Site Announcements

 GPU Technology Conference

_______________________________________________________________________________________________

Building High Performance Computers and Clusters with GPU's

Welcome to the Building High Performance Computers and Servers with GPU's community.

 Champions:

Wen-mei W. Hwu: I am a professor at the Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign. Since 1997. My research interests include architecture, implementation, and compilation for high performance computer systems. I am currently the co-principal investigator for the Blue Waters Project., a supercomputer  which will be capable of one petaflop of performance when it goes live in 2011.

Volodymyr Kindratenko: I am a research scientist in the Innovative Systems Laboratory (ISL) at the National Center for Supercomputing Applications (NCSA), University of Illinois at Urbana-Champaign (UIUC). My research interests are mainly in the area of high-performance computing and special-purpose computing architectures, GPU clusters in particular.

Featured Stories and Papers

Initial set of community papers.


Below is the initial set of papers for the Building High Performance Computers and Servers with GPU's community.

 

 

 


Read More

Get CUDA Certified


NVIDIA has launched its first CUDA Certification program.

Be one of the first Certified CUDA Programmers - find out the full details at www.nvidia.com/certification

This exam tests candidates CUDA C programming and optimization skills. This 3 hour test can be taken at over 6500 test centers in over 165 countries.

Discounts are available for companies planning to certify 6 engineers or more. General questions or applications for bulk discounts can be addressed to certification@nvidia.com


Read More

Featured Forum Topics

Optimal GPU cluster node configuration


I guess "optimal" is really application-dependent criterion, but there are some practical limits that otherwise would make a particular configuration less than optimal. As a baseline, PCIe gen
Read More

Latest Stories and Papers

Title New Replies Last postsort icon
Evolution of Thread-Level Parallelism in Desktop Applications New 0 new 09-01-2010
JESPP: Joint Experimentation on Scalable Parallel Processors Supercomputers New 0 new 08-19-2010
Multi-Frame Rate Rendering for Standalone Graphics Systems New 0 new 08-19-2010
Implementation of a Cartesian Grid Imcompressible Navier-Stokes Solver on Multi-GPU Desktop Platforms Using CUDA New 0 new 08-19-2010
‘ePX’ Cluster Supercomputing New 0 new 08-19-2010
Get CUDA Certified New 0 new 08-19-2010
Towards Systematic Exploration of Tradeoffs for Medical Image Registration on Heterogeneous Platforms New 0 new 08-19-2010
Efficient Simulation of Agent-Based Models on Multi-GPU and Multi-Core Clusters New 0 new 08-19-2010
A Parallel Multi-view Rendering Architecture New 0 new 08-17-2010
Task Parallelism for Ray Tracing on a GPU Cluster New 0 new 08-16-2010
Interactive Visualization of the Largest Radioastronomy Cubes New 0 new 08-16-2010
Teraflop per second gravitational lensing ray-shooting using graphics processing units New 0 new 08-15-2010
Interactive High-Quality Visualization of Higher-Order Finite Elements New 0 new 08-10-2010
Real-time phase-only color holographic video display system using LED illumination New 0 new 08-09-2010
The PALM-3000 high-order adaptive optics system for Palomar Observatory New 0 new 08-04-2010
High Resolution Imaging Testbed Utilizing Sodium Laser Guide Star Adaptive Optics: The Real Time Wavefront Reconstructor Computer New 0 new 08-01-2010

Latest Blog Posts

Latest Events