Rocks+ Intel® Cluster Ready on the Intel Xeon® 5500

March 25th, 2009 10:35 am
Posted by Tim McIntire
Tags: , , , , , , ,

Everybody at Clustercorp is excited about the Intel Xeon® 5500 launch – I was buzzing up and down the California coast, working with the open source Rocks guys in San Diego and our commercial Rocks+ dev & support team in Northern California – intermixed with partner site visits to make sure everybody was ready on launch day.  This type of launch allowed us to show off how nimble a company building from mature open source solutions can be.  Rocks+ was  fully certified and tested as Intel Cluster Ready on a number of our hardware partners’ new systems within 1-week of the Intel Xeon® 5500's release to sales.

It’s cool to see hardware partners’ eyes light up when they first experience the tight integration Clustercorp’s engineers have built between Rocks+ and Intel Cluster Ready. One of our principal goals when we entered the program was to extend the Rocks mantra of “making clusters easy” to the Intel Cluster Ready spec.  We’ve seen vendors struggle for weeks with other solutions sit down with Rocks+ for the first time, and build Intel Cluster Ready systems in about an hour – this is a true testament to the power of the open source Rocks framework and the design of the Intel Cluster Ready Roll spearheaded by Jason Bishop at Clustercorp.

We are looking forward to a continued ramp in end-user adoption of Intel Cluster Ready in ’09 and increased interaction with the other ISVs in the program.  In the second half of ‘08 we started seeing more ISVs leverage our work with Rocks+ as a base to build their Intel Cluster Ready codes.  As a former HPC end-user, I dreamed of the day a cluster would be delivered to my lab fully-configured, with a standards-based cluster management platform, and most of my developer tools or applications ready to run…  I expect there are a lot of eager HPC sys admins waiting to get their hands on Intel’s new architecture – our aim is to make their new cluster purchases and continued administration of their systems as pleasant and efficient as possible.

JOIN THE CONVERSATION


You must be a Registered Member in order to comment on Cluster Connection posts.

Members enjoy the ability to take an active role in the conversations that are shaping the HPC community. Members can participate in forum discussions and post comments to a wide range of HPC-related topics. Share your challenges, insights and ideas right now.

Login     Register Now


Author Info


Tim McIntire, CEO and Co-Founder of Clustercorp, is a leader in bringing the HPC (i.e. Supercomputing) industry's thriving open source software community together with the industry's major hardware suppliers. McIntire's vision led to Clustercorp's development of Rocks+ and subsequent partnerships with Dell Inc, Cray Inc, Intel Corporation (and others) to produce the world's fastest class of computers using a simple, repeatable process.

McIntire's previous work includes leading the development team at the Digital Image Analysis Lab at Scripps Institution of Oceanography. His research, which was primarily funded as part of NASA's Direct Broadcast program, has been published in various IEEE and Elsevier Journals on topics ranging from remote sensing using neural networks to parallel image processing using HPC Clusters. He also contributes or has been featured in IBM developerWorks, HPCwire, Bio IT World, Apple Developer Connection and the computational science magazine, enVision.