Inside HPC & AI News | High-Performance Computing & Artificial Intelligence

The new Intel Xeon Scalable Processors provide up to a 2x FLOPs/clock improvement1 with Intel AVX-512 as well as integrated Intel Omni-Path Architecture ports, delivering improved compute capability, I/O flexibility and memory bandwidth to accelerate discovery and innovation.The post New Intel Xeon Scalable Processors Boost HPC Performance appeared first on insideHPC.

In this special guest feature, Rajeev Thakur from Argonne describes why Exascale would be a daunting software challenge even if we had the hardware today. “The scale makes it complicated. And we don’t have a system that large to test things on right now.” Indeed, no such system exists yet, the hardware is changing, and a final vendor or possibly multiple vendors to build the first exascale systems have not yet been selected."The post Developing a Software Stack for Exascale appeared first on insideHPC.

Today Penguin Computing announced completion of the company’s major technology transition to the Intel Xeon Scalable platform for all Penguin Computing product lines. "Penguin Computing’s server solution offers an unrivaled array of compute and storage form factors, in standard 19” EIA, Open Compute and Tundra Extreme Scale platform,” said William Wu, Director of Product Management, Penguin Computing. “We are excited to introduce Intel Xeon Scalable platform based solutions into our versatile Relion and Tundra product lines to tackle today’s computing challenges. Organizations looking to deploy across Data Centers, Cloud Computing, hyper-scale HPC and Deep Learning will find Penguin Computing’s unique and expanding solutions to meet their needs.”The post Penguin Computing Announces Transition to Intel Xeon Scalable Processors appeared first on insideHPC.

Nicola Marzari from EPFL gave this public lecture at PASC17. "The talk offers a perspective on the current state-of-the-art in the field, its power and limitations, and on the role and opportunities for novel models of doing computational science - leveraging big data or artificial intelligence - to conclude with some examples on how quantum simulations are accelerating our quest for novel materials and functionalities."The post Video: Computational Discovery in the 21st Century appeared first on insideHPC.

In this video from PASC17, Maria Grazia Giuffreda (ETH Zurich / CSCS, Switzerland) moderates a Flash Poster Session. "The aim of this session is to allow poster presenters to introduce the topic of their poster and motivate the audience to visit them at the evening poster session. Authors will be strictly limited to 40 seconds each - after this time the presentation will be stopped automatically."The post Video: Flash Poster Session at PASC17 appeared first on insideHPC.

In this RCE Podcast, Brock Palen and Jeff Squyres speak with Shane Canon and Doug Jacobsen from NERSC, the authors of Shifter. "Shifter is a prototype implementation that NERSC is developing and experimenting with as a scalable way of deploying containers in an HPC environment. It works by converting user or staff generated images in Docker, Virtual Machines, or CHOS (another method for delivering flexible environments) to a common format."The post RCE Podcast Looks at Shifter Containers for HPC appeared first on insideHPC.

In this video from ISC 2017, Gaétan Didier Head of CFD, Sahara Force India Formula One Racing Team describes how he uses Univa software to manage CFD workloads that simply cannot be done in a wind tunnel. After that, Bill Bryce from Univa describes how the company's software powers simulation for everything from Formula 1 racing to manufacturing and life sciences.The post Univa Powers Formula One and More at ISC 2017 appeared first on insideHPC.

"The von Neumann design has also led computing to its current limits in efficiency and cooling. As engineers built increasingly complex chips to carry out sequential operations faster and faster, the speedier chips have also been producing more waste heat. Recognizing that modern computing cannot continue on this trajectory, a number of companies are looking to the brain for inspiration and developing “neuromorphic” chips that process data the way our minds do. One such technology is IBM's TrueNorth Neurosynaptic System."The post Testing Brain-Inspired Chips for Big Data Problems at Berkeley Lab appeared first on insideHPC.

In this video from ISC 2017, Sunita Chandrasekaran and Michael Wolfe present an overview of OpenACC and a preview of upcoming GPU Hackathon events. "OpenACC is a user-driven directive-based performance-portable parallel programming model designed for scientists and engineers interested in porting their codes to a wide-variety of heterogeneous HPC hardware platforms and architectures with significantly less programming effort than required with a low-level model."The post Video: OpenACC Update from ISC 2017 appeared first on insideHPC.

