Back to Table of contents

Primeur weekly 2016-12-05

Exascale supercomputing

Hewlett Packard Enterprise demonstrates world's first Memory-Driven Computing architecture ...

Crowd computing

Einstein@home discovers new gamma-ray pulsar ...

Computing tackles the mystery of the dark universe ...

Quantum computing

Construction of practical quantum computers radically simplified ...

Researchers take first look into the 'eye' of Majoranas ...

More reliable way to produce single photons for quantum information imprinting ...

Focus on Europe

Deadline for ISC research paper submission extended to December 16 ...

PRACE to hold awards ceremony at Cineca for Summer of HPC 2016 ...

An open harbour for research data ...

New MareNostrum4 supercomputer to be 12 times more powerful than MareNostrum3 ...

Hardware

Lincoln Laboratory's supercomputing system ranked most powerful in New England ...

PolyU and Huawei jointly set up the first lab in optical communication and advanced computing system in Hong Kong ...

DDN Infinite Memory Engine burst buffer exceeds 1 TB per second file system performance for Japan's fastest supercomputer ...

Fujitsu develops in-memory deduplication technology to accelerate response for large-scale storage ...

Fujitsu announces start of operations for Japan's fastest supercomputer ...

Applications

Using supercomputers to illuminate the renaissance ...

IBM unveils Watson-powered imaging solutions for health care providers ...

New algorithm could explain human face recognition ...

Researchers use Stampede supercomputer to study new chemical sensing methods, desalination and bacterial energy production ...

Physicists spell 'AV' by manipulating Abrikosov vortices ...

BSC researchers to study the response of European climate to Arctic sea ice depletion ...

IBM and Pfizer to accelerate immuno-oncology research with Watson for Drug Discovery ...

Fujitsu offers deep learning platform with world-class speed and AI services that support industries and operations ...

The Cloud

Cloud Systems Management Software Market: Global Industry Analysis and Opportunity Assessment 2016-2026 ...

Juniper Networks simplifies Cloud transition for enterprises with carrier-grade routing and unified security for AWS marketplace ...

DDN Infinite Memory Engine burst buffer exceeds 1 TB per second file system performance for Japan's fastest supercomputer

30 Nov 2016 Tokyo, Santa Clara - Japan's highest performance supercomputer has achieved effective I/O performance exceeding 1 TB per second using DataDirect Netorks (DDN)'s Infinite Memory Engine (IME) to deliver an ultra-high speed file cache system.

"Storage performance has been one of the biggest challenges in developing supercomputers. To meet the demands for storage performance, IME was introduced to the Oakforest-PACS on a massive scale, the first such introduction in the world", stated Osamu Tatebe, lead, public relations, JCAHPC / professor, Center for Computational Sciences, University of Tsukuba. "We are very pleased that we could achieve effective I/O performance exceeding 1 TB per second in writing tens of thousands of processes to the same file. With this new storage technology, we believe that we will be able to contribute to society with the further development of computational science, big data analysis and machine learning."

The Oakforest-PACS massively parallel supercomputer is operated by the Joint Center for Advanced High Performance Computing (JCAHPC), which is run collaboratively by the Information Technology Center at the University of Tokyo and the Center for Computational Sciences at the University of Tsukuba. With resources for joint use, Oakforest-PACS will dramatically advance research and development in a variety of next-generation science and technology fields. It will be used for cutting-edge computational science research, as well as to develop talent in the computational science and high performance computing fields, contributing to the future development of each field.

To measure effective I/O performance, DDN used IOR, the I/O throughput benchmark published by Livermore Computing Center of Lawrence Livermore National Laboratory, and achieved more than 1 TB per second in both I/O access patterns: FPP - File Per Process where parallel processes perform independent file I/O respectively - and SSF - Single Shared File where all parallel processes perform I/O to a single shared file. Importantly, SSF is an access method that cannot realize sufficient performance with a conventional parallel file system, but is considered an effective access method for the next generation of Exascale supercomputers. With its marks for effective performance across FPP and SSF I/O access patterns, DDN IME has proven its eminence as an I/O system not only for conventional I/O processing, but also for future Exascale supercomputing.

Results of the IOR benchmark are as follows:

  • I/O Pattern: FPP Write, Performance: 1.14 TB per second
  • I/O Pattern: FPP Read, Performance: 1.20 TB per second
  • I/O Pattern: SSF Write, Performance: 1.18 TB per second
  • I/O Pattern: SSF Read, Performance: 1.25 TB per second

The file system cache of the Oakforest-PACS comprises 25 DDN IME14KX systems. One DDN IME14KX has 48 x 800GB NVMe SSDs and eight Intel Omni-Path ports. The 25 DDN IME14KX systems provide a cache of 960 TB and a logical bandwidth of 1.5 TB per second within a space as small as 100 rack units, which is about 2 ½ data centre racks. This is one-tenth to one one-hundredth the amount of equipment required to support other current TB/s file systems.

"We are very excited to work with JCAHPC and Fujitsu Limited on innovative, next-generation flash-based storage technologies for scientific computing and Big Data, and we regard the Oakforest-PACS project as a true partnership between users and suppliers that will advance the way we think about data and storage in high-performance computing", stated Robert Triendl, senior vice president of global sales, marketing and field services, DDN.

Source: DataDirect Networks - DDN

Back to Table of contents

Primeur weekly 2016-12-05

Exascale supercomputing

Hewlett Packard Enterprise demonstrates world's first Memory-Driven Computing architecture ...

Crowd computing

Einstein@home discovers new gamma-ray pulsar ...

Computing tackles the mystery of the dark universe ...

Quantum computing

Construction of practical quantum computers radically simplified ...

Researchers take first look into the 'eye' of Majoranas ...

More reliable way to produce single photons for quantum information imprinting ...

Focus on Europe

Deadline for ISC research paper submission extended to December 16 ...

PRACE to hold awards ceremony at Cineca for Summer of HPC 2016 ...

An open harbour for research data ...

New MareNostrum4 supercomputer to be 12 times more powerful than MareNostrum3 ...

Hardware

Lincoln Laboratory's supercomputing system ranked most powerful in New England ...

PolyU and Huawei jointly set up the first lab in optical communication and advanced computing system in Hong Kong ...

DDN Infinite Memory Engine burst buffer exceeds 1 TB per second file system performance for Japan's fastest supercomputer ...

Fujitsu develops in-memory deduplication technology to accelerate response for large-scale storage ...

Fujitsu announces start of operations for Japan's fastest supercomputer ...

Applications

Using supercomputers to illuminate the renaissance ...

IBM unveils Watson-powered imaging solutions for health care providers ...

New algorithm could explain human face recognition ...

Researchers use Stampede supercomputer to study new chemical sensing methods, desalination and bacterial energy production ...

Physicists spell 'AV' by manipulating Abrikosov vortices ...

BSC researchers to study the response of European climate to Arctic sea ice depletion ...

IBM and Pfizer to accelerate immuno-oncology research with Watson for Drug Discovery ...

Fujitsu offers deep learning platform with world-class speed and AI services that support industries and operations ...

The Cloud

Cloud Systems Management Software Market: Global Industry Analysis and Opportunity Assessment 2016-2026 ...

Juniper Networks simplifies Cloud transition for enterprises with carrier-grade routing and unified security for AWS marketplace ...