High-Performance Computing News Analysis | insideHPC

"InfiniBand's advantages of highest performance, scalability and robustness enable users to maximize their data center return on investment. InfiniBand was chosen by far more end-users compared to a proprietary offering, resulting in a more than 85 percent market share. We are happy to see our open Ethernet adapter and switch solutions enable all of the 40G and the first 100G Ethernet systems on the TOP500 list, resulting in overall 194 systems using Mellanox for their compute and storage connectivity."The post Mellanox Brings HDR to SC16 while Dominating Today’s TOP500 appeared first on insideHPC.

In this video from the Intel HPC Developer Conference, Justin Gottschlich, PhD from Intel describes how the company doubling down on Anomaly Detection using Machine Learning and Intel technologies. "In this talk, we present future research directions at Intel Labs using deep learning for anomaly detection and management. We discuss the required machine learning characteristics for such systems, ranging from zero positive learning, automatic feature extraction, and real-time reinforcement learning. We also discuss the general applicability of such anomaly detection systems across multiple domains such as data centers, autonomous vehicles, and high performance computing."The post Using Machine Learning to Avoid the Unwanted appeared first on insideHPC.

Demonstrating Asetek’s adaptability to any data center cooling need, HPC installations from around the world are currently on display at SC16 in Salt Lake City, Utah November 14-17. Servers from these installations featuring Asetek liquid cooling will be on display including servers installed at Oakforest-PACS, the highest Performance Supercomputer System in Japan.The post Asetek’s Adaptable Liquid Cooling on Display at SC16 appeared first on insideHPC.

Watch this video of Nvidia CEO Jen-Hsun Huang's talk from SC16 in Salt Lake City. Can't make it to the show? Tune in right here on insideHPC to watch Nvidia talks all this week. "See how other leaders in the field are advancing computational science across domains, get free hands-on training with the newest GPU-accelerated solutions, and connect with NVIDIA experts."The post Video: Jen-Hsun Huang Keynote from the Nvidia Booth at SC16 appeared first on insideHPC.

Today Aquila announced a liquid-cooled edge data center co-development program featuring the first ruggedized modular edge data center developed around the Aquarius liquid cooled compute platform. This platform combines TAS’s industry-leading efficient modular data centers with Aquarius’s liquid cooled compute, switching, and storage to address the need for small modular data centers.The post Aquila and TAS Energy Launch Liquid Cooled Edge Data Center Solution appeared first on insideHPC.

The new TOP500 list is out, and Rad is Free HPC is here podcasting the scoop in their own special way. With two new systems in the TOP10, there are many different perspectives to share. "The Cori supercomputer, a Cray XC40 system installed at Berkeley Lab’s National Energy Research Scientific Computing Center (NERSC), slipped into the number 5 slot with a Linpack rating of 14.0 petaflops. Right behind it at number 6 is the new Oakforest-PACS supercomputer, a Fujitsu PRIMERGY CX1640 M1 cluster, which recorded a Linpack mark of 13.6 petaflops."The post Radio Free HPC Reviews the New TOP500 appeared first on insideHPC.

FPGAs will become increasing important for organizations that have a wide range of applications that can benefit from performance increases. Rather than a brute force method to increasing performance in a data center by purchasing and maintaining racks of hardware and associated costs, FPGAs may be able to equal and exceed the performance of additional servers, while reducing costs as well.The post Can FPGAs Help You? appeared first on insideHPC.

Today Seagate Technology introduced the ClusterStor 300N storage system with Nytro Intelligent I/O Manager, the newest addition to its family of scale-out storage systems for high-performance computing and the first with a flash cache accelerator. “Seagate’s ClusterStor 300N expands on our proven, engineered systems approach that delivers performance efficiency and value for HPC environments of any size, using a hybrid technology architecture to handle tough workloads at a fraction of the cost of all-flash approaches.”The post Seagate Accelerates ClusterStor with Flash appeared first on insideHPC.

