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

Data accumulation is just one of the challenges facing today weather and climatology researchers and scientists. To understand and predict Earth’s weather and climate, they rely on increasingly complex computer models and simulations based on a constantly growing body of data from around the globe. "It turns out that in today’s HPC technology, the moving of data in and out of the processing units is more demanding in time than the computations performed. To be effective, systems working with weather forecasting and climate modeling require high memory bandwidth and fast interconnect across the system, as well as a robust parallel file system."The post How HPC is Helping Solve Climate and Weather Forecasting Challenges appeared first on insideHPC.

Researchers using the Gordon Supercomputer at SDSC have identified a class of possible antibiotics with the potential to disable previously drug-resistant bacteria. In essence, these new agents were found to attack the bacteria along two fronts: its external lipid cellular wall and its internal factory responsible for generating cellular energy in the form of adenosine triphosphate or ATP.The post Gordon Supercomputer Aids Search for New Antibiotics appeared first on insideHPC.

Today Nimbix announced plans to use Infomart Dallas to support the infrastructure needs of its upgraded HPC cloud platform, JARVICE 2.0. Infomart Dallas provides Nimbix with a high-density data center complete with industry-leading connectivity options, access to the core Dallas/Fort Worth (DFW) network hub, and the low-cost power it needs to deliver its innovative HPC solutions.The post Nimbix HPC Cloud Moves to 100 MW Dallas Datacenter appeared first on insideHPC.

Today ProphetStor Data Services rolled out a reference cloud computing platform with Mellanox based on the open-source projects OpenStack and Ceph. The solution leverages each company's respective strength in software-defined-storage, state-of-the-art server hardware, and high-speed networking. Based on ProphetStor Federator SDS, this joint project addresses the key issues of OpenStack's storage management solution as well as improving the functionality and performance of Ceph, the de facto storage backend for OpenStack.The post ProphetStor Leverages Mellanox Tech for Next-Gen Cloud Computing appeared first on insideHPC.

There are just two weeks left to submit papers to PASC16. The event takes place June 8-10, 2016 in Lausanne, Switzerland.The post PASC16 Seeks Your Paper Submissions by Jan. 15 appeared first on insideHPC.

Dr. Lewey Anton reports on who's moving on up in High Peformance Computing. Familiar names in this edition include: Sharan Kalwani, John Lee, Jay Muelhoefer, Brian Sparks, and Ed Turkel.The post HPC People on the Move – New Year’s Edition appeared first on insideHPC.

In this Chigago Tonight video, Katrin Heitmann from Argonne National Lab describes one of the most complex simulations of the evolution of the universe ever created. "What we want to do now with these simulations is exactly create this universe in our lab. So we build this model and we put it on a computer and evolve it forward, and now we have created a universe that we can look at and compare it to the real data."The post Video: How Argonne Simulated the Evolution of the Universe appeared first on insideHPC.

Researchers from Zhejiang University and Hangzhou Dianzi University in China have developed the Darwin Neural Processing Unit (NPU), a neuromorphic hardware co-processor based on Spiking Neural Networks, fabricated by standard CMOS technology. "Its potential applications include intelligent hardware systems, robotics, brain-computer interfaces, and others. Since it uses spikes for information processing and transmission, similar to biological neural networks, it may be suitable for analysis and processing of biological spiking neural signals, and building brain-computer interface systems by interfacing with animal or human brains."The post China Develops Darwin Neuromorphic Chip appeared first on insideHPC.

In this Chip Chat Podcast, Intel's Barry Davis describes how today’s requirements for high performance computing fabrics are outstripping the capabilities of traditional fabric technologies in performance, reliability, and economic feasibility. He highlights how Intel Omni-Path Architecture (OPA) is delivering performance for tomorrow’s HPC workloads and has the ability to scale to tens and eventually thousands of nodes at competitive price to today’s fabrics. Barry illustrates that Intel OPA is a foundational element of the Intel Scalable System Framework (Intel SSF) and will continue to drive higher performance, lower latency, and more bandwidth across the Intel CPU roadmap.The post Podcast: Changing HPC Economics with the Intel Omni-Path Architecture appeared first on insideHPC.

Penguin Computing has renewed as a Platinum Member of Open Compute Project (OCP). Leading with the OCP-based Tundra Extreme Scale (ES) Series, Penguin was recently awarded the CTS-1 contract with the NNSA to bolster computing for national security at Los Alamos, Sandia and Lawrence Livermore national laboratories.The post Penguin Computing is now Platinum Member of Open Compute Project (OCP) appeared first on insideHPC.

