by staff on (#5S1JR)
A team of collaborators from the U.S. Department of Energy’s Oak Ridge National Laboratory, Google Inc., Snowflake Inc. and Ververica GmbH has tested a computing concept that could help speed up real-time processing of data that stream on mobile and other electronic devices. The concept explores the function of watermarks, considered the most efficient mechanism […]The post ORNL, Google and Snowflake Formalize Novel Data Stream Processing Concept appeared first on insideHPC.
|
High-Performance Computing News Analysis | insideHPC
Link | https://insidehpc.com/ |
Feed | http://insidehpc.com/feed/ |
Updated | 2024-11-23 08:45 |
by staff on (#5S1GN)
A research team used machine-learned descriptions of interatomic interactions on the 200-petaflop Summit supercomputer at the US Department of Energy’s (DOE’s) Oak Ridge National Laboratory (ORNL) to model more than a billion carbon atoms at quantum accuracy and observe how diamonds behave under some of the most extreme pressures and temperatures imaginable. The team was led by scientists […]The post Research Team Uses Summit to Earn Gordon Bell Prize Nomination for Simulating Carbon in Extreme Conditions appeared first on insideHPC.
by staff on (#5S1ER)
Bing Xie, a high-performance computing systems engineer for the Oak Ridge Leadership Computing Facility, has received the Institute of Electrical and Electronics Engineers Computer Society’s Early Career Researchers Award for excellence in high-performance computing, or HPC. The award recognizes outstanding, influential and potentially long-lasting HPC contributions. Xie received her Ph.D. in computer science from Duke University […]The post OLCF’S HPC Systems Engineer Bing Xie Wins IEEE Early Career Award appeared first on insideHPC.
|
by staff on (#5S1ES)
Today, MLCommons released new results for MLPerf HPC v1.0, the organization’s machine learning training performance benchmark suite for high-performance computing (HPC). To view the results, visit https://mlcommons.org/en/training-hpc-10/. NVIDIA announced that NVIDIA-powered systems won four of five MLPerf HPC 1.0 tests, which measures training of AI models in three typical workloads for HPC centers: CosmoFlow estimates details […]The post MLPerf Releases Results for HPC v1.0 ML Training Benchmark appeared first on insideHPC.
|
by staff on (#5S15G)
We sat down with XTREME-D to get an update on the company’s supercomputing-as-service strategy and what the company will be highlighting during SC21. Speaking on behalf of the company are Daisuke Nagao, Senior Vice President and CTO; Andrei Vakhnin, chief HPC cloud architect; and Dr. David Barkai, technical advisor, about new developments in the company’s […]The post XTREME-D’s Evolving Supercomputing-as-a-Service Strategy appeared first on insideHPC.
by staff on (#5S15H)
The U.S. Department of Energy’s Office of Science announced allocations of supercomputer access to 51 high-impact computational science projects for 2022 through its Innovative and Novel Computational Impact on Theory and Experiment, or INCITE, program. These awards, which will pursue transformational advances in science and engineering, account for 60 percent of the available time on the […]The post INCITE Program Awards HPC Time to 51 Open Science Projects appeared first on insideHPC.
by staff on (#5S15J)
Siemens Energy, a supplier of power plant technology in the worldwide energy market, is relying on the NVIDIA Omniverse platform to create digital twins to support predictive maintenance of power plants. In doing so, Siemens Energy joins companies across industries using digital twins to enhance operations. Among them, BMW Group, which has 31 factories around the […]The post Siemens Energy Taps NVIDIA Omniverse for Power Plant Digital Twin appeared first on insideHPC.
by staff on (#5S15K)
We sat down with Penguin Computing President and CEO Sid Mair to talk about the interesting year his company — the developer of open, Linux-based solutions for enterprise data centers, HPC and cloud — has had in 2021 and about the latest development in the company’s strategy. Mair talks about the rapid emergence of the […]The post Penguin CEO Sid Mair Talks Origin AI and the Emergence of the ‘AI Infrastructure’ appeared first on insideHPC.
