by Rich Brueckner on (#2VQDX)
In this video from ISC 2017, Oliver Tennert from NEC Deutschland GmbH introduces the company's advanced technologies for HPC and Machine Learning. "Today NEC Corporation announced that it has developed data processing technology that accelerates the execution of machine learning on vector computers by more than 50 times in comparison to Apache Spark technologies."The post NEC’s Aurora Vector Engine & Advanced Storage Speed HPC & Machine Learning at ISC 2017 appeared first on insideHPC.
|
High-Performance Computing News Analysis | insideHPC
Link | https://insidehpc.com/ |
Feed | http://insidehpc.com/feed/ |
Updated | 2024-11-25 09:30 |
by staff on (#2VQBG)
Today NVIDIA and Baidu today announced a broad partnership to bring the world’s leading artificial intelligence technology to cloud computing, self-driving vehicles and AI home assistants. “We believe AI is the most powerful technology force of our time, with the potential to revolutionize every industry. Our collaboration aligns our exceptional technical resources to create AI computing platforms for all developers – from academic research, startups creating breakthrough AI applications, and autonomous vehicles.â€The post NVIDIA and Baidu Partner Up to Accelerate AI appeared first on insideHPC.
|
by Rich Brueckner on (#2VNQ6)
In this video, CoolIT Systems debuts high TDP processor coldplates, STULZ Micro Data Center with Rack DCLCâ„¢, and new liquid cooled OEM servers at ISC High Performance 2017 in Frankfurt Germany.The post Liquid Cooling Ecosystem Expands for HPC with CoolIT Systems appeared first on insideHPC.
|
by staff on (#2VMYZ)
"In the future, though, it may be possible to diagnose cancer much earlier using more sensitive body scans, new types of biomarker tests, and even nano-sensors working in the bloodstream. Experimenting with these techniques in cancer patients or healthy individuals is difficult and potentially unethical. But scientists can test these technologies virtually using supercomputers to simulate the dynamics of cells and tissues."The post Supercomputing New Tools for Cancer Detection appeared first on insideHPC.
|
by Rich Brueckner on (#2VMWH)
In this video from ISC 2017, Raj Hazra, Corporate Vice President and General Manager of the Enterprise and Government Group at Intel, discusses key trends impacting the future growth of High Performance Computing. He focuses on the opportunities of enabling HPC in the cloud, and how this drives the need for a consistent platform that bridges the worlds of dedicated supercomputers and hyperscale cloud service providers.The post Intel’s Raj Hazra on how new technologies are Clouding our Future appeared first on insideHPC.
|
by Rich Brueckner on (#2VJRP)
Today NEC Corporation announced that it has developed new Aurora Vector Engine data processing technology that accelerates the execution of machine learning on vector computers by more than 50 times in comparison to Spark technologies. "This technology enables users to quickly benefit from the results of machine learning, including the optimized placement of web advertisements, recommendations, and document analysis," said Yuichi Nakamura, General Manager, System Platform Research Laboratories, NEC Corporation. "Furthermore, low-cost analysis using a small number of servers enables a wide range of users to take advantage of large-scale data analysis that was formerly only available to large companies."The post NEC Vector Computers Accelerate Machine Learning appeared first on insideHPC.
|
by staff on (#2VJK8)
Today Atos announced that a new Bull Sequana supercomputer will enable high-performance computing solutions to boost next-generation scientific modeling for the UK defense organization. The new system will feature a single Bull Sequana x1000 supercomputer with a theoretical peak performance of 4.3 Petaflops. The Bull Sequana supercomputer uses the latest generation of direct-liquid cooling to enable the densest and most energy-efficient platform in the industry with the system to be installed using the latest Mellanox EDR interconnect and a high performance Seagate Lustre storage appliance offering around 100 Gigabytes per second of I/O performance.The post Atos to Build 4.3 Petaflop Bull Sequana Supercomputer for AWE in the UK appeared first on insideHPC.
