Primeur weekly 2017-10-30

Focus

Scalable Vector Extension instructions well tailored for code size and execution overhead reduction of HPC applications ...

Focus on Europe

GCS supports multi-institution Bavarian student team at SC17 Student Cluster Competition ...

Listening to the sound of the universe ...

Middleware

Bright Computing announces version 8.1 alpha of Bright Cluster Manager and Bright OpenStack ...

Hardware

Green Revolution Cooling deploys immersed HPC cluster at John Paul Catholic University ...

Resistive memory components the computer industry cannot resist ...

Research team led by NUS scientists breaks new ground in memory technology ...

NVIDIA and Taiwan's Ministry of Science and Technology to accelerate Taiwan AI revolution with NVIDIA AI computing platform ...

Stampede1 and Stampede2 help USGS and Southern California Earthquake Center scientists improve seismic forecasts for California ...

Tele Greenland and Verne Global lower network costs from Iceland to North America by 90% ...

LTO Program outlines generation 8 specifications and extends technology roadmap to 12th generation ...

NEC releases new high-end HPC product line, SX-Aurora TSUBASA ...

Fujitsu deploys liquid immersion cooling-based x86 cluster for Japan Automobile Research Institute ...

Applications

Machine learning used to predict earthquakes in a lab setting ...

Researchers unveil tool to debug 'black box' deep learning algorithms ...

Artificial intelligence to evaluate brain maturity of preterm infants ...

Researchers bring optical communication onto silicon chips ...

TACC teams up with Children's Optimal Health to improve child welfare ...

HPE introduces new set of Artificial Intelligence platforms and services ...

ALCF summer students gain real-world experience in scientific HPC ...

Public-private consortium aims to cut preclinical cancer drug discovery from six years to just one ...

The Cloud

UTSA receives $5 million to support new cybersecurity education pipeline ...

NVIDIA launches AI Cloud container registry to accelerate deep learning, Volta GPUs debut on Amazon Web Services ...

Unisys to provide Cloud services to support Nuclear Regulatory Commission's high-performance computing ...

AWS announces availability of P3 instances for Amazon EC2 ...

Primeur magazine

Edition: weekly - Issue: 2017-10-30

Focus

During the Workshops Day at ISC'17 in Frankfurt, Germany on June 22, 2017, Jonathan Beaumont from the University of Michigan, was the fourth speaker of the "Going ARM" Workshop. He talked about porting and adapting applications to ARM's Scalable Vector Extension (SVE). Read further...

Focus on Europe

The Gauss Centre for Supercomputing (GCS) is continuing to serve as a co-sponsor of undergraduate students participating in the Student Cluster Competition (SCC) at the Supercomputing Conference 2017 (SC17) in Denver, Colorado, USA, November 12-17, 2017. Team TUMany segFAUlts - pronounced too many segfaults, is a joint six-person team representing the Technische Universität München (TUM) and the Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). The team - evenly divided between males and females - is the only German participant among the 16 teams taking part in the competition. Read further...
One hundred years ago, Albert Einstein proposed the existence of gravitational waves in his general theory of relativity. To prove the existence of gravitational waves, the Laser Interferometer Gravitational-Wave Observatory (LIGO) collaboration, funded by the National Science Foundation in the Unites States, uses incredibly sophisticated geographically distributed laser detectors to detect the elusive sounds of the universe. To hear the vibrations of space-time, data is analysed using supercomputers. High Performance Computing has had a crucial impact on the research outcome of the LIGO collaboration, which was awarded the 2017 Nobel Prize in Physics. Read further...

Middleware

Bright Computing, a provider of vendor-independent cluster and Cloud management software, continues to enhance its software solutions with the announcement of Bright Cluster Manager and Bright OpenStack version 8.1 alpha. The update features OpenStack Pike, Cloud bursting to OpenStack, workload management accounting and reporting, a lightweight cluster management daemon, customer rebuildable deep learning packages, and many enhancements to Ceph and Kubernetes support. Read further...

