High-Performance Computing News Analysis | insideHPC

"Buffered read performance under Lustre has been inexplicably slow when compared to writes or even direct IO reads. A balanced FDR-based Object Storage Server can easily saturate the network or backend disk storage using o_direct based IO. However, buffered IO reads remain at 80% of write bandwidth. In this presentation we will characterize the problem, discuss how it was debugged and proposed resolution. The format will be a presentation followed by Q&A."The post Debugging Slow Buffered Reads on the Lustre File System appeared first on insideHPC.

The discovery of gravitational waves, announced by an international team of scientists, including Cardiff University’s Gravitational Physics Group, was verified using simulations of black-hole collisions produced on a Bull supercomputer. The discovery is being considered one of the biggest breakthroughs in physics for the last 100 years, as these tiny ripples in space-time offer new insights into theoretical physics and provide scientists with new avenues to explore the universe.The post Bull Supercomputer Aids Discovery of Gravitational Waves appeared first on insideHPC.

Today Nvidia announced that Rob High, IBM Fellow, VP and chief technology officer for Watson, will deliver a keynote at our GPU Technology Conference on April 6. High will describe the key role GPUs will play in creating systems that understand data in human-like ways. "Late last year, IBM announced that its Watson cognitive computing platform has added NVIDIA Tesla K80 GPU accelerators. As part of the platform, GPUs enhance Watson’s natural language processing capabilities and other key applications."The post IBM Watson CTO Rob High to Keynote GPU Technology Conference appeared first on insideHPC.

"Vector instruction sets have progressed over time, and it important to use the most appropriate vector instruction set when running on specific hardware. The OpenMP SIMD directive allows the developer to explicitly tell the compiler to vectorize a loop. In this case, human intervention will override the compilers sense of dependencies, but that is OK if the developer knows their application well."The post OpenMP and SIMD Instructions on Intel Xeon Phi appeared first on insideHPC.

In this week’s Sponsored Post, Katie Garrison of One Stop Systems explains how Flash storage arrays are becoming more accessible as the economics of Flash becomes more attractive. "Comprised of a unique combination of a Haswell-based engine and 200TB Flash arrays, the FSA-SAN can be increased to a petabyte of storage with additional Flash arrays. Each 200TB array delivers 16 million IOPS, making it the ideal platform for high-speed data recording and processing with lightning fast data response time, high-availability and flexibility in the cloud."The post Flash Storage Arrays in HPC Applications appeared first on insideHPC.

In this slidecast, Jeff Squyres from Cisco Systems presents: How to make MPI Awesome - MPI Sessions. As a proposal for future versions of the MPI Standard, MPI Sessions could become a powerful tool tool to improve system resiliency as we move towards exascale. "Now that we have brought these ideas to a larger audience, my hope is that we (the Forum) start refining these ideas to fit them into a future release of the MPI standard. Meaning: please don’t assume that exactly what is proposed in these slides are going to make it into the MPI standard."The post Slidecast: How to Make MPI Awesome – MPI Sessions appeared first on insideHPC.

In this special guest feature, John Kirkley writes that Argonne is already building code for their future Theta and Aurora supercomputers based on Intel Knights Landing. "One of the ALCF’s primary tasks is to help prepare key applications for two advanced supercomputers. One is the 8.5-petaflops Theta system based on the upcoming Intel® Xeon Phi™ processor, code-named Knights Landing (KNL) and due for deployment this year. The other is a larger 180-petaflops Aurora supercomputer scheduled for 2018 using Intel Xeon Phi processors, code-named Knights Hill. A key goal is to solidify libraries and other essential elements, such as compilers and debuggers that support the systems’ current and future production applications."The post Paving the Way for Theta and Aurora appeared first on insideHPC.

Rich Graham presented this talk at the Stanford HPC Conference. "Exascale levels of computing pose many system- and application- level computational challenges. Mellanox Technologies, Inc. as a provider of end-to-end communication services is progressing the foundation of the InfiniBand architecture to meet the exascale challenges. This presentation will focus on recent technology improvements which significantly improve InfiniBand’s scalability, performance, and ease of use."The post Rich Graham Presents: The Exascale Architecture appeared first on insideHPC.