This year the ISC conference dedicated an entire day to deep learning, Wednesday, June 21, to discuss the recent advances in artificial intelligence based on deep learning technology. However it, not just the conference where deep learning was dominating the conversation as the showfloor of the exhibition hosted many new products dedicated to optimizing HPC hardware for use in deep learning and AI workloads.The post Deep Learning in the Spotlight at ISC appeared first on insideHPC.

Katrin Heitmann from the University of Chicago presented this talk at PASC17. "In this talk I will introduce HACC, the Hardware/Hybrid Accelerated Cosmology Code, which is being developed to combat the tremendous computational challenge to simulate our Universe." After the talk, she discusses Dark Matter with Rich Brueckner from insideHPC.The post Video: Unlocking the Mysteries of the Universe with Supercomputers appeared first on insideHPC.

This position will specifically focus on management and support of an HPC cluster and multipetabyte storage platform that provides essential infrastructure for Stanford’s growing bioinformatics and genomics communities.The post Job of the Week: HPC System Administrator at Stanford appeared first on insideHPC.

"We decided to use a slightly more interesting use case of solving for Captcha because it not only highlights the power of deep learning to be a useful tool create models to recognize and classify unwieldy data, such as distorted characters, grainy images and overlapping characters, but it also demonstrates that it is possible for this powerful technology to be used in less positive ways, such as solving for security or privacy. Realizing that everyone has access to the tools we use to move society forward, we need to be aware of the possible mis-use, especially as it becomes more pervasive across industry, healthcare, financial services, and the like."The post Deep Learning Comes to the Student Cluster Competition appeared first on insideHPC.

"Given the importance of the precise sparsity pattern, and even the actual matrix data, which decides the effective fill-in upon multiplication, the tests are performed within the CP2K package with application benchmarks. Results show a substantial boost in performance for the RMA based 2.5D algorithm, up to 1.80x, which is observed to increase with the number of processes involved in the parallelization."The post Video: Increasing Efficiency of Sparse Matrix-Matrix Multiplication appeared first on insideHPC.

Today Rescale announced that it has become a full member of the Automotive Simulation Center Stuttgart, or asc(s. The asc(s is a non-profit organization promoting high-performance simulation in virtual vehicle development. It consists of automotive OEMs and suppliers, software and hardware manufacturers, engineering service providers, and research institutes. "Rescale is delighted to be accepted as a member of asc(s,” said Wolfgang Dreyer, Rescale’s EMEA General Manager. “asc(s provides a forum for simulation innovation across the European automotive sector and Rescale is enabling scalable, turnkey on-demand high-performance computing, all pivotal for making automotive simulation cost-effective, fast, and efficient. We look forward to working with the members of the association to better understand industry requirements and trends and to push the boundaries of automotive simulation.”The post Automotive Simulation Center Stuttgart teams with Rescale appeared first on insideHPC.

Aaron Dubrow writes that researchers at the University of Texas Medical Branch are exploring DNA folding and cellular packing with supercomputing power from TACC. "In the field of molecular biology, there's a wonderful interplay between theory, experiment and simulation," Pettitt said. "We take parameters of experiments and see if they agree with the simulations and theories. This becomes the scientific method for how we now advance our hypotheses."The post Supercomputing DNA Packing in Nuclei at TACC appeared first on insideHPC.

In this video from ISC 2017, Mateo Valero from the Barcelona Supercomputing Center describes the innovations behind MareNostrum 4, the #13 supercomputer on the TOP500. "MareNostrum 4, hosted by Barcelona Supercomputing Center, is entirely aimed at generating scientific knowledge and its computer architecture has been called ‘the most diverse and interesting in the world’ by international experts. Equipped with Intel's latest processing and networking technologies, MareNostrum provides 11.1 Petaflops of processing power to scientific production."The post Mateo Valero on how the MareNostrum 4 Supercomputer will Advance Science appeared first on insideHPC.

