GPU

GPU Computing on zcluster

Hardware

For a description of the Graphics Processing Units (GPU) resources available, please see GPU Hardware.

Software

zcluster has the following tools for programming for GPUs:

1. NVIDIA CUDA toolkit

Several versions of the CUDA toolkit are available. Please see our CUDA page.

2. PGI/CUDA compilers

The default version of the PGI compilers, which are on users’ default path, support GPU acceleration, including Fortran/CUDA.

For more information on the GPU support of PGI compilers, please see the pdf documents in /usr/local/pgi/linux86-64/2012/doc, or visit the PGI website http://www.pgroup.com/resources/cudafortran.htm

3. PGI Accelerators

Using PGI Accelerator compilers, programmers can accelerate applications on x64+accelerator platforms by adding OpenACC compiler directives to Fortran and C programs and then recompiling with appropriate compiler options. Please see http://www.pgroup.com/resources/accel.htm

4. OpenCL libraries

Several versions of the OpenCL libraries are available. Please see our OpenCL page.

Running Jobs

For information on how to run GPU jobs on zcluster, please refer to Running GPU Jobs.