by staff on (#5S073)
SANTA CLARA, Calif. & SAN DIEGO — Fungible Inc., a data-centric computing company, and the San Diego Supercomputer Center (SDSC) at the University of California San Diego, today announced they have shattered the NVMe over TCP storage initiator performance world record, achieving 10M IOPS,* beating the old record of 6.55 IOPS. The tests were administered […]The post SDSC and Fungible Claim Record HPC Storage Performance appeared first on insideHPC.
by staff on (#5S074)
As the coronavirus pandemic entered its second year, a team of scientists from the U.S. Department of Energy’s Oak Ridge National Laboratory used the nation’s fastest supercomputer to streamline the search for potential treatments. “The approach we used to search for promising molecules resembles natural selection in fast forward,” said Andrew Blanchard, one of the […]The post ORNL Study on COVID-19 Earns Gordon Bell Prize Nomination appeared first on insideHPC.
by staff on (#5S05E)
SUNNYVALE, CALIF. – November 16, 2021 – Cerebras Systems, whose mission is to accelerate artificial intelligence (AI) compute, today announced at SC21 a new Cerebras Software Development Kit (SDK) designed to enable creation of new wafer-scale applications across computational fluid dynamics, molecular dynamics, signal processing, and more. The SDK is in Beta now and will be […]The post Cerebras Systems Launches Software Development Kit for Wafer-Scale Applications appeared first on insideHPC.
by staff on (#5S05F)
The development of the VTK-m toolkit, a scientific visualization toolkit for emerging architectures, is a critical advancement in support of scientific visualization on exascale and GPU-accelerated systems for high-performance computing (HPC) users. VTK-m is needed because—counterintuitively—GPUs currently have software challenges when supporting large-scale scientific visualization tasks. For historical reasons, their massively multithreaded architecture, separate memory subsystems, and advent of new visualization workflows, such as in situ and in transit visualization, that bypass data movement for big-data simulations are currently problematic for scientific visualization.The post ECP Brings Visualization Software to Exascale and GPU-accelerated HPC Systems appeared first on insideHPC.
|
by staff on (#5S04C)
TEL-AVIV, ISRAEL and SANTA CLARA, Calif.–November 16, 2021– Habana Labs, an Intel Company and developer of AI processors, today announced the availability of a turnkey, enterprise-class AI training solution featuring the Supermicro X12 Gaudi AI Training Server with the DDN AI400X2 Storage system. This system is the product of the collaboration of Habana Labs and […]The post Habana Labs Announces Turnkey AI Training Solution Featuring Supermicro Server and DDN Storage appeared first on insideHPC.
by staff on (#5RZY4)
insideHPC in association with the technology analyst firm OrionX.net today announced the launch of the @HPCpodcast, featuring OrionX.net analyst Shahin Khan and Doug Black, insideHPC’s editor-in-chief. @HPCpodcast is intended to be a lively and informative forum examining key technology trends driving high performance computing and artificial intelligence. Each podcast will feature Khan and Blacks’ comments […]The post insideHPC and OrionX.net Launch the @HPCpodcast appeared first on insideHPC.
by staff on (#5RZM5)
Nov. 16, 2021 — At SC21, Dell has announced new computer-aided engineering and design solutions, expanded HPC/AI managed services, a Dell EMC PowerSwitch and GPU accelerator options for PowerEdge servers, all designed for modeling and simulation-intensive workloads. In CAE, new Dell Technologies validated designs are available for Siemens Simcenter Star CCM+ computational fluid dynamics software. […]The post Dell Announces New CAE Solutions, PowerSwitch and GPU-Driven HPC Server Options appeared first on insideHPC.
by staff on (#5RZFE)
Moving high performance AI capabilities out to the edge – what One Stop Systems calls its “AI transportable” strategy – is the company’s mission. In this interview with OSS President and CEO David Raun, he updates us on edge computing modules and systems developed by the company over the past year and new developments it […]The post One Stop Systems: Transporting AI to the Edge appeared first on insideHPC.
