Posted by: momentics on Saturday December 16 2006 @ 05:57AM EST views: 1505
This is an idea to join together math models of execution environment and the software that is running on a distributed hardware to meet fault tolerant requirements through parallel n-versions application execution and continuous configuration of the system. Math model leverages environment and software faults (including missed deadlines) to the faults with better failure semantics and allows managed redundancy. Scal@Grid proposes event-driven style of application development and C# programming interface.
Posted by: Barbara Jewett on Friday December 15 2006 @ 05:54PM EST views: 1295
LCI is the premier international forum to share information on management, administration, and scientific computing techniques for high performance computing. The 8th LCI International Conference on Clustered Computing will be held May 14-17, 2007, in South Lake Tahoe, California.
Posted by: Kristen Meyer on Friday December 15 2006 @ 03:20PM EST views: 1251
LSU Center for Computation and Technology (CCT) Professor Thomas Sterling will travel to University of Arkansas to demonstrate his "Introduction to High-Performance Computing" course, which will be offered at LSU for the first time during the Spring 2007 semester.
Posted by: Ken Farmer on Tuesday December 12 2006 @ 06:37PM EST views: 1233
Clustercast's Doug Eadline and Jeff Layton traveled far and wide looking for interesting news at Supercomputing 2006. Let's Join Doug and Jeff as they chat about SC06 just before the showroom floor opens.
Posted by: Ken Farmer on Tuesday December 12 2006 @ 03:45PM EST views: 1287
Global supercomputer leader Cray Inc. (NASDAQ: CRAY) today announced that Pittsburgh Supercomputing Center (PSC) will double the capacity of its 10-teraflops (10 trillion floating point operations per second) Cray XT3 system to over 21 teraflops by the end of this year. Nicknamed "BigBen," PSC's system was the first Cray XT3 supercomputer to be installed and became the leading performer among tightly coupled supercomputer architectures on the National Science Foundation's TeraGrid computing infrastructure. The upgrade is expected to significantly boost the TeraGrid's ability to support the most demanding, large-scale scientific applications -- known as "capability" computing.
Posted by: Ken Farmer on Tuesday December 12 2006 @ 03:02PM EST views: 1198
The Itanium® Solutions Alliance today announced a $100,000 sponsorship of the Gelato Federation, a global technical community dedicated to the advancement of Linux on Intel® Itanium® architecture. The partnership will strengthen the community of support for Itanium® 2-based platforms and open source through research, education, development and improvement of Linux on the Intel Itanium processor.
Posted by: Dana D Booze on Tuesday December 12 2006 @ 10:03AM EST views: 1312
South Africa's department of science and technology, Intel and the Meraka Institute yesterday unveiled a new high performance computer (HPC) designed to assist in HIV and Aids research.
Posted by: Ken Farmer on Monday December 11 2006 @ 10:04PM EST views: 1785
RealWorldTech: Even to the casual observer, it is apparent that the time of multi-core computing is upon us. In fact, this shift occurred several years in the past. The first general purpose CPU to feature Chip Multi-Processing (CMP) was the IBM POWER4, which debuted in 2001. Today, there is not a high performance MPU family without a shipping CMP design. Even our video game consoles are shifting towards CMP oriented designs. The Xbox 360 feature 3-way symmetrical CMP, while the CELL processor uses upto 8 SIMD Processing Elements, each with its own private address space, which could be considered a form of CMP. With the shift towards CMP systems, it is more important than ever to understand the additional complexities of multi-processor systems over traditional uni-processor machines.
Posted by: TSS Media Relations on Monday December 11 2006 @ 02:18PM EST views: 1270
Yellow Dog Linux gives the PLAYSTATION®3 the full functionality of a personal computer, incorporating code from Barcelona Supercomputing Center, Sony Group, and Fedora.
Posted by: Dana D Booze on Monday December 11 2006 @ 09:18AM EST views: 1287
CCRT Supercomputer Will be Dedicated to Scientific and Industrial Research
Designed Around Bull NovaScale(R) Servers, the Computer Will Deliver Performance in Excess of 43 Teraflops, Positioning it Among the 15 Most Powerful Systems in the World
Posted by: Ken Farmer on Sunday December 10 2006 @ 06:30PM EST views: 1182
New measure techniques have improved the understanding of how biological molecules form their 3-D structures. The improved precision of the measurements means that researcher can now trace the whole route taken when a bio-molecule is formed which should help researchers improve their understanding of what causes mis-folding diseases like Mad Cow (BSE) and Alzeimer's.
Posted by: Ken Farmer on Saturday December 09 2006 @ 05:07PM EST views: 1467
Bioinformatics.Org will be running an on-line version of the well-received, "Introduction to Bioinformatics Programming: Perl & R for Biologists, Level 1" (Open Source Bioinformatics for Researchers), and we're also pleased to introduce an advanced and extended version of the course.
Posted by: Dana D Booze on Monday December 04 2006 @ 10:27AM EST views: 1539
While stock Linux is optimized for desktop and server tasks, a simplified version can speed up performance on the nodes of a high-performance comptuing cluster.
Posted by: Michael Creel on Friday December 01 2006 @ 08:11AM EST views: 1470
ParallelKnoppix 2.0 is released. The 2.x series makes setting up and using the cluster even easier than before. It is also much easier to save a PK setup for re-use. Of course, it is also possible to use a PK cluster without leaving traces on the host machines.
Video - The Road to PetaFlop Computing
Explore the Scalable Unit concept where multiple clusters of various sizes can be rapidly built and deployed into production. This new architectural approach yields many subtle benefits to dramatically lower total cost of ownership.
White Paper - Optimized HPC Performance
Multi-core processors provide a unique set of challenges and opportunities for the HPC market. Discover MPI strategies for the Next-Generation Quad-Core Processors.
Appro and the Three National Laboratories
[Appro delivers a new breed of highly scalable, dynamic, reliable and effective Linux clusters to create the next generation of supercomputers for the National Laboratories.