Primeur weekly 2019-11-25

Focus

Exascale Computing Project has a four-pronged software strategy ...

Exascale supercomputing

Argonne teams up with Altair to manage use of upcoming Aurora supercomputer ...

Quantum computing

ColdQuanta closes additional $10 million in seed financing ...

Quantum computers learn to mark their own work ...

Atos partners with Zapata to deliver complete quantum computing solution to the enterprise ...

Fermilab launches new institute for quantum science ...

Focus on Europe

eScience Center holds National eScience Symposium on open science ...

e-IRG workshop in Helsinki focuses on e-Infrastructures and education ...

BSC announces the opening of a global collaboration facility to develop open computer architectures ...

PRACE invites to submit requests for interoperable support services between PRACE, XSEDE and RIST by collaborating teams ...

Netherlands eScience Center and DANS launch new FAIR Software website ...

Hardware

GRC to provide all-in-one immersion-cooling server systems through collaboration with global technology company ...

Compute North Launches 100 Megawatt High-Performance Computing Campus in Nebraska ...

Mellanox 200 Gigabit HDR InfiniBand advances innovations in high-performance computing and Artificial Intelligence ...

FUNET builds 400G-ready network on ADVA FSP 3000 open line system ...

Tachyum shares why its processor is valuable for Chinese market ...

ASSET SourcePoint now supports AMD EPYC processors ...

Credo joins Open Compute Project (OCP) to accelerate 400G and beyond connectivity solutions for hyperscale data centres and telecom ...

HPE tackles AI Ops R&D to improve energy efficiency, sustainability and resiliency in data centres ...

A super-fast 'light switch' for future cars and computers ...

Beyond Moore's Law: Taking transistor arrays into the third dimension ...

Kick-starting Moore's Law? New 'synthetic' method for making microchips could help ...

NEC receives order for a new SX-Aurora TSUBASA supercomputer from the National Institute for Fusion Science ...

DDN works with NVIDIA to ease deployment and set new boundaries in performance for data-intensive AI and HPC ...

DDN completes acquisition of Western Digital's IntelliFlash NVMe, hybrid flash and predictive analytics enterprise business unit ...

Gadi Phase 1 now available to users ...

NASA NCCS Discover supercomputer is expanded with Aspen Systems ...

E4 Computer Engineering announces E4 RK008 - Marvell ThunderX2-based node powered by NVIDIA GPUs ...

New rugged supercomputing servers enable AI, HPC and sensor fusion applications at the edge ...

Applications

Lise Stork wins Young eScientist Award 2019 ...

MathWorks boosts support for scientific research with updated access model for MATLAB and MATLAB Parallel Server ...

2019 ACM Gordon Bell Prize awarded to ETH Zurich team for simulation that maps heat in transistors ...

Artificial intelligence algorithm can learn the laws of quantum mechanics ...

RJM International's first HPC cluster supports power plant emissions reductions ...

In its 15th year, INCITE advances open science with supercomputer grants to 47 projects ...

Mount Sinai announces expanded capability in medical research ...

FC Barcelona and BSC to create a smart system to manage Espai Barça ...

The Cloud

Rescale unveils ScaleX Government, the first federally compliant HPC Cloud service ...

Qumulo to showcase scalable, multi-protocol, Cloud-native distributed file storage at Google Cloud Next '19 UK ...

Mid-Atlantic Crossroads selects Zayo for colocation and connectivity ...

Hewlett Packard Enterprise introduces Kubernetes-based platform for bare-metal and edge to Cloud deployments ...

Atos' BullSequana S server validated for Google Cloud's Anthos ...

SDSC and Wisconsin University IceCube Center conduct GPU Cloudburst experiment ...

Primeur magazine

Edition: weekly - Issue: 2019-11-25

Focus

At the 75th HPC User Forum in Edinburgh, Scotland, Todd Munson from Argonne National Laboratory, gave a presentation about the software strategy of the Exascale Computing Project (ECP) in the United States. Todd Munson wears many hats within ECP but at the HPC User Forum he was talking as the lead for the software ecosystem and delivery activity inside ECP. He gave a brief overview of the ECP project and explained the software strategies that ECP is using in order to deliver a performance software stack on the exascale machines. Read further...

Exascale supercomputing

The U.S. Department of Energys (DOE) Argonne National Laboratory has teamed up with the global technology company Altair to implement a new scheduling system that will be employed on the Aurora supercomputer, slated for delivery in 2021. Read further...