Welcome to the Mobile Edition for the Print ‘n Fly Guide to SC16 in Salt Lake City. Inside this guide you will find technical features on supercomputing, HPC interconnects, and the latest developments on the road to exascale. It also has great recommendations on food, entertainment, and transportation in SLC.The post Mobile Edition: Print ‘n Fly Guide to SC16 in Salt Lake City appeared first on insideHPC.

Today Penguin Computing announced several important achievements of its Penguin Computing On-Demand (POD) HPC cloud service, including a recent 50 percent increase in capacity and plans to double POD’s total capacity in Q1 2017. The upgrade will include new Intel Xeon processors and Intel Omni-Path architecture. “Rapid demand for and growth in our POD business reflects the significant benefits customers are experiencing, particularly since we announced availability of the OCP-compliant Tundra platform on POD late last year,” said Tom Coull, President and CEO, Penguin Computing. “With the Tundra platform, our customers have greater capacity due to faster scaling combined with increased performance and streamlined costs. Tundra on POD also highlights the growth and maturing market role of open computing, with thousands of high-speed, cost-efficient cores available to meet customers’ needs for faster, easier deployment of capacity at a low cost.”The post Omni Path Comes to Penguin Computing On-Demand appeared first on insideHPC.

In this video from the Intel HPC Developer Conference, Ananth Sankaranarayanan from Intel describes how the company is optimizing Machine Learning frameworks for Intel platforms. Open source frameworks often are not optimized for a particular chip, but bringing Intel's developer tools to bear can result in significant speedups. For meaningful impact and business value, organizations require that the time to train a deep learning model be reduced from weeks to hours. In this talk, we will present the details of the optimization and characterization of Intel-Caffe and the support of new deep learning convolutional neural network primitives in the Intel Math Kernel Library."The post Accelerating Machine Learning on Intel Platforms appeared first on insideHPC.

Today Cray announced the launch of the Cray XC50 supercomputer – the company’s fastest supercomputer ever with a peak performance of one petaflop in a single cabinet. "Supercomputing applications are evolving to include more deep learning algorithms, and with this evolution, the uses for GPUs in our systems are increasing, enabling our customers to use new analytics techniques to gain insight from increasingly large and complex data,” said Ryan Waite, Cray senior vice president of products. “The new Cray XC50 system represents a major advancement in our supercomputing capabilities. It provides the highest performance density of any Cray supercomputer, and gives customers the computational resources they need to take on larger, more complex workloads, as well as the next generation of scientific challenges.”The post New Cray XC50 Delivers 1 Petaflop Per Cabinet appeared first on insideHPC.

If the keys to health, longevity, and a better overall quality of life are encoded in our individual genetic make-up then few advances in the history of medicine can match the significance and potential impact of the Human Genome Project. Instigated in 1985 and since that time, the race has been centered on dramatically improving the breadth and depth of genomic understanding as well as reducing the costs involved in sequencing, storing, and processing an individual’s genomic information.The post Enabling Personalized Medicine through Genomic Workflow Acceleration appeared first on insideHPC.

"We go to the show for the technology, the engineering, the science, and the math. It’s HPCMatters and STEM. The vendors are showcasing their technology and the science their technology has enabled. The research exhibits are showing how they are contributing to the scientific process with the largest supercomputers that have cool names. That’s what’s so great about SC: It brings together many of the brilliant minds behind these technologies."The post Top 10 Things to Love About HPC and the SC16 Conference appeared first on insideHPC.

In this video from SC16, Dr. Eng Lim Goh from HPE/SGI discusses new trends in HPC Energy Efficiency and Deep Learning. "SGI's leadership in data analytics derives from deep expertise in High Performance Computing and over two decades delivering many of the world's fastest supercomputers. Leveraging this experience and SGI's innovative shared and distributed memory computing solutions for data analytics enables organizations to achieve greater insight, accelerate innovation, and gain competitive advantage."The post Fireside Chat: Dr. Eng Lim Goh on New Trends in HPC Energy Efficiency & Deep Learning appeared first on insideHPC.