by staff on (#5RZ20)
For tech enthusiasm, you’d be hard pressed to top Mike Scriber, senior director, Server Solutions Management, at Supermicro. In this interview, he talks about how the “server building block solutions” company, as it describes itself, has done in the HPC market in 2021 as well as what the company is featuring at SC21. In particular, […]The post Tech Enthusiast Mike Scriber Talks What’s New & Next at Supermicro appeared first on insideHPC.
by Doug Black on (#5RYRY)
Nov. 15, 2021 — IBM today announced a 127-quantum bit (qubit) ‘Eagle’ processor at the IBM Quantum Summit 2021. The company said the processor is a significant step toward tapping into the massive computing potential of devices based on quantum physics and “heralds the point in hardware development where quantum circuits cannot be reliably simulated […]The post IBM Unveils 127-Qubit Quantum Processor appeared first on insideHPC.
by staff on (#5RYPP)
November 15, 2021 — Atos and NVIDIA today announced the Excellence AI Lab (EXAIL), which brings together scientists and researchers to help advance European computing technologies, education and research. The lab’s first research projects will focus on five key areas enabled by advances in high performance computing and AI: climate research, healthcare and genomics, hybridization […]The post Atos and Nvidia Join to Launch European AI Lab appeared first on insideHPC.
by staff on (#5RYPQ)
SANTA CLARA, CA, U.S. – November 15, 2021 – Astera Labs, a maker of connectivity solutions for intelligent systems, today announced its new Taurus Smart Cable Module (Taurus SCM) portfolio designed to overcome performance bottlenecks in data center Switch-to-Switch and Switch-to-Server interconnects running up to 100G/Lane for 200/400/800 GbE. The Taurus SCM enables cloud system […]The post Astera Labs Targest 400/800G Ethernet Connectivity Bottlenecks with Smart Cable Modules appeared first on insideHPC.
by staff on (#5RYMF)
SANTA CLARA, CA, U.S. – November 15, 2021 – Astera Labs, make of connectivity solutions for intelligent systems, today announced its new Leo Memory Accelerator Platform for Compute Express Link (CXL) 1.1/2.0 interconnects to enable disaggregated memory pooling and expansion for processors, workload accelerators, and smart I/O devices. Leo overcomes processor memory bandwidth bottlenecks and […]The post Astera Labs Claims 1st CXL 2.0 Memory Accelerator SoC Platform appeared first on insideHPC.
by staff on (#5RYMG)
November 15, 2021 – Beaverton, OR – The CXL Consortium, an industry standards body dedicated to advancing Compute Express Link (CXL) technology, will showcase growing momentum for CXL technology at Supercomputing (SC21), taking place at America’s Center in St. Louis, Missouri and virtually November 15-18. The CXL specification enables a high-speed, efficient interconnect between the CPU and […]The post CXL Consortium at SC21: 1st Public Demo of Compute Express Link appeared first on insideHPC.
by staff on (#5RYHY)
The newest edition of the twice-yearly TOP500 list of the world’s most powerful supercomputers was released today at SC21 in St. Louis — with little change in the Top10. The Microsoft Azure system called Voyager-EUS2 was the only machine to shake up the top spots, claiming No. 10. Based on an AMD EPYC processor with […]The post TOP500: Little Change to HPC Top 10 appeared first on insideHPC.
|
by staff on (#5RYC8)
ST. LOUIS – NOVEMBER 15, 2021 – At SC21 today, MemVerge and the DMTCP Project announced a partnership designed to accelerate development and adoption of long-awaited Distributed MultiThreaded Checkpointing (DMTCP) technology. Checkpointing is commonly used by enterprise apps to minimize downtime but checkpointing is almost impossible for complex distributed HPC apps with massive data sets. […]The post MemVerge and Open Source Community Partnering to Protect Distributed HPC Apps with DMTCP appeared first on insideHPC.
by staff on (#5RY99)
Uli Plechschmidt brings extensive knowledge and good cheer to the deep challenges of high performance storage. In this interview, HPE’s worldwide product marketing for HPC storage offers a review course in the storage capabilities required for increasingly complex user environments encompassing HPC and AI. According to Plechschmidt, HPC-AI demands a mix of storage ingredients that […]The post HPE on the Critical Storage Elements for HPC-AI appeared first on insideHPC.
