httpv://www.youtube.com/watch?v=CO8oPlXV00Y In this excellent presentation video by ETH’s Christian Bolliger, the mission and goals of the new European Open Filesystem organization are described in detail. Lustre users in Europe have combined forces to form a legal entity known as a Societas Cooperativa Europaea (SCE) with a mission to promote the establishment and adoption of an […]
Archives for December 2010
Whitepaper: HP Cluster Platform 3000SL a Balanced Approach to HPC
December 21, 2010 by
While more and more companies are embracing HPC by utilizing clusters of computers, application performance doesn’t always scale with expectations. In this HP whitepaper, the company describes how the HP Cluster Platform 3000SL balanced computing system delivers increased density while fully leveraging economies of scale. To meet the specific requirements of this growing population of […]
Parallelism Trends: in the Cloud, Cluster and Client
December 20, 2010 by
In this slide presentation with transcription from Intel Tech Days, Microsoft’s Amit Chatterjee discusses recent trends in parallelism. Current global trends in information explosion and innovative experiences in the digital age require immense computational power. The only answer to this need is leveraging parallelism and the presence of multiple cores in today’s processors. This ’Multi-core […]
insideHPC to Keep Up Over Holidays
December 20, 2010 by
I’ve always found it best to manage expectations, so I wanted to let our readers and sponsors know that insideHPC will continue to publish daily posts over the holiday season. There may be fewer press releases this time of year, but there is never a shortage of interesting HPC stories out there. Happy Holidays!
Berkeley Lab Develops Flexible Reservation Algorithm for Network Provisioning
December 20, 2010 by
As scientific research becomes more collaborative and more data-intensive, larger teams of scientists are generating, sharing and analyzing increasingly large datasets. Many of these applications need networking support that provides predictable performance, which in turn requires effective algorithms for bandwidth reservations. A team of Berkeley Lab researchers have recently developed an algorithm that will allow […]
Amax Rolls Out High-Density JBOD NAS
December 20, 2010 by
Last week AMAX announced the availability of the new StorMax-X1 scalable NAS storage solution. According to John Tran, the StorMax-X1 is ideal for multi-petabyte rich media and content sharing platforms that integrate the latest computing technologies requiring performance scalability, extreme density and high throughput computing with robust storage-management features.
Workshop: Manycore and Accelerator-based Scientific Computing
December 20, 2010 by
Registration is now open for a workshop on “Manycore and Accelerator-based High-performance Scientific Computing” to be held Jan. 24-28, 2011, in Berkeley, Calif. Workshop organizers have also issued a call for research papers and posters. The deadline for submissions and registration is Tuesday, Jan. 4. According to workshop co-organizer Hemant Shukla, the meeting will focus […]
Video: DK Panda on Virtualization for HPC
December 20, 2010 by
In this video from SC10, Ohio State’s DK Panda presents on virtualization for HPC and enabling high-performance communication between guest OS instances. A tip of the hat goes to Josh Simons for pointing us to this video.
Video: 2010 Beowulf Bash in New Orleans
December 19, 2010 by
httpv://www.youtube.com/watch?v=yK2b35KnaBA Our Video Sunday feature continues with this piece where Don Becker, Douglas Eadline, and others provide the backstory for the 2010 Beowulf Bash at SC10 in New Orleans. As described in the video, the B Bash is a cooperative effort made possible by sponsors including AMD, Penguin Computing, Adaptive Computing, AEON Computing, Arista Networks, […]
LRZ to Build 3 Petaflop Water-cooled Super
December 18, 2010 by
Germany’s Leibniz Supercomputing Centre (LRZ) has has signed a contract with IBM to build a 3 petaflop water-cooled supercomputer for scientific research. To be known as the “SuperMUC” system, the supercomputer will reported be builth with IBM System x iDataPlex using 14 000 next-generation Intel Xeon processors. With SuperMUC as the third Tier-0 system, the […]