In this video, Dr. Michael Karasick from IBM moderates a panel discussion on Machine Learning. "The success of cognitive computing will not be measured by Turing tests or a computer’s ability to mimic humans. It will be measured in more practical ways, like return on investment, new market opportunities, diseases cured and lives saved."The post Video: IBM Panel Discussion on Machine Learning appeared first on insideHPC.

Quantlab Financial in Houston is seeking a Senior HPC Engineer in our Job of the Week.The post Job of the Week: Senior HPC Engineer at Quantlab Financial appeared first on insideHPC.

Rob Futrick presented this talk at SC15. "Cycle Computing’s CycleCloud software suite is the leading cloud orchestration, provisioning, and data management platform for Big Compute, Big Data, and large technical computing applications running on any public, private, or internal environment. For years, customers in Life Sciences, Manufacturing, Financial Services, and other Engineering and Research areas have used CycleCloud software to manage some of the world’s largest production cloud deployments."The post Video: Why Wouldn’t You Use Public Cloud for HPC? appeared first on insideHPC.

In this video from the Cycle Computing the HPC in the Cloud Educational Series, Jeff Layton, HPC Principal Architect at Amazon Web Services, explains concepts and options around using storage in the AWS Cloud.The post HPC Cloud Data Management at AWS appeared first on insideHPC.

OpenHPC is a collaborative, community effort that initiated from a desire to aggregate a number of common ingredients required to deploy and manage High Performance Computing Linux clusters including provisioning tools, resource management, I/O clients, development tools, and a variety of scientific libraries.The post Podcast: Strengthening High Performance Computing with OpenHPC appeared first on insideHPC.

In this video from SC15, Dell's Onur Celebioglu discusses why HPC is now important to a broader group of use cases. He also provides an overview of HPC for research, life sciences and manufacturing. Participants learned more about why HPC, big data and cloud are converging, and how Dell solves challenges in our HPC engineering lab and through collaborative work with other leading technology partners and research institutions.The post Video: Trends and Tech in the HPC Market appeared first on insideHPC.

In this Chip Chat podcast, Bill Mannel, Vice President and General Manager for HPC and Big Data from Hewlett Packard Enterprise (HPE) describes the High Performance Computing Alliance between HPE and Intel. He highlights how the two companies are developing innovative solutions based on Intel Scalable System Framework (Intel SSF) and are working to enhance HPC solutions while engaging customers directly in centers of excellence (COEs) located in Grenoble, France and Houston, Texas. Bill also emphasizes how HPE compute solutions are experiencing incredible momentum in government, commercial and academic market verticals and that HPE is receiving excellent results from the integration of HPE Apollo products and Intel HPC technology.The post Podcast: HPE and Intel Alliance for High Performance Computing & Big Data appeared first on insideHPC.

Who are the world’s most important vendors of supercomputers, at least as measured by the number of systems they have in the Top500? HP is the leader with a 31 per cent share; Cray is number two with just under 14 per cent. So far, so unsurprising. But what has been little remarked upon is that in third place – with 49 systems, or 9.8 per cent of the Top500 list – is the Chinese vendor, Sugon. And both Sugon and Inspur, the other main Chinese vendor, have their sights set on expanding still further, with trade missions to Europe and setting up partnerships and subsidiaries in both Europe and the USA.The post China’s HPC Vendors Look to US and European Markets appeared first on insideHPC.

Ruud van der Pas from Oracle presented this talk at OpenMPcon. "Unfortunately it is a very widespread myth that OpenMP Does Not Scale – a myth we intend to dispel in this talk. Every parallel system has its strengths and weaknesses. This is true for clustered systems, but also for shared memory parallel computers. While nobody in their right mind would consider sending one zillion single byte messages to a single node in a cluster, people do the equivalent in OpenMP and then blame the programming model. Also, shared memory parallel systems have some specific features that one needs to be aware of. Few do though. In this talk we use real-life case studies based on actual applications to show why an application did not scale and what was done to change this. More often than not, a relatively simple modification, or even a system level setting, makes all the difference."The post Dispelling the Myth “OpenMP Does Not Scale” appeared first on insideHPC.

Steve Cooper from One Stop Systems presented this talk at SC15. “The OSS GPUltima is the densest and most cost-effective petaflop solution for scalable data center infrastructures," said Steve Cooper, OSS CEO. “Supporting up to 128 NVIDIA Tesla K80 GPU accelerators, the OSS GPUltima shows tremendous performance gains in many applications like oil and gas exploration, financial calculations, and medical devices. Providing ample cooling and power to accommodate this many high-end cards, it surpasses other devices in performance. In addition, the OSS GPUltima is a preconfigured rack of GPUs, servers and interconnections already integrated and the whole unit is tested and ready to add application software."The post Video: GPUltima – The Ultimate in GPU Networks appeared first on insideHPC.

