HP-CAST Morning Wrap-Up

A great morning for HPC enthusiasts at the HP-CAST user group being held prior to the SC11 conference. While the agenda may give you a hint at some of HP’s announcements for next week, there where definitely clear trends in HP executive and customer presentations that I can discuss now. You can also follow HP’s HP-CAST and SC11 news by following @HPHyperscale on Twitter and by joining the new HP-CAST group on Linkedin.

As is always the case, there is great interest in the latest AMD and Intel x86 processors. But increasingly, HPC customers are looking beyond the x86 architecture at alternative processor architectures at both ends of the power spectrum. Already today, GPU based systems such as the HP ProLiant SL390s with Nvidia GPUs have made a significant impact on the HPC landscape. More recently, there has been an interest in extremely low power processors such as ARM and at least one project, the Mont Blanc effort at BSC, is looking to ARM to power future exascale systems. No doubt I expect at least a few HPC customers will be interested in the ARM powered Redstone server development platform, part of HP Project Moonshot.

Of course, this new diversity of architectures will bring new challenges to HPC practioners as well. To make best use of these new hardware architectures, software co-design will become increasingly important. With ARM being so new as a server platform, HP launched as part of Project Moonshot the HP Discovery Lab which gives developers an early opportunity to start porting, testing, and benchmarking their applications on the ARM powered Redstone server development platform. HP’s Nvidia GPU Starter Kit has also provided a great opportunity for many customers to acquire a fully integrated GPU cluster and speed development of new GPU powered applications. This afternoon HP will discuss some of our work on the DOE Exascale program, and it should come as no surprise that co-design is one of that program’s big themes.

As much as I get excited about the technology, HP-CAST provides a great opportunity to be reminded of what our customers are actually using these systems for. Hearing how Purdue’s Dr. Alan Qi was already using their brand new Carter cluster for near real time cancer stem cell detection was amazing. From Purdue to MD Anderson Cancer Center to UCLA’s LONI Laboratory of Neural Imaging, I’m extremely proud and humbled by the impact HP supercomputers have on improving the human condition.

Time for lunch, but I’ll have another update this evening and also @marchamilton on Twitter.

Advertisements

About Marc Hamilton

Marc Hamilton – Vice President, Solutions Architecture and Engineering, NVIDIA. At NVIDIA, the Visual Computing Company, Marc leads the worldwide Solutions Architecture and Engineering team, responsible for working with NVIDIA’s customers and partners to deliver the world’s best end to end solutions for professional visualization and design, high performance computing, and big data analytics. Prior to NVIDIA, Marc worked in the Hyperscale Business Unit within HP’s Enterprise Group where he led the HPC team for the Americas region. Marc spent 16 years at Sun Microsystems in HPC and other sales and marketing executive management roles. Marc also worked at TRW developing HPC applications for the US aerospace and defense industry. He has published a number of technical articles and is the author of the book, “Software Development, Building Reliable Systems”. Marc holds a BS degree in Math and Computer Science from UCLA, an MS degree in Electrical Engineering from USC, and is a graduate of the UCLA Executive Management program.
This entry was posted in Uncategorized. Bookmark the permalink.