Here’s a collection of highlights, selected totally subjectively, from the recent enterprise HPC news stream as reported at insideHPC.com.
Too busy to keep up? Make your commute productive and subscribe to the Weekly Takeout, insideHPC.com’s weekly podcast summary of the HPC news week in review.
NSF announces a pair of really (really) big computers
NSF announced last week one giant and one huge supercomputer. The giant computer was awarded as part of NSF’s Track 1 procurement, and will fund NCSA at $208M over five years to build a multi-petaFLOPS supercomputer. A petaFLOPS is one thousand trillion floating point operations per second for those of you not used to getting a headache trying to get your head around what your computer is capable of.
The huge super was awarded to the University of Tennessee at Knoxville; they’ll get $65M over five years to build a machine that is expected to run at just under a petaFLOPS. (More on this HPC news item)
What Digipede brings to the table over MS CCS
In my quest to understand how enterprise users are getting their work done I’ve found a recent post from Dan Ciruli over at the West Coast Grid blog. Dan works at Digipede, a provider of tools to enable enterprise users to get their work done on HPC machines (Gigaspaces is another that we’ve talked about).
Dan walks us through how Microsoft’s Windows CCS 2003 is built, what it’s good for, and the specific value that the Digipede Network adds for enterprise customers looking to run Windows .Net apps in parallel. (More on this enterprise HPC news item)
AMD ups the icky ante
Not satisfied with the one-shot approach of underwriting economic studies that end up showing unsurprisingly conclude that Intel is bad, AMD has launched a whole website to educate you, the hapless (and, hopefully, gullible) consumer about just how bad Intel is.
AMD is enjoying the fact the European Commission charged Intel for anticompetitive measures. The company enjoys the fact so much it has launched a new pseudo-advertising campaign website providing updates on the case. The new AMD website, breakfree.amd.com, provides all the information you would ever need to know on the allegations. Additionally, the site provides information on antitrust, competition and procurement.
Methinks that AMD should try to focus more on fixing their execution and roadmap problems (lackluster fabs, early indications of Barcelona under performance, delays in production) than swatting at Intel.
XenSource revs virtualization offering
XenSource has just announced the release of the next generation of its flagship product, XenEnterprise v4.
New advanced management features in v4 include XenMotion™ for live migration of running virtual machines; XenCenter, a scalable, resilient virtual infrastructure management solution with an easy to use Windows user interface; a powerful 64-bit hypervisor that supports both 32- and 64-bit enterprise workloads; and, an open, standards-based XenAPI which enables ISVs and OEMs to develop add-on solutions for XenEnterprise v4. This release includes version 3.1 of the Xen open source hypervisor “engine” and leverages the latest hardware virtualization support features from Intel and AMD to deliver near bare metal performance.
John West summarizes the HPC news headlines every day at insideHPC.com, and writes on leadership and career issues for technology professionals at InfoWorld. You can contact him at firstname.lastname@example.org.