Quantum computing

ColdQuanta Inc., a quantum atomics company, has closed $10 million in additional seed round equity financing from its current investors, Maverick Ventures and Global Frontier Investments. This brings the total investment in the seed round to $16,75 million. The funding will be used to advance the development of ColdQuanta's cold atom Quantum Core technology, the foundation for the company's development of quantum computers and real-time quantum signal processing and positioning systems. Read further...
A new test to check if a quantum computer is giving correct answers to questions beyond the scope of traditional computing could help the first quantum computer that can outperform a classical computer to be realised. Read further...
Atos, a global expert in digital transformation, and US-based Zapata Computing Inc., an enterprise software company for quantum applications, have signed a global partnership to deliver an end-to-end quantum computing solution that combines Zapata's software platform Orquestra with the Atos Quantum Learning Machine (QLM) to address vertical markets. Read further...
The United States' premier particle physics laboratory has become a major player in the rapidly expanding field of quantum science and technology. The U.S. Department of Energy's Fermi National Accelerator Laboratory has launched the Fermilab Quantum Institute, which will bring all of the lab's quantum science projects under one umbrella. This new enterprise signals Fermilab's commitment to this burgeoning field, working alongside scientific institutions and industry partners from around the world. Read further...

Focus on Europe

The Netherlands eScience Center held its 6th National eScience Symposium at the Johan Cruijff ArenA in Amsterdam on 21 November 2019. Titled 'Digital Challenges in Open Science', this year's edition included interdisciplinary sessions on various topics on open science, the launch of a new FAIR Software website and the announcement of the Young eScientist Award 2019. Read further...
e-Infrastructures are IT infrastructures designed to help science. Most of the time the focus is on how e-Infrastructures can help scientific discovery. Science however cannot be in progress without skilled, well-trained scientists. What role can e-Infrastructures play in the scientific education and training process? That is a topic addressed in the e-IRG workshop in Helsinki. Read further...
The Barcelona Supercomputing Center (BSC), one of the leading supercomputing centres in Europe, has announced the opening of the European Laboratory for Open Computer Architecture (LOCA). LOCA's mission is to design and develop energy efficient and high performance chips, based on open architectures like RISC-V, OpenPOWER, and MIPS, in Europe, for use within future exascale supercomputers and other high performance domains. Read further...
The PRACE Board of Directors, the XSEDE Senior Management Team and the RIST Kobe Centre are now inviting requests from new or established collaborative teams spanning Europe, the USA, and/or Japan whose research could be accelerated by coordinated access to staff expertise and/or high-end HPC resources from PRACE, XSEDE and RIST. Read further...
The Netherlands eScience Center and Data Archiving and Networked Services (DANS) have developed a new FAIR Software website for researchers. The website, which was officially launched during the National eScience Symposium on 21 November 2019, provides recommendations to researchers on ways to improve the quality and reproducibility of their software. Read further...

