Difference between revisions of "Applications/Cuda"
From HPC
m |
m |
||
| Line 16: | Line 16: | ||
<pre style="background-color: black; color: white; border: 2px solid black; font-family: monospace, sans-serif;"> | <pre style="background-color: black; color: white; border: 2px solid black; font-family: monospace, sans-serif;"> | ||
| − | [username@gpu01 ~]$ module cuda/8.0.61 | + | [username@gpu01 ~]$ module load cuda/8.0.61 |
[username@gpu01 ~]$ ./gpuTEST | [username@gpu01 ~]$ ./gpuTEST | ||
Revision as of 15:28, 5 April 2017
Application Details
- Description: CUDA is NVIDIA’s parallel computing architecture that enables dramatic increases in computing performance by harnessing the power of the GPU (graphics processing unit).
- Version: 6.5.14, 7.5.18 and 8.0.61
- Modules: cuda/6.5.14, cuda/7.5.18 and cuda/8.0.61
- Licence: Free, but owned by NVidia
Usage Examples
|
NVIDIA CUDA® modules 7.5.18 and 8.0.61 have the Deep Neural Network library (cuDNN) included. It is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers. cuDNN is part of the NVIDIA Deep Learning SDK. |
Note: this example is done on a node with a GPU accelerator, usually access would be achieved with the scheduler
[username@gpu01 ~]$ module load cuda/8.0.61 [username@gpu01 ~]$ ./gpuTEST
Further Information
|