|
by staff on (#2VJGW)
The DEEP exascale research computing project has entered its next phase with launch of the DEEP-EST project at the Jülich Supercomputing Center in Germany. "The optimization of homogeneous systems has more or less reached its limit. We are gradually developing the prerequisites for a highly efficient modular supercomputing architecture which can be flexibly adapted to the various requirements of scientific applications,†explains Prof. Thomas Lippert, head of the Jülich Supercomputing Centre (JSC).The post DEEP-EST Project Looks to Building-blocks for Exascale appeared first on insideHPC.
|
by staff on (#2VG53)
Graduate Assistant Hongyu Chen used data from the National Longitudinal Survey of Youth to model individuals’ education, career, borrowing, and spending decisions based on whether or not they were part of a loan forgiveness program. Chen wrote a program that ran simulations of over 151 parameters on a population of approximately 2,500 individuals between the ages of 18 to 65 during different periods of their lives. "The estimation takes around 10 years if I’m running just one single computer,†Chen said. “That’s why I have to use the cluster of computers, like the supercomputer, that use multiple cores at the same time, so that saves me a lot of time.â€The post Supercomputing the Impact of Loan Forgiveness Programs appeared first on insideHPC.
|
by Rich Brueckner on (#2VG3A)
"The mission of the Virtual Institute - High Productivity Supercomputing (VI-HPS) is to improve the quality and accelerate the development process of complex simulation codes in science and engineering that are being designed to run on highly-parallel computer systems. For this purpose, we are developing integrated state-of-the-art programming tools for high-performance computing that assist programmers in diagnosing programming errors and optimizing the performance of their applications."The post The Virtual Institute – High Productivity Supercomputing Celebrates 10th Anniversary appeared first on insideHPC.
|
by Rich Brueckner on (#2VEAW)
The MHPC program in Italy has announced their Call for Masters of High Performance Computing. The Master in High Performance Computing (MHPC) is an innovative degree program that prepares students for exciting careers in the fast-growing field of HPC. Set in the stimulating research environment of its co-organizer institutions, SISSA and ICTP, the program combines lectures with hands-on and applied projects to prepare future HPC specialists for academia and industry.The post SISSA in Italy Issues Call for Masters of High Performance Computing appeared first on insideHPC.
|
by Rich Brueckner on (#2VE36)
"Intersect360 Research has posted an Executive Summary of their most recent HPC User Site Census on Interconnect Suppliers. The report provides an examination of the server interconnects and network characteristics found at a sample of HPC user sites. Intersect360 Research surveyed a broad range of users about their current computer system installations, storage systems, networks, middleware, and software supporting these computer installations."The post Intersect360 Research Site Census Looks at HPC Interconnects appeared first on insideHPC.
|
by Rich Brueckner on (#2VBT7)
In this video from ISC 2017, Olivier de Laet from Calyos describes the company’s innovative cooling technology for high performance computing. "The HPC industry is ever facing is facing the challenge of ever-increasing cooling requirements. While liquid cooling cooling looks to be the best solution, what if you could achieve the same efficiencies without out using water and pumps?"The post Is Water-Free Cooling the Real Future of HPC? appeared first on insideHPC.
|
by staff on (#2VBT9)
"At NASA, what we're doing is we're really looking at ways of making aircraft more efficient. We're trying to make them quieter. We're trying to make them get to cruise altitude faster, which saves the taxpayer or the people who are using airplanes a lot of money, and we look at really complex problems. We look at things like rotorcraft. If you think about how that model looks, it's a very complex model. What do we do with supercomputing? Pretty much everything across the board."The post Podcast: Why HPC is Vital at NASA appeared first on insideHPC.