Hardware

Data centres across the globe in nearly every industry are facing rising heat loads and increased density, as well as the pressure to significantly reduce energy consumption, prompting end-users to demand more agile infrastructure that utilizes liquid immersion cooling. Additionally, with the proliferation of edge computing, operators are realizing the importance of being able to quickly deploy critical infrastructure in challenging geographic locations. Read further...
Compute North's largest colocation facility is now live in Kearney, Nebraska. This data centre facility is Compute North's third site, along with others in Texas and South Dakota, and is its highest power offering to date. Read further...
Mellanox Technologies Ltd., a supplier of high-performance, end-to-end smart interconnect solutions for data centre servers and storage systems, has announced the Extreme-Scale High-Performance Computing Programme, teaming with Dell Technologies to empower customers to quickly and easily deploy advanced innovations in high-performance computing (HPC) and artificial intelligence (AI) technologies. Read further...
CSC - IT Center for Science, which operates the Finnish University and Research Network (FUNET), has deployed ADVA technology in response to soaring bandwidth demand. The new solution is now providing Finland's universities and research facilities with highly reliable connectivity at speeds up to 200Gbit/s. Built on the ADVA FSP 3000 open line system (OLS), the fully redundant network leverages ADVA's QuadFlex transponders and ultra-flexible ROADM technology. This enables FUNET to rapidly respond to increasing demand for new services and bandwidth at the touch of a button. Continual, real-time assurance is provided by ADVA's ALM fiber monitoring solution. The network is also ready to expand to 400Gbit/s, ensuring that it will satisfy the needs of Finland’s research and education (R&E) community both now and in years to come. Read further...
Dr. Radoslav Danilak, founder and CEO of semiconductor start-up Tachyum Inc., was invited to visit Hong Kong and Shenzhen, China as part of the recent Central Europe Business Summit (CEBS) under patronage of Forbes to help build bridges and expand relationships with potential customers, partners and investors in the data centre looking to introduce the company's Prodigy Universal Processor Chip as a transformational asset for China. Read further...
Source-level UEFI debug support for the second-generation AMD EPYC processors is now available on ASSET InterTech's SourcePoint debuggers. This brings the SourcePoint debugger's market-leading ease-of-use, performance, and familiar interface to all x86 firmware developers. ASSET is the leading supplier of JTAG-based software and hardware debug, validation and test tools. Read further...
Credo, a global innovation expert in Serializer-Deserializer (SerDes) technology which delivers high performance, low power connectivity solutions for 100G, 400G, and 800G port enabled networks, is participating as a Community Member of the Open Compute Project (OCP). The OCP is an open consortium aiming to design and enable the delivery of the most efficient server, storage, and data centre hardware for scalable computing. Read further...
Hewlett Packard Enterprise (HPE) has signed an AI Ops R&D collaboration with the U.S Department of Energy's National Renewable Energy Laboratory (NREL) to develop Artificial Intelligence (AI) and Machine Learning (ML) technologies to automate and improve operational efficiency, including resiliency and energy usage, in data centres for the exascale era. The effort is part of NREL's ongoing mission as a world leader in advancing energy efficiency and renewable energy technologies to create and implement new approaches that reduce energy consumption and lower operating costs. Read further...
Self-driving cars have become better and more reliable in recent years. Before they might be allowed to drive completely autonomously on our roads in the near future, however, a few hurdles have to be taken. Above all, the need to assess the surroundings at lightning speed and to recognize people and obstacles takes current technologies to its limits. A team of scientists led by Juerg Leuthold at the Institute for Electromagnetic Fields at ETH Zurich, together with colleagues at the National Institute of Standards and Technology (NIST) in the USA and at Chalmers University in Gothenburg, Sweden, has now developed a novel electro-opto-mechanical switch that might be able to elegantly solve both problems in the future. Read further...
Silicon integrated circuits, which are used in computer processors, are approaching the maximum feasible density of transistors on a single chip - at least, in two-dimensional arrays. Read further...
Researchers at Johns Hopkins University have developed a new method for producing atomically-thin semiconducting crystals that could one day enable more powerful and compact electronic devices. By using specially-treated silicon surfaces to tailor the crystals' size and shape, the researchers have found a potentially faster and less expensive way to produce next-generation semiconductor crystals for microchips. Read further...
NEC Corporation has received an order for the "NEC SX-Aurora TSUBASA" supercomputer from the National Institute for Fusion Science (NIFS), a research institute belonging to Japan's National Institutes of Natural Sciences. The system is scheduled to commence operation in June 2020. Read further...
DDN, a global expert in artificial intelligence (AI) and multi-Cloud data management, has worked with NVIDIA to combine the power of NVIDIA DGX SuperPOD systems with DDN's A3I data management system so customers can deploy HPC infrastructure with minimal complexity and reduced timelines. Additionally, by leveraging the new NVIDIA Magnum IO software stack to optimize IO and DDN's parallel file system, customers can speed up data science workflows by up to 20 times. Read further...
DDN, a global expertr in artificial intelligence (AI) and multi-Cloud data management, has completed its acquisition of the IntelliFlash business from Western Digital Corp. The acquisition of IntelliFlash expands DDN's portfolio of intelligent infrastructure offerings for the enterprise with best-in-class NVMe flash solutions and highly versatile hybrid storage arrays, backed by an industry leading AI-enabled, predictive analytics platform. With IntelliFlash, DDN extends its market leadership in end-to-end data management solutions and enables enterprises to solve their most demanding data centre requirements across AI, analytics, IoT, multi-Cloud, and virtualized environments. Read further...
NCI's newest supercomputer, Gadi, is now available to users for an initial transition phase. Users can test out this new machine and find out what it can do for them in the lead-up to its official launch in early 2020. Gadi, named after the words "to search for" in the language of the Ngunnawal people, the traditional owners of the Canberra region, will provide the next generation of computational performance to Australia's researchers. When its full complement of processors comes online in January, Gadi will offer a 5-10 times increase in computational capacity from the original Raijin install in 2012. Read further...
Aspen Systems Inc. has announced that NASA Center for Climate Simulation (NCCS) at NASA's Goddard Space Flight Center in Greenbelt, Maryland has increased the computational power to their primary computing platform the Discover supercomputer by over an incredible 30%. The project Scalable Unit 15 (SCU15) was awarded to, built by and installed by Aspen Systems Inc., in order to add a 25.600-core scalable compute unit onto the system for increased data analysis on our climate through visualized data modelling. Read further...
E4 Computer Engineering, an industry-leading server platform design manufacturer, has announced the validation of the E4 RK008, a Marvell ThunderX2-based node with two NVIDIA V100 Tensor Core GPUs. Read further...
Mercury Systems Inc. has unveiled the EnterpriseSeries RES AI rugged rackmount server line, bringing High Performance Computing (HPC) capabilities to aerospace, defense and other mission-critical applications at the edge. Read further...

