HPCwire: Tokyo Tech Selects HMPP Compiler for TSUBAME 2.0 Developers

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

Translation Disclaimer

Subscribe | Sign In

Visit additional Tabor Communication Publications

Leading HPC
Solution Providers

January 11, 2012

Tokyo Tech Selects HMPP Compiler for TSUBAME 2.0 Developers

CAPS entreprise, the manycore programming company, JCC Gimmick and Global Scientific Information and Computing Center, Tokyo Institute of Technology today announced the availability of HMPP for both academic and professional users of TSUBAME 2.0.

TOKYO, Jan. 11 -- A team of Global Scientific Information and Computing Center (GSIC), Tokyo Institute of Technology (Tokyo Tech) was recently awarded the ACM Gordon Bell Prize, for its supercomputing breakthroughs using hybrid manycore systems TSUBAME 2.0 based on NVIDIA Tesla GPUs and Intel Xeon has today acquired licenses of the HMPP workbench software.

HMPP workbench is a compiler for manycore architecture, based on a set of OpenMP-like directives that preserve legacy codes. HMPP fully leverages the performance offered by most of today's stream processors. Being complementary to OpenMP and MPI, HMPP lets users incrementally develop or port existing applications to manycore without the complexity associated with manycore programming.

Pioneer in the directive-based approach with its HMPP flagship product, initiator of the OpenHMPP standard and member of the OpenACC initiative, CAPS - the manycore programming company - is proud to both serve HPC and Digital Manufacturing professionals. CAPS is providing a Global Solution based on innovative development tools, methodology and technology trainings, onsite consulting or outsourcing expertise to quickly secure manycore performances while preparing for future architecture evolutions.

"I'm happy today to provide Tokyo Tech with our HMPP solution" said Benoît Raoult, VP APAC for CAPS entreprise. "Tokyo Tech is recognized worldwide for its hybrid computing expertise. This has been possible thanks to its visionary TSUBAME project. This system has been providing computing and storage resources for research but has also been made available to the industries. If HPC users are used to adapt, it is the Digital Manufacturing users that will face challenges soon. We should serve them thanks to all the experienced that we acquired from HPC success stories. I appreciate sharing this mission with Tokyo Tech."

"It is our pleasure that many users have benefits of HMPP on TSUBAME 2.0" said Takayuki Aoki, Professor/Deputy Director, GSIC Tokyo Tech. "There are many types of TSUBAME users in Tokyo Tech and not all of them write their programs in CUDA or Open CL. The directive-based code generator HMPP will make their efforts small to speed-up the code executions on TSUBAME 2.0".

"We are very pleased to receive this opportunity to supply HMPP solution" said T. Onodera, chief technician of JCC Gimmick "This cooperation with Tsubame 2.0 users will allow us to understand precisely their expectations in terms of manycore programming tools and solution. Learning this is our honor."

About CAPS entreprise

CAPS is a major supplier of solutions dedicated to application migration and deployment on manycore processors. CAPS global solutions for manycore lead the developer to performance by providing top-of-the-range technology (HMPP hybrid compiler and wizard), code porting methodology and ecosystem. Its directive-based & multi-target HMPP compiler enables developers to safely move to hybrid CPU / GPU model and leverage the computing power of stream processors without the pain associated to GPU programming. HMPP is offered within CAPS DevDeck package: an ALL-IN-ONE multi-level suite for manycore application definition, porting and optimization with tools, methodology and resources. Website: www.caps-entreprise.com.

About JCC Gimmick

JCC-Gimmick provides consulting expertise in the area of GPU computing tools such as HMPP, the directive-based compiler developed by CAPS. JCC-Gimmick can assist in deploying GPGPU tools effectively and optimizing code performance. Website: www.hmpp.jp.

About Global Scientific Information Computing Center (GSIC), Tokyo Institute of Technology

GSIC has started the operation of the TSUBAME 2.0 supercomputer, which is equipped with 4224 NVIDIA Tesla M2050 GPUs since November 2010. The peak performance is 2.4 PFLOPS and the 5th fastest supercomputer the Top 500 ranking. Website: http://www.gsic.titech.ac.jp/en.

-----

Source: CAPS enterprise

Share Options

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

Become a Registered User Today!

Registered Users Log in join the Discussion

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Subscribe to All Content

All

May 22, 2012

May 21, 2012

May 18, 2012

May 17, 2012

May 16, 2012

May 15, 2012

May 14, 2012

May 11, 2012

May 10, 2012

Feature Articles

OpenACC Starts to Gather Developer Mindshare

PGI, Cray, and CAPS enterprise are moving quickly to get their new OpenACC-supported compilers into the hands of GPGPU developers. At NVIDIA's GPU Technology Conference this week, there was plenty of discussion around the new HPC accelerator framework, and all three OpenACC compiler makers, as well as NVIDIA, were talking up the technology.
Read more...

NVIDIA Launches Kepler Into HPC

NVIDIA has introduced its first Kepler-generation GPU product for high performance computing, and revealed some of the inner working of the new architecture. The announcement took place at the kickoff of the company's GPU Technology Conference taking place this week in San Jose, California.
Read more...

Intel Rolls Out New Server CPUs

Intel Corp. has launched three new families of Xeon processors, joining the Xeon E5-2600 series the chipmaker introduced in March. These latest chips span the entire market for the Xeon line, from four- and two-socket servers, down to entry-level workstations and microservers. A number of HPC server makers, including SGI, Dell, and Appro announced updated hardware based on the new silicon.
Read more...