"Spectrum-2 Open Ethernet switch enables our customers and partners to meet the voracious demands of data speed, data processing and real time data analytics, and to gain competitive advantages,” said Gilad Shainer, vice president of marketing at Mellanox Technologies. “With 10 times better scalability, 1.3 times better power efficiency, full programmability and flexibility, and the capability to seamlessly migrate to 200G and 400G data speeds, Spectrum-2 provides data centers with the ability to maximize return on investment and future proof their investment.”The post Mellanox Unveils Spectrum-2 400 Gigabit Open Ethernet Switch appeared first on insideHPC.

In this video from ISC 2017, Mike Vildibill describes how Hewlett Packard Enterprise describes why we need Exascale and how the company is pushing forward with Memory-Driven Computing. "At the heart of HPE’s exascale reference design is Memory-Driven Computing, an architecture that puts memory, not processing, at the center of the computing platform to realize a new level of performance and efficiency gains. HPE’s Memory-Driven Computing architecture is a scalable portfolio of technologies that Hewlett Packard Labs developed via The Machine research project. On May 16, 2017, HPE unveiled the latest prototype from this project, the world’s largest single memory computer."The post How HPE is Approaching Exascale with Memory-Driven Computing appeared first on insideHPC.

In this podcast, the Radio Free HPC team looks back at the recent ISC 2017 conference and summarizes results from the Student Cluster Competition. "Eleven student teams were on the show floor this year, vying against each other for the top honors in the sixth annual ISC Student Cluster Competition. Tsinghua University from China emerged as the Overall Competition Winner, thus marking their third win in the contest."The post Radio Free HPC Looks at Results from the ISC 2017 Student Cluster Competition appeared first on insideHPC.

In this video, Yan Fisher from Red Hat describes the company's multi-architecture solutions that were on display at ISC 2017. "Historically, HPC workloads have had to rely on custom-built software stacks, most of which relied on proprietary software and overly-specialized hardware. Red Hat is bringing change to the supercomputing arena, from the world’s leading enterprise Linux platform tailored for HPC workloads to massively scalable, fully open cloud infrastructure, along with the management and automation technologies needed to keep these deployments running smoothly."The post Red Hat Debuts Multi-Architecture Solutions for HPC at ISC 2017 appeared first on insideHPC.

PSSC Labs recently announced the deployment of a powerful, turn-key HPC Cluster for the University of Dayton’s Intelligent Optics Laboratory. "It was important for us to select a vendor familiar with the systems requirements of this type of advanced research, that can simultaneously offer the processing power we need while staying within the budget permitted by our research grants,” said Morris Maynard, Sr. Software Engineer at UD. “PSSC offered the best combination of price, software and support available to help advance our research goals.”The post PSSC Labs Powers University of Dayton Atmospheric Optics Research appeared first on insideHPC.

Some of Europe’s leading supercomputing centers have joined forces to create a buyers group that will enable joint public procurement of new HPC systems. "The new partnership of four public HPC centers (BSC, CINECA, JSC, and GENCI), located in four different countries (Spain, Italy, Germany, and France) means that new supercomputers can be procured through a market consultation for the purchase of HPC systems. This group will operate under as part of the Public Procurement of Innovative Solutions for High-Performance Computing (PPI4HPC) project."The post European Supercomputing Centers Adopt Joint Procurement Process appeared first on insideHPC.

"There is real excitement about new technologies like Quantum Computing, however many things are needed to help users learn how to program and use Quantum computers," said Earl Joseph, CEO at Hyperion Research. "By providing universities, research institutes and both large and small businesses across the world access to its QLM, Atos is enabling organizations to experiment with Quantum computing and prepare for this potential revolution in computing."The post Atos Launches World’s Fastest Quantum Simulator appeared first on insideHPC.

Today Maxeler Technologies announced it is now on the G-Cloud 9 framework and can offer its world class accelerated compute performance to the entire UK Public Sector. "I am delighted we can support all parts of the UK Public Sector with our advanced technology," said Oskar Mencer, CEO & CTO of Maxeler. "We look forward to bringing our expertise in working with large data sets in Financial Services and Scientific computing to the UK Government.”The post Maxeler Technologies Accelerates Analytics on UK G-Cloud appeared first on insideHPC.

