High-Performance Computing News Analysis | insideHPC

"We wanted to get away from the complexity of POSIX for data, yet retain the parts of POSIX that people are used to (metadata manipulation). By divorcing ourselves from the complications of ensuring a completely POSIX data flow, we can massively simplify the data movement and storage mechanisms. MarFS lets us retain the parts of POSIX that users appreciate for data management (chown, chmod, rename, mv, etc) without inheriting the complexity of managing POSIX semantics for data manipulation. By treating the data as essentially immutable, we can leverage the very simple PUT/GET/DELETE semantics of “cloudy” data storage systems to scale out storage with ease."The post Interview: Moving Beyond POSIX with the new MarFS Object Storage Project appeared first on insideHPC.

In this video from the 2016 OpenFabrics Workshop, James Wright from Intel presents: Intel Omni-Path Fabric Management and Tools Features. "The Intel Omni-Path Fabric includes a number of hardware and software features to make fabric monitoring, management and diagnosis easier. This session will provide a brief overview of the management software architecture and key features."The post Video: Intel Omni-Path Fabric Management and Tool Features appeared first on insideHPC.

Berkeley Lab recently hosted the fourth annual X-Stack PI event, where X-Stack researchers, facilities teams, application scientists, and developers from national labs, universities, and industry met to share the latest developments in X-Stack application codes. "X-Stack was launched in 2012 by the U.S. Department of Energy’s Advanced Scientific Computing Research program to support the development of exascale software tools, including programming languages and libraries, compilers and runtime systems, that will help programmers handle massive parallelism, data movement, heterogeneity and failures as the scientific community transitions to the next generation of extreme-scale supercomputers."The post X-Stack PI Meeting Showcases Exascale Code appeared first on insideHPC.

In news from China this week, the Huazhong University of Science has won the ASC16 Student Cluster Challenge. The final round of the competition concluded Friday in Wuhan at the Central China University of Science.The post Huazhong University of Science Wins ASC16 Student Cluster Challenge appeared first on insideHPC.

Zach Smocha from Rescale presented this talk at the HPC User Forum. "Manor Racing is partnering with San Francisco based Rescale as a key technology provider for its 2016 FIA Formula 1 World Championship challenge. Manor Racing will use Rescale’s cloud high performance computing (HPC) platform to enable trackside simulation on a whole new scale for the team. Working in tandem with Manor Racing’s existing race strategy simulation software, the Rescale cloud HPC platform will enable its engineers to evaluate thousands of simulations and strategies, placing the team to be at the cutting edge of innovative decision making during a Grand Prix weekend. The whole process is executed from a laptop web browser by Rescale’s massively scalable cloud infrastructure and computer environment."The post Performing Simulation-Based, Real-time Decision Making with Cloud HPC appeared first on insideHPC.

Today Mellanox announced that University of Cambridge has selected Mellanox End-to-End Ethernet interconnect solution including Spectrum SN2700 Ethernet switches, ConnectX-4 Lx NICs and LinkX cables for its OpenStack-based scientific research cloud. This new win has expanded Mellanox’s existing footprint of InfiniBand solution and empowers the UoC to realize its vision of HPC and Cloud convergence through high-speed cloud networks at 25/50/100Gb/s throughput.The post Mellanox Powers OpenStack Cloud at University of Cambridge appeared first on insideHPC.

The good folks at the European Network on High Performance and Embedded Architecture and Compilation (HiPEAC) have launched a call for contributions to the 2017 edition of the HiPEAC Vision, which will set out the way forward for computing systems over the next ten years. "Published every two years, HiPEAC’s definitive roadmap provides guidance for policy makers and technologists on key issues in the area of computing systems, such as security, reliability and energy efficiency."The post HiPEAC Seeks Your Input for the Next Ten Years of Computing appeared first on insideHPC.

In this video, Chris Dagdigian from Bioteam delivers his annual assessment of the best, the worthwhile, and the most overhyped information technologies for life sciences at the 2016 Bio-IT World Conference & Expo in Boston. "The presentation tries to recap the prior year by discussing what has changed (or not) around infrastructure, storage, computing, and networks. This presentation will help scientists, leadership and IT professionals understand the basic topics involved in supporting data intensive science."The post Video: HPC Trends from the Trenches at Bio-IT World appeared first on insideHPC.