|
by Rich Brueckner on (#2VBM9)
In this video from ISC 2017, Tom Krueger from Intel and John Wagner from Fujitsu describe the new KNL Remote Access Program. Now, with the power of Intel HPC Orchestrator, Fujitsu customers can gain access to a small cluster of Intel Xeon Phi processors to test and tune their codes. The freely available cluster environment enables users to participate in activities such as benchmarking, code development, as well as code optimization and validation either using the pre-installed applications or those brought by the user."The post Fujitsu Powers KNL Remote Access Program with Intel HPC Orchestrator appeared first on insideHPC.
|
by staff on (#2VBMB)
Today the ISC Group announced that their 2017 ISC High Performance conference drew a record 3,253 attendees from 60 countries. The attendance represented a 5.2 percent increase compared to last year’s event.The post ISC 2017 Wrapup by the Numbers appeared first on insideHPC.
|
by Rich Brueckner on (#2VBH5)
In this video from ISC 2017, Bill Bryce from Univa describes how the company's software powers simulation for everything from Formula 1 racing to manufacturing and life sciences. "Univa is the leading innovator in workload management and containerization solutions. Univa's suite includes the world's most trusted workload optimization solution enabling organizations to manage and optimize distributed applications, containers, data center services, legacy applications, and Big Data frameworks in a single, dynamically shared set of resources."The post Univa Powers Formula 1 Racing and more at ISC 2017 appeared first on insideHPC.
|
by MichaelS on (#2V8T2)
In many cases, applications that perform various simulations use some of the same math functions that many other applications use. Rather than each developer recoding the same math functions over and over, libraries, developed by experts can significantly speed up execution of the overall application. Since there can be many optimizations that experts who understand many of the nuances of the hardware would understand, it is important that developers be familiar with various libraries that are made available for HPC types of applications.The post Performance Gains Using Libraries appeared first on insideHPC.
|
by staff on (#2V8KP)
Today the InfiniBand Trade Association (IBTA) announced that InfiniBand remains the most used HPC interconnect on the TOP500. Additionally, the majority of newly listed TOP500 supercomputers are accelerated by InfiniBand technology. These results reflect continued industry demand for InfiniBand’s unparalleled combination of network bandwidth, low latency, scalability and efficiency.As demonstrated on the June 2017 TOP500 supercomputer list, InfiniBand is the high-performance interconnect of choice for HPC and Deep Learning platforms,†said Bill Lee, IBTA Marketing Working Group Co-Chair. “The key capabilities of RDMA, software-defined architecture, and the smart accelerations that the InfiniBand providers have brought with their offering resulted in enabling world-leading performance and scalability for InfiniBand-connected supercomputers.â€The post InfiniBand Continues Momentum on Latest TOP500 appeared first on insideHPC.
|
by staff on (#2V8H5)
Today SPEC’s High-Performance Group released a new version of its SPEC ACCEL software that adds a suite of OpenMP applications for measuring the performance of systems using hardware accelerator devices and supporting software. SPEC ACCEL also measures performance for computationally intensive parallel applications running under the OpenCL and OpenACC programming models.The OpenMP application benchmarks are the first of their kind and now give our customers the opportunity to compare hardware configurations based on the most popular open-programming models," says Guido Juckeland, SPEC/HPG vice chair. "We look forward to a wide variety of SPEC ACCEL result submissions on the SPEC website and a number of research papers comparing various optimization settings on multiple platforms."The post SPEC/HPG hardware acceleration benchmark adds OpenMP Suite appeared first on insideHPC.
|
by Rich Brueckner on (#2V7TV)
At ISC 2017, Hyperion Research announced the newest recipients of the HPC Innovation Excellence Award. The program's main objectives are to showcase return on investment (ROI) and success stories involving HPC; to help other users better understand the benefits of adopting HPC; and to help justify HPC investments, including for small and medium-size enterprises (SMEs). "There are three awards categories, including the HPC User Innovation Award, the HPC Data Center Innovation Award; and the HPC Vendor Innovation Award. The judgement process for these awards is fair and clear."The post HPC Innovation Excellence Awards announced by Hyperion Research appeared first on insideHPC.
