Announcing the New SGI® UV™: The Big Brain Computer
The world's largest in-memory system for data-intensive problems
Hamburg, Germany — June 18, 2012 — SGI (NASDAQ: SGI), the trusted leader in technical computing, today announced the availability of the new SGI® UV™ 2 product family. SGI UV 2 doubles the number of cores (up to 4096 cores) and quadruples the amount of coherent main memory (up to 64 terabytes) from the previous generation, available for in-memory computing in a single-image system. SGI UV 2 can scale to eight petabytes of shared memory and at a peak I/O rate of four terabytes per second (14 PB/hour), it could ingest the entire contents of the U.S. Library of Congress print collection in less than three seconds. This unprecedented capability enables users to find answers to the world's most difficult problems on a system as easy to administer as a workstation. Built on industry standards and supporting a wide range of storage options, SGI UV 2 offers a complete solution for no-limit computing.
"The new design advancement demonstrated in this next-generation SGI UV platform is not simply focused on increasing our lead in cache-coherent memory size and corresponding core count. We have been able to deliver all of this additional capability while driving down the cost of the system," said Dr. Eng Lim Goh, chief technology officer, SGI. "In fact, the entry level configuration of SGI UV 2 is 40% less expensive than SGI UV 1. This creates a new level of accessibility to large coherent memory systems for researchers, analysts and the 'missing middle,' providing an effective lower overall TCO alternative to clusters."
The world's largest in-memory system for data-intensive problems
SGI UV 2 is the only system available on the market that leverages the power of the newest Intel® Xeon® processor E5 family beyond four sockets and 1.5 terabytes of memory, delivering twice the price/performance of the HP ProLiant DL980 server¹. With as little as 16 cores and 32 gigabytes of memory, SGI UV 2 can start small and seamlessly expand. At the upper end of the spectrum, SGI UV 2 holds the world record benchmark for SPECompL2001, and top 64 socket Intel® Xeon® E5-4600 benchmarks for SPECint_rate_base2006 and SPECfp_rate_base2006². With a peak I/O rate of up to four terabytes per second, and coherent shared memory that is up to 1000 times faster than flash memory, all of these features make SGI UV the most powerful in-memory system for all data-intensive problems.
"I am very pleased to be receiving the first SGI UV 2 supercomputer in the world. New observations of our Universe, like the Planck satellite, are offering us exquisite new insights. In order to test our mathematical theories, we need to match this detail in our computer simulations. The flexible new UV 2 COSMOS³ system, soon to be supercharged with Intel's MIC technology, will ensure that UK researchers remain at the forefront of fundamental and observational cosmology," said Professor Stephen Hawking.
Focus on solving your problems, not IT problems
SGI UV operates just like a workstation (on one system image any program has access to all the cores and all the memory of the system); it is far less complex to manage than traditional scale-out systems with many nodes, and applications can scale without the complexity of multi-instance software. Because of the huge capacity of SGI UV 2, users can consolidate complete workflows in a single system, with very low IT burden per compute core versus comparable clusters or scale-out systems.
SGI UV can run anything from desktop applications to common cluster applications, making it an alternative to small to medium clusters. Users can focus on outcomes, not algorithms and therefore rapidly innovate; taking analysis from a laptop, scaling it up on SGI UV with no re-writing of code or moving data to different systems required. With support for a variety of file systems and storage options, including SGI DMF, which makes storage hierarchies look like a local drive, SGI UV 2 offers a complete solution.
SGI UV 2 provides the fastest path to solve multi-terabyte problems, making it the ideal platform to accelerate the pace of innovation in decision support, genomics and bioscience, chemistry and materials, physics, integrative systems science, national security, product design, and other data-intensive fields. The Genome Analysis Centre (TGAC) and Centre Biological Sciences (CBS) at the Danish Technical University, both widely recognized in their respective fields of next-gen sequencing and metagenomics respectively, are among the first organizations to deploy SGI UV 2 for these research areas. For more information on CBS, join the upcoming webinar "Conquering Complexities in Cancer Research."
No-limit computing, built on industry standards
With world-leading scalability, users of SGI UV 2 can leave the node memory limits of scale-out computing behind on an open, industry standard platform. SGI UV 2 features the latest Intel® Xeon® processor E5 product family and runs unmodified, off-the-shelf Linux® software. SGI UV 2 also supports Intel's many integrated cores (MIC) technology as well as NVIDIA® Quadro® GPUs and Tesla® Accelerators.
"SGI has taken advantage of Intel's new Xeon processors to design the highly differentiated SGI UV 2 delivering strong performance for applications ranging from in-memory data mining to a wide range of commercial applications to data-intensive High Performance Computing and beyond," said Raj Hazra, IAG vice president and general manager Technical Computing Group, Intel. "SGI UV 2 shows what is possible with a single-image compute system for commercial and scientific applications."
SGI UV 2000 is available immediately. SGI UV 20 can be ordered today and will start shipping in August 2012. Pricing starts at $30,000 USD.
Ogilvy Public Relations
© 2012 Silicon Graphics International Corporation. SGI and the SGI logo are trademarks or registered trademarks of Silicon Graphics International Corp. or its subsidiaries in the United States and/or other countries. Intel and Xeon are registered trademarks of Intel Corporation. NVIDIA, Quadro and Tesla are registered trademarks of NVIDIA Corporation. All other trademarks are property of their respective holders.
¹ Calculation based on floating point performance and standard web price of HP ProLiant DL980 server and SGI UV 2 standard pricing.
² SPEC® and the benchmark names SPECompL®, SPECint® and SPECfp® are registered trademarks of the Standard Performance Evaluation Corporation. Competitive benchmark results stated above reflect results published on www.spec.org as of May 14, 2012. For the latest SPEC benchmark results, visit www.spec.org.
* SPECompL2001 at 2993987 on 64 chips, 512 cores, 512 threads. 58% improvement over previous generation with Intel® Xeon® processor E7 family (SGI Altix UV 1000, SPECompL2001 = 1892885, 64 chips, 512 cores, 512 threads)
³ The COSMOS consortium, headed by Professor Hawking, is part of the UK DiRAC HPC facility, funded by the Science and Technology Facilities Council and Department of Business, Innovation and Skills. Please direct enquiries to Andrey Kaliazin, COSMOS system manager, or Professor Paul Shelled, Director.