In this video from the HPC User Forum in Tucson, Gary Paek from Intel presents: Intel's Machine Learning Strategy. "Earlier this week, Intel announced the inception of the Intel Data Analytics Acceleration Library (Intel DAAL) open source project. Intel DAAL helps to speed up big data analysis by providing highly optimized algorithmic building blocks for all stages of data analytics (preprocessing, transformation, analysis, modeling, validation, and decision making) in batch, online, and distributed processing modes of computation."The post Video: Intel’s Machine Learning Strategy appeared first on insideHPC.

Mellanox is seeking an HPC Application Performance Engineer in our Job of the Week. "Mellanox Technologies is looking for a talented engineer to lead datacenter application performance optimization and benchmarking over Mellanox networking products. This individual will primarily work with marketing and engineering to execute low-level and application level benchmarks focused on High Performance Computing (HPC) open source and ISV applications in addition to providing software and hardware optimization recommendations. In addition, this individual will work closely with hardware and software partners, and customers to benchmark Mellanox products under different system configurations and workloads."The post Job of the Week: HPC Application Performance Engineer at Mellanox appeared first on insideHPC.

Today the University of Iceland unveiled a new supercomputer that will boost research in a range of scientific areas. Manufactured by Lenovo, the cluster was funded by the Research Infrastructure Fund Iceland with matching funds from the University of Iceland, Reykjavik University.The post University of Iceland Unveils Lenovo Supercomputer appeared first on insideHPC.

Over at the Dell HPC Community Blog, Ashish Kumar Singh, Mayura Deshmukh and Neha Kashyap discuss the performance characterization of Intel Broadwell processors with High Performance LINPACK (HPL) and STREAM benchmarks. "The performance of all Broadwell processor used for this study is higher for both HPL and STREAM benchmarks. "There is ~12% increase in measured memory bandwidth for Broadwell processors compared to Haswell processors. Broadwell processors measure better power efficiencies than the Haswell processors. In conclusion, Broadwell processors may fulfill the demands of more compute power for HPC applications."The post HPC Benchmarking Results for Intel Broadwell Processors appeared first on insideHPC.

Leo Reiter from Nimbix presented this deck at the HPC User Forum. “Nimbix is a pure high performance computing cloud built for volume, speed and simplicity. We give people the tools and the processing power to solve their biggest, toughest problems. We give you the freedom to imagine new possibilities, to test the limits of reality, and to model the future. For most workloads, Nimbix is far less expensive than building, running and maintaining your own supercomputer. It’s also more efficient at spinning up, executing, completing the job and delivering your results — which saves you time and money. And our user-friendly platform means you invest less in development and infrastructure.”The post Video: Cloud for the “Missing Middle” appeared first on insideHPC.

The Board of Directors of the OpenMP Architecture Review Board (ARB) is pleased to announce the appointment of Dr. Michael Klemm as the new CEO of the OpenMP organization, a group of vendors and research organizations creating the standard for one of the most popular shared-memory and embedded parallel programming models in use today. Dr. Klemm succeeds Mr. Michael Wong, who served as the OpenMP CEO for almost 5 years.The post Michael Klemm Appointed CEO of OpenMP ARB appeared first on insideHPC.

In this video from the 2016 GPU Technology Conference, Greg Schmidt from Hewlett Packard Enterprise describes the new Apollo 6500 server. "With up to eight high performance NVIDIA GPU cards designed for maximum transfer bandwidth, the HPE Apollo 6500 System is purpose-built for deep learning applications. Its high ratio of GPUs to CPUs, dense 4U form factor and efficient design enable organizations to run deep learning recommendation algorithms faster and more efficiently, significantly reducing model training time and accelerating the delivery of real-time results, all while controlling costs."The post Hewlett Packard Enterprise Packs 8 GPUs into Apollo 6500 Server appeared first on insideHPC.