"Adaptive Computing is driving up our customers’ productivity by helping them gain true insight into how their resources are being used, how to handle future capacity planning, and the service levels they are delivering to their most critical projects,” says Marty Smuin, CEO of Adaptive Computing. “This latest solution helps deliver the insights that organizations need in order to eliminate waste, avoid unnecessary delays, and make the changes that will align resources to better achieve organizational goals.”The post Adaptive Computing Rolls Out New Reporting & Analytics Tool appeared first on insideHPC.

In this podcast, Jason Stowe from Cycle Computing provides an update on the world of HPC in the Cloud. After that, he describes how the company is augmenting its software capabilities so that more users can take advantage of HPC for their toughest computing challenges. “Our CycleCloud V6 further optimizes what is already unique about its predecessor, bringing unmatched scalability, provisioning, and data management in a secure process. We are extremely pleased to bring V6 to market.”The post Podcast: How Cycle Computing is Riding the Wave of HPC in the Cloud appeared first on insideHPC.

"Real-time-analytics and Big Data environments are extremely demanding and the network is critical in linking together the extra high performance IBM POWER based servers and Tencent Cloud’s massive amounts of data,”said Amir Prescher, Sr. Vice President, Business Development, at Mellanox Technologies. “Tencent Cloud developed an optimized hardware/software platform to achieve new computing records, showing that Mellanox’s 100Gb/s Ethernet technology can deliver total infrastructure efficiency and improves application performance, making them ideal for Big Data applications.”The post Tencent Cloud Breaks World Record for Data Sorting with IBM & Mellanox appeared first on insideHPC.

One of the primary conversations these days in the field of networking is whether it is better to onload network functions onto the CPU or better to offload these functions to the interconnect hardware. "Onloading interconnect technology is easier to build, but the issue becomes the CPU utilization; because the CPU must manage and execute network operations, it has less availability for applications, which is its primary purpose."The post Offloading vs. Onloading: The Case of CPU Utilization appeared first on insideHPC.

Deep learning is one of the hottest topics at SC16. Now, DK Panda and his team at Ohio State University have announced an exciting new High-Performance Deep Learning project that aims to bring HPC technologies to the DL field. "Availability of large data sets like ImageNet and massively parallel computation support in modern HPC devices like NVIDIA GPUs have fueled a renewed interest in Deep Learning (DL) algorithms. This has triggered the development of DL frameworks like Caffe, Torch, TensorFlow, and CNTK. However, most DL frameworks have been limited to a single node. The objective of the HiDL project is to exploit modern HPC technologies and solutions to scale out and accelerate DL frameworks."The post DK Panda Team Launches High-Performance Deep Learning Project appeared first on insideHPC.

This version of COMPSs, available from today, updates the result of the team’s work in the last years on the provision of a set of tools that helps developers to program and execute their applications efficiently on distributed computational infrastructures such as clusters, grids and clouds. COMPSs is a task based programming model known for notably improving the performance of large scale applications by automatically parallelizing their execution.The post BSC Releases COMPSs Version 2.0 at SC16 appeared first on insideHPC.

Today OpenSFS, the nonprofit organization dedicated to the success of the Lustre file system, announced organizational changes to give its users—the researchers and scientists who use Lustre every day—more of a say in how OpenSFS moves forward. "Now the time has come for those who rely most on Lustre—its users—to guide OpenSFS into the future," said Stephen Simms, OpenSFS president and manager, high performance file systems at Indiana University.The post OpenSFS Reinvents Itself with a Focus on Lustre Users appeared first on insideHPC.

Today Appentra Solutions announced that the company will participate in the Emerging Technologies Showcase at SC16. As an HPC startup, Appentra was selected for its Parallware technology, an LLVM-based software technology that assists in the parallelization of scientific codes with OpenMP and OpenACC. "The new Parallware Trainer is a great tool for providing support to parallel programmers on their daily work,” said Xavier Martorell, Parallel Programming Models Group Manager at Barcelona Supercomputing Center.The post Appentra Solutions will be part of SC16 Emerging Technologies Showcase appeared first on insideHPC.

