Visit additional Tabor Communication Publications
April 02, 2009
10 words and a link
SiCortex says Nehalem is too little, too late
AMD comments on Nehalem
(See more Nehalem coverage in the feature below…)
Intel details future graphics silicon
Sun confirms additional 1,500 jobs cut
Cray option buy back update; total cost? $668,699.65.
Intel CEO Otellini says Sun was "shopped around"
The computations behind Monsters vs. Aliens
STFC Daresbury Laboratory installs new Tesla, Nehalem combo cluster
India's Saha Institute Buys a Cray
Oxford installs supercomputer from Streamline Computing
10th Russian Top50 released
Macedonia's first supercomputer
UPCRC Illinois hosts summer school for multicore programming
HPC conferences: smaller can be better
Rackable Systems to Acquire Silicon Graphics
Although it wasn't totally unexpected, this week brought a raft of news about potential shifts in the balance of the HPC force as SGI filed for Chapter 11 bankruptcy protection and issued notice that it intends to initiate a Section 363 sale of assets to satisfy its debtors. It is going into the public auction process with one bidder already announced: according to the press release, Rackable has agreed to acquire "substantially all the assets of Silicon Graphics, Inc. for approximately $25 million in cash."
"The combined company will be positioned to solve the most demanding business and technology challenges our customers confront today," said Mark J. Barrenechea, president and CEO of Rackable Systems. "In addition, this combination gives us the potential for significant operational synergies, a strong balance sheet, and positions the combined company for long-term growth and profitability."
"We have been working very hard to strengthen our company, and today, we've taken another big step in that direction," stated Robert "Bo" Ewald, CEO of Silicon Graphics. "This transaction represents a compelling opportunity for Silicon Graphics' customers, partners and employees, who can all benefit from the emerging stronger company with better technologies, products and markets reach."
Barrenechea added, "Together, we believe we will be a much stronger entity with great products and people offering a compelling proposition to compete more effectively in, and across, our collective markets."
Rackable has since suspended its previously announced stock repurchase program. Read the full releases and filings here:
In an exclusive conversation, Penguin CEO Charlie Wuischpard comments on the SGI/Rackable deal, and you can also read analysis on the mechanics HPC's deal of the year, that includes insight into SGI's stalking horse strategy.
Everyone: Nehalem. Nehalem, meet everyone.
Intel's Xeon 5500 series processor, the follow-on to Harpertown, the latest Core i7 processor -- that's right, Nehalem-EP -- is out of the closet. From the press release:
The new enterprise-class chips can automatically adjust to specified energy usage levels, and speed data center transactions and customer database queries. They also will play a key role in scientific discoveries by researchers who use supercomputers as their foundation for research, all whilst delivering great energy efficiency for reduced electricity costs.
The are many things to like about this processor for intensive computing, including the dramatically increased bandwidth to memory and Intel's QuickPath Interconnect (the return salvo for AMD's HyperTransport). The (many, many) vendors who also announced new products today are claiming anywhere from 2 to 4 times speedup on applications -- especially those apps that were previously memory bound -- from the 5400s to the 5500s, even though the clocks aren't that different. Of course your mileage may vary.
With over 30 new world records the Intel Xeon processor 5500 series establishes new standards for two-socket performance while delivering gains of more than double the previous-generation Intel Xeon processor 5400 series.
...Cisco delivered an outstanding result on SPEComp*Mbase2001, a high performance computing benchmark which helps evaluate performance of OpenMP applications, that was 154 percent better than previous generation 5400 series.
Intel's 5500 landing page has more detail. An interesting feature of the chips that many seem to be taking advantage of is the advanced power management features. On HP's new G6 lineup of ProLiant servers, for example, you can set a per processor power cap that you won't allow the system to exceed. Why do this in HPC? Well you can put these processors in an existing datacenter that you're "pretty sure" can handle the load without worrying about exceeding the design point for the facility … you just set the cap where you need it to keep from tripping breakers, and run worry free (of course, monitoring power usage to make sure things are behaving as expected).
There are also component improvements:
Intel is also announcing new server boards that offer a higher degree of integrated components. In addition, the company is announcing the Intel 82599 10 Gigabit Ethernet Controller, featuring advanced virtualization technology and unified networking support, which greatly improves network I/O performance in virtualized datacenters. It is optimized to support the increased bandwidth provided by platforms based on the Intel Xeon processor 5500 series, which provides more than 250 percent the I/O throughput of previous-generation servers to best meet the needs of the most demanding virtualization applications.
Some of the vendor products announced today sporting the Nehalem-EP take advantage of the new virtualization and network features to enable users to start efficiently dedicating bandwidth to cores.
Who's on deck with new products? Well, everyone, but let's point to a sampling of HPC vendors and their press announcements
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.
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.
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.
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.
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.
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.
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.
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.