compared with mvapich, for example. This is noticed also in application codes.
Link Copied
0 Replies
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page