The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing
December 15, 2006
In collaboration with the University of Tokyo and Taiwan Semiconductor Manufacturing Company (TSMC), Alchip Technologies, a fabless ASIC company, has announced its first silicon success of the SING processor for GRAPE-DR, a next-generation supercomputer design that is targeting a performance goal of two petaflops. The SING chip features 512 CPUs with over 60 million logic gates and 10 million bits of SRAM utilizing TSMC's 90nm process and flip-chip package technology.
The GRAPE series are among the world's fastest supercomputers and have been awarded the Gordon Bell Prize six times. The GRAPE systems have yielded simulation results used worldwide for scientific research in exploring the planet and galaxy.
GRAPE-DR is a research project funded by the University of Tokyo, National Astronomical Observatory of Japan, Institute of Physical and Chemical Research, NTT Communications plus corporations and research organizations. Its goals are to construct a two petaflops computing engine and global research infrastructure utilizing multi-10 Gbps networks by 2008. The GRAPE-DR machine is designed to compute more than 31 times faster than its predecessor, GRAPE-6 (64 trillion computations per second), and to support general-purpose computing.
According to Alchip, development of the SING processor was very challenging due to its large gate count complexity and performance target. The SING processor contains over 60 million logic gates and is designed to run at 500 MHz while consuming 50 to 60 watts of power. Alchip was responsible for the complete design integration which includes physical, electrical, timing and thermal design of the System-on-Chip (SoC) project. The chip adopted TSMC's 90nm eight-layer metal process with a silicon redistribution layer (RDL) in a flip-chip BGA package. Alchip's divide-and-conquer methodology was used to partition the design into three levels of hierarchy for parallel implementation. Alchip's on-chip clocking distribution structure achieved minimum global clock skew on the scale of 18mm by 18mm die size. It enabled high speed operation by avoiding serious nanometer on-chip variation (OCV) which can affect circuits performance. Close collaboration with the customer allowed Alchip to provide effective design and packaging solutions to achieve a one-pass design tapeout and a one-pass silicon success.
"Having selected Alchip as our SoC development partner, we are extremely delighted and satisfied with Alchip's on-time and one-pass silicon success delivery of SING chip," said Professor Kei Hiraki of the University of Tokyo. "Alchip demonstrated superior design and manufacturing capabilities and supported the development of GRAPE-DR project well. With Alchip's efforts, we are able to test, demonstrate and bring GRAPE-DR to the market on time."
"TSMC supports a broad range of existing and emerging applications," said Makoto Onodera, president of TSMC Japan. "The GRAPE-DR project achieved the first silicon success and marks a major collaborative milestone among private, public, and academic segments."
"Alchip is pleased to provide total SoC solutions to the University of Tokyo for the fastest supercomputer in the world," said Kinying Kwan, chairman, president and chief executive officer of Alchip. "The first silicon success of this complex and challenging chip illustrates Alchip's superior SoC design capabilities in cutting-edge technologies and demonstrates our robust turnkey infrastructure that seamlessly integrates physical design, IP, fabrication, packaging and testing solutions. We will continue to delight our customers by powering them with the fastest time-to-market and the lowest total cost of ownership."
For information about the GRAPE-DR project, visit http://grape-dr.adm.s.u-tokyo.ac.jp/index-en.html or contact Professor Kei Hiraki at hiraki@is.s.u-tokyo.ac.jp.
(Digg, Technorati, more)
PGI Accelerator™ Fortran 95/03 and C99 compilers for x64+NVIDIA
Accelerate applications on x64+GPU platforms by adding OpenMP-like compiler directives to existing Fortran and C programs. Available now for Linux, MacOS and Windows. Download a free 15 day trial.
Platform HPC Workgroup Manager
Platform HPC Workgroup Manager integrates all the cluster productivity tools you need to deploy, run and manage your HPC environment.
C-DAC announces plans for a petaflop system; IBM researchers are working on vertical integration techniques to extend Moore's Law another 15 years. We recap those stories and more in our weekly wrapup.
Read More...
The Moscow State University supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of tripling its processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
Read More...
Right on schedule, Intel has launched its Xeon 5600 processors, codenamed "Westmere EP." The 5600 represents the 32nm sequel to the Xeon 5500 (Nehalem EP) for dual-socket servers. Intel is touting better performance and energy efficiency, along with new security features, as the big selling points of the new Xeons.
Read More...
Mar 19 | OfficialWire | New super to support intelligence work Down Under. Read more...
Mar 18 | ChannelWeb | Westmere parts already showing up in HPC machines. Read more...
Mar 17 | The Register | But what about the tier ones? Read more...
Mar 17 | Cadalyst Magazine | A new generation of workstations is changing the nature of technical computing. Read more...
Mar 17 | Linux Magazine | Latest iteration of Sun Grid Engine able to tap into Cloud. Read more...
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.
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.
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.
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.
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