The Ohio Supercomputer Center has named its newest HPC cluster after Olympic champion Jesse Owens. The new Owens Cluster will be powered by Dell PowerEdge servers featuring the new Intel Xeon processor E5-2600 v4 product family, include storage components manufactured by DDN, and utilize interconnects provided by Mellanox. "Our newest supercomputer system is the most powerful that the Center has ever run,” ODHE Chancellor John Carey said in a recent letter to Owens’ daughters. “As such, I thought it fitting to name it for your father, who symbolizes speed, integrity and, most significantly for me, compassion as embodied by his tireless work to help youths overcome obstacles to their future success. As a first-generation college graduate, I can relate personally to the value of mentors in the lives of those students.”The post Ohio Supercomputer Center Names New Cluster after Jesse Owens appeared first on insideHPC.

This week, the European Commission presented a vision for the European Science Cloud that will bring together current and future data infrastructures. The European Open Science Cloud will be created for European researchers and their global scientific collaborators by integrating and consolidating e-infrastructure platforms, federating existing scientific clouds and research infrastructures, and supporting the development of cloud-based services.The post e-IRG Roadmap to Help Shape European Open Science Cloud appeared first on insideHPC.

In this video from the 2016 GPU Technology Conference, Rich Friedrich from Hewlett Packard Enterprise describes how the company makes it easier for Data Scientists to program GPUs. "In April, HPE announced a public, open-source version of the platform called the Cognitive Computing Toolkit. Instead of relying on the traditional CPUs that power most computers, the Toolkit runs on graphics processing units (GPUs), inexpensive chips designed for video game applications."The post How HPE Makes GPUs Easier to Program for Data Scientists appeared first on insideHPC.

Today Cray announced that its Board of Directors has appointed Brian V. Turner as a member of the Board and as a member of its Audit and Compensation Committees, effective April 18, 2016.The post Brian V. Turner Joins Cray’s Board appeared first on insideHPC.

In this special guest feature from Scientific Computing World, ISC's Nages Sieslack highlights a convergence of technologies around HPC, a focus of the ISC High Performance conference, which takes place June 19-23 in Frankfurt. "In addition to the theme of convergent HPC technologies, this year’s conference will also offer two days of sessions in the industry track, specially designed to meet the interests of commercial users. Our focus is Industrie 4.0, a German strategic initiative conceived to take a leading role in pioneering industrial IT, which is currently revolutionizing engineering in the manufacturing sector."The post Why the HPC Industry will Converge on Europe at ISC 2016 appeared first on insideHPC.

Peter Jones from Intel presented this talk at LUG 2016 in Portland. "The OpenSFS Lustre Working Group (LWG) is the place the where the participants of OpenSFS come together to coordinate their software development efforts for the Lustre high-performance, Open Source, parallel filesystem. This includes planning and the roadmap for community releases of Lustre."The post Video: Lustre Community Release Update appeared first on insideHPC.

"As clock speeds for CPU’s have not been increasing as compared to a decade ago, chip designers have been enhancing the performance of both CPUs, such as the Intel Xeon and the Intel Xeon Phi coprocessor by adding more cores. New designs allow for applications to perform more work in parallel, reducing the overall time to perform a simulation, for example. However, to get this increase in performance, applications must be designed or re-worked to take advantage of these new designs which can include hundreds to thousands of cores in a single computer system."The post Why Parallelism? appeared first on insideHPC.

In this video from the 2016 OpenFabrics Workshop, Zili Zheng from LBNL presents: UPC++. "UPC++ is a parallel programming extension for developing C++ applications with the partitioned global address space (PGAS) model. UPC++ has demonstrated excellent performance and scalability with applications and benchmarks such as global seismic tomography, Hartree-Fock, BoxLib AMR framework and more. In this talk, we will give an overview of UPC++ and discuss the opportunities and challenges of leveraging modern network features."The post Video: UPC++ Parallel Programming Extension appeared first on insideHPC.

