wiki:Hardware/fDevices/gCUDA

Version 5 (modified by jkol, 9 years ago) ( diff )

CUDA

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

Domains 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.