Back to Table of contents

Primeur weekly 2013-12-02

Exascale supercomputing

Human Brain Project to hold Open Dialogue with potential HPC suppliers ...

U.S. Government awards AMD contract to research interconnect architectures for high-performance computing ...

The Cloud

Carnegie Mellon leads multi-university project to improve web and Cloud computing accessibility ...

Need a Cloud resource for science? TACC serves up Rodeo ...

IBM Cloud capabilities help ENN Energy drive business growth and build smarter operations ...

iomartcloud and Paragon Development Systems (PDS) to deliver back-up to the Cloud services based on VMware vSphere Data Protection 5.5 advanced ...

Palo Alto Networks and VMware transform Cloud deployments with integrated network virtualization and next-generation security solution ...

IBM awards multi-million dollar Cloud computing platform to seven Nova Scotia schools ...

University of Texas at San Antonio opens Cloud and Big Data Laboratory ...

Unlocking business insights and sales opportunities with Cloud services ...

Scalable Informatics' Unison Appliance shines in first ever public report of STAC-M3 benchmarks on a parallel filesystem with Ceph ...

EuroFlash

European Union funds holistic approach on greener computing ...

Eni's new supercomputer for Eni's exploration & production activity starts work ...

PRACE partners launch Pre-Commercial Procurement: Whole-System Design for Energy Efficient HPC ...

TotalSim to launch a new range of CFD Hardware ...

Beyond encryption: Stronger security for wireless communications ...

USFlash

Intel brings supercomputing horsepower to Big Data analytics ...

Penguin Computing releases Arctica 3200xl open switches based on Broadcom Trident II chipset ...

Aeon Computing to deploy 7 Petabyte Lustre filesystem for SDSC's Comet supercomputer ...

Bright Cluster Manager helps Intel's "Cherry Creek" supercomputer achieve top rankings for SC13 ...

DataDirect Networks introduces the industry's fastest Big Data storage platform - the SFA12KX appliance series ...

OSC unveiled new industrial engagement initiative at SC13 ...

Top honours awarded for productivity in a high-performance supercomputer parallel programming language implementation and overall performance ...

TACC to deploy Maverick for interactive, remote visualization and data analysis ...

Supercomputer helps model lakes, oceans and much more ...

Micron announces development of new parallel processing architecture ...

Spectra Logic expands support of TS1140 Tape Drive technology with T-Series tape libraries and BlackPearl ...

Designed for Big Data applications, AMD announces industry's first "supercomputing" server graphics card with 12GB memory ...

Carnegie Mellon computer searches web 24/7 to analyze images and teach itself common sense ...

NIST demonstrates how losing information can benefit quantum computing ...

Italian physicist delivered 2013 Pitzer Lecture in Theoretical Chemistry ...

Rensselaer professor Deborah L. McGuinness named Fellow of the AAAS ...

Top honours awarded for productivity in a high-performance supercomputer parallel programming language implementation and overall performance


RIKEN
25 Nov 2013 Tokyo - RIKEN, the University of Tsukuba and Fujitsu were recognized in the 2013 HPC Challenge Awards. RIKEN and the University of Tsukuba received the prize in the HPC Challenge Class 2 Awards, which recognize the overall performance of a programming language. This recognition is based on performance results measured using the K computer for implementations of the high-performance supercomputer parallel programming language XcalableMP, which was jointly developed by RIKEN and the University of Tsukuba. This is the first time a Japanese organisation has received the award.

Furthermore, RIKEN, the University of Tsukuba, and Fujitsu received top ranks in three of the four benchmarks at the 2013 HPC Challenge Class 1 Awards for the performance of the K computer. The first-place rankings were received in the following three benchmarks used for evaluating the all-around performance of a supercomputer: (1) Global HPL, which measures the floating point rate of execution for solving a linear system of equations; (2) EP STREAM (Triad) per system, which measures sustainable memory bandwidth and the corresponding computation rate for simple vector kernels; and (3) Global FFT, which measures the floating point rate of execution of double precision complex one-dimensional Discrete Fourier Transform.

With this, the K computer ranked first, for the third consecutive year from 2011 to 2013, in the HPC Challenge Class 1 Awards. The awards were announced on November 21, 2013 in Denver, Colorado at SC13, the International Conference for High Performance Computing, Networking, Storage and Analysis.

The HPC Challenge benchmarks are benchmark programmes designed to evaluate the overall performance of supercomputers in terms of processing performance in 28 tests derived from frequently used computational patterns in the field of scientific computation. There are two classes of awards: Class 1, which measures benchmark performance values, and Class 2, which measures the productivity of programming language implementations.