In this RCE Podcast, Marcel Kornacker from Cloudera describes the Impala project. Impala brings scalable parallel database technology to Hadoop, enabling users to issue low-latency SQL queries to data stored in HDFS and Apache HBase without requiring data movement or transformation. Impala is integrated with Hadoop to use the same file and data formats, metadata, security and resource management frameworks used by MapReduce, Apache Hive, Apache Pig and other Hadoop software.The post RCE Podcast Looks at the Impala Project appeared first on insideHPC.

The New York Scientific Data Summit (NYSDS) has issued its Call for Papers. The event takes place August 14-17 in New York City.The post Call for Papers: New York Scientific Data Summit appeared first on insideHPC.

Today DDN announced a year of unprecedented growth in the usage of its advanced WOS object storage platform. In less than a year, use of the company’s object storage solutions have grown by more than 150 percent to 500+ billion objects in production. Fast-paced growth and strong demand for scale-out storage clouds have propelled DDN’s WOS to one of the industry’s top solutions based on the number of objects in production and have fortified DDN’s position as a strong market leader in object storage.The post WOS Object Storage Increases Momentum at DDN appeared first on insideHPC.

Gregory Stoner from AMD presented this talk at the HPC User Forum. "With the announcement of the Boltzmann Initiative and the recent releases of ROCK and ROCR, AMD has ushered in a new era of Heterogeneous Computing. The Boltzmann initiative exposes cutting edge compute capabilities and features on targeted AMD/ATI Radeon discrete GPUs through an open source software stack. The Boltzmann stack is comprised of several components based on open standards, but extended so important hardware capabilities are not hidden by the implementation."The post Video: AMD ROC – Radeon Open Compute Platform appeared first on insideHPC.

The 2016 Hot Interconnects Conference has issued its Call for Papers. The event takes place August 24-26 at Huawei in Santa Clara, California. "Hot Interconnects is the premier international forum for researchers and developers of state-of-the-art hardware and software architectures and implementations for interconnection networks of all scales, ranging from multi-core on-chip interconnects to those within systems, clusters, datacenters and Clouds."The post Call for Papers: 2016 Hot Interconnects Conference appeared first on insideHPC.

Today Spectra Logic announced the Spectra TFinity ExaScale Edition, the world’s largest and most richly-featured tape storage system. "Since 2008, Spectra Logic has worked with engineers in the NASA Advanced Supercomputing (NAS) Division at NASA’s Ames Research Center, in California’s Silicon Valley, first deploying a Spectra tape library with 22 petabytes of capacity. According to NASA, the Spectra tape library’s capacity has grown to approximately one half an Exabyte of archival storage today. After extensive testing over the past year, NASA recently deployed a Spectra TFinity ExaScale Edition in their 24x7 production HPC environment."The post Spectra Logic Rolls Out World’s Largest Capacity Tape Library appeared first on insideHPC.

Today Intel announced the inception of the Intel Data Analytics Acceleration Library (Intel DAAL) open source project. "Intel DAAL helps to speed up big data analysis by providing highly optimized algorithmic building blocks for all stages of data analytics (preprocessing, transformation, analysis, modeling, validation, and decision making) in batch, online, and distributed processing modes of computation. The open source project is licensed under Apache License 2.0."The post Intel DAAL Data Analytics Acceleration Library Moves to Open Source appeared first on insideHPC.

Today Altair announced that eleven international customers participated in the company's recent HPC Cloud Challenge. The contest was set up to demonstrate the benefits of leveraging the cloud for large-scale design exploration in the area of computer-aided engineering. Organizations of all sizes from manufacturing and academic fields participated in the Challenge, utilizing Altair technologies in structural, CFD and design studies, and expressed great satisfaction with the program overall.The post Altair HPC Cloud Challenge Shows Customers a New Way Forward appeared first on insideHPC.

The Extreme Science and Engineering Discovery Environment (XSEDE), a five-year project supported by the US National Science Foundation, has awarded 324 million cpu hours, valued at $16.2 million, to 150 research projects throughout the US.The post XSEDE Awards 324 Million CPU hours to NSF Research Projects appeared first on insideHPC.