Hardware

Green Revolution Cooling (GRC), an expert in immersion cooling, has installed its liquid immersion computing system at John Paul Catholic University (JPCU) in San Diego, California. The high density cluster made up of industry standard servers optimized for immersion, and built in partnership with Supermicro, exploits the enhanced performance and compelling economic value inherent with GRC liquid immersion technology. Read further...
Make way for some new memsistors. For years, the computer industry has sought memory technologies with higher endurance, lower cost, and better energy efficiency than commercial flash memories. Now, an international collaboration of scientists may have solved many of those challenges with the discovery of thin, molecular films that can store information. Read further...
An international research team led by scientists from the National University of Singapore (NUS) pioneered the development of a novel thin, organic film that supports a million more times read-write cycles and consumes 1,000 times less power than commercial flash memories. Read further...
NVIDIA is collaborating with Taiwan's Ministry of Science and Technology (MOST) to accelerate the development of artificial intelligence across Taiwan's commercial sector in support of its recently announced AI Grand Plan to help foster domestic AI-related industries. Read further...
Southern California has the highest earthquake risk of any region in the U.S., but exactly how risky and where the greatest risks lie remains an open question. Earthquakes occur infrequently and depend on complex geological factors deep underground, making them hard to reliably predict in advance. For that reason, forecasting earthquakes means relying on massive computer models and multifaceted simulations, which recreate the rock physics and regional geology and require big supercomputers to execute. Read further...
Verne Global, a provider of highly-optimised, secure, and 100% renewably powered data centre solutions, and Tele Greenland have announced that the 12.4-Tbps upgrade to the Greenland Connect subsea cable system with three new 100-Gpbs connections into Verne Global's Icelandic data centre, is now complete. The upgraded network provides streamlined routing from Iceland to the New York City metro area, lower latency and up to 90% lower network costs. Tele Greenland has also invested in improving route security to ensure data integrity and protect cables from elemental factors. Read further...
The LTO Program Technology Provider Companies (TPCs), Hewlett Packard Enterprise, IBM and Quantum, have announced the specifications of the latest LTO Ultrium format, generation 8, which is now available for licensing by media manufacturers. The LTO Program also released a new LTO technology roadmap, detailing specifications up to twelve (12) generations of tape technology, extending the total capacity of data held on one LTO Ultrium generation 12 tape cartridge to 480TB - an increase of 32 times the capacity of current-generation 7 cartridges. Read further...
NEC Corporation has launched a new high-end HPC product line, the SX-Aurora TSUBASA. This new platform drastically increases processing performance and scalability on real world applications, aiming for the traditional application areas, such as science and engineering, but also targeting the new fields of Machine Learning, Artificial Intelligence and Big Data analytics. With this new technology, NEC opens supercomputing to a wide range of new markets, in addition to the traditional HPC arena. Read further...
Fujitsu has provided the Japan Automobile Research Institute (JARI) with an x86 cluster that uses a liquid immersion cooling system, as a new computational system to simulate automobile collisions. Operations have commenced in October 2017. The cluster system consists of Fujitsu Server PRIMERGY CX2550 M2 x86 servers in PRIMERGY CX400 M1 chassis, as well as a PRIMERGY RX2530 M2 as a management server. The system is cooled by applying a Fujitsu-developed liquid immersion cooling system, in which the servers are directly immersed in a non-conductive fluid with high thermal transport capacity. Read further...

Applications

A group of researchers from the UK and the US have used machine learning techniques to successfully predict earthquakes. Although their work was performed in a laboratory setting, the experiment closely mimics real-life conditions, and the results could be used to predict the timing of a real earthquake. Read further...
Computers can now beat humans at chess and Go, but it may be a while before people trust their driving. The danger of self-driving cars was highlighted last year when Tesla's autonomous car collided with a truck it mistook for a cloud, killing its passenger. Read further...
Researchers at the University of Helsinki and the Helsinki University Hospital (HUH), Finland, have developed software based on machine learning, which can independently interpret EEG signals from a premature infant and generate an estimate of the brain's functional maturity. Read further...
The huge increase in computing performance in recent decades has been achieved by squeezing ever more transistors into a tighter space on microchips. However, this downsizing has also meant packing the wiring within microprocessors ever more tightly together, leading to effects such as signal leakage between components, which can slow down communication between different parts of the chip. This delay, known as the "interconnect bottleneck", is becoming an increasing problem in high-speed computing systems. Read further...
The Texas Advanced Computing Center (TACC) at the University of Texas at Austin has teamed up with Austin, Texas-based non-profit Children's Optimal Health (COH) to provide the technical infrastructure needed to help solve issues in children's health and education throughout Central Texas, including disease, mental health and adverse childhood experiences. Read further...
Hewlett Packard Enterprise has introduced new purpose-built platforms and services capabilities to help companies simplify the adoption of Artificial Intelligence, with an initial focus on a key subset of AI known as deep learning. Read further...
Every summer, the Argonne Leadership Computing Facility (ALCF), a U.S. Department of Energy (DOE) Office of Science User Facility, opens its doors to a new class of student researchers who work alongside staff mentors to tackle research projects that address issues at the forefront of scientific computing. Read further...
Scientists from two U.S. national laboratories, industry and academia today launched an unprecedented effort to transform the way cancer drugs are discovered by creating an open and sharable platform that integrates high-performance computing, shared biological data from public and industry sources and emerging biotechnologies to dramatically accelerate the discovery of effective cancer therapies. Read further...