Today the Department of Energy’s Exascale Computing Project (ECP) today announced that it has selected four co-design centers as part of a 4 year, $48 million funding award. The first year is funded at $12 million, and is to be allocated evenly among the four award recipients. “By targeting common patterns of computation and communication, known as “application motifs”, we are confident that these ECP co-design centers will knock down key performance barriers and pave the way for applications to exploit all that capable exascale has to offer.”The post Exascale Computing Project Announces $48 Million to Establish Four Exascale Co-Design Centers appeared first on insideHPC.

“We chose to work with CoolIT Systems because their solutions are modular and robust, and as a result the most flexible and efficient for our situation,” says Keith Vanderlinde, Assistant Professor at the University of Toronto. “With the custom liquid cooling solution, we can drastically reduce CHIME’s energy consumption and squeeze additional processing out of the GPUs.”The post Custom Liquid Cooling to Support Canada’s Largest Radio Telescope appeared first on insideHPC.

Researchers and staff from the U.S. Department of Energy’s national laboratories will showcase some of DOE’s best computing and networking innovations and techniques at SC16 in Salt Lake City. "Computational scientists working for various DOE laboratories have been in involved in the conference since its 1988 beginnings, and this year’s event is no different. Experts from 14 national laboratories will be sharing a booth featuring speakers, presentations, demonstrations, discussions and simulations."The post DOE to Showcase Leadership in HPC at SC16 appeared first on insideHPC.

Intel Omni-Path Architecture (Intel OPA) volume shipments started a mere nine months ago in February of this year, but Intel’s high-speed, low-latency fabric for HPC has covered significant ground around the globe, including integration in HPC deployments making the Top500 list for June 2016. Intel’s fabric makes up 48 percent of installations running 100 Gbps fabrics on the Top500 June list, and they expect a significant increase in Top500 deployments, including one that could end up in the stratosphere among the top ten machines on the list.The post Intel Omni-Path Architecture Fabric, the Choice of Leading HPC Institutions appeared first on insideHPC.

Over at the ARM Connected Community, Darren Cepulis, writes that the popular chip platform is now part of the OpenHPC community. As one of a series of strategic moves, the effort should help bolster ARM as a platform for high performance computing.The post OpenHPC now available on ARM at SC16 appeared first on insideHPC.

To get maximum parallelization for an application, not only must the application be developed to take advantage of multiple cores, but should also have the code in place to keep a number of threads working on each core. A modern processor architecture, such as the Intel Xeon Phi processor, can accommodate at least 4 threads for each core. "On the Intel Xeon Phi processor, each of the threads per core is known as a hyper-thread. In this architecture, all of the threads on a core progress through the pipeline simultaneously, producing results much more quickly than if just one thread was used. The processor decides which thread should progress, based on a number of factors, such as waiting for data from memory, instruction availability, and stalls."The post Maximize Parallelization with Threading On A Core appeared first on insideHPC.

Today the Department of Energy’s Exascale Computing Project (ECP) today announced the selection of 35 software development proposals representing 25 research and academic organizations. “After a lengthy review, we are pleased to announce that we have selected 35 proposals for funding. The funding of these software development projects, following our recent announcement for application development awards, signals the momentum and direction of ECP as we bring together the necessary ecosystem and infrastructure to drive the nation’s exascale imperative.”The post Exascale Computing Project Awards $34 Million for Software Development appeared first on insideHPC.

In this slidecast, Gilad Shainer from Mellanox announces the world’s first HDR 200Gb/s data center interconnect solutions. "These 200Gb/s HDR InfiniBand solutions maintain Mellanox’s generation-ahead leadership while enabling customers and users to leverage an open, standards-based technology that maximizes application performance and scalability while minimizing overall data center total cost of ownership. Mellanox 200Gb/s HDR solutions will become generally available in 2017."The post Slidecast: Mellanox Announces 200Gb/s HDR InfiniBand Solutions appeared first on insideHPC.

With the SC conference returning to Salt Lake City next week, we’d like to share some of the reasons why we think SLC is one of the most underrated American cities.The post Salt Lake City Guide – A Wonder of the West appeared first on insideHPC.