Michael Resch from HLRS gave this rousing talk at the HPC User Forum. "HLRS supports national and European researchers from science and industry by providing high-performance computing platforms and technologies, services and support. Supercomputer Hazel Hen, a Cray XC40-system, is at the heart of the HPC system infrastructure of the HLRS. With a peak performance of 7.42 Petaflops (quadrillion floating point operations per second), Hazel Hen is one of the most powerful HPC systems in the world (position 8 of TOP500, 11/2015) and is the fastest supercomputer in the European Union. The HLRS supercomputer, which was taken into operation in October 2015, is based on the Intel Haswell Processor and the Cray Aries network and is designed for sustained application performance and high scalability."The post Video: Europe’s Fastest Supercomputer and the World Around It appeared first on insideHPC.

In this slidecast, Gilad Shainer from Mellanox describes the advantages of InfiniBand and the company's off-loading network architecture for HPC. “The path to Exascale computing is clearly paved with Co-Design architecture. By using a Co-Design approach, the network infrastructure becomes more intelligent, which reduces the overhead on the CPU and streamlines the process of passing data throughout the network. A smart network is the only way that HPC data centers can deal with the massive demands to scale, to deliver constant performance improvements, and to handle exponential data growth.”The post Slidecast: Advantages of Offloading Architectures for HPC appeared first on insideHPC.

Rangan Sukumar from ORNL presented this talk at the HPC User Forum in Tucson. "ORiGAMI is a tool for discovering and evaluating potentially interesting associations and creating novel hypothesis in medicine. ORiGAMI will help you “connect the dots” across 70 million knowledge nuggets published in 23 million papers in the medical literature. The tool works on a ‘Knowledge Graph’ derived from SEMANTIC MEDLINE published by the National Library of Medicine integrated with scalable software that enables term-based, path-based, meta-pattern and analogy-based reasoning principles."The post ORiGAMI – Oak Ridge Graph Analytics for Medical Innovation appeared first on insideHPC.

Today Intersect360 Research published a new research report on the Hyperscale market. "This report provides definitions, segmentations, and dynamics of the hyperscale market and describes its scope, the end-user applications it touches, and the market drivers and dampers for future growth. It is the foundational report for the Intersect360 Research hyperscale market advisory service."The post Intersect360 Publishes New Report on the Hyperscale Market appeared first on insideHPC.

Matt Vaughan from TACC presented this talk at the HPC User Forum. "Jetstream is the first user-friendly, scalable cloud environment for XSEDE. The system enables researchers working at the "long tail of science" and the creation of truly customized virtual machines and computing architectures. It has a web-based user interface integrated with XSEDE via Globus Auth. The architecture is derived from the team's collective experience with CyVerse Atmosphere, Chameleon and Quarry. The system also fosters reproducible, sharable computing with geographically isolated clouds located at Indiana University and TACC."The post Jetstream – Adding Cloud-based Computing to the National Cyberinfrastructure appeared first on insideHPC.

The NVIDIA DGX-1 features up to 170 teraflops of half precision (FP16) peak performance, 8 Tesla P100 GPU accelerators with 16GB of memory per GPU, 7TB SSD DL Cache, and a NVLink Hybrid Cube Mesh. Packaged with fully integrated hardware and easily deployed software, it is the world’s first system built specifically for deep learning and with NVIDIA's revolutionary, Pascal-powered Tesla P100 accelerators, interconnected with NVIDIA's NVLink. NVIDIA designed the DGX-1 to meet the never-ending computing demands of artificial intelligence and claims it can provide the throughput of 250 CPU-based servers delivered via a single box.The post Exxact to Distribute NVIDIA DGX-1 Deep Learning System appeared first on insideHPC.

In today's highly competitive world, High Performance Computing (HPC) is a game changer. Though not as splashy as many other computing trends, the HPC market has continued to show steady growth and success over the last several decades. Market forecaster IDC expects the overall HPC market to hit $31 billion by 2019 while riding an 8.3% CAGR. The HPC market cuts across many sectors including academic, government, and industry. Learn which industries are using HPC and why.The post Who Is Using HPC (and Why)? appeared first on insideHPC.

In this video, Siraj Rival from Twilio presents a quick tutorial on How to Build a Neural Net in 4 Minutes. Siraj describes himself as the Bill Nye of Computer Science.The post Video: How to Build a Neural Net in 4 Minutes appeared first on insideHPC.

The hpc-ch Forum on Intra- and Inter-Site Networking has posted its Call for Participation. Hosted by the University of Zurich, the event will take place Thursday, May 19, 2016.The post Call for Participation: hpc-ch Forum on Intra- and Inter-Site Networking appeared first on insideHPC.

"Over the last years the OFA community has shown the potential of using high performance networks (InfiniBand) to boost the performance of virtualized cloud environments, however, the network reconfiguration challenges still continue to exist. In this session we present the work we have been doing on InfiniBand subnet management and routing, in the context of dynamic cloud environments. This work includes, but not limited to, techniques in order to provide better management scalability when virtual machines are live migrating, tenant network isolation in multi-tenant environments, and fast performance-driven network reconfiguration."The post Using High Performance Interconnects in Dynamic Environments appeared first on insideHPC.

"This talk will present RDMA-based designs using OpenFabrics Verbs and heterogeneous storage architectures to accelerate multiple components of Hadoop (HDFS, MapReduce, RPC, and HBase), Spark and Memcached. An overview of the associated RDMAenabled software libraries being designed and publicly distributed as a part of the HiBD project."The post Video: Exploiting HPC Technologies to Accelerate Big Data Processing appeared first on insideHPC.

Hadoop and Spark clusters have a reputation for being extremely difficult to configure, install, and tune, but help is on the way. The good folks at Cluster Monkey are hosting a crash course entitled Apache Hadoop with Spark in One Day. "After completing the workshop attendees will be able to use and navigate a production Hadoop cluster and develop their own projects by building on the workshop examples."The post Learn Apache Hadoop with Spark in One Day appeared first on insideHPC.

Today Silicon Mechanics announced that the company was recently named one of the Intel Corporation’s 2015 ISS Partner’s of the Year, specifically with Intel’s Channel Cares program. TheISS Partner of the Year award is given out each year at the company’s Intel Solutions Summit to 16 different partners across 16 different categories ranging from retail to security to healthcare, cloud solutions and more. This is the first time that Silicon Mechanics has appeared on the prestigious list.The post Silicon Mechanics is Intel’s ‘Channel Cares’ Partner of the Year appeared first on insideHPC.

Today ISC 2016 announced that five renowned experts in computational science will participate in their new Distinguished Speaker series. Topics will include exascale computing efforts in the US, the next supercomputers in development in Japan and China, cognitive computing advancements at IBM, and quantum computing research at NASA.The post Distinguished Speaker Series Coming to ISC 2016 appeared first on insideHPC.

"At Verne Global we combine low power costs, free cooling for 365 days of the year and optimized infrastructure to reduce the total costs of ownership for your data center. Our customers have achieved savings of more than 80% on power alone. The only place in the world where your data center can operate with 100% sustainable green power is at Verne Global's Icelandic campus. Powered by geothermal and hydro-electric sources, your IT power costs will be stable and predictable for up to 20 years."The post How Verne Global is Moving HPC Workloads to Iceland appeared first on insideHPC.

"NWPerf is software that can measure and collect a wide range of performance data about an application or set of applications that run on a cluster. With minimal impact on performance, NWPerf can gather historical information that then can be used in a visualization package. The data collected includes the power consumption using the Intelligent Platform Management Interface (IPMI) for the Intel Xeon processor and the libmicmgmt API for the Intel Xeon Phi coprocessor. Once the data is collected, and using some data extraction mechanisms, it is possible to examine the power used across the cluster, while the application is running."The post Monitoring Power Consumption with the Intelligent Platform Management Interface appeared first on insideHPC.

In this video, Steve Hebert from Nimbix presents: The Internet of Machines. "The good folks at Nimbix have also posted full a set video presentations from their recent Developer Summit. The event brought together the best and brightest minds building the next generation of cloud computing applications. The invigorating discussions span topics from rendering and simulation to big data and machine learning, and everything in between."The post Video: The Internet of Machines appeared first on insideHPC.