Tagged: insideHPC Toggle Comment Threads | Keyboard Shortcuts

  • richardmitnick 3:24 pm on August 18, 2019 Permalink | Reply
    Tags: "Supercomputing Galactic Winds with Cholla", , Cholla, insideHPC,   

    From insideHPC: “Supercomputing Galactic Winds with Cholla” 

    From insideHPC

    August 18, 2019
    Elizabeth Rosenthal at ORNL


    In this video, a galactic wind simulation depicts interstellar gas and stars (red) and the outflows (blue) captured using the Cholla astrophysics code.

    2

    “Using the Titan supercomputer at Oak Ridge National Laboratory, a team of astrophysicists created a set of galactic wind simulations of the highest resolution ever performed. The simulations will allow researchers to gather and interpret more accurate, detailed data that elucidates how galactic winds affect the formation and evolution of galaxies.”

    ORNL Cray XK7 Titan Supercomputer, once the fastest in the world, to be decommissioned

    Brant Robertson of the University of California, Santa Cruz, and Evan Schneider of Princeton University developed the simulation suite to better understand galactic winds—outflows of gas released by supernova explosions—which could help explain variations in their density and temperature distributions.

    The improved set of galactic wind simulations will be incorporated into larger cosmological simulations.

    “We now have a much clearer idea of how the high speed, high temperature gas produced by clusters of supernovae is ejected after mixing with the cooler, denser gas in the disk of the galaxy,” Schneider said.”

    Cholla is a GPU-based hydrodynamics code I developed as part of my thesis work at the University of Arizona. It was designed to be massively-parallel and extremely efficient, and has been run on some of the largest supercomputers in the world. I am committed to keeping Cholla free and open-source. The most recent public release of the code can be found on GitHub.

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 3:13 pm on August 18, 2019 Permalink | Reply
    Tags: "Micron Starts Volume Production of 1z Nanometer DRAM Process Node", Advancement in DRAM scaling, , insideHPC, Micron Technology,   

    From insideHPC: “Micron Starts Volume Production of 1z Nanometer DRAM Process Node” 

    From insideHPC

    August 18, 2019

    1

    Today Micron Technology announced advancements in DRAM scaling, making Micron the first memory company to begin mass production of 16Gb DDR4 products using 1z nm process technology.

    “Development and mass production of the industry’s smallest feature size DRAM node are a testament to Micron’s world-class engineering and manufacturing capabilities, especially at a time when DRAM scaling is becoming extremely complex,” said Scott DeBoer, executive vice president of Technology Development for Micron Technology. “Being first to market strongly positions us to continue offering high-value solutions across a wide portfolio of end customer applications.”

    Micron’s 1z nm 16Gb DDR4 product delivers substantially higher bit density, as well as significant performance enhancements and lower cost compared to the previous generation 1Y nm node. It also reinforces Micron’s continued progress in delivering improvements in relative performance and power consumption for compute DRAM (DDR4), mobile DRAM (LPDDR4) and graphics DRAM (GDDR6) product lines. The optimized balance between power and performance will be a key differentiator for applications including, among others, artificial intelligence, autonomous vehicles, 5G, mobile devices, graphics, gaming, network infrastructure and servers.

    “Micron initiated the transition to 1z nm with mass production of its 16Gb DDR4 memory solution. Production using the smaller node delivers several benefits, including an approximately 40% reduction in power consumption compared to previous generations of 8Gb DDR4-based products. Micron’s comprehensive portfolio of 1z nm DDR4 products targets the growing need for better performance, higher density and reduced power consumption in the modern data center.”

    Separately, Micron is also announcing today that it has begun volume shipments of the industry’s highest-capacity monolithic 16Gb low-power double data rate 4X (LPDDR4X) DRAM in UFS-based multichip packages (uMCP4). Micron’s 1z nm LPDDR4X and uMCP4 address the needs of mobile device manufacturers seeking low power and smaller packages to design devices with attractive form factors and long battery life.