Today Intel Corporation announced that it has completed the acquisition of Altera, a leading provider of field-programmable gate array (FPGA) technology. The acquisition complements Intel's leading-edge product portfolio and enables new classes of products in the high-growth data center and Internet of Things (IoT) market segments.The post Intel Completes Altera Acquisition appeared first on insideHPC.

In this podcast, the Radio Free HPC team makes their tech predictions for 2016. Will secure firmware be the key differentiator for HPC vendors? Will this be the year of FPGAs? And could we see a 100 Petaflop machine on the TOP500 before the year ends?The post 2016 Predictions from Radio Free HPC appeared first on insideHPC.

In this Intel Chip Chat podcast, Alan Gara describes how Intel’s Scalable System Framework (SSF) is meeting the extreme challenges and opportunities that researchers and scientists face in high performance computing today. He explains that SSF incorporates many different Intel technologies including; Intel Xeon and Phi processors, Intel Omni-Path Fabrics, silicon photonics, innovative memory technologies, and efficiently integrates these elements into a broad spectrum of system solutions optimized for both compute and data-intensive workloads. Mr. Gara emphasizes that this framework has the ability to scale from very small HPC systems all the way up to exascale computing systems and meets the needs of users in a very scalable and flexible way.The post Podcast: Alan Gara on the Intel Scalable System Framework appeared first on insideHPC.

The EMiT 2016 Emerging Technologies Conference has issued its Call for Papers. Hosted by the Mont-Blanc project and the Barcelona Supercomputing Centre, the event takes place June 2-3, 2016 in Barcelona.The post Call for Papers: EMiT 2016 Emerging Technologies Conference appeared first on insideHPC.

"Developers of modern HPC applications face a challenge when scaling out their hybrid (MPI/OpenMP) applications. As cluster sizes continue to grow, the amount of analysis data collected can easily become overwhelming when going from 10s to 1000s of ranks and it’s tough to identify which are the key metrics to track. There is a need for a lightweight tool that aggregates the performance data in a simple and intuitive way, provides advice on next optimizations steps, and hones in on performance issues. We’ll discuss a brand new tool that helps quickly gather and analyze statistics up to 100,000 ranks. We’ll give examples of the type of pertinent information collected at high core counts, including memory and counter usage, MPI and OpenMP imbalance analysis, and total communication vs. computation time. We’ll work through analyzing an application and effective ways to manage the data."The post Video: Profiling at Scale appeared first on insideHPC.

The InterCloud-HPC 2016 conference has issued its Call for Papers. As part of The International Conference on High Performance Computing & Simulation (HPCS 2016), the event takes place July 18-22 in Innsbruck, Austria.The post Call for Papers: InterCloud-HPC 2016 in Austria appeared first on insideHPC.

"SeqAn (www.seqan.de) is an open-source C++ template library (BSD license) that implements many efficient and generic data structures and algorithms for Next-Generation Sequencing (NGS) analysis. It contains gapped k-mer indices, enhanced suffix arrays (ESA) or an (bidirectional) FM-index, as well algorithms for fast and accurate alignment or read mapping. Based on those data types and fast I/O routines, users can easily develop tools that are extremely efficient and easy to maintain. Besides multi-core, the research team at Freie Universität Berlin has started generic support for distinguished accelerators such as Intel Xeon Phi in a new IPCC. In this talk we will introduce SeqAn and its generic design, describe successful applications that use SeqAn, and describe how SeqAn will incorporate SIMD and multicore parallelism for its core data structures using the pairwise alignment module as an example."The post Video: The SeqAn C++ Library for Efficient NGS Sequence Analysis appeared first on insideHPC.

A new high performance computing and cloud facility has been unveiled by scientists in London, named after Dr Rosalind Franklin, the unsung heroine of elucidating the double-helix structure of DNA. "Before Rosalind, if we wanted to analyze the data from 500 DNA samples it would have taken us approximately six months, now with the launch of Rosalind it will take only a week."The post HPC Facility in London Named After Dr Rosalind Franklin appeared first on insideHPC.

Bill Lee presented this talk at the Mellanox booth at SC15. "The IBTA is responsible for compliance and interoperability testing of commercial products and has successfully added hundreds of products to its Integrators’ List. The IBTA unites the industry through IBTA-sponsored technical events and resources, and actively promotes InfiniBand from a vendor-neutral perspective through online communications, marketing and public relations engagements."The post Video: InfiniBand Trade Association Update appeared first on insideHPC.