In this video from ISC 2017, Oliver Tennert from NEC Deutschland GmbH introduces the company's advanced technologies for HPC and Machine Learning. "Today NEC Corporation announced that it has developed data processing technology that accelerates the execution of machine learning on vector computers by more than 50 times in comparison to Apache Spark technologies."The post NEC’s Aurora Vector Engine & Advanced Storage Speed HPC & Machine Learning at ISC 2017 appeared first on insideHPC.

Today NVIDIA and Baidu today announced a broad partnership to bring the world’s leading artificial intelligence technology to cloud computing, self-driving vehicles and AI home assistants. “We believe AI is the most powerful technology force of our time, with the potential to revolutionize every industry. Our collaboration aligns our exceptional technical resources to create AI computing platforms for all developers – from academic research, startups creating breakthrough AI applications, and autonomous vehicles.”The post NVIDIA and Baidu Partner Up to Accelerate AI appeared first on insideHPC.

In this video, CoolIT Systems debuts high TDP processor coldplates, STULZ Micro Data Center with Rack DCLCâ„¢, and new liquid cooled OEM servers at ISC High Performance 2017 in Frankfurt Germany.The post Liquid Cooling Ecosystem Expands for HPC with CoolIT Systems appeared first on insideHPC.

"In the future, though, it may be possible to diagnose cancer much earlier using more sensitive body scans, new types of biomarker tests, and even nano-sensors working in the bloodstream. Experimenting with these techniques in cancer patients or healthy individuals is difficult and potentially unethical. But scientists can test these technologies virtually using supercomputers to simulate the dynamics of cells and tissues."The post Supercomputing New Tools for Cancer Detection appeared first on insideHPC.

In this video from ISC 2017, Raj Hazra, Corporate Vice President and General Manager of the Enterprise and Government Group at Intel, discusses key trends impacting the future growth of High Performance Computing. He focuses on the opportunities of enabling HPC in the cloud, and how this drives the need for a consistent platform that bridges the worlds of dedicated supercomputers and hyperscale cloud service providers.The post Intel’s Raj Hazra on how new technologies are Clouding our Future appeared first on insideHPC.

Today NEC Corporation announced that it has developed new Aurora Vector Engine data processing technology that accelerates the execution of machine learning on vector computers by more than 50 times in comparison to Spark technologies. "This technology enables users to quickly benefit from the results of machine learning, including the optimized placement of web advertisements, recommendations, and document analysis," said Yuichi Nakamura, General Manager, System Platform Research Laboratories, NEC Corporation. "Furthermore, low-cost analysis using a small number of servers enables a wide range of users to take advantage of large-scale data analysis that was formerly only available to large companies."The post NEC Vector Computers Accelerate Machine Learning appeared first on insideHPC.

Today Atos announced that a new Bull Sequana supercomputer will enable high-performance computing solutions to boost next-generation scientific modeling for the UK defense organization. The new system will feature a single Bull Sequana x1000 supercomputer with a theoretical peak performance of 4.3 Petaflops. The Bull Sequana supercomputer uses the latest generation of direct-liquid cooling to enable the densest and most energy-efficient platform in the industry with the system to be installed using the latest Mellanox EDR interconnect and a high performance Seagate Lustre storage appliance offering around 100 Gigabytes per second of I/O performance.The post Atos to Build 4.3 Petaflop Bull Sequana Supercomputer for AWE in the UK appeared first on insideHPC.

The DEEP exascale research computing project has entered its next phase with launch of the DEEP-EST project at the Jülich Supercomputing Center in Germany. "The optimization of homogeneous systems has more or less reached its limit. We are gradually developing the prerequisites for a highly efficient modular supercomputing architecture which can be flexibly adapted to the various requirements of scientific applications,” explains Prof. Thomas Lippert, head of the Jülich Supercomputing Centre (JSC).The post DEEP-EST Project Looks to Building-blocks for Exascale appeared first on insideHPC.