"Lenovo is on a mission to become the market leader in datacenter solutions," said Gerry Smith, Lenovo executive vice president and chief operating officer, PC and Enterprise Business Group. "We will continue to invest in the development and delivery of disruptive IT solutions to shape next-generation data centers. Our partnership with Juniper Networks provides Lenovo access to an industry leading portfolio of products that include Software Defined Networking (SDN) solutions – essential for state-of-the-art data center offerings.”The post Lenovo and Juniper Networks Partner for Next-gen Datacenter Infrastructure appeared first on insideHPC.

Cloud computing has become a strong alternative to in house data centers for a large percentage of all enterprise needs. Most enterprises are adopting some form of could computing, with some estimates that as high as 90 % are putting workloads into a public cloud infrastructure. The whitepaper, Empowering Cloud Utilization with Cloud Bursting is an excellent summary of various options for enterprises that are planning for using a public cloud infrastructure.The post Empowering Cloud Utilization with Cloud Bursting appeared first on insideHPC.

Today IBM that it is opening a new Cloud Data Center in Johannesburg, South Africa. The new cloud center is the result of a close collaboration with Gijima and Vodacom and is designed to support cloud adoption and customer demand across the continent. IBM will provide clients with a complete portfolio of cloud services for running enterprise and as a service workloads.The post IBM Opens First Cloud Datacenter in South Africa appeared first on insideHPC.

"UberCloud specializes in running HPC workloads on a broad spectrum of infrastructures, anywhere from national centers to public Cloud services. This session will be review of the learnings of UberCloud Experiments performed by industry end users. The live demonstration will cover how to achieve peak simulation performance and usability in the Cloud and national centers, using fast interconnects, new generation CPU's, SSD drives and UberCloud technology based on Linux containers."The post Video: Ubercloud Workloads & Marketplace appeared first on insideHPC.

Today Seagate unveiled a production-ready unit of the fastest single solid-state drive (SSD) demonstrated to date, with throughput performance of 10 gigabytes per second. The early unit meets Open Compute Project (OCP) specifications, making it ideal for hyperscale data centers looking to adopt the fastest flash technology with the latest and most sustainable standards. "The 10GB/s unit, which is expected to be released this summer, is more than 4GB/s faster than the previous fastest-industry SSD on the market. It also meets the OCP storage specifications being driven by Facebook, which will help reduce the power and cost burdens traditionally associated with operating at this level of performance."The post Seagate Demonstrates 10 GB/sec SSD Flash Drive for OCP appeared first on insideHPC.

Registration now open for ISC High Performance, the largest high performance computing forum in Europe. By registering between now and May 11, attendees can save over 45 percent off the onsite registration rates. Now in its 31st year, the ISC High Performance conference and exhibition will be held from June 19 - 23 in Frankfurt.The post Registration Opens for ISC 2016 appeared first on insideHPC.

The 2016 OpenFabrics Workshop has posted their speaker agenda with session abstracts. The event takes place April 4-8, 2016 in Monterey, California. "The Workshop is the premier event for collaboration between OpenFabrics Software (OFS) producers and those whose systems and applications depend on the technology. Every year, the workshop generates lively exchanges among Alliance members, developers and users who all share a vested interest in high performance networks."The post Agenda Posted for OpenFabrics Workshop in Monterey appeared first on insideHPC.

Today Advanced Clustering Technologies announced it has partnered with CD-adapco to offer the company’s industry-leading engineering simulation software solution, STAR-CCM+, to customers using Advanced Clustering’s on demand HPC cluster in the cloud, ACTnowHPC. "We’re pleased to announce that our HPC cloud now makes STAR-CCM+ immediately accessible to engineers who purchase the license from CD-adapco,” said Kyle Sheumaker, President of Advanced Clustering Technologies. “With STAR-CCM+, we’re making it easier than ever for our customers to enhance workflow productivity in order to discover better designs faster.”The post STAR-CCM+ Moves to the Cloud with ACTnowHPC appeared first on insideHPC.