In this video, Dr. David Southwell from Obsidian Strategics discusses conventional InfiniBand technology and goes on to describe how the company's Longbow, Crossbow and Bowman devices enable what is generally considered as an 'indoor use only' protocol to be deployed at scale with security over global distances. The resulting Global InfiniBand Fabrics can be used for a variety of purposes including technical computing, big data migration and streaming distribution.The post Obsidian Introduces Global InfiniBand Fabrics appeared first on insideHPC.

Are you planning to ISC 2016 in June? Special flight discounts are now available through Star Alliance member airlines.The post Save up to 20 Percent on Travel to ISC 2016 Through the Star Alliance appeared first on insideHPC.

"In this presentation, we will discuss several important goals and requirements of portable standards in the context of OpenMP. We will also encourage audience participation as we discuss and formulate the current state-of-the-art in this area and our hopes and goals for the future. We will start by describing the current and next generation architectures at NERSC and OLCF and explain how the differences require different general programming paradigms to facilitate high-performance implementations."The post Video: Enabling Application Portability across HPC Platforms appeared first on insideHPC.

An interesting use of HPC technologies is in the area of understanding the propagation of radio frequency energy in an outdoor environment. "Applications of this type need to be completed in seconds to minutes to be useful. Since the tracing of each ray is independent of another ray, this type of application can be distributed easily among the many cores of the Intel Xeon Phi coprocessor."The post Tracing Radio Frequencies with Intel Xeon Phi appeared first on insideHPC.

Today NetApp announced it has entered into a definitive agreement to acquire SolidFire for $870 million in cash. Founded in 2010, SolidFire is a market leader in all-flash storage systems built for the next-generation data center where simple scaling, set-and-forget management, assured performance and multi-tenancy, and cloud economic models are driving new market growth.The post NetApp to Acquire SolidFire for All-Flash SSDs appeared first on insideHPC.

Thomas Schulthess from CSCS presented this talk at the Nvidia booth at SC15. "On October 1, 2015 "Piz Kesch", a Cray CS-Storm system with NVIDIA K80 GPUs became operational at CSCS on behalf of MeteoSwiss. In this talk, we will discuss the hardware-software co-design project behind this most cost and energy efficient system for numerical weather prediction."The post Piz Kesch: The Making of a GPU-based Weather Forecasting System appeared first on insideHPC.

The 2016 International Conference on High Performance Computing & Simulation (HPCS 2016) has issued its Call for Doctoral Dissertation Colloquium Abstracts. The mission of HPCS is to address, explore and exchange information on the state-of-the-art in high performance and large scale computing systems, their use in modeling and simulation, their design, performance and use, and their impact. The Conference will be held on July 18 - 22, 2016 in Innsbruck, Austria.The post Call for Doctoral Dissertation Colloquium Abstracts: HPCS 2016 appeared first on insideHPC.

Prof. Kai Li from Princeton presented this talk at the Intel HPC Developer Conference at SC15. "Full correlation matrix analysis (FCMA) is an unbiased approach for exhaustively studying interactions among brain regions in functional magnetic resonance imaging (fMRI) data from human participants. In order to answer neuro-scientific questions efficiently, we are developing a closed-loop analysis system with FCMA on a cluster of nodes with Intel Xeon Phi coprocessors. In this talk, we will discuss our current results and future plans."The post Building A Real-Time, Closed Loop fMRI Data Analysis System for Neuroscience Experiments appeared first on insideHPC.

The use of High Performance Computing continues to grow in the enterprise and beyond. In this podcast, James Reinders from Intel describes how Intel will continue to drive HPC democratization in 2016. "At Intel, our passion to help drive the democratization of HPC is exemplified by many things. Here is my list of ten things which caught my attention as being most significant as we enter 2016."The post Podcast: Top 10 Ways Intel Will Drive HPC Democratization in 2016 appeared first on insideHPC.

In this video, Tommy Minyard from TACC describes how Dell helped develop the 9.6 Petaflop Stampede supercomputer for scientific computing. "The Texas Advanced Computing Center supports the University of Texas System and National Science Foundation researchers with the newest version of their Stampede High Performance Computing cluster. Stampede uses Dell PowerEdge servers, Intel Xeon processors and the new Dell Networking H-Series switches and adapters based on Intel Omni-Path Architecture. These newly implemented technologies greatly reduce latency, optimize traffic flow, and give Stampede a peak performance of 10 petaflops."The post Video: TACC Powers Stampede Supercomputer with Dell Servers and Intel Omni Path appeared first on insideHPC.