by staff on (#5RY6A)
Here’s a fascinating look at how a national lab works in partnership with advanced computing vendors to further the lab’s supercomputing mission. From Argonne National Laboratory’s leadership computing facility (ALCF) we have Bill Allcock, manager of the Advanced Integration Group, and Bill Nitzberg, CTO of PBS Works at Altair Engineering. The two talk about ALCF’s […]The post Altair and NVIDIA at Argonne: Using Workload Management Software to Maximize HPC Resources appeared first on insideHPC.
by staff on (#5RY6B)
Supercomputing 2021 – November 15, 2021 – Penguin Computing today announced GovPOD (Government Penguin On Demand) HPC/AI Cloud, built for federal government agencies featuring a software, hardware and management platform designed to eliminate performance, scalability, and security challenges associated with traditional cloud computing environments. GovPOD HPC/AI Cloud is designed to enable federal government customers to access a bare-metal, HPC […]The post Penguin Announces GovPOD HPC/AI Cloud On-Demand for the Federal Government appeared first on insideHPC.
|
by staff on (#5RY6C)
After more than a decade of discussion, planning, designing and system building, 2021 is expected to be the year that exascale-class computing finally arrives in the U.S. Hewlett Packard Enterprise is at the epicenter of this effort. The company is the prime contractor or system architect for the first three exascale systems to be delivered […]The post HPE’s Neil Dey Talks Exascale-class System Building appeared first on insideHPC.
by staff on (#5RY3N)
Europe’s leading HPC systems provider, Atos, is enjoying a successful 2021, highlighted by major contract wins, new product rollouts and the acquisition of US-based Nimbix, providing Atos with a ready-made cloud HPC capability. In this interview with Andy Grant, global head of sales, HPC, AI and Quantum at Atos, he reviews the past year’s achievements […]The post Atos Talks HPC, AI, Exascale and Quantum Strategies appeared first on insideHPC.
by staff on (#5RY3P)
Composable infrastructure company Liqid was one of the first entrants in that market segment, and the company has steadily built up its composable capabilities since its founding eight years ago. In this interview with Sumit Puri, Liqid CEO and co-founder, he says it’s all about “moving away from what we call ‘statically configured infrastructure’ to […]The post Liqid Expands Infrastructure Composability to GPUs appeared first on insideHPC.
by staff on (#5RY3Q)
Cloud HPC is one of the hottest segments of the HPC industry – yet it has a variety of iterations from various vendors. One of them, from the HPC industry’s leader for systems revenues, is in effect a private cloud offering that operates and is designed to deliver many of the benefits of a public […]The post HPE Greenlake: A Private HPC Cloud that Seems Public appeared first on insideHPC.
by staff on (#5RY3R)
Hewlett Packard Enterprise (NYSE: HPE) today announced it is building what it said will be one of Europe’s most powerful supercomputers to be installed and operated next year at CINES (National Computing Center for Higher Education), one of the three high performance computing (HPC) centers in France. The system was procured by GENCI, a national […]The post HPE Builds Supercomputer for France’s GENCI-CINES appeared first on insideHPC.
by staff on (#5RY1H)
Microsoft Azure early on took an aggressive stance in the cloud HPC segment, becoming, for example, one of the first to offer the InfiniBand interconnect on its public cloud platform. The strategy has paid off as cloud has become one of the fastest growing segments in the HPC industry. In this interview, Evan Burness, Azure’s […]The post How AMD Helps Push Azure’s HPC Strategy appeared first on insideHPC.
by staff on (#5RY1J)
Managers from two AI powerhouses, Nvida and NetApp, sat down with us to talk about their several years-long partnership, along with its latest developments, which are considerable. >From NetApp, Joey Parnell, senior member of technical staff, software; and from Nvidia, Premal Savla, director of product management, Deep Learning Systems, discuss a slew advancements across AI-related […]The post Nvidia and NetApp: What’s Coming Next from Their AI Partnership appeared first on insideHPC.