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 12:07 pm on August 13, 2019 Permalink | Reply
    Tags: "IBM Deploys Triton AI Supercomputer at University of Miami", , insideHPC,   

    From insideHPC: “IBM Deploys Triton AI Supercomputer at University of Miami” 

    From insideHPC

    August 13, 2019

    Today the University of Miami (UM) announced that their new Triton supercomputer is installed and helping their researchers explore new frontiers of science. The new supercomputer will be UM’s first GPU-accelerated HPC system, representing a completely new approach to computational and data science for the university’s campuses. Built using IBM Power Systems AC922 servers, the new HPC system was designed to maximize data movement between the IBM POWER9 CPU and attached accelerators like GPUs.

    With advances in artificial intelligence and science, we wanted to advance our research with this new generation of supercomputer and enable more discoveries,” said Nicholas Tsinoremas, director of the University of Miami Center for Computational Science and vice provost for data and research computing. “Advances in data science and big data drove us to this new technology.”

    1

    The new high-performance system uses the same AI-optimized architecture as the most powerful supercomputers in the world, the U.S. Department of Energy’s Summit and Sierra supercomputers.

    ORNL IBM AC922 SUMMIT supercomputer, No.1 on the TOP500. Credit: Carlos Jones, Oak Ridge National Laboratory/U.S. Dept. of Energy

    LLNL IBM NVIDIA Mellanox ATS-2 Sierra Supercomputer, NO.2 on the TOP500

    The $3.7 million system was assembled and validated distally by IBM and the University’s Center for Computational Science (CCS) personnel. CCS personnel along with UM investigators have been installing and testing software since its arrival to UM’s downtown facility last month.

    “Modern computational science requires a system that can handle the demands of Big Data, classic modeling and simulation, as well as the analytical techniques of artificial intelligence,” said David Turek, Vice President of Exascale Systems for IBM Cognitive Systems. “From the purpose-built hardware to the integrated machine learning and deep learning software stack, the IBM technology in Triton represents a new chapter in the way researchers approach data and computation.”

    “Some thought cloud-based computing would eliminate the need for supercomputers. However, many research projects with massive multi-dimensional datasets run much faster on these specially designed high-performance supercomputers like Triton,” said Ernie Fernandez, the University’s vice president for information technology and chief information officer. “Providing a hybrid environment at the University of Miami which offers both cloud options and a dedicated supercomputer is the best way to equip students and faculty to solve some of the world’s biggest problems.”

    The new supercomputer is designed to process data more efficiently, and students will be able to access the supercomputer from their laptops, log in and start processing data independently. Currently, about 1,500 people on UM’s three campuses utilize the supercomputer.

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 10:15 am on August 9, 2019 Permalink | Reply
    Tags: , Cray Shasta for US Air Force, insideHPC,   

    From insideHPC: “Cray Shasta Supercomputer to power weather forecasting for U.S. Air Force” 

    From insideHPC

    August 9, 2019

    Today Cray announced that their first Shasta supercomputing system for operational weather forecasting and meteorology will be acquired by the Air Force Life Cycle Management Center in partnership with Oak Ridge National Laboratory. The powerful high-performance computing capabilities of the new system, named HPC11, will enable higher fidelity weather forecasts for U.S. Air Force and Army operations worldwide. The contract is valued at $25 million.

    1

    “We’re excited with our Oak Ridge National Laboratory strategic partner’s selection of Cray to provide Air Force Weather’s next high performance computing system,” said Steven Wert, Program Executive Officer Digital, Air Force Life Cycle Management Center at Hanscom Air Force Base in Massachusetts, and a member of the Senior Executive Service. “The system’s performance will be a significant increase over the existing HPC capability and will provide Air Force Weather operators with the ability to run the next generation of high-resolution, global and regional models, and satisfy existing and emerging warfighter needs for environmental impacts to operations planning.”

    Oak Ridge National Laboratory (ORNL) has a history of deploying the world’s most powerful supercomputers and through this partnership, will provide supercomputing-as-a-service on the HPC11 Shasta system to the Air Force 557th Weather Wing. The 557th Weather Wing develops and provides comprehensive terrestrial and space weather information to the U.S. Air Force and Army. The new system will feature the revolutionary Cray Slingshot interconnect, with features to better support time-critical numerical weather prediction workloads, and will enhance the Air Force’s capabilities to create improved weather forecasts and weather threat assessments so that Air Force missions can be carried out more effectively.