Graduate Assistant Hongyu Chen used data from the National Longitudinal Survey of Youth to model individuals’ education, career, borrowing, and spending decisions based on whether or not they were part of a loan forgiveness program. Chen wrote a program that ran simulations of over 151 parameters on a population of approximately 2,500 individuals between the ages of 18 to 65 during different periods of their lives. "The estimation takes around 10 years if I’m running just one single computer,” Chen said. “That’s why I have to use the cluster of computers, like the supercomputer, that use multiple cores at the same time, so that saves me a lot of time.”The post Supercomputing the Impact of Loan Forgiveness Programs appeared first on insideHPC.

"The mission of the Virtual Institute - High Productivity Supercomputing (VI-HPS) is to improve the quality and accelerate the development process of complex simulation codes in science and engineering that are being designed to run on highly-parallel computer systems. For this purpose, we are developing integrated state-of-the-art programming tools for high-performance computing that assist programmers in diagnosing programming errors and optimizing the performance of their applications."The post The Virtual Institute – High Productivity Supercomputing Celebrates 10th Anniversary appeared first on insideHPC.

The MHPC program in Italy has announced their Call for Masters of High Performance Computing. The Master in High Performance Computing (MHPC) is an innovative degree program that prepares students for exciting careers in the fast-growing field of HPC. Set in the stimulating research environment of its co-organizer institutions, SISSA and ICTP, the program combines lectures with hands-on and applied projects to prepare future HPC specialists for academia and industry.The post SISSA in Italy Issues Call for Masters of High Performance Computing appeared first on insideHPC.

"Intersect360 Research has posted an Executive Summary of their most recent HPC User Site Census on Interconnect Suppliers. The report provides an examination of the server interconnects and network characteristics found at a sample of HPC user sites. Intersect360 Research surveyed a broad range of users about their current computer system installations, storage systems, networks, middleware, and software supporting these computer installations."The post Intersect360 Research Site Census Looks at HPC Interconnects appeared first on insideHPC.

In this video from ISC 2017, Olivier de Laet from Calyos describes the company’s innovative cooling technology for high performance computing. "The HPC industry is ever facing is facing the challenge of ever-increasing cooling requirements. While liquid cooling cooling looks to be the best solution, what if you could achieve the same efficiencies without out using water and pumps?"The post Is Water-Free Cooling the Real Future of HPC? appeared first on insideHPC.

"At NASA, what we're doing is we're really looking at ways of making aircraft more efficient. We're trying to make them quieter. We're trying to make them get to cruise altitude faster, which saves the taxpayer or the people who are using airplanes a lot of money, and we look at really complex problems. We look at things like rotorcraft. If you think about how that model looks, it's a very complex model. What do we do with supercomputing? Pretty much everything across the board."The post Podcast: Why HPC is Vital at NASA appeared first on insideHPC.

In this video from ISC 2017, Tom Krueger from Intel and John Wagner from Fujitsu describe the new KNL Remote Access Program. Now, with the power of Intel HPC Orchestrator, Fujitsu customers can gain access to a small cluster of Intel Xeon Phi processors to test and tune their codes. The freely available cluster environment enables users to participate in activities such as benchmarking, code development, as well as code optimization and validation either using the pre-installed applications or those brought by the user."The post Fujitsu Powers KNL Remote Access Program with Intel HPC Orchestrator appeared first on insideHPC.

Today the ISC Group announced that their 2017 ISC High Performance conference drew a record 3,253 attendees from 60 countries. The attendance represented a 5.2 percent increase compared to last year’s event.The post ISC 2017 Wrapup by the Numbers appeared first on insideHPC.

In this video from ISC 2017, Bill Bryce from Univa describes how the company's software powers simulation for everything from Formula 1 racing to manufacturing and life sciences. "Univa is the leading innovator in workload management and containerization solutions. Univa's suite includes the world's most trusted workload optimization solution enabling organizations to manage and optimize distributed applications, containers, data center services, legacy applications, and Big Data frameworks in a single, dynamically shared set of resources."The post Univa Powers Formula 1 Racing and more at ISC 2017 appeared first on insideHPC.

