The Green500 is probably not quite besides is named the Top500 , but it’s no less of an honor to remember a number of the world’s most energy efficient supercomputers. NVIDIA is tooting its own horn for making it directly to the list for the second one year in a row as section of the “greenest” petaflop machine. The Tsubame 2.0 on the Tokyo Institute of Technology’s Global Scientific Information Center is powered by Intel’s Xeon CPUs, but NVIDIA’s Tesla general purpose GPUs do an unlimited majority of the number crunching, allowing it to deliver 1.19 petaflops of performance while consuming only one.2 megawatts. That’s roughly 958 megaflops per watt, a big increase over the most productive CPU-only super computer, the Cielo Cray , which gets only 278 megaflops per watt. The Tsubame 2.0 is not the greenest machine in the world though, that honor belongs to IBM’s BlueGene which takes the head five spots at the Green500. Still, number ten ain’t bad… right? Inspect the PR after the break.
Tokyo Institute of Technology’s “Tsubame 2.0″ System Is 3 times More Energy-Efficient Than Comparable CPU-Only Supercomputers
SANTA CLARA, CA — (Marketwire) — 11/23/2011 — NVIDIA today announced that, for the second one year in a row, the world’s most energy efficient petaflop-class supercomputer is powered by NVIDIA® Tesla™ GPUs.
The Tsubame 2.0 system on the Tokyo Institute of Technology’s Global Scientific Information Center (GSIC) ranks because the greenest petaflop-class supercomputer at the recently released Green500 list. Published twice annually, the Green500 list, rates the five hundred most energy efficient supercomputers according to performance achieved relative to power consumed.
Tsubame 2.0 is a heterogeneous supercomputer (combining both CPUs and GPUs) used to accelerate more than a few scientific and industrial research in Japan. With sustained performance of one.19 petaflops per second while consuming 1.2 megawatts, Tsubame 2.0 delivers 958 megaflops of processing power per watt of energy. It’s 3.4-times more energy efficient than a better-closest x86 CPU-only petaflop system, the Cielo Cray supercomputer at Los Alamos National Laboratory, which delivers 278 megaflops per watt.
Within the race to exascale computing, power efficiency has become the defining component to computing performance. Heterogeneous GPU-accelerated systems are inherently more energy efficient than CPU-only systems because applications can profit from different processors for executing different jobs. The sequential parts of the appliance runs on CPUs, and the information- and compute-intensive parts are accelerated by the massively parallel GPU processor.
Tsubame 2.0 is constituted of HP ProLiant SL390 servers with Intel Xeon CPUs accelerated by NVIDIA Tesla GPUs. The Tesla GPUs provide greater than 80 percent of its performance, enabling Tsubame 2.0 to gain high levels of performance with very low power usage. This year, two of the five finalists for the distinguished Gordon Bell Prize ran on Tsubame 2.0, including the winner for Special Achievement in Scalability and Time-to Solution.
The most recent Green500 list underscores the energy efficiency of heterogeneous computer design. Five of the world’s 10 optimal systems, and 22 of the head 30 best systems, combine GPUs with CPUs.
Tesla GPUs are massively parallel accelerators in response to the CUDA® parallel computing architecture. Application developers can accelerate their applications either using CUDA C, CUDA C++, CUDA Fortran or using the easy, easy-to-use directive-based compilers.
For more info about Tsubame 2.0, visit the Tokyo Institute of Technology, Global Scientific Information and Computing Center site. To be informed more about Tesla GPUs, visit the Tesla website. To benefit more about CUDA, visit the CUDA web page.
About NVIDIA
NVIDIA (NASDAQ: NVDA) awakened the realm to special effects when it invented the GPU in 1999. Today, its processors power a broad range of goods from smart phones to supercomputers. NVIDIA’s mobile processors are utilized in cellphones, tablets and auto infotainment systems. PC gamers depend upon GPUs to enjoy spectacularly immersive worlds. Professionals use them to create visual effects in movies and design everything from golf clubs to jumbo jets. And researchers utilize GPUs to advance the frontiers of science with high-performance computing. The corporate holds greater than 2,100 patents worldwide, including ones covering ideas necessary to modern computing. For more info, see www.nvidia.com.
Tags / Keywords:
NVIDIA, CUDA, Tesla, SC11, Gordon Bell, Green500, Tsubame, Top500, GPU, GPU computing, supercomputing, parallel computing, GPGPU, high performance computing, HPC, programmer, directives, complier, developers, research, scientific computing
Certain statements on this press release including, but not limited to statements as to: the advantages of Tesla GPUs and their impact on Tsubame 2.0; and the consequences of the company’s patents on modern computing are forward-looking statements which are subject to risks and uncertainties which may cause results to be materially different than expectations. Important factors which could cause actual results to vary materially include: global economic conditions; our reliance on third parties to fabricate, assemble, package and test our products; the impact of technological development and competition; development of latest products and technologies or enhancements to our existing product and technologies; market acceptance of our products or our partners products; design, manufacturing or software defects; changes in consumer preferences or demands; changes in industry standards and interfaces; unexpected lack of performance of our products or technologies when integrated into systems; in addition to other factors detailed now and again within the reports NVIDIA files with the Securities and Exchange Commission, or SEC, including its Form 10-Q for the fiscal period ended October 30, 2011. Copies of stories filed with the SEC are posted at the company’s website and come from NVIDIA for gratis. These forward-looking statements should not guarantees of future performance and speak only as of the date hereof, and, except as required by law, NVIDIA disclaims any obligation to update these forward-looking statements to mirror future events or circumstances.
© 2011 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo CUDA, and Tesla are trademarks and/or registered trademarks of NVIDIA Corporation within the U.S. and other countries. Other company and product names could also be trademarks of the respective companies with which they’re associated. Features, pricing, availability, and specifications are subject to vary abruptly.
OMAP 5′s dual A15 cores wipe the ground with four A9s in browsing benchmark
The winners of the 2011 Engadget Awards — Readers’ Choice