by staff on (#5RY1K)
In this interview with AMD’s Senior Product Manager, Datacenter and Embedded Solutions Group, Evan Groenke, he discusses the buzz around the company’s newly announced MI200 data center GPU, which AMD says is the most powerful on the market. Along with its speeds-and-feeds, Groenke discusses how AMD engineered the new accelerator and looks at the HPC […]The post AMD’s Evan Groenke on the New MI200 GPU appeared first on insideHPC.
|
by staff on (#5RY1M)
It’s been a good year for Inspur, as the company’s Global AI and HPC Director, Vangel Bojaxhi, explains in this SC21 interview. He shares updated market research numbers showing Inspur’s strong position in the global HPC and AI computing arenas, and he talks about the performance characteristics of its NF5448A5 server, showcased at the conference, […]The post Inspur: Growing Strength in HPC and AI appeared first on insideHPC.
by staff on (#5RY1N)
We caught up with Phil Murphy, CEO of fabrics technology company Cornelis Networks, which has one of the most interesting vendor histories in the HPC community. Extending back to the 1990s and carrying forward extensive interconnect R&D by both Intel and Cray, Cornelis’s OmniPath is a fabric uniquely well-suited to the increasingly heterogeneous world of […]The post Cornelis Networks Talks High Speed Fabrics for Heterogeneous HPC-AI appeared first on insideHPC.
by staff on (#5RT2Y)
The Argonne Leadership Computing Facility (ALCF) is building a testbed comprised of advanced artificial intelligence (AI) platforms. Designed to explore the possibilities of high-performance computing (HPC) architectures, the ALCF AI Testbed will enable the facility and its user community to help define the role of AI accelerators in next-generation scientific machine learning. “The testbed combines a […]The post ALCF Deploys Testbed to Advance AI for Science appeared first on insideHPC.
by staff on (#5RT02)
CHATSWORTH, Calif. – Nov. 11, 2021 – DDN, the artificial intelligence (AI) and multi-cloud data management company, today announced that it has joined with NVIDIA to establish an AI Innovation Lab in Singapore to drive innovation and accelerate the deployment of AI-based solutions for enterprises. The AI Innovation Lab will provide customers and partners the necessary infrastructure […]The post DDN Launches AI Innovation Lab with NVIDIA in Singapore appeared first on insideHPC.
by staff on (#5RSQK)
SC21, the biggest HPC confab of the year, is upon us, and making the most of the hybrid conference calls for good time management. As an assist to both in-person and virtual attendees we spoke with three industry thought leaders – Katie Antypas of NERSC, Earl Joseph of Hyperion Research and Addison Snell of Intersect360 Research – about conference events they think will be noteworthy.We cover key technologies to be covered by sessions and BOFs; significant HPC market trends (software, storage and cloud HPC in particular); the explosion of HPC+AI; the coming of exascale supercomputing....The post SC21: Three HPC Thought Leaders’ Planning Suggestions for the Hybrid Conference appeared first on insideHPC.
|
by staff on (#5RRAF)
SANTA CLARA, Calif. — Nov. 10, 2021 — AMD (NASDAQ: AMD) announced today that IBM Cloud has chosen 3rd Gen AMD EPYC processors to expand its bare metal service offerings designed to power customers’ demanding workloads and solutions. The new servers, featuring 128 cores, up to 4TB of memory and 10 NVMe drives per server, […]The post IBM Cloud Selects AMD EPYCs for Compute-Intensive Workloads appeared first on insideHPC.
|
by staff on (#5RR7H)
Building on its UK Met Office win, one of the largest supercomputer deals of the past year, Hewlett Packard Enterprise today announced that it is building a supercomputer for the United Weather Centres – West (UWC-West), a collaboration between the Danish Meteorological Institute, Icelandic Met Office, Met Éireann, Ireland’s national weather service, and the Royal Netherlands Meteorological Institute to advance […]The post HPE to Build Weather Supercomputer for Denmark, Iceland, Ireland and The Netherlands appeared first on insideHPC.
