banner-nvidia

NVIDIA CUDA Center of Excellence

"Often before a great discovery there is the creation of a new tool or a tool that is used in a different way than before. GPUs and the algorithms and software that they use are today's tools and with them we are entering a golden age, where scientific computing is going to truly change the way we do science and medicine."

-Chris Johnson


As a CUDA Center of Excellence, the University of Utah is using CUDA technology extensively across three facilities:

 

Scientific Computing and Imaging (SCI) Institute
The SCI Institute has established itself as an internationally recognized leader in visualization, scientific computing, and image analysis. The overarching research objective of the SCI Institute is to create new scientific computing techniques, tools, and systems that enable solutions to important problems in biomedicine, science, and engineering. For more information: www.sci.utah.edu
The School of Computing 
The School of Computing has a long history of distinguished faculty and alumni who have made substantial contributions to research and industry. The CUDA Center will play a key role in the School's new Digital Media Initiative linking Computing with Fine Art and Film and funded by the USTAR Initiative
Center for the Simulation of Accidental Fires and Explosions (CSAFE)
As one of the Department of Energy's five Advanced Simulation and Computing (ASC) centers, Utah runs detailed simulations of high energy devices and hydro-carbon fires, designed to increase the safety of dangerous material transportation and storage.

"The synergy of graphics combined with computational horsepower provided by NVIDIA GPUs and the CUDA programming environment provides incredible opportunities in science, industry and commerce," stated Dr. Steven Parker, adjunct professor of computer science at the University of Utah and principal research scientist at NVIDIA.

"The worlds of scientific computing and computer graphics owe a great deal to the University of Utah and those who have passed through its halls," said David Kirk, chief scientist at NVIDIA. "CUDA technology has the potential to truly transform industries, as we have already seen in fields such as medicine, geophysics and finance. With a school of Utah's caliber incorporating it into their curriculum and across many of its research facilities, I am personally very excited to see what advances can be made."

The CUDA Center of Excellence at the University of Utah is using GPU technology to make significant advances in a number of scientific applications, including seismic data processing and visualization, MRI and diffusion tensor image reconstruction, cardiac electrical wave propagation simulation, combustion and fluid dynamics simulation, and several projects in large-scale scientific visualization.

 

SCI GPU publications


nvidia

front

Meet "Tess," our 128 GPU NVIDIA Cluster

A Few Technical Specs

qty 1 HP DL380 G5 Xeon Admin Node

qty 64 HP DL160 G6 computation nodes
512 Xeon X5550 2.67GHz Processors, 8 Core per node
1.5TB of memory, 24GB of RAM per node
750GB local scratch disk space
HP InfiniBand 4X DDR Conn-X PCI-E G2 Dual Port HCA
OS Red Hat Enterprise Linux Server release 5.3

qty 32 NVIDIA Tesla S1070's
128 Tesla GPUs, 4 per S1070 1U Tesla
512GB of dedicated GPU Memory (16 per Tesla, 8 per CPU node)

The system has 3 networks

1- InfiniBand with a Voltaire InfiniBand 4X DDR Rev B 96P Switch

This network is used for MPI and NFS traffic to the SGI file server with 8TB of dictated space.

The IB network is connected to the SCI core switch and the SGI file server via a 10Gb fiber link.

2- 1Gb ethernet network

This network is used for low bandwidth access such as ssh and is used to netboot all the nodes.

3- Lights out management network

HP iLO2 network lets us reboot and manage crashed nodes.

The node are netbooted using the standard Redhat netboot node manager. This allows for easy software upgrades and also also us to easily run multiple OS version across any combination of nodes.

Currently the cluster is running interactively, meaning that any user can ssh directly to a node and can run jobs on as many nodes as they need.

In the future we are evaluating cluster management and scheduling software that includes but is not limited to:
  • Sun Grid Manager (Sun)
  • Moab Cluster Suite (Cluster Resources)

CUDA Research and Teaching Efforts

GKLEE - A concolic (concrete + symbolic) verifier plus test generator. Accepted at PPoPP 2012

CS6963: Parallel Programming for GPUs