    “The HPC11 system will be the first Shasta delivery to the production weather segment, and we’re proud to share this milestone with ORNL and the Air Force,” said Peter Ungaro, president and CEO at Cray. “The years of innovation behind Shasta and Slingshot and the success of prior generations of Cray systems continue to demonstrate Cray’s ability to support demanding 24/7 operations like weather forecasting. This is a great example of the upcoming Exascale Era bringing a new set of technologies to bear on challenging problems and empowering the Air Force to more effectively execute on its important mission.”


    In this video, Cray CTO Steve Scott announces Slingshot, the company’s new high-speed, purpose-built supercomputing interconnect, and introduces its many ground-breaking features.

    HPC11 will be ORNL’s first Cray Shasta system, as well as the first supercomputing system with 2nd Gen AMD EPYC™ processors for use in operational weather forecasting. HPC11 will join the 85% bastion of weather centers that rely on Cray, and will feature eight Shasta cabinets in a dual-hall configuration.

    “We are incredibly excited to continue our strategic collaboration with Cray to deliver the first Shasta supercomputer to the U.S. Air Force, helping to improve the fidelity of weather forecasts for U.S. military operations around the globe,” said Forrest Norrod, senior vice president and general manager, Datacenter and Embedded Systems Group, AMD. “The 2nd Gen AMD EPYC processors provide exceptional performance in highly complex workloads, a necessary component to power critical weather prediction workloads and deliver more accurate forecasts.”

    The system is expected to be delivered in Q4 2019 and accepted in early 2020.

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 1:31 pm on August 8, 2019 Permalink | Reply
    Tags: ALLOT-See.Control.Secure, , , insideHPC, Lenovo’s ThinkSystem SR635 and SR655,   

    From insideHPC: “Lenovo Launches Single Socket Servers with AMD EPYC 7002 Series” 

    From insideHPC

    2

    Today Lenovo introduced the Lenovo ThinkSystem SR635 and SR655 server platforms, two of the industry’s most powerful single-socket servers.

    3
    Lenovo ThinkSystem SR635 & SR655 Servers with AMD’s EPYC ‘Rome’ CPUs

    5

    As businesses are tasked with doing more with less, the new Lenovo solutions provide the performance of a dual-socket server at the cost of a single-socket. These new additions to Lenovo’s expansive server portfolio are powered by next-generation AMD EPYC 7002 Series processors and were designed specifically to handle customers’ evolving, data-intensive workloads such as video security, software-defined storage and network intelligence, as well as support for virtualized and edge environments. The result is a solution that packs power along with efficiency for customers who place a premium on balancing throughput and security with easy scalability.

    “Lenovo’s integration of next generation I/O and processing technology gives Allot the ability to manage more network bandwidth at higher speeds, allowing us to pull actionable insights from increasingly heavy traffic without any degradation in performance,” said Mark Shteiman, AVP of Product Management with Allot.

    2

    “The communication service providers and enterprises we support need to see and react to their network needs in real time. We evaluated Lenovo’s ThinkSystem SR635 and SR655 server platform prototypes and were immediately impressed.”

    Organizations are juggling business priorities with tight budgets. Lenovo’s new ThinkSystem SR635 and SR655 server platforms not only allow customers to run more workloads on fewer servers, but also offer up to 73 percent savings on potential software licensing, empowering users to accelerate emerging workloads more efficiently. Additionally, customers can realize a reduction in total cost of ownership (TCO) by up to 46 percent. Further supporting these advances in workload efficiency and TCO savings are the ThinkSystem SR635 and SR655 servers’ world records for energy efficiency. The net result of all these enhancements is better price for performance.

    The Lenovo ThinkSystem SR635 and SR655 provide more throughput, lower latency and higher core density, as well as the largest NVMe drive capacity of any single-socket on the market. Beyond that, the new 2nd Gen AMD EPYC processor based systems also provide a solid opportunity for the enablement of additional hyperconverged infrastructure solutions. This gives Lenovo the ability to offer customers VX and other certified nodes and appliances for simple deployment, management, and scalability.

    Unleashing Smarter Networks with Data Intelligence

    Many customers have been eagerly anticipating these systems due to their ability to handle data-intensive workloads, including Allot, a leading global provider of innovative network intelligence and security solutions for communications service providers (CSPs) and enterprises. They require solutions that can turn network, application, usage and security data into actionable intelligence that make their customers’ networks smarter and their users more secure. The market dictates that those solutions be able to match their ever-evolving needs and help them to address new pain points that surface as IT demands continue to change.