|
by Rich Brueckner on (#2V7TW)
In this video from ISC 2017, Bill Nitzberg from Altair describes how PBS Pro adds powerful workload management capabilities to Intel HPC Orchestrator.Offering PBS Professional as the preferred workload manager for Intel’s HPC Orchestrator provides a comprehensive and reliable workload management product to customers,†said Piush Patel, Vice President, Corporate Development for HPC at Altair. “Altair is committed to the pursuit of exascale computing and the democratization of HPC for organizations to achieve the next great innovations. Intel’s HPC Orchestrator with PBS Pro is a great step toward both goals.â€The post Intel HPC Orchestrator – Now with Altair PBS Pro Inside appeared first on insideHPC.
|
by Rich Brueckner on (#2V7PE)
"Liquid cooling is becoming the new norm in the face of skyrocketing wattages by CPUs, GPUs and cluster nodes. Asetek cooling solutions are currently provided by OEMs such as Cray, Fujitsu, Format, Penguin. Liquid cooling for NVIDIA P100, Intel Knight’s Landing and Skylake were all on display at Asetek’s booth as well as rack-level options such as InRackCDU and Vertical RackCDU."The post Liquid Cooling for HPC Gains Momentum with Asetek at ISC 2017 appeared first on insideHPC.
|
by staff on (#2V50N)
Today Iceland-based co-hosting provider Verne Global announced powerDIRECT+, a reduced-cost compute environment engineered specifically for the next generation of power intensive computing. With the addition of powerDIRECT+, Verne Global has expanded its compute environments to equip CIOs with streamlined and cost-effective data center options, breaking the decades-old model of one-size-fits-all data center design.The post Bring your workloads to Iceland: Verne Global adds powerDIRECT+ appeared first on insideHPC.
|
by staff on (#2V4W1)
Today Bright Computing announced that it has been selected by Hyperion Research for a 2017 HPC Innovation Award for its ability to provision and manage virtual servers in Microsoft Azure. "Helping organizations easily create hybrid clouds is a critical scenario for many customers, especially those using HPC in the cloud for the first time. We are pleased that Bright Computing is already receiving industry recognition for its work with Microsoft Azure, and look forward to more to come from this collaboration.â€The post Hyperion Research Recognizes Bright Computing for their Integration with Azure appeared first on insideHPC.
|
by staff on (#2V4HD)
Today Asetek announced an additional order from Penguin Computing for an undisclosed HPC installation. "This repeat order reflects our strong partnership with Penguin Computing. It is also another confirmation of the increasing need for liquid cooling in high density HPC clusters,†said André Sloth Eriksen, CEO and founder of Asetek."The post Penguin Computing doubles down on Asetek Liquid Cooling appeared first on insideHPC.
|
by Rich Brueckner on (#2V4KC)
Katrin Amunts from Jülich presented this keynote at the PASC17 conference. "The human brain has a multi-level organization and high complexity. New approaches are necessary to decode the brain with its 86 billion nerve cells, each with 10,000 connections. 3D Polarized Light Imaging, for example, elucidates the connectional architecture at the level of axons, while keeping the topography of the whole organ; it results in data sets of several petabytes per brain, which should be actively accessible while minimizing their transport. The Human Brain Project creates a cutting-edge HPC- and HPDA infrastructure to address such challenges including cloud-based collaboration and development platforms with databases, workflow systems, petabyte storage, and supercomputers."The post Video: Towards the Decoding of the Human Brain appeared first on insideHPC.
|
by staff on (#2V2BJ)
Last week at ISC 2017, the Russian RSC Group showcased its ultra high-dense scalable and energy efficient RSC Tornado cluster solution as well as a full set of components for modernizing HPC systems to become 100% hot liquid cooling. "The RSC Tornado is based on 72-core Intel Xeon PhiTM 7290 processor has established the world computing density record for x86 architecture in 1.41 Petaflops per cabinet or over 490 Teraflops/m3."The post RSC Group from Russia Brings Hot Water Cooling to HPC appeared first on insideHPC.