"Rescale provides a unified HPC simulation platform for the Enterprise IT environment. Rescale’s platform integrates with existing job schedulers to burst workloads to cloud computing resources. We provide high performance computing options such as InfiniBand-connected and GPU-accelerated nodes that can be provisioned on-demand. We will demo an example workload on such an on-demand cluster. Finally, we will cover the Rescale administration panel for managing your cloud/on-premise connectivity for software licenses and single sign-on authentication."The post Video: Boosting HPC with Cloud appeared first on insideHPC.

At the Open Compute Project Summit this week, ASRock Rack will showcase its OCP3-1L and OCP3-6S servers for cloud-based datacenter and High Performance Computing. The event is the annual gathering for industry’s top leaders to discuss the new developments of OCP technology - an open design for datacenter products initiated by Facebook.The post ASRock Rack Joins Open Compute Project U.S. Summit 2016 appeared first on insideHPC.

Today Mellanox unveiled its next-generation Open Composable Networks (OCN) platform at the Open Compute Project (OCP) Summit. OCN delivers ground-breaking open network platforms for enterprises and service providers to unlock performance and unleash innovation with predictable application performance and the efficiency of Web-Scale IT.The post Mellanox Introduces Open Composable Networks for OCP Platforms appeared first on insideHPC.

Today E4 Computer Engineering announced that it has recently sealed an agreement with BOXX Technologies to become their exclusive manufacturing and distribution partner for Italy and Switzerland. As one of the world’s leading performance computing brands, BOXX Technologies manufactures bespoke high performance workstations for a range of industries and boasts a blue chip client list including Boeing, Disney, MIT, NASA, and Nike.The post E4 Computer Engineering to Distribute BOXX Technologies in Italy and Switzerland appeared first on insideHPC.

"Today’s server systems provide many knobs which influence energy efficiency and performance. Some of these knobs control the behavior of the operating systems, whereas others control the behavior of the hardware itself. Choosing the optimal configuration of the knobs is critical for energy efficiency. In this talk recent research results will be presented, including examples of big data applications that consume less energy when dynamic tuning is employed."The post Best Practices – Dynamic Tuning for Energy Efficiency appeared first on insideHPC.

Today SGI announced that ŠKODA AUTO has deployed an SGI UV and two SGI ICE high performance computing systems to further enhance its computer-aided engineering capabilities. "Customer satisfaction and the highest standard of production are at the very core of our brand and is the driving force behind our innovation processes," said Petr Rešl, head of IT Services, ŠKODA AUTO. "This latest installation enables us to conduct complex product performance and safety analysis that will in turn help us to further our commitment to our customer's welfare and ownership experience. It helps us develop more innovative vehicles at an excellent value-to-price ratio."The post Trio of SGI Systems to Drive Innovation at SKODA AUTO appeared first on insideHPC.

In this video from the 2016 Stanford HPC Conference, Sumit Sanyal from Minds.ai presents: Deep Learning: Convergence of HPC & Hyperscale. "Minds.ai an early stage startup building software and hardware infrastructure to deploy, manage and accelerate Deep Learning Networks. minds.ai (maɪndz-aɪ) is developing a deep neural network training platform with disruptive acceleration performance. minds.ai’s platform makes the power of High Performance Computing available to the deep learning community and equips a new generation of developers with the tools needed to quickly refine and deploy neural networks into their businesses."The post Accelerating Deep Learning with HPC appeared first on insideHPC.

Stony Brook University is seeking a Senior HPC Engineer in our Job of the Week. "The Senior HPC Engineer will be responsible for day-to-day oversight, integration, administration & maintenance of the HPC Clusters. The selected candidate will participate in hardware decisions, prepare training materials and assisting advanced users."The post Job of the Week: Senior HPC Engineer at Stony Brook University appeared first on insideHPC.

