HPCwire: SGI's Personal Cluster: Lots of Options, Lots of Challenges

The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing

HPCwire >> Features

August 20, 2009

SGI's Personal Cluster: Lots of Options, Lots of Challenges

by John E. West, for HPCwire

Earlier this month SGI announced its new CloudRack X2, a deskside (optionally rack-mountable) workgroup supercomputing solution aimed at the same crowd as Cray's CX-1.

The CloudRack X2 uses Rackable's server tray technology and packs nine trays (how many sockets you can get on those trays depends on the processors selected, more on that later) in a 14U chassis along with 2U for switches. Power supplies and an array of fans are in the back, and both are provisioned at the chassis, not tray, level. One of the features that Geoffrey Noer, senior director of product marketing at SGI, emphasized when I talked with him is the decision to pull the fans off the trays; this reduces the vibrations that can shorten the life of components like disk drives, and goes to the engineering effort that SGI has invested in the technologies surrounding the product.

You can get CloudRack X2 trays with two two-socket servers that have either Nehalems or 4- and 6-core Opterons, for a total of 144 Nehalem-cores or 216 Istanbul cores in a full 9-tray configuration. The Nehalems support up to 96 GB available on a tray (48 GB/socket), while the Opteron trays support up to 128 GB (64 GB/socket).

You can also opt for MicroSlice boards on the X2's trays. In this case you'll get three (for AMD Phenoms) or six (for Atoms or Athlons) motherboards on a single tray. No GPU-enabled configurations are available yet, but Noer did say they were coming "this quarter." Connection options include 1 GbE and both DDR and QDR InfiniBand, and the Intel-based configurations are Intel Cluster Ready certified.
SGI CloudRack X2

SGI's previous evolution of the CloudRack line (the C2) started the move to more standard rack footprints, and the CloudRack X2 takes that a step further. It uses an enclosure that mounts in standard 19-inch racks if you are buying a bunch, or you can just put wheels on one and park it beside your desk.

You can get your CloudRack X2 with Windows HPC Server 2008, SLES, and Red Hat, along with SGI's Industrial Strength Linux Environment (ISLE). Targeting the rich variety of processors and operating systems that they offer is a product management challenge, but on the other hand, it does increase the chances that users may find a configuration that will support their favorite COTS application.

Regarding pricing, Noer says that the CloudRack X2 enclosure with two server trays has a US list price starting at $20,000. That only gets you six Athlon X2-based servers, twelve if you go for the Atoms (two MicroSlice trays). If you need more compute power, as you might if you were in the market for a personal supercomputer, the price goes up from there.

This puts the CloudRack X2 in the same price neighborhood as Cray's CX-1, although in this market a few thousands of dollars matter, and the diversity of SGI's processor options may make a difference with customers. Of course Cray isn't the only company after this business. HP has the Cluster Platform Workgroup System, and NVIDIA is pushing its Personal Supercomputer concept. There is a growing amount of activity in this market, and what remains to be established is the degree to which customers are responding.

Another execution concern that SGI will have to manage is service and support for its new CloudRack offering, and developing a sales model that will create the potential for success without forcing the company to dramatically grow its sales staff. This will probably mean moving to a channel distribution model as Cray has done with its CX-1 line. This does let you manage fixed costs, but it also eats into profits and it takes a while to develop the channel.

Still, with a new product the one thing you know for sure is that no one will buy it if you don't launch it. I put this one in the category of worth trying.

Article Tools

Share Options

(Digg, Technorati, more)

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

You must be a registered user in order to comment on HPCwire stories.

Members enjoy:

	Access to Special Content, including Podcasts, Webcasts, and Whitepapers and more!
	Ability to take an active role in the discussions that are shaping the HPC technology discipline!
	Special offers available only to HPCwire members!

Become a Registered User Today!

Registered Users Log in Here to Comment

Email Address:	Password (case sensitive)

Remember me	Forgot Password?

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Top Headlines

IBM Releases Energy Efficient Power7 System

Feb 09 | eWeek Europe | Company says new high-end servers will deliver "intelligent performance." Read more...

Inductive Coupling Packs Flash Drive in a Chip

Feb 09 | EE Times | Wireless technology promises energy-efficient chip-to-chip communication. Read more...

IBM, Microsoft Help Create Montana Supercomputer

Feb 08 | eWeek | A new kind of Rocky Mountain high. Read more...

AMD Aims for GPUs in Mainstream Servers Starting 2012

Feb 08 | Computerworld | Chip maker hopes to bring CPU-GPU processors to servers in two years. Read more...

Graphene Transistors That Work at Blistering Speeds

Feb 05 | Technology Review | IBM has created graphene transistors that leave silicon ones in the dust. Read more...

Read more headlines...

Featured Whitepapers

Virtualization for Aggregation And The vSMP Architecture™

Jan 12 | | In-depth look at vSMP Foundation server virtualization technology, technical implementation, use cases and capabilities. The technical whitepaper provides an architectural overview and details on the three vSMP Foundation products: vSMP Foundation for SMP, vSMP Foundation for Cluster and vSMP Foundation for Cloud.

Copper Cable Technologies for High Performance Computing

Jan 18 | | This white paper discusses Gore’s copper cable assemblies, and how they continue to exceed the standards for providing reliable, cost-effective solutions for high-performance computer applications.

Appro Assists LLNL with Cluster Designed for Extreme Scale Visualization

Jan 11 | | LLNL is home to some of the fastest computers in the world. In 2012, LLNL expects to have the Sequoia supercomputing cluster operational with a projected performance of over 20 PFLOP/s. These systems will focus on strengthening the foundations of predictive simulation through running large suites of complex simulations and then comparing model predictions with experimental data. To visualize this project’s large amount of data, LLNL requested an Appro Supercomputing Cluster specifically designed to support interactive data analysis.

View the White Paper Library

Multimedia

Webcast: Virtualized Data Center Roundtable

Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.

Webcast: Watch SC09 Birds of a Feather Video: Scalable Fault-Tolerant HPC Supercomputers

Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.

Webcast: High Performance Computing for a Smarter Planet

LIVE@SCO9: The IBM team discusses new innovations in hardware, software and services that help clients better understand their workloads and get insight from their R&D efforts. Technology demonstrations include the soon-to-be-released Power7 HPC processor, the DCS990 system with 2.4 petabytes of storage, the xCAT management tool, secure HPC cloud computing and more. Winners of two HPCwire Readers' and Editors’ Choice Awards! Take the IBM virtual tour at SC09 or more information go online to: http://www-03.ibm.com/systems/deepcomputing/sc09.html