|
by Rich Brueckner on (#2V1WP)
SHIELD is an innovative interconnect technology that improves data center fault recovery by 5000 times by enabling interconnect autonomous self-healing capabilities. “The CPU-centric data center architecture has come to an end and new data centers are now built based on a data-centric architecture. These systems require an intelligent interconnect that can deliver In-Network Computing and Self-healing capabilities, to ensure highest performance, scalability and resiliency."The post Video: New Mellanox SHIELD Technology Enables Self Healing Networks appeared first on insideHPC.
|
by Rich Brueckner on (#2V1M6)
In this video from ISC 2017, Bill Wagner from Bright Computing describes the company's new capabilities for Cloud Bursting to Microsoft Azure. “Cloud bursting from an on-premises cluster to Microsoft Azure offers companies an efficient, cost-effective, secure and flexible way to add additional resources to their HPC infrastructure. Bright’s integration with Azure also gives our clients the ability to build an entire off-premises cluster for compute-intensive workloads in the Azure cloud platform.â€The post Bright Computing Steps up with Cloud Bursting to Azure at ISC 2017 appeared first on insideHPC.
|
by Rich Brueckner on (#2V1JG)
In this video from PASC17 in Lugano, Michele De Lorenzi from CSCS discussed the recent advancement of Piz Daint supercomputer to the #3 position on the TOP500. After that, he describes the mission of the PASC conference and the location of PASC18 next year.The post Interview: Piz Daint Supercomputer advances to the #3 position on the TOP500 appeared first on insideHPC.
|
by staff on (#2V1H0)
In this special guest feature, Andrew Jones from NAG offers his perspective on ISC 2017. How he came to know such things is a mystery as Mr. Jones did not attend the show this year. One thing is for sure; from now on I'm going to assume his agents are everywhere.The post Andrew Jones wraps up ISC 2017 appeared first on insideHPC.
|
by staff on (#2TZD5)
Researchers at the University of Texas at Arlington are using TACC supercomputers to study the unique traits of snake evolution. Led by assistant professor of biology Todd Castoe, the team is exploring the genomes of snakes and lizards to answer critical questions about these creatures' evolutionary history. For instance, how did they develop venom? How do they regenerate their organs? And how do evolutionarily-derived variations in genes lead to variations in how organisms look and function? "Some of the most basic questions drive our research. Yet trying to understand the genetic explanations of such questions is surprisingly difficult considering most vertebrate genomes, including our own, are made up of literally billions of DNA bases that can determine how an organism looks and functions," says Castoe. "Understanding these links between differences in DNA and differences in form and function is central to understanding biology and disease, and investigating these critical links requires massive computing power."The post Supercomputing the Secrets of the Snake Genome at TACC appeared first on insideHPC.
|
by staff on (#2TZ55)
This is the last of four articles on Intel Omni-Path Architecture (Intel OPA) next-generation fabric for high-performance computing (HPC) solutions. Intel OPA is in clusters used for traditional supercomputing, artificial intelligence (AI), HPC cloud, and in the enterprise.The post Intel Omni-Path Architecture: Incredible Momentum for a New Technology appeared first on insideHPC.
|
by Rich Brueckner on (#2TYZF)
Haohuan Fu from Tsinghua University in China at the PASC17 conference in Lugano. "This talk reports efforts on refactoring and optimizing the climate and weather forecasting programs – CAM and WRF – on Sunway TaihuLight. To map the large code base to the millions of cores on the Sunway system, OpenACC-based refactoring was taken as the major approach, with source-to-source translator tools applied to exploit the most suitable parallelism for the CPE cluster and to fit the intermediate variable into the limited on-chip fast buffer."The post Video: Scaling Climate and Weather Forecasting on Sunway TaihuLight appeared first on insideHPC.