In this podcast, the Radio Free HPC team looks at Dell's acquisition of EMC, which is expected to close soon pending regulatory approval. "The transaction combines two of the world’s greatest technology franchises—with leadership positions in Servers, Storage, Virtualization and PCs—and brings together strong capabilities in the fastest growing areas of our industry, including Digital Transformation, Software Defined Data Center, Hybrid Cloud, Converged Infrastructure, Mobile and Security."The post Radio Free HPC Looks at Dell’s Imminent Acquisition of EMC appeared first on insideHPC.

"Co-Design is a collaborative effort among industry thought leaders, academia, and manufacturers to reach Exascale performance by taking a holistic system-level approach to fundamental performance improvements. Co-Design architecture enables all active system devices to become acceleration devices by orchestrating a more effective mapping of communication between devices in the system. This produces a well-balanced architecture across the various compute elements, networking, and data storage infrastructures that exploits system efficiency and even reduces power consumption."The post Interview: Why Co-design is the Path Forward for Exascale Computing appeared first on insideHPC.

Today AMD announced that CGG, a pioneering global geophysical services and equipment company, has deployed AMD FirePro S9150 server GPUs to accelerate its geoscience oil and gas research efforts, harnessing more than 1 PetaFLOPS of GPU processing power. Employing AMD’s HPC GPU Computing software tools available on GPUOpen.com, CGG rapidly converted its in-house Nvidia CUDA code to OpenCL for seismic data processing running on an AMD FirePro S9150 GPU production cluster, enabling fast, cost-effective GPU-powered research.The post With GPUOpen, CGG Fuels Petroleum Exploration using AMD FirePro GPUs appeared first on insideHPC.

In this video from the 2016 Stanford HPC Conference, Gilad Shainer from the HPC Advisory Council moderates a panel discussion on Exascale Computing. "Exascale computing will uniquely provide knowledge leading to transformative advances for our economy, security and society in general. A failure to proceed with appropriate speed risks losing competitiveness in information technology, in our industrial base writ large, and in leading-edge science."The post Video: Panel Discussion on Exascale Computing appeared first on insideHPC.

Ensuring reliability and reproducibility in computational research raises unique challenges in the supercomputing context. Specialized architectures, extensive and customized software, and complex workflows all raise barriers to transparency, while established concepts such as validation, verification, and uncertainty quantification point ways forward. The topic has attracted national attention: President Obama's July 2015 Executive Order, "Creating a National Strategic Computing Initiative," includes accessibility and workflow capture as objectives; an XSEDE14 workshop released a report, "Standing Together for Reproducibility in Large-Scale Computing"; on May 5, 2015, ACM Transactions in Mathematical Software began the Replicated Computational Results Initiative; and this conference is host to a new workshop, "Numerical Reproducibility at Exascale,” to name but a few examples. In this context, I will outline a research agenda to establish reproducibility and reliability as a cornerstone of scientific computing.The post Video: Reproducibility in High Performance Computing appeared first on insideHPC.

Researchers from across University College London are now benefitting from "Grace," a new 181 Teraflop HPC system named in honor of pioneering computer scientist Grace Hopper. Designed and integrated by OCF in the UK, the Grace cluster integrates Lenovo and DDN technology to provide HPC services alongside UCL’s existing HPC machines, Legion and Emerald.The post OCF Deploys 181 Teraflop “Grace” HPC Cluster at University College London appeared first on insideHPC.

"Although commerce and consumers have been computing in the cloud for years, the high-performance computing sector has been more hesitant. But all that may now be changing. The cost of cloud computing for HPC is falling, while new programming models that will allow HPC workloads to run more efficiently in the cloud are becoming available. Public cloud providers are installing hardware configurations that are more suited to HPC, while private clouds are giving users experience of how to run their jobs in a cloud environment."The post HPC Finally Climbing to the Cloud appeared first on insideHPC.