In many cases, applications that perform various simulations use some of the same math functions that many other applications use. Rather than each developer recoding the same math functions over and over, libraries, developed by experts can significantly speed up execution of the overall application. Since there can be many optimizations that experts who understand many of the nuances of the hardware would understand, it is important that developers be familiar with various libraries that are made available for HPC types of applications.The post Performance Gains Using Libraries appeared first on insideHPC.

Today the InfiniBand Trade Association (IBTA) announced that InfiniBand remains the most used HPC interconnect on the TOP500. Additionally, the majority of newly listed TOP500 supercomputers are accelerated by InfiniBand technology. These results reflect continued industry demand for InfiniBand’s unparalleled combination of network bandwidth, low latency, scalability and efficiency.As demonstrated on the June 2017 TOP500 supercomputer list, InfiniBand is the high-performance interconnect of choice for HPC and Deep Learning platforms,” said Bill Lee, IBTA Marketing Working Group Co-Chair. “The key capabilities of RDMA, software-defined architecture, and the smart accelerations that the InfiniBand providers have brought with their offering resulted in enabling world-leading performance and scalability for InfiniBand-connected supercomputers.”The post InfiniBand Continues Momentum on Latest TOP500 appeared first on insideHPC.

Today SPEC’s High-Performance Group released a new version of its SPEC ACCEL software that adds a suite of OpenMP applications for measuring the performance of systems using hardware accelerator devices and supporting software. SPEC ACCEL also measures performance for computationally intensive parallel applications running under the OpenCL and OpenACC programming models.The OpenMP application benchmarks are the first of their kind and now give our customers the opportunity to compare hardware configurations based on the most popular open-programming models," says Guido Juckeland, SPEC/HPG vice chair. "We look forward to a wide variety of SPEC ACCEL result submissions on the SPEC website and a number of research papers comparing various optimization settings on multiple platforms."The post SPEC/HPG hardware acceleration benchmark adds OpenMP Suite appeared first on insideHPC.

At ISC 2017, Hyperion Research announced the newest recipients of the HPC Innovation Excellence Award. The program's main objectives are to showcase return on investment (ROI) and success stories involving HPC; to help other users better understand the benefits of adopting HPC; and to help justify HPC investments, including for small and medium-size enterprises (SMEs). "There are three awards categories, including the HPC User Innovation Award, the HPC Data Center Innovation Award; and the HPC Vendor Innovation Award. The judgement process for these awards is fair and clear."The post HPC Innovation Excellence Awards announced by Hyperion Research appeared first on insideHPC.

In this video from ISC 2017, Bill Nitzberg from Altair describes how PBS Pro adds powerful workload management capabilities to Intel HPC Orchestrator.Offering PBS Professional as the preferred workload manager for Intel’s HPC Orchestrator provides a comprehensive and reliable workload management product to customers,” said Piush Patel, Vice President, Corporate Development for HPC at Altair. “Altair is committed to the pursuit of exascale computing and the democratization of HPC for organizations to achieve the next great innovations. Intel’s HPC Orchestrator with PBS Pro is a great step toward both goals.”The post Intel HPC Orchestrator – Now with Altair PBS Pro Inside appeared first on insideHPC.

"Liquid cooling is becoming the new norm in the face of skyrocketing wattages by CPUs, GPUs and cluster nodes. Asetek cooling solutions are currently provided by OEMs such as Cray, Fujitsu, Format, Penguin. Liquid cooling for NVIDIA P100, Intel Knight’s Landing and Skylake were all on display at Asetek’s booth as well as rack-level options such as InRackCDU and Vertical RackCDU."The post Liquid Cooling for HPC Gains Momentum with Asetek at ISC 2017 appeared first on insideHPC.

Today Iceland-based co-hosting provider Verne Global announced powerDIRECT+, a reduced-cost compute environment engineered specifically for the next generation of power intensive computing. With the addition of powerDIRECT+, Verne Global has expanded its compute environments to equip CIOs with streamlined and cost-effective data center options, breaking the decades-old model of one-size-fits-all data center design.The post Bring your workloads to Iceland: Verne Global adds powerDIRECT+ appeared first on insideHPC.