|
by staff on (#2TYKC)
The 8th Irish Supercomputer List was released last week, featuring two new Top500-class machines. The new entrants, from an undisclosed software company, feature at spots 196 and 197 on the 49th Top500 Supercomputer List, each with a Linpack Rmax of 819.16 TFlop/s. This more than doubles the Irish HPC capacity, up from 1.46 PFlop/s to 3.01 Pflop/s.The post HPC Capacity Doubles on Irish Supercomputer List appeared first on insideHPC.
|
by Rich Brueckner on (#2TYHH)
We interrupt our stream of serious HPC news for this post-ISC update from Europe. "After ISC wrapped up last week, I had the good fortune to join the First Annual Lustre Motorcycle Tour of the Alps. This amazing three day trip to us through Italy, Switzerland, and Austria."The post Video: The Amazing Lustre through the Alps Tour appeared first on insideHPC.
|
by Rich Brueckner on (#2TYCQ)
The Proceedings from ISC 2017 are now available for download at no cost for a limited time. "We are pleased to announce that many fascinating topics in HPC are covered by the proceedings."The post Proceedings from ISC 2017 are now available for download appeared first on insideHPC.
|
by Rich Brueckner on (#2TWTG)
Today PEARC17 announced that 66 students will attend their conference coming up July 9-13 in New Orleans. PEARC17—Practice & Experience in Advanced Research Computing 2017—is for those engaged with the challenges of using and operating advanced research computing on campuses or for the academic and open science communities. This year’s inaugural conference offers a robust technical program, as well as networking, professional growth and multiple student participation opportunities.The post PEARC17 Seeds Next Generation of HPC Professionals appeared first on insideHPC.
|
by Rich Brueckner on (#2TW84)
In the world of HPC, moving data is a sin. That may be changing. "Just a few weeks ago, AIC announced the successful completion of a landmark, 1-petabyte transfer of data in 34 hours, during a recent test by Zettar that relied on the company's SB122A-PH, 1U 10-bay NVMe storage server. The milestone was reached using a unique 5000-mile 100Gbps loop which is a SDN layer over a shared, production 100G network operated by the US DOE's ESNet."The post How Zettar Transferred 1 Petabyte of Data in Just 34 Hours Using AIC Servers appeared first on insideHPC.
|
by staff on (#2TV1Y)
Today IBM announced they are collaborating with the U.S. Air Force Research Laboratory (AFRL) on a first-of-a-kind brain-inspired supercomputing system powered by a 64-chip array of the IBM TrueNorth Neurosynaptic System. The scalable platform IBM is building for AFRL will feature an end-to-end software ecosystem designed to enable deep neural-network learning and information discovery.The post AFRL Taps IBM to Build Brain-Inspired AI Supercomputer appeared first on insideHPC.
|
by Rich Brueckner on (#2TTMS)
The University of Oregon High Performance Computing Research Core Facility (HPCRCF) is seeking a Computational Scientist in our Job of the Week. The HPCRCF is a new facility located on the campus of the UO in Eugene, Oregon. The mission of the HPCRCF is to support computational research at the UO and collaborating institutions, and is home to a new flagship research cluster.The post Job of the Week: Computational Scientist at the University of Oregon appeared first on insideHPC.
|
by staff on (#2TR8R)
This week in Frankfurt, One Stop Systems showcased all-new HPC Appliances at ISC 2017. "One Stop Systems offers a wide variety of GPU and Flash appliances to support a range of customer needs,†Said Steve Cooper, CEO of One Stop Systems. “As GPU and flash technology continue to improve, OSS products are immediately able to accommodate the newest and most powerful GPUs and the highest capacity flash cards. Now we’re offering customers the opportunity to lease time on our HPC appliances through SkyScale. SkyScale utilizes OSS GPU appliances to build, configure, and manage dedicated systems strategically located in maximum-security facilities, allowing customers to focus on results while minimizing capital equipment investment.â€The post One Stop Systems Showcases GPU and Flash Appliances at ISC appeared first on insideHPC.