The HPC Challenge Class 2 Award, the first to be received by a Japanese organisation, is a contest for programming languages used in developing HPC applications. Among the 28 tests mentioned above, the award is designed to evaluate both programming language productivity and performance for four HPC Challenge benchmarks: Global HPL, which measures the floating point rate of execution for solving a linear system of equations; Global RandomAccess, which measures random memory access performance in parallel processing; EP STREAM (Triad) per system, which measures memory access speed under multiple loads; and Global FFT, which measures total performance of Fast Fourier Transform. Participants can also choose to include up to two additional benchmarks besides the HPC Challenge benchmarks for consideration, and the award is determined based on the total score for the implementations including the additional benchmarks.

The award-winning XcalableMP is a programming language that was jointly developed by the RIKEN Advanced Institute for Computational Science and the University of Tsukuba's Center for Computational Sciences. The HPC Challenge benchmarks and the Himeno benchmark - a benchmark programme to evaluate the performance of incompressible fluid analysis code - are the benchmarks that were implemented. The performance results of each of these benchmarks on K computer demonstrated that implementations using XcalableMP exhibit extremely high performance.

Programming languages that can be used to develop highly productive, high-speed applications that run on large-scale computation environments - such as K computer - make it possible to accelerate the pace of research. As a result, they are highly desirable by researchers both inside and outside Japan. The awards reveal both the high productivity and high performance of XcalableMP, in addition to demonstrating the substantial effectiveness of XcalableMP for developing HPC applications.

The K computer, which was developed jointly by RIKEN and Fujitsu as a part of the High-Performance Computing Infrastructure (HPCI) initiative led by Japan's Ministry of Education, Culture, Sports, Science and Technology (MEXT), was opened to shared use in September 2012. The University of Tsukuba contributed extensively to increasing the computational speed for the Global FFT benchmark.

Source: RIKEN

Back to Table of contents

Primeur weekly 2013-12-02

Exascale supercomputing

Human Brain Project to hold Open Dialogue with potential HPC suppliers ...

U.S. Government awards AMD contract to research interconnect architectures for high-performance computing ...

The Cloud

Carnegie Mellon leads multi-university project to improve web and Cloud computing accessibility ...

Need a Cloud resource for science? TACC serves up Rodeo ...

IBM Cloud capabilities help ENN Energy drive business growth and build smarter operations ...

iomartcloud and Paragon Development Systems (PDS) to deliver back-up to the Cloud services based on VMware vSphere Data Protection 5.5 advanced ...

Palo Alto Networks and VMware transform Cloud deployments with integrated network virtualization and next-generation security solution ...

IBM awards multi-million dollar Cloud computing platform to seven Nova Scotia schools ...

University of Texas at San Antonio opens Cloud and Big Data Laboratory ...

Unlocking business insights and sales opportunities with Cloud services ...

Scalable Informatics' Unison Appliance shines in first ever public report of STAC-M3 benchmarks on a parallel filesystem with Ceph ...

EuroFlash

European Union funds holistic approach on greener computing ...

Eni's new supercomputer for Eni's exploration & production activity starts work ...

PRACE partners launch Pre-Commercial Procurement: Whole-System Design for Energy Efficient HPC ...

TotalSim to launch a new range of CFD Hardware ...

Beyond encryption: Stronger security for wireless communications ...

USFlash

Intel brings supercomputing horsepower to Big Data analytics ...

Penguin Computing releases Arctica 3200xl open switches based on Broadcom Trident II chipset ...

Aeon Computing to deploy 7 Petabyte Lustre filesystem for SDSC's Comet supercomputer ...

Bright Cluster Manager helps Intel's "Cherry Creek" supercomputer achieve top rankings for SC13 ...

DataDirect Networks introduces the industry's fastest Big Data storage platform - the SFA12KX appliance series ...

OSC unveiled new industrial engagement initiative at SC13 ...

Top honours awarded for productivity in a high-performance supercomputer parallel programming language implementation and overall performance ...

TACC to deploy Maverick for interactive, remote visualization and data analysis ...

Supercomputer helps model lakes, oceans and much more ...

Micron announces development of new parallel processing architecture ...

Spectra Logic expands support of TS1140 Tape Drive technology with T-Series tape libraries and BlackPearl ...

Designed for Big Data applications, AMD announces industry's first "supercomputing" server graphics card with 12GB memory ...

Carnegie Mellon computer searches web 24/7 to analyze images and teach itself common sense ...

NIST demonstrates how losing information can benefit quantum computing ...

Italian physicist delivered 2013 Pitzer Lecture in Theoretical Chemistry ...

Rensselaer professor Deborah L. McGuinness named Fellow of the AAAS ...