Applications

Lise Stork was announced winner of the Young eScientist Award 2019 during the 6th National eScience Symposium on 21 November. Lise Stork, a PhD researcher at Leiden University's Institute of Advanced Computer Science (LIACS), received the award for her project proposal to make historical biodiversity data directly available to researchers. As winner, Lise Stork will receive 50.000 euro worth of expertise from the Netherlands eScience Center to develop her proposal. Read further...
MathWorks has created expanded access to MATLAB and MATLAB Parallel Server to accelerate scientific research and enable collaboration. Today, more than a thousand universities and top research centres around the world offer their own researchers, faculty and students open access to MATLAB and MATLAB Parallel Server. The updated access model has two advantages. First, academic collaborators of these institutions may use the institute MATLAB and MATLAB Parallel Server licenses, facilitating collaboration and reproducibility of research. Second, these academic users with open access will be also able to speed up their research by taking advantage of unlimited access to scale MATLAB programmes and Simulink simulations with MATLAB Parallel Server. Read further...
ACM, the Association for Computing Machinery, named a 6-member team from the Swiss Federal Institute of Technology (ETH) Zurich recipients of the 2019 ACM Gordon Bell Prize for their project, 'A Data-Centric Approach to Extreme-Scale Ab initio Dissipative Quantum Transport Simulations'. Read further...
Artificial Intelligence can be used to predict molecular wave functions and the electronic properties of molecules. This innovative AI method developed by a team of researchers at the University of Warwick, the Technical University of Berlin and the University of Luxembourg, could be used to speed-up the design of drug molecules or new materials. Read further...
RJM International, an award-winning provider of emissions reduction and combustion improvement solutions, is further able to help global power generators and other large combustion plants reduce emissions and improve efficiencies with its first high performance computing (HPC) cluster. The move also supports the growth of the company's business in the EU and the UK, particularly in the biomass and Energy from Waste segments of the market. The new HPC environment is designed, integrated and supported by HPC, storage and data analytics integrator, OCF. Read further...
The U.S. Department of Energy's (DOE) Office of Science announced allocations of supercomputer access to 47 science projects for 2020 - awarding 60% of the available time on some of the United States' most powerful supercomputers, with the ultimate goal of accelerating discovery and innovation. Read further...
Mount Sinai Health System, one of New York's largest integrated health systems, has been awarded a grant from the U.S. Department of Health and Human Services valued at $2 million to build a second "big omics data engine" - BODE 2 - that will enable Mount Sinai researchers to explore more complex scientific questions more quickly. Read further...
FC Barcelona and the Barcelona Supercomputing Center (BSC) are working on a ground-breaking project that applies the Internet of Things (IoT) and Artificial Intelligence (AI) to create a smart system that will analyse and predict the movement of people within and outside the Club facilities - Camp Nou, Palau Blaugrana, Johan Cruyff Stadium, Campus Barça, Museum and Barça Store, etc. - providing information that will allow to take real-time decisions to manage, in an optimal manner, activities of the Club and Espai Barça. Read further...

The Cloud

Rescale, an expert in high performance computing (HPC) in the Cloud, is the first company to deliver a completely Cloud-based HPC platform for the public sector. Rescale's latest offering, ScaleX Government, is the only fully managed HPC service that delivers the scalability of the Cloud with FedRAMP Moderate (In-Process), ITAR compliance, or both. Read further...
Qumulo, a provider of enterprise-proven hybrid Cloud file storage, has signed a partnership with Agile Systems Integrator Appsbroker, the largest Google Cloud-only practice in Europe, to provide enterprises with scalable file storage in the Cloud. The Qumulo file system enables the seamless shift of workflows to the Cloud without refactoring applications to write to new interfaces. With SMB and NFS interfaces available, users can access and share data in the Cloud across different applications and operating systems. Read further...
Zayo Group Holdings Inc. was selected by Mid-Atlantic Crossroads (MAX) to provide data centre colocation in zColo's Ashburn facility and fiber connectivity to support MAX's network services to its academic, research, government, scientific and business communities. MAX is a centre at the University of Maryland (UMD) that operates a regional advanced cyberinfrastructure platform. Read further...
Hewlett Packard Enterprise (HPE) has introduced the HPE Container Platform, the industry's first enterprise-grade Kubernetes-based container platform designed for both Cloud-native applications and monolithic applications with persistent storage. With the HPE Container Platform, enterprise customers can accelerate application development for new and existing apps - running on bare-metal or virtualized infrastructure, on any public Cloud, and at the edge. Read further...
Atos, global expert in digital transformation, has announced at Google Next '19 UK, that its BullSequana S servers are now validated to run Google Cloud's Anthos for multi and hybrid Cloud environments. Read further...
The San Diego Supercomputer Center (SDSC), an Organized Research Unit of UC San Diego; and the Wisconsin IceCube Particle Astrophysics Center (WIPAC) at the University of Wisconsin–Madison successfully completed a computational experiment as part of a multi-institution collaboration that marshalled all globally available for sale GPUs (graphics processing units) across Amazon Web Services, Microsoft Azure, and the Google Cloud Platform. Read further...