Today Extoll, the German HPC innovation company, announced that is has it has successfully implemented its new GreenICE immersion cooling system at the Jülich Supercomputing Centre. As part of the DEEP Dynamical Exascale Entry Platform project, GreenICE was developed to meet the need for increased compute power, density, and energy efficiency.The post EXTOLL Deploys Immersion Cooled Compute Booster at Jülich appeared first on insideHPC.

"An interesting aspect to prefetching is the distance ahead of the data that is being used to prefetch more data. This is a critical parameter for success and can be defined as how many iterations ahead to issue a prefetch instruction, and can be referred to as the distance. A compiler will automatically determine the distance to prefetch, and can be determined by looking at the compiler optimization reports."The post PreFetch for Intel Xeon Phi – Part 2 appeared first on insideHPC.

"With Docker v1.9 a new networking system was introduced, which allows multi-host networking to work out-of-the-box in any Docker environment. This talk provides an introduction on what Docker networking provides, followed by a demo that spins up a full SLURM cluster across multiple machines. The demo is based on QNIBTerminal, a Consul backed set of Docker Images to spin up a broad set of software stacks."The post Video: Multi-Host Containerized Clusters – Using Docker Networking To Spin-Up SLURM appeared first on insideHPC.

Pioneering a new consulting services model for strategy, marketing, and PR, OrionX today announced the appointment of Dan Olds as partner. Our clients value OrionX’s ability to understand their technology, their competition, and their customers, as they pave the way for digital transformation,” said Shahin Khan, Founding Partner at OrionX. “We are raising the bar with Dan’s extensive knowledge of technology trends and insightful appreciation of customer adoption patterns.”The post OrionX Appoints Big Data & HPC Expert Dan Olds as Partner appeared first on insideHPC.

Mellanox announced today that it has joined the RISC-V foundation as a Founding Platinum Sponsor. The RISC-V foundation promotes the open RISC-V instruction set architecture and associated hardware and software ecosystem for a broad range of computing devices.The post Video: Introduction to RISC-V appeared first on insideHPC.

"Alineos clients are keen to simplify the installation of HPC, big data and OpenStack, and then blend these environments into a single view," said Clemens Engler, Director, Business Development in EMEA at Bright. "Bright is uniquely positioned to service these requirements, so we look forward to some interesting discussions with Alineos’ clients in the coming months.”The post Bright Computing Partners with France-based Alineos appeared first on insideHPC.

Registration opened today for the ISC 2016 conference, which takes place June 19-23 in Frankfurt. This year, the ISC 2016 conference program features an increased focus on Cloud, Machine Learning, and Robotics. In fact, insideHPC has learned that bulk of topics normally covered at the annual ISC Cloud conference have been absorbed into the ISC High Performance industry track. To learn more, we caught up with Wolfgang Gentzsch, a member of the ISC Steering Committee who has chaired the ISC Cloud event since its beginnings.The post Interview: ISC Cloud Absorbs into ISC High Performance appeared first on insideHPC.

“DDN’s selection for seven consecutive years as strategic partner and storage vendor of choice by the overwhelming majority of supercomputer centers on the Top500 list is a testament to the continuous innovation and performance leadership we bring to the HPC space,” said Alex Bouzari, CEO and founder, DDN. “From SSD to Persistent Storage and Archive, File Systems to Object Stores and Burst Buffers, DDN’s comprehensive end to end data lifecycle solutions continue to power the most data-intensive workflows in the world – generation after generation.”The post DDN Leads 2015 TOP500 List of Global Supercomputing Centers appeared first on insideHPC.

"In high performance computing, data sets are increasing in size and workflows are growing in complexity. Additionally, it is becoming too costly to have copies of that data and, perhaps more importantly, too time and energy intensive to move them. Thus, the novel Zero Copy Architecture (ZCA) was developed, where each process in a multi-stage workflow writes data locally for performance, yet other stages can access data globally. The result is accelerated workflows with the ability to perform burst buffer operations, in-situ analytics & visualization without the need for a data copy or movement."The post SGI Update: Zero Copy Architecture (ZCA) appeared first on insideHPC.

