gpu.md
... ...
@@ -0,0 +1,18 @@
1
+## GPU computing
2
+
3
+GPU-accelerated computing uses a graphics processing unit (GPU) to accelerate computations in computer programs. Several applications in the SBGrid programs tree are GPU-accelerated. Some examples are RELION, GCTF, MotionCor2, Gautomatch, IMOD, etc. Here's what you need to take advantage of a GPU:
4
+
5
+### Requirements for GPU (CUDA) applications
6
+
7
+1. To use GPU-accelerated applications, you will need an NVIDIA GPU. We don't currently support other co-processors (Xeon Phi, AMD). If you think we should, let us know at bugs@sbgrid.org .
8
+
9
+ Not all GPUs are created equal - some applications are restricted to GPUs with a certain 'Compute Capability (i.e. of 3.5 or greater)'. You can check your card's rating and find more information on GPU computing here : [https://developer.nvidia.com/cuda-gpus](https://developer.nvidia.com/cuda-gpus)
10
+
11
+2. Drivers
12
+You linux workstation must have the proper drivers for your GPU. You can find drivers for your card here : [https://developer.nvidia.com/cuda-zone](https://developer.nvidia.com/cuda-zone)
13
+
14
+We currently support applications that rely on versions of CUDA 5 to 8 and these libraries are included with the SBGrid distribution. For best results, it is important to have a recent driver version if possible.
15
+
16
+For more information on GPUs and RELION, check Erik Lindahl's blog at the Department of Biochemistry & Biophysics, Stockholm University, [http://www.cryoem.se/relion-gpu](http://www.cryoem.se/relion-gpu)
17
+
18
+GPU questions? Please email *bugs@sbgrid.org*