Today StartupHPC posted their final agenda for their Workshop at SC16 in Salt Lake City. StartupHPC is focused on fostering entrepreneurship in high performance computing,” said founding member Shahin Khan of OrionX. “The StartupHPC Summit has a stellar lineup of speakers and thought leaders from the supercomputing community, and now, thanks to a generous sponsorship […]The post Free to Attend: StartupHPC Summit Monday, Nov. 14 in Salt Lake City appeared first on insideHPC.

Today Atos announced Bull Director for HPSS, Data Management software dedicated to High Performance Computing. Bull Director for HPSS optimizes current large scale storage solutions and frees up compute time for users. "In a context of data explosion, storage is often a bottleneck and has a negative impact on application performance. Atos has a long experience of implementing HPSS in challenging environments where long-term data preservation and re-use of massive data sets are key. Our ultimate objective with Bull Director for HPSS and the other future components is to get rid of these bottlenecks and free up compute time for users." explains Eric Eppe, Head of Products and Solutions for extreme computing at Atos.The post Tackling HPC Storage Bottlenecks with Bull Director for HPSS appeared first on insideHPC.

Today ECI announced plans to demonstrate a 400G backbone at SCinet, the world's largest and fastest high-performance network at SC16 in Salt Lake City. "ECI was delighted to receive the invitation to participate in this exciting demonstration for the high performance computing sector. ECI is no stranger to this sector. We provide services to many research and education networks worldwide. Some of our wins include DFN (Germany), Switch (Sweden), GRNet (Greece), and most recently an exciting win at DeIC (Denmark), details of which will be disclosed in the near future," said Tony Gomez, VP of Business Development for ECI in N. America."The post ECI to Demo 400G Optical Backbone on SC16 SCinet appeared first on insideHPC.

"By joining iEnergy, Cray can offer Landmark processing customers access to its high-performance hardware platform to help software users maximize their benefits from the SeisSpace processing system,” said Steve Angelovich, SeisSpace product manager, at Halliburton Landmark. iEnergy members have this opportunity because this online technical community enables its members to work, learn, contribute, and collaborate together. Rekha Patel, ecosystem evangelist at Halliburton Landmark, said, “We welcome Cray as a new iEnergy member and look forward to the synergy between SeisSpace and Cray’s cluster systems.”The post Cray Joins iEnergy Oil & Gas Community appeared first on insideHPC.

In this slidecast, Tony DeVarco from SGI describes how the company delivers Production Supercomputing for SMEs. “As the trusted leader in high performance computing, SGI helps companies find answers to the world’s biggest challenges. Our commitment to innovation is unwavering and focused on delivering market leading solutions in Technical Computing, Big Data Analytics, and Petascale Storage. Our solutions provide unmatched performance, scalability and efficiency for a broad range of customers.”The post Slidecast: How SGI is Meeting Manufacturing’s Need for Production Supercomputing appeared first on insideHPC.

SC16 returns to Salt Lake City this year. And while SLC is known for its gorgeous views of the mountains, what our readers may not know is that Salt Lake City is full of Hip, yes hip restaurants, cafes, bars, and things to see and do. "In this feature from the Print 'n Fly Guide Guide to SC16 in Salt Lake City, we offer you some great restaurant recommendations from the locals. Plus, we'll tell you where to get great cigars, a day at the spa, and more."The post Local’s Guide to Food & Entertainment at SC16 in Salt Lake City appeared first on insideHPC.

With SC16 coming to Salt Lake City, we asked the local's for their top pick for a great dinner place. The winner was Copper Onion. "The restaurant located on busy Broadway (and steps from the convention center) in downtown SLC, is a welcome respite from the city."The post Our Top Recommendation for a Great Dinner at SC16 in Salt Lake City appeared first on insideHPC.

In this special guest feature, Bill Mannel from Hewlett Packard Enterprise writes that upcoming Intel HPC Developer Conference in Salt Lake City is a great opportunity to learn about code modernization for the next generation of high performance computing applications. "As computing systems grow increasingly complex and new architecture designs become mainstream, training developers to write code which runs on future HPC systems will require a collaborative environment and the expertise of the best and brightest in the industry."The post Preparing Developers for Tomorrow’s Systems appeared first on insideHPC.

