NERSCPowering Scientific Discovery Since 1974

Dirac GPU Cluster

Current Status: Up

NOTICE: Dirac was shut down permanently and retired from service at 17:00 on Friday, December 12, 2014.

Dirac was a testbed experimental system that well served its intended purpose of allowing users to evaluate GPU technologies.  It was removed from service on December 12, 2014.

 

 

Request for Dirac Account

Dirac is a 48-node GPU cluster intended to help researchers better understand the use of GPUs for scientific applications. Access is available to those who want to investigate the following: GPU computing using CUDA and/or OpenCL. Scaling codes on a multi-GPU system. Evaluate programming models for using GPUs in HPC, e.g. MPI + CUDA, OpenMP + CUDA, etc. To request access to Dirac, please fill out the form below. You can expect a response from NERSC within two weeks. Please contact the NERSC… Read More »

Node and GPU Configuration

Dirac is a 50 node GPU cluster with NVIDIA Fermi chips. Read More »

Access, Compiling and Running Jobs

Information on compiling CUDA codes and hybrid MPI+CUDA applications. Read More »

OpenCL Tutorial on Dirac

Information on compiling CUDA codes and hybrid MPI+CUDA applications. Read More »