by staff on (#5RR2C)
Simulation software company Altair has announced that Argonne National Laboratory will utilize Altair PBS Professional workload manager across the organization’s HPC systems at the Argonne Leadership Computing Facility (ALCF) – including the Polaris and Aurora supercomputers – to accelerate research in science and engineering. PBS Professional – which replaces the ALCF’s in-house Cobalt workload manager […]The post Argonne Selects Altair Workload Manager for Polaris, Aurora appeared first on insideHPC.
|
by staff on (#5RPZP)
Microsoft Azure has announced that a preview is now live for Azure HBv3 virtual machines powered by 3rd Gen AMD EPYC processors with AMD 3D V-cache, codenamed “Milan-X.” The processors significantly improve the performance, scaling efficiency, and cost-effectiveness of a variety of memory performance-bound workloads, such as CFD, explicit finite element analysis, computational geoscience, weather […]The post Azure: HBv3 VMs for HPC up to 80% Faster with AMD Milan-X CPUs appeared first on insideHPC.
|
by staff on (#5RPSX)
SAN JOSE, November 9, 2021 – At this week’s OCP Global Summit in San Jose Inspur and Samsung will jointly launch the Poseidon V2 E3.x reference system. This product adopted composable architecture to maximize the benefits of EDSFF E3.x form factor. The Poseidon V2 system can accommodate not only the PCIe Gen5 SSDs but also various […]The post Inspur and Samsung Announce Joint Open Storage Solution for OCP appeared first on insideHPC.
by staff on (#5RPSY)
San Jose, November 9, 2021 – Super Micro Computer, Inc. (SMCI), maker of enterprise computing, storage, networking solutions, and green computing technology, announces the enhancement of its portfolio of artificial intelligence (AI) GPU servers which integrate new NVIDIA Ampere-family GPUs, including the NVIDIA A100, A30, and A2. Supermicro’s latest NVIDIA-certified systems deliver 10 times more […]The post Supermicro Adds to Portfolio of Edge-to-Cloud AI Systems appeared first on insideHPC.
|
by staff on (#5RPSZ)
NEW YORK and TEL AVIV — November 9, 2021 — Noogata, a no-code artificial intelligence (AI) data analytics for enterprises company, today announced the launch of its location analytics library. Building on the success of its existing ecommerce library, the location analytics library applies the power of Noogata’s no code AI data analytics platform to physical […]The post Noogata Launches AI Location Analytics Library for Bricks & Mortar Insights appeared first on insideHPC.
by staff on (#5RPT0)
LEESBURG, Va., Nov. 9, 2021 – Quantum Computing Inc. (Nasdaq: QUBT), whose mission is to brige the power of classical and quantum computing, announced that its Qatalyst quantum software was selected as one of three finalists for the final round of the BMW Group and Amazon Web Services (AWS) Quantum Computing Challenge for the Vehicle Sensor Placement use case. The […]The post BMW Group and AWS Pick QCI Qatalyst as Finalist in Quantum Computing Challenge appeared first on insideHPC.
by staff on (#5RPPE)
SEOUL, Korea – Nov. 9, 2021 – Samsung Electronics Co., Ltd. today said it has launched the industry’s first 14-nanometer (nm) based 16-gigabit (Gb) Low Power Double Data Rate 5X (LPDDR5X) DRAM, designed to drive further growth throughout the high-speed data service applications including 5G, artificial intelligence (AI) and the metaverse. “In recent years, hyperconnected […]The post Samsung Claims First 14nm, 16Gb DRAM appeared first on insideHPC.
|
by staff on (#5RNBN)
Continuing its long and impressive march back to prominence in data center and HPC-AI chips, AMD this morning announced the new Instinct MI200 GPU series, labeled by the company as “the first exascale-class GPU accelerators.” The product line includes the Instinct MI250X HPC-AI accelerator, built on AMD CDNA 2 architecture and providing up to 4.9X […]The post AMD Announces 4.9x HPC and AI Jump from Instinct MI200 Multi-die GPU appeared first on insideHPC.
|