Today FlyElephant announced a collaboration with HPC HUB, a developer of complex software and hardware solutions in high performance computing. Now entering its second year, FlyElephant is a platform for data scientists, engineers and researchers that accelerates their work and improves their business by automating data science and engineering simulation tasks.The post FlyElephant Collaborates with HPC-HUB for High Performance in the Cloud appeared first on insideHPC.

Today BIOS IT announced plans for their exhibit at SC16 in Salt Lake City. BIOS IT is will be showcasing the latest HPC solutions and services, including their converged cloud platform in partnership with vScaler Ltd. "vScaler gives our clients the ability to deploy and manage HPC environments with on demand parallel file system creation within their own datacenters and when demand dictates, off-premise as well,” Ian Mellett, General Manager at BIOS IT comments.The post BIOS IT Collaborates with vScaler for HPC in the Cloud appeared first on insideHPC.

The ExaFLOW project has announced 3.3 Million Euros of funding for a group of eight organizations to take Europe’s CFD community one step closer to performing simulations in exascale environments.The post ExaFLOW Funds CFD Research for Exascale appeared first on insideHPC.

"CycleCloud has made an impact on a host of use cases - from our recently announced NASA Sub-Saharan carbon-emissions project to needs in the financial sector, manufacturing and life sciences. CycleCloud has saved countless hours overcoming the challenges typically associated with Cloud HPC and brought in real ROI,” said Jason Stowe, CEO, Cycle Computing. “Our CycleCloud V6 further optimizes what is already unique about its predecessor, bringing unmatched scalability, provisioning, and data management in a secure process. We are extremely pleased to bring V6 to market.”The post CycleCloud V6 spins up HPC Clusters in the Cloud appeared first on insideHPC.

“We have taken a flexible and adaptive approach to multi-level security that combines recent community advances with DDN-developed Lustre features to deliver full Lustre isolation, while minimizing the performance impact of the system overhead associated with implementing security,” said Robert Triendl, senior vice president, global sales, marketing and field services, DDN. “This approach lets us customize configurations that meet our customers’ security requirements without them having to sacrifice workflow efficiency.”The post DDN Announces Multi-Level Security Lustre Solution for HPC appeared first on insideHPC.

In this slidecast, Silicon Mechanics CTO Daniel Chow describes how the company brings value and performance to its HPC customers. "When looking for a leading solutions integrator to couple disparate hardware and software products into a “HPC Built For You” solution, that will keep up with the evolution and disruptive forces in technology – the Experts at Silicon Mechanics are here to help you."The post Slidecast: Silicon Mechanics – An Open-Technology Solutions Integrator appeared first on insideHPC.

The OpenACC standards group today announced several major milestones including the addition of new member, the National Supercomputing Center in Wuxi, the adoption of OpenACC by several major HPC applications, the addition of support for new target platforms and expanded implementationThe post OpenACC Gains Momentum in 2016 appeared first on insideHPC.

Attendees of SC16 who are interested in open source data management will have plenty of opportunities to learn about the integrated Rule-Oriented Data System (iRODS) and the new iRODS 4.2, which will be released just in time for the conference.The post iRODS Consortium Plans Busy Week at SC16 appeared first on insideHPC.

The Beowulf Bash returns to Salt Lake City on Monday, Nov 14. As the one party you don't want to miss, the Bash starts at 9pm, right after the SC16 opening gala. "Since its inception the Bash has been consistent about two things: 1) it is held on Monday night after the SC Opening Gala, and 2) most attendees have a darn good time. For almost a decade now the Beowulf Bash invites have come to us with a bit of an edge. We caught up with the two people who create the Beowulf Bash invitations, Lara Kisielewska of Xand McMahon and Doug Eadline of Cluster Monkey, to find out more about these unique invites."The post The 2016 Beowulf Bash Interview: The Story Behind “Beosnark” appeared first on insideHPC.

Today Cray announced the Department of Defense High Performance Computing Modernization Program (HPCMP) has awarded the Company with a $26 million supercomputer contract for a Cray XC40 supercomputer and three Cray Sonexion storage systems.The post DoD Modernization Program to Acquire Cray XC40 appeared first on insideHPC.