"To be successful in high-performance computing (HPC) today, it is no longer enough to sell good hardware: vendors need to develop an ‘ecosystem’ in which other hardware companies use their products and components; in which system administrators are familiar with their processors and architectures; and in which developers are trained and eager to write code both for the efficient use of the system and for end-user applications. No one company, not even Intel or IBM, can achieve all of this by itself anymore."The post Is HPC Heading Towards Openness, Chaos, or a Split? appeared first on insideHPC.

An interdisciplinary research team from JYU in Finland has set a new world record in the field of fluid flow simulations through porous materials. The team, coordinated by Dr. Keijo Mattila from the University of Jyväskylä, used the world’s largest 3D images of a porous material--synthetic X-ray tomography images of the microstructure of Fontainebleau sandstone, and successfully simulated fluid flow through a sample of the size of 1.5 cubic centimeters with a submicron resolution.The post JYU Sets World Record for Pore-scale Flow Simulations appeared first on insideHPC.

Today the French ESI Group announced the opening of its new European HPC Center. The datacenter is now based on the Teratec Campus, an ideal location to launch collaborative High-Performance Computing projects as it is in the vicinity of Europe’s biggest HPC center: the CEA’s Très Grand Centre de Calcul. The new datacenter will effectively act as ESI’s POD (Point of Delivery), serving all ESI offices across Europe as a platform for ESI’s new software development and engineering services alike. ESI teamed up with Legrand, the global specialist in electrical and digital building infrastructures to meet the technical challenges surrounding this project.The post ESI Opens New European HPC Center appeared first on insideHPC.

Lustre was originally developed as the fastest scratch file system for HPC workloads that supercomputer centers could get, but has over the years matured to be an enterprise-class parallel file system supporting mission-critical workloads. Unfortunately, in spite of Lustre having become extremely attractive to enterprises and adopted by IT departments, some naysayers continue toclaim that Lustre is still just a scratch file system. We in the Lustre community see quite a different picture.The post Lustre and Persistent Storage appeared first on insideHPC.

"This presentation will describe how OpenMP is used at NERSC. NERSC is the primary supercomputing facility for Office of Science in the US Depart of Energy (DOE). Our next production system will be an Intel Xeon Phi Knights Landing (KNL) system, with 60+ cores per node and 4 hardware threads per core. The recommended programming model is hybrid MPI/OpenMP, which also promotes portability across different system architectures."The post Video: Using OpenMP at NERSC appeared first on insideHPC.

Alexandre Caldeira from IBM writes that CentOS is now available for the POWER8 platform. This is a big step for the OpenPOWER community, as the business world uses Red Hat Enterprise Linux (RHEL) and its twin CentOS for their servers.The post CentOS Comes to POWER8 Platforms appeared first on insideHPC.

The High Performance Conjugate Gradients (HPCG) benchmark continues to gain traction in the high-performance computing community. “HPCG is designed to complement the traditional High Performance Linpack (HPL) benchmark used as the official metric for ranking the top 500 systems,” said Sandia National Laboratories researcher Mike Heroux, who developed the HPCG program in collaboration with Jack Dongarra and Piotr Luszczek from the University of Tennessee.The post HPCG Benchmark Gains Traction for Ranking Supercomputers appeared first on insideHPC.

Harvey Newman from CalTech presented this talk at the Mellanox booth at SC15. "We describe activities of the Caltech High Energy Physics team and collaborators, related to the use Software Defined Networking to help achieve fast and efficient data distribution and access. Results from Supercomputing 2014 are presented together with our work on the Advanced Network Services for the Experiments project, and a new project developing a Next Generation Integrated SDN Architecture, as well as our plans for Supercomputing 2015."The post Next Generation SDN Driven Systems for Exascale Data Intensive Science appeared first on insideHPC.

"Over the last several years, an enormous amount of development effort has gone into Lustre to address users’ enterprise-related requests. Their work is not only keeping Lustre extremely fast (the Spider II storage system at the Oak Ridge Leadership Computing Facility (OLCF) that supports OLCF’s Titan supercomputer delivers 1 TB/s ; and Data Oasis, supporting the Comet supercomputer at the San Diego Supercomputing Center (SDSC) supports thousands of users with 300GB/s throughput) but also making it an enterprise-class parallel file system that has since been deployed for many mission-critical applications, such as seismic processing and analysis, regional climate and weather modeling, and banking."The post Lustre: This is Not Your Grandmother’s (or Grandfather’s) Parallel File System appeared first on insideHPC.