The Cloud

The University of Texas at San Antonio (UTSA) has received a five-year, $5 million grant from the National Science Foundation to create a multidisciplinary centre fostering education and research at the intersection of cybersecurity and Cloud computing. The Center for Security and Privacy Enhanced Cloud Computing (C-SPECC) will act as a pipeline to create well-trained professionals in the industry and strengthen San Antonio as a cybersecurity hub. The project is led by Ravi Sandhu, Lutcher Brown Endowed Professor of computer science and founding executive director of the UTSA Institute for Cyber Security. Read further...
NVIDIA has made available the NVIDIA GPU Cloud (NGC) container registry for AI developers worldwide. In just a few steps, NGC helps developers get started with deep learning development through no-cost access to a comprehensive, easy-to-use, fully optimized deep learning software stack. Read further...
Unisys Corporation has been selected for award of a task order to provide services and support to move the Nuclear Regulatory Commission's (NRC) high-performance computing operations to a Cloud platform. Read further...
Amazon Web Services Inc. (AWS), an Amazon.com company, has launched P3 instances, the next generation of Amazon Elastic Compute Cloud (Amazon EC2) GPU instances designed for compute-intensive applications that require massive parallel floating point performance, including machine learning, computational fluid dynamics, computational finance, seismic analysis, molecular modelling, genomics, and autonomous vehicle systems. The first instances to include NVIDIA Tesla V100 GPUs, P3 instances are the most powerful GPU instances available in the Cloud. Read further...

Primeur weekly 2017-10-30

Focus

Scalable Vector Extension instructions well tailored for code size and execution overhead reduction of HPC applications ...

Focus on Europe

GCS supports multi-institution Bavarian student team at SC17 Student Cluster Competition ...

Listening to the sound of the universe ...

Middleware

Bright Computing announces version 8.1 alpha of Bright Cluster Manager and Bright OpenStack ...

Hardware

Green Revolution Cooling deploys immersed HPC cluster at John Paul Catholic University ...

Resistive memory components the computer industry cannot resist ...

Research team led by NUS scientists breaks new ground in memory technology ...

NVIDIA and Taiwan's Ministry of Science and Technology to accelerate Taiwan AI revolution with NVIDIA AI computing platform ...

Stampede1 and Stampede2 help USGS and Southern California Earthquake Center scientists improve seismic forecasts for California ...

Tele Greenland and Verne Global lower network costs from Iceland to North America by 90% ...

LTO Program outlines generation 8 specifications and extends technology roadmap to 12th generation ...

NEC releases new high-end HPC product line, SX-Aurora TSUBASA ...

Fujitsu deploys liquid immersion cooling-based x86 cluster for Japan Automobile Research Institute ...

Applications

Machine learning used to predict earthquakes in a lab setting ...

Researchers unveil tool to debug 'black box' deep learning algorithms ...

Artificial intelligence to evaluate brain maturity of preterm infants ...

Researchers bring optical communication onto silicon chips ...

TACC teams up with Children's Optimal Health to improve child welfare ...

HPE introduces new set of Artificial Intelligence platforms and services ...

ALCF summer students gain real-world experience in scientific HPC ...

Public-private consortium aims to cut preclinical cancer drug discovery from six years to just one ...

The Cloud

UTSA receives $5 million to support new cybersecurity education pipeline ...

NVIDIA launches AI Cloud container registry to accelerate deep learning, Volta GPUs debut on Amazon Web Services ...

Unisys to provide Cloud services to support Nuclear Regulatory Commission's high-performance computing ...

AWS announces availability of P3 instances for Amazon EC2 ...