Version 4 (modified by 9 years 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 of their respective domain. See the individual domain pages for more detailed information.
Available Cards
Name | # of CUDA Cores | Memory (GB) | Memory Bandwidth (GB/s) | Single-Precision Performance | Double-Precision Performance | More Info |
GeForce GT 640 GDDR5 | 384 | 1 | 40.1 | 803 Gflops | 1 2 | |
GeForce GTX 750 Ti | 640 | 2 | 86.4 | 1306 Gflops | 1 2 3 | |
Quadro 2000D | 192 | 1 | 41.6 | 480 Gflops | 1 2 3 | |
Quadro K5000 | 1536 | 4 | 173 | 2.1 Tflops | 1 2 3 | |
Tesla C2025 | 448 | 3 | 144 | 1.03 Tflops | 515 Gflops | 1 2 3 |
Tesla K40 | 2880 | 12 | 288 | 4.29 Tflops | 1.43 Tflops | 1 2 |
Tesla K80 | 4992 | 24 | 480 | 8.73 Tflops | 2.91 Tflops | 1 2 3 |
ORBIT Testbeds with CUDA Capabilities
Domain | Node: CUDA Card(s) |
SB1 | node1-3: GeForce GTX 750 Ti |
SB8 | node1-3: Quadro K5000 |
SB9 | node1-13: Quadro 2000D |
Grid | node21-1: 2x K40, node21-2: K80 |
Note:
See TracWiki
for help on using the wiki.