|
by Rich Brueckner on (#2TQEA)
In this RichReport podcast from the German Autobahn, Brent Gorda gives us a Lustre update from ISC 2017 in Frankfurt. "On the latest Top500 list, Lustre leads the pack with 9 systems out of the Top 10."The post Podcast: Brent Gorda on the State of Lustre at ISC 2017 appeared first on insideHPC.
|
by Rich Brueckner on (#2TQCM)
In this video, Kim McMahon describes her new role as Diversity Chair for the ISC 2018 conference. "ISC has named me the Diversity Chair for ISC18. With this comes a position on the Steering Committee. While this is really cool in and of itself, I am very excited about the industry luminaries, experts, and innovators that I’ll get to meet and work with. The list of people on the ISC Steering Committee is a Who’s Who of the HPC industry! I am deeply honored with the trust ISC has placed in me and look forward to the upcoming year’s activities."The post Kim McMahon on her role as Diversity Chair at ISC 2018 appeared first on insideHPC.
|
by staff on (#2TQAY)
Are you ready? ARM-based HPC systems will be available by the end of 2017. At ISC 2017, Penguin Computing and Bull both announced that they will deliver products tailored for the HPC industry. Both companies systems will feature Cavium’s ARMv8-based ThunderX2 platform.The post HPC Vendors showcase plans for ARM products appeared first on insideHPC.
|
by staff on (#2TMP3)
Flying drone aircraft are no longer rare sightings these day. In fact, their may be one above you somewhere taking pictures at this very moment. This begs the question: how do we keep our skies safe? "Scientists at NASA Langley Research Center have developed a breakthrough technology called Safeguard that can alleviate hazards with unmanned aircrafts (UA) flying beyond their authorized perimeters and into no-fly zones. Safeguard works by continuously detecting a UAs proximity to virtual perimeters established around no-fly-zones taking action to guarantee the perimeters are not breached.The post NASA’s Develops SAFEGUARD Safety Net Technology for Drones appeared first on insideHPC.
|
by staff on (#2TMMJ)
Over at Lenovo, Gavin O'Hara writes that the world's most beautiful supercomputer center now sports a 13.7 Petaflop system so novel in design that it has captured the attention of the global HPC community. It landed at #13 on the TOP500 this week, and that's just the beginning.The post Simply Beautiful: MareNorstum4 Supercomputer Sports 13.7 Petaflops appeared first on insideHPC.
|
by Richard Friedman on (#2TMJM)
Intel® Math Kernel Library 2017 (Intel® MKL 2017) includes new GEMM kernels that are optimized for various skewed matrix sizes. The new kernels take advantage of Intel® Advanced Vector Extensions 512 (Intel® AVX-512) and achieves high GEMM performance on multicore and many-core Intel® architectures, particularly for situations arising from deep neural networks..The post Deep Learning Frameworks Get a Performance Benefit from Intel MKL Matrix-Matrix Multiplication appeared first on insideHPC.
|
by staff on (#2THZR)
Today Inspur unveiled GX4, a new flexible and high scalability AI accelerating box at ISC 2017. The GX4 is able to achieve the decoupling coprocessor resources including CPU and GPU, Xeon Phi and FPGA, expand the computing power on demand, and provide highly flexible support to various AI applications in GPU-accelerated computing. This is another innovative effort followed by the release of the ultra-high density AI supercomputer AGX-2 last month at GTC 2017 in California. "According to Jay Zhang from Inspur, the GX4 sufficiently addresses the major differences in the AI deep-learning training model, using a flexible expansion method to support different levels of AI training models, and effectively lowering energy consumption and delays. The GX4 provides a flexible and innovative AI computing solution for companies and research organizations engaged in artificial intelligence across the world."The post Inspur Unveils GX4 Ai Accelerator appeared first on insideHPC.
|