Nvidia
Oakridge Top Right
HPCwire

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Language Flags

Visit additional Tabor Communication Publications

Datanami
Digital Manufacturing Report
HPC in the Cloud
Green Computing Report

Tabor Communications
Corporate Video

AMD Goes Native with New Server Chipsets


AMD has launched its Fiorano server platform, consisting of chipsets that, for the first time, use only company-branded silicon. The three chipsets announced this week are aimed to serve a range of market segments.

Up until now if you cracked open the hood of your favorite six-core AMD server you'd find the familiar logo on the processor, but not on the chips that glue the processor to the rest of the I/O cards, memory, and so forth. Instead, you'd have found Broadcom or NVIDIA silicon doing duty in that role. Now, AMD hopes you'll be spotting its own silicon in your servers courtesy of the engineering team from ATI, which AMD acquired in 2006.

Today the company announced three different northbridge chipsets, the SR5650, SR5670, and the SR5690, which are to be paired with the SP5100 southbridge. All three northbridge versions are aimed at Socket F and support HypterTransport 3, and PCI Express 2.0 (up to 42 lanes according to one report but we are still waiting for confirmation from AMD), among other features.

These chips will also figure in support for next year's Magny-Cours DDR3-based AMD chips which use Socket G34 and will come in 8 and 12 core variants. The chipset is available for Original Device Manfacturers like Tyan and Supermicro (both of which are announcing configurations that use the new chipsets), but the big OEMs like HP, IBM, and others are focusing their efforts on AMD's 2010 lineup (expected in the first quarter) according to Gina Longoria, senior product manager for server workstations with AMD.

Unhelpfully for a family of server chipsets, AMD isn't yet talking specifics on costs or speeds and feeds. In fact, the variety of things that AMD isn't talking about with this release (cost specifics, speeds and feeds, OEM partners) suggests a launch hurried along to preempt any IDF news.

What we do know, however, are some qualitative statements about the three configurations, which are each aimed at different segments of the server space. The SR5650 is designed for lower power configurations paired with the EE and HE variants, and, in fact, is being used in Tyan's S8208 server featuring AMD's ultra lower Opteron variant, the EE at 40W. The S8208 isn't expected to be available until November.

The SR5670 is the middle-of-the-road chipset, designed for a balance of performance and power efficiency that AMD hopes will help it appeal to the HPC crowd. AMD's Longoria says that this chipset was chosen as part of the new supercomputer headed for PRACE, where the PCI Express 2.0 features will allow that cluster to support data communications over QDR InfiniBand. The cluster is being built from quad-socket Supermicro blades (this puts 24 cores on a blade). PRACE is one of the first customers for the chipset and, according to Longoria, the system being built now will feature 4,320 cores.

OTOY, the startup that is developing technology it hopes will enable real-time, high quality graphics to be streamed over the Web to your browser, is building with the high end of just about everything AMD makes. They are building a 240 processor (1,440 Istanbul cores) cluster with 480 FireStream graphics cards (4 per node, 2 per CPU). The cluster will be built from Supermicro 2P blades, using the SR5690 high end chipset. The 5690 can scale up to 8 sockets on a board, but I don't see that configuration being practical in anything but custom builds for highly-targeted customers.

Both Tyan and Supermicro have products using the new chipsets that will come available starting this month, and proceeding over the next two months. A look at Tyan's roadmap shows 3 motherboards (and 3 1U servers as well) that will launch between now and November. An MEB form factor (the S8212) is expected in September for "dense infrastructure" deployments; an ATX form factor (the S8005) in October; and the S8208 we've already talked about in November.

Supermicro has three motherboards coming out over the next two months: a new EATX in each of September and October, and an SWTX form factor in October aimed at HPC (which is odd because I thought that Supermicro was moving away from SWTX). According to AMD, Supermicro is also launching the SBA-7141i-T blade in September and the 1U AS-1041A-2TF server in October, both of which are also aimed at HPC.

Although AMD isn't talking about costs, they did characterize the relative costs of the three chipsets. Not surprisingly, pricing parallels the expected performance of the three models with the low end SR5650 costing the least, and the high end 5690 topping out the price sheet.

Sponsored Links

High-Performance Computing in Action
Businesses that want to be on the cutting edge of their industries are increasingly turning to high-performance computing (HPC) solutions to handle complex compute processes and speed up their rate of innovation. Download this Executive Brief to see how businesses in energy, life sciences and entertainment put HPC solutions to work in their operations.

Accelerate your science with Seneca
One of the first HPC providers installing a 4X NVIDIA Kepler K-20 cluster. Invites you to a free evaluation on Seneca’s NVIDIA K20 Kepler cluster, pre-loaded with AMBER, NAMD, LAMMPS

Webinar: Programming Heterogeneous X64+GPU Systems Using OpenACC
Join Michael Wolfe as he compares the advantages and costs of using both low-level models and the directive-based OpenACC model for programming accelerated heterogeneous systems. Registration is free.

May 24, 2013

May 23, 2013

May 22, 2013

May 21, 2013

May 20, 2013

May 17, 2013

May 16, 2013

May 15, 2013

May 14, 2013

May 13, 2013


Most Read Features

Most Read Around the Web

Most Read This Just In

Supermicro

Short Takes

NASA Builds 'Climate in a Box'

May 23, 2013 | The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
Read more...

Building Supercomputers with Raspberries

May 22, 2013 | At some point in the not-too-distant future, building powerful, miniature computing systems will be considered a hobby for high schoolers, just as robotics or even Lego-building are today. That could be made possible through recent advancements made with the Raspberry Pi computers.
Read more...

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

Computing the Physics of Bubbles

May 15, 2013 | Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Progress in Parallel: the Bull Parallel Programming Center

04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.

Sponsored Multimedia

SGI DMF ZeroWatt Disk Solution

In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.

Cray CS300-AC Cluster Supercomputer Air Cooling Technology Video

The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.

SC12 Editorial Feature HPCwire Soundbite sponsored by ISC Xyratex

HPC Job Bank


Featured Events


  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States





HPCwire Events