    ‘Lenovo’s integration of next generation I/O and processing technology gives Allot the ability to manage more network bandwidth at higher speeds, allowing us to pull actionable insights from increasingly heavy traffic without any degradation in performance,” said Mark Shteiman, AVP of Product Management with Allot. “The communication service providers and enterprises we support need to see and react to their network needs in real time. We evaluated Lenovo’s ThinkSystem SR635 and SR655 server platform prototypes and were immediately impressed.”

    The new Lenovo ThinkSystem SR635 and SR655 solutions are now available through Lenovo sales representatives and channel partners across the globe.

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 1:02 pm on August 8, 2019 Permalink | Reply
    Tags: , , Army Research Lab (ARL), , ERDC-U.S. Army Engineering and Research Development Center, insideHPC,   

    From insideHPC: “AMD to Power Two Cray CS500 Systems at Army Research Centers” 

    From insideHPC

    August 8, 2019

    Today Cray announced that the U.S. Department of Defense (DOD) has selected two Cray CS500 systems for its High Performance Computing Modernization Program (HPCMP) annual technology procurement known as TI-18.

    3

    The Army Research Lab (ARL) and the U.S. Army Engineering and Research Development Center (ERDC) will each deploy a Cray CS500 to help serve the U.S. through accelerated research in science and technology.

    2
    Cray CS500

    The two contracts are valued at more than $46M and the CS500 systems are expected to be delivered to ARL and ERDC in the fourth quarter of 2019.

    “We’re proud to continue to support the DOD and its advanced use of high-performance computing in providing ARL and ERDC new systems for their research programs,” said Peter Ungaro, CEO at Cray. “We’re looking forward to continued collaboration with the DOD in leveraging the capabilities of these new systems to achieve their important mission objectives.”

    Cray has a long history of delivering high-performance computing technologies to ARL and ERDC and continues to play a vital role in helping the organizations deliver on their missions to ensure the U.S. remains a leader in science. Both organizations’ CS500 systems will be equipped with 2nd Gen AMD EPYC processors and NVIDIA Tensor Core GPUs, and will provide access to high-performance capabilities and resources that make it possible for researchers, scientists and engineers across the Department of Defense to better understand insights and enable new discoveries across diverse research disciplines to address the Department’s most challenging problems.

    “We are truly proud to partner with Cray to create the world’s most powerful supercomputing platforms. To be selected to help accelerate scientific research and discovery is a testament to our commitment to datacenter innovation,” said Forrest Norrod, senior vice president and general manager, Datacenter and Embedded Solutions Business Group, AMD. “By leveraging breakthrough CPU performance and robust feature set of the 2nd Gen AMD EPYC processors with Cray CS500 supercomputers, the DOD has a tremendous opportunity to grow its computing capabilities and deliver on its missions.”

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 10:38 am on August 5, 2019 Permalink | Reply
    Tags: "Lenovo and Intel Collaboration to Extend HPC and AI Leadership", insideHPC, , Lenovo   

    From insideHPC: “Lenovo and Intel Collaboration to Extend HPC and AI Leadership” 

    From insideHPC

    August 5, 2019

    1
    “Intel chief executive officer Bob Swan and Navin Shenoy, Intel executive vice president and general manager of the Data Center Group, meet with Lenovo chief executive officer Yuanqing Yang and Kirk Skaugen, executive vice president and president, Lenovo Data Center Group to sign multiyear global collaboration agreement. (Credit: Intel Corporation)

    Today Intel and Lenovo announced a multiyear collaboration focused on the rapidly growing opportunity in the convergence of HPC and AI to help accelerate solutions for the world’s most challenging problems. Building on the companies’ long-standing partnership in the data center, the multiyear global collaboration will accelerate the convergence of HPC and AI, creating solutions for organizations of all sizes.