Today Monash University announced that it has become the first spoke of the NVIDIA Technology Centre Asia Pacific. With its hub is in Singapore, the NVIDIA Southeast Asia Technology Centre is based at Singapore’s Nanyang Technological University and has a core focus on deep learning research and development.The post Monash University Joins NVIDIA Technology Centre Asia Pacific appeared first on insideHPC.

Students interested in demonstrating their high-performance computing skills on a global stage are invited to team up and sign up to compete in the tenth annual Student Cluster Competition at the SC16 Conference to be held Nov. 13-18, 2016, in Salt Lake City. SC16 is the premier international conference on high performance computing, networking, storage and analysis.The post Students: Get your Team Together for the SC16 Student Cluster Competition appeared first on insideHPC.

Today the Red Bull Racing Formula One team announced an extended agreement with ANSYS. The team uses ANSYS' simulation software to optimize its vehicle design enhancements for a competitive edge on the track.The post Red Bull Racing Speeds Simulation with ANSYS appeared first on insideHPC.

"In this talk, Intersect360 Research returns with an annual deep dive into the trends, technologies and usage models that will be propelling the HPC community through 2016 and beyond. Emerging areas of focus and opportunities to expand will be explored along with insightful observations needed to support measurably positive decision making within your operations."The post A Look at HPC and Hyperscale Trends for 2016 appeared first on insideHPC.

Today Brocade announced the industry’s first Gen 6 Fibre Channel switch for storage networking. The Brocade G620 is a high-density SAN switch that delivers breakthrough performance and scalability designed to support data growth and demanding workloads from mission-critical applications.The post Brocade Launches Industry-First Gen 6 Fibre Channel Switch appeared first on insideHPC.

In this video, Bill Wagner of Bright Computing describes what attracted him to join the company as CEO and what's ahead for system management software. "Bright addresses the exploding demand to manage increasingly complex IT infrastructures with a simple yet powerful ‘single pane of glass’ management platform that can extend across the datacenter and the cloud. I am excited to join Bright’s talented team and eager to build on the company’s upward growth trajectory.”The post Interview with Bill Wagner, CEO of Bright Computing appeared first on insideHPC.

Today the Centre for Modeling & Simulation (CFMS) in the UK announced it will be taking part in a follow-on to the Hyperflux project. "Hyperflux ++ builds on the successful Innovate UK project ‘Hyperflux’ - developing next generation CFD technology for the civil, automotive, renewable and aerospace sectors."The post CFMS Joins Hyperflux++ Project to Advance CFD appeared first on insideHPC.

"Fred brings to Cray a proven track record of building strategic partnerships and increasing sales through a customer-centric view of the market,” said Peter Ungaro, president and CEO of Cray. “Fred’s background at industry-leading technology companies is perfectly tailored for this position. His experience and insight will help us as we work to continue our growth as a company, and bring to our customers the promised convergence of the exciting worlds of supercomputing and big data.”The post Cray Appoints Fred Kohout as Chief Marketing Officer appeared first on insideHPC.

In this video from the 2016 Stanford HPC Conference, Michael Jennings from LBNL presents: Node Health Check (NHC) Project Update. "In this follow-up to his 2014 presentation at the Stanford HPCAC Conference, Michael will provide an update on the latest happenings with the LBNL NHC project, new features in the latest release, and a brief overview of the roadmap for future development."The post Video: Node Health Check (NHC) Project Update appeared first on insideHPC.

Today Allinea announced plans to champion what it sees as a key survival message for the Energy industry when it exhibits at the Rice Oil and Gas HPC Conference in Houston next week. "We'll be underlining to geophysicists at the conference the real commercial gains to be had from focusing on code performance," said Robert Rick, Allinea's VP of Sales, Americas. "HPC is helping the industry to operate more efficiently. The next step is for this market is to use code optimization to speed up the valuable seismic imaging and reservoir modeling processes, which are now essential to this industry."The post Code Modernization for Smarter Geophysics appeared first on insideHPC.