Primeur weekly 2019-11-25

Focus

Exascale Computing Project has a four-pronged software strategy ...

Exascale supercomputing

Argonne teams up with Altair to manage use of upcoming Aurora supercomputer ...

Quantum computing

ColdQuanta closes additional $10 million in seed financing ...

Quantum computers learn to mark their own work ...

Atos partners with Zapata to deliver complete quantum computing solution to the enterprise ...

Fermilab launches new institute for quantum science ...

Focus on Europe

eScience Center holds National eScience Symposium on open science ...

e-IRG workshop in Helsinki focuses on e-Infrastructures and education ...

BSC announces the opening of a global collaboration facility to develop open computer architectures ...

PRACE invites to submit requests for interoperable support services between PRACE, XSEDE and RIST by collaborating teams ...

Netherlands eScience Center and DANS launch new FAIR Software website ...

Hardware

GRC to provide all-in-one immersion-cooling server systems through collaboration with global technology company ...

Compute North Launches 100 Megawatt High-Performance Computing Campus in Nebraska ...

Mellanox 200 Gigabit HDR InfiniBand advances innovations in high-performance computing and Artificial Intelligence ...

FUNET builds 400G-ready network on ADVA FSP 3000 open line system ...

Tachyum shares why its processor is valuable for Chinese market ...

ASSET SourcePoint now supports AMD EPYC processors ...

Credo joins Open Compute Project (OCP) to accelerate 400G and beyond connectivity solutions for hyperscale data centres and telecom ...

HPE tackles AI Ops R&D to improve energy efficiency, sustainability and resiliency in data centres ...

A super-fast 'light switch' for future cars and computers ...

Beyond Moore's Law: Taking transistor arrays into the third dimension ...

Kick-starting Moore's Law? New 'synthetic' method for making microchips could help ...

NEC receives order for a new SX-Aurora TSUBASA supercomputer from the National Institute for Fusion Science ...

DDN works with NVIDIA to ease deployment and set new boundaries in performance for data-intensive AI and HPC ...

DDN completes acquisition of Western Digital's IntelliFlash NVMe, hybrid flash and predictive analytics enterprise business unit ...

Gadi Phase 1 now available to users ...

NASA NCCS Discover supercomputer is expanded with Aspen Systems ...

E4 Computer Engineering announces E4 RK008 - Marvell ThunderX2-based node powered by NVIDIA GPUs ...

New rugged supercomputing servers enable AI, HPC and sensor fusion applications at the edge ...

Applications

Lise Stork wins Young eScientist Award 2019 ...

MathWorks boosts support for scientific research with updated access model for MATLAB and MATLAB Parallel Server ...

2019 ACM Gordon Bell Prize awarded to ETH Zurich team for simulation that maps heat in transistors ...

Artificial intelligence algorithm can learn the laws of quantum mechanics ...

RJM International's first HPC cluster supports power plant emissions reductions ...

In its 15th year, INCITE advances open science with supercomputer grants to 47 projects ...

Mount Sinai announces expanded capability in medical research ...

FC Barcelona and BSC to create a smart system to manage Espai Barça ...

The Cloud

Rescale unveils ScaleX Government, the first federally compliant HPC Cloud service ...

Qumulo to showcase scalable, multi-protocol, Cloud-native distributed file storage at Google Cloud Next '19 UK ...

Mid-Atlantic Crossroads selects Zayo for colocation and connectivity ...

Hewlett Packard Enterprise introduces Kubernetes-based platform for bare-metal and edge to Cloud deployments ...

Atos' BullSequana S server validated for Google Cloud's Anthos ...

SDSC and Wisconsin University IceCube Center conduct GPU Cloudburst experiment ...