Difference between revisions of "Performance"
From Gw-qcd-wiki
| Line 47: | Line 47: | ||
|252 GFLOP/s | |252 GFLOP/s | ||
|- | |- | ||
| − | |Vector | + | |rowspan="3"|Vector utilities |
| + | |Addition | ||
|82 GB/s | |82 GB/s | ||
|3.4 GFLOP/s | |3.4 GFLOP/s | ||
|- | |- | ||
| − | | | + | |Dot product |
|88 GB/s | |88 GB/s | ||
|N/A | |N/A | ||
|- | |- | ||
| − | | | + | |Copy |
|84 GB/s | |84 GB/s | ||
|N/A | |N/A | ||
|- | |- | ||
|} | |} | ||
Revision as of 13:36, 14 July 2010
Carver Tester: Ben Gamari Test date: 14 Jul 2010 Commit: e3e4ffafd158abd004c483694a27f4f6bc7d2185 Hardware: CUDA version 3.0
| Kernel | Configuration | Bandwidth | FLOPs |
|---|---|---|---|
| Dslash_cuda | Dslash (24^4) | 73 GB/s | 32 GFLOP/s |
| hopping (24^4) | 74 GB/s | 34 GFLOP/s | |
| Dslash_multi_gpu (double) | 1 node, 24^4 Dslash | 79 GB/s | 35 GFLOP/s |
| 2 nodes, 24^4 Dslash | 145 GB/s | 64 GFLOP/s | |
| 4 nodes, 24^4 Dslash | 256 GB/s | 114 GFLOP/s | |
| Dslash_multi_gpu (double) | 1 node, 24^4 Dslash | 79 GB/s | 76 GFLOP/s |
| 2 nodes, 24^4 Dslash | 156 GB/s | 140 GFLOP/s | |
| 4 nodes, 24^4 Dslash | 283 GB/s | 252 GFLOP/s | |
| Vector utilities | Addition | 82 GB/s | 3.4 GFLOP/s |
| Dot product | 88 GB/s | N/A | |
| Copy | 84 GB/s | N/A |