    “Our goal is to further accelerate innovation into the Exascale era, aggressively waterfalling these solutions to scientists and businesses of all sizes to accelerate discovery and outcomes. We are passionate in helping researchers solve humanity’s greatest challenges,” said Kirk Skaugen, executive vice president of Lenovo and president of Lenovo Data Center Group. “Lenovo’s Neptune liquid cooling, in combination with the 2nd Gen Intel Xeon Scalable platform, helps customers unlock new insights and deliver unprecedented outcomes at new levels of energy efficiency.”

    Lenovo, the leading global system provider of TOP500 supercomputers will be optimizing Intel’s full portfolio of HPC and AI hardware and software solutions to serve as the foundation for its market acceleration strategy. Working together, the companies aim to accelerate the convergence of HPC and AI to unlock new levels of customer insight. The combination of 2nd Gen Intel Xeon Scalable platform and Lenovo Neptune liquid cooling technology has already produced remarkable results from joint engineering and utilizing a unique combination of HPC IP from the two companies. Today, 173 of the world’s TOP500 fastest supercomputers, spanning 19 markets run on Lenovo servers [none in top 10]. Additionally, 17 of the world’s top 25 research universities rely on Lenovo infrastructure.

    “Intel is laser-focused on helping our customers accelerate innovation and discovery through the convergence of AI with HPC,” said Navin Shenoy, Intel executive vice president and general manager of the Data Center Group. “Our extended collaboration with Lenovo combines the best of both companies’ innovations to drive our customers’ progress forward even faster.”

    The multiyear collaboration plans to focus on three areas:

    Systems and solutions: The collaboration brings together the best of Lenovo’s portfolio, including Lenovo TruScale Infrastructure, and Intel’s leading-edge technologies, including Intel Xe computing architecture; Intel Optane DC persistent memory; Intel oneAPI programming framework; and both current and future generations of Intel Xeon Scalable processors, the only CPUs with the built-in AI acceleration of Intel Deep Learning Boost. This partnership will be critical as breakthrough HPC and AI technologies are cascaded to users of any size, or what Lenovo calls “From Exascale to Everyscale.”

    Software optimization for HPC and AI convergence: A key focus area will be building out Lenovo’s smarter software offerings, including optimizing Lenovo’s LiCO HPC/AI software stack for Intel’s next-generation technologies, and alignment with the Intel oneAPI programming framework. Additionally, the collaboration will focus on enabling DAOS advanced storage frameworks and other exascale-class software optimizations, targeted at helping HPC and AI users run their applications with greater ease than before.

    Ecosystem enablement: Additionally, Intel and Lenovo plan to partner to help create the new ecosystem for the convergence of HPC and AI. This includes building joint “HPC & AI centers of excellence” around the world to further enable research and university centers to develop solutions that address some of the most pervasive world challenges, including genomics, cancer, weather and climate, space exploration and more.

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 9:48 am on August 3, 2019 Permalink | Reply
    Tags: , ArcticDEM and REMA really showed what’s possible taking the poles from the worst to the best mapped regions of Earth., ArcticDEM was spurred by a 2015 Presidential Executive Order bringing together researchers from The Ohio State University and the University of Minnesota., Blue Waters Project, , EarthDEM and the data processed on Blue Waters will allow researchers a path to assess various research areas where major geological changes are occurring., Geospatial research projects, insideHPC, National Geospatial-Intelligence Agency (NGA), This research has allowed scientists to accurately track changes in the Arctic and Antarctic landscape and environment.   

    From insideHPC: “NCSA to help build world’s most powerful geospatial system” 

    From insideHPC

    NCSA has announced a new collaboration between the Blue Waters Project, the National Geospatial-Intelligence Agency (NGA), the University of Minnesota, and The Ohio State University to produce digital elevation models (DEM) of the entire Earth, among other geospatial research projects.

    2
    “We’re very excited to announce this relationship with NGA,” said NCSA Director William “Bill” Gropp. “This is the beginning of building a long-term strategic relationship between NGA and the University of Illinois, centered on high-performance computing and data analysis. The Blue Waters collaboration is the first of what we anticipate will be many years of research collaborations between NGA and Illinois faculty as well as NCSA.”

    NCSA U Illinois Urbana-Champaign Blue Waters Cray Linux XE/XK hybrid machine supercomputer

    The collaboration, which is proceeding with an initial $11.1 million in funding from the NGA through the National Science Foundation (NSF) for one year, will make Blue Waