Version 27 (modified by 20 months ago) ( diff ) | ,
---|
CUDA
Table of Contents
Certain specialized nodes are outfitted with NVIDIA CUDA capable GPUs or accelerators. The tables below list brief specifications of currently installed CUDA cards and which domain/node they are installed in. Currently, the nodes that have CUDA cards do not have any wireless radios and are meant for offloading computation via ethernet networking. The nodes are accessible via the Control and Data networks of their respective domain. See the individual domain pages for more detailed information.
Available Cards
Model | Architecture | # of CUDA Cores | Memory (GB) | Memory Bandwidth (GB/s) | Single-Precision Performance | Double-Precision Performance | Compute Capability | More Info |
---|---|---|---|---|---|---|---|---|
Tesla K80 | Kepler | 4992 | 24 | 480 | 8.73 Tflops | 2.91 Tflops | 3.7 | 1 2 3 |
Tesla P100 12GB | Pascal | 4992 | 12 | 549 | 9.3 Tflops | 4.7 Tflops | 6.0 | 1 2 3 |
Tesla V100 16GB | Volta | 5120 | 16 | 900 | 13 Tflops | 7 Tflops | 7.0 | 1 2 3 |
Domains with CUDA Capabilities
Domain | Node: CUDA Card(s) |
---|---|
sb4.orbit-lab.org | node2-1: GeForce GT 640 GDDR5 |
sb9.orbit-lab.org | node1-1 to node1-8: Tesla V100 |
grid.orbit-lab.org | node21-1 to node21-7: Tesla K80 node21-9 to node21-32: Tesla P100 |
COSMOS | see COSMOS testbed for details |
Useful Links
Note:
See TracWiki
for help on using the wiki.