Blogs written by HPC innovators & influencers including end-users, developers and others with a unique perspective on the world of supercomputing.

Duke University: Higher Performance with Less Power

Dr. John B. Pormann, Director of Research Computing, Director of Scalable Computing Support Center at Duke overviews data from the past several years tracking power consumption of its cluster computing resources.

Link to blog

TACC's Longhorn Visualization Cluster Enables Scientific Insight with Dell Hardware

Interview with Kelly Gaither, Director of Data & Information Analysis, Texas Advanced Computing Center (TACC). Longhorn is the largest hardware-accelerated, interactive visualization cluster in the world, capable of providing data visualization at an unprecedented scale. Located at the Texas Advanced Computing Center (TACC) at The University of Texas at Austin, the system provides scientists with unprecedented visualization capabilities and enables them to effectively analyze ever-growing volumes of data. To date, there are 486 active projects on the system and more than 40,425 jobs have been completed.

Link to blog

Memory Bandwidth and Performance, Part 2

In our last installment, we introduced the concept that performance was not all about clock rate and core count, and how in particular access speed to main memory often dominated performance. We also pointed out how the changes in architecture Intel had introduced with the Nehalem line of processors had dramatically changed the available bandwidth per core, and what a leap forward we had seen in the performance of typical applications.

Link to blog

GPGPU Computing: Here Come the Tools

Over the last few years there has been a steady rise in the number of people interested in using GPUs for general purpose computing. Microsoft's David Rich outlines many of the tools now available for GPGPU Computing.

Link to blog

A Unified User Interface for the Lustre File System - The Terascala Management Console

An overview of the Dell | Terascala Management Console provided by Terascala's Rick Friedman.

Link to Blog

University of Louisville: Using High Performance Computing for Personalized Medicine

Dr. Rouchka describes his work at the intersection of computer science and biology along with that of his colleagues at the University of Louisville. The advances they are making towards personalized medicine are promising and exciting. Their use of the viz wall to view and study results generated by the HPC cluster is very interesting and representative of the growing scope of the extent of our challenge on the Dell HPC team.

Link to Blog

HPC Advisory Council Announces 2nd Annual China High-Performance Computing Workshop Program

The 2nd Annual China High-Performance Computing Workshop will be on October 27th, 2010 in Beijing, China in conjunction with the HPC China National Annual Conference on High-Performance Computing. Read post for more details.

Link to Blog

Cluster Performance: It's not just about clock rate anymore

Texas Advanced Computing Center's Dan Stanzione & Tommy Minyard uncover real life application performance gains achieved through Intel's boost in memory bandwidth with its Nehalem arch.

Link to Blog

Dell partners with the University of Cambridge to deliver the power of HPC to researchers

Troy West, VP and General Manager of Dell Federal Systems introduces the Dell | Cambridge High Performance Computing (HPC) Solution Centre. This significant new collaboration aims to form EMEA’s leading HPC centre of excellence for all areas of the HPC community, whether academic or commercial.

Link to Blog

Enabling Discovery Events Translate in to Community Forums

Scientific Computing magazine editor Suzanne Tracy reviews final thoughts of Dell's Enabling Discovery HPC Road Show from Spring 2010, highlighting how important gatherings like these are for the Life Sciences Community. An introduction by Dell's Dr. Glen Otero discusses how these events bring great substance to those who attend.

Link to Blog

Paving the Road to Exascale - Part 2 of many

Post outlines the importance of CPUs and GPUs, and optimizations for GPU communications on high speed networks in search of performance gains.

Blog contributed by HPC Advisory Council Chair Gilad Shainer.

Link to Blog

Paving the Road to Exascale - Part 1 of many

1996 was the year when the world saw the first TeraFLOPS system. 12 years after, the first PetaFLOPS system was built. It took the HPC world 12 years to increase the performance by a factor of 1000. Exascale computing, another performance jump by a factor of 1000 will not take another 12 years.

Blog contributed by HPC Advisory Council Chair Gilad Shainer.

Link to Blog

CAC: Scientists Leverage Experimental MATLAB Resources Powered by Dell

CAC’s Dr. David Lifka describes how researchers are seamlessly scaling desktop MATLAB applications up to a 512-core Dell PowerEdge cluster at Cornell to accelerate data analysis and discovery.

Link to Blog

Seeking Nominations for HPC Advisory Council Awards at ISC’10 - May 18, 2010

The HPC Advisory Council is asking all HPC hardware and software vendors and end-users to nominate their choice for the four 2009-2010 HPC Advisory Council Awards. Winners of the awards will be announced on Thursday, June 3rd 2010 at 1:00pm during the closing session at ISC 2010 in Hamburg, Germany.

Link to Blog

GPU-Direct Technology - Accelerating GPU Based Systems

An overview from Mellanox's Gilad Shainer on creating faster GPU computing by eliminating the need for a CPU to be involved in GPU communications and eliminating the need for the buffer copy. Introduction provided by Dell's Dr. Jeff Layton.

Link to Blog

HPC Advisory Council: Attend the HPC Advisory Council European Workshop, May 30th, Hamburg, Germany

As part of the HPC outreach activities, the council hosts multiple workshops around the world. Previous workshops held in China and Switzerland, and the next workshop will take place on May 30th in conjunction with ISC’10 (the International Supercomputing Conference) in the CCH-Congress Center Hamburg, Hamburg, Germany.

Link to Blog

TACC: Real World Examples of HPC Working to Improve Human Health

TACC's Michael Gonzales outlines some examples of how life scientists, including biologists, physicians, and biochemists, are increasingly using advanced computing to improve human health. Over the past three years, the Texas Advanced Computing Center (TACC), a leader in high-performance computing (HPC), has broadened its computational biology programming adding software, support, and expertise to increase the impact of HPC systems on cutting-edge research projects in this field.

Link to Blog

TACC: Visualization in HPC - Seeing is Understanding

Paul Navrátil from the Texas Advanced Computing Center (TACC) overviews some of the exciting scientific imagery performed on the world's highest resolution title display called Stallion. The blog features an overview of some of the projects from Stallion, and Dell's Dr. Jeff Layton poses some simple questions about how other research and development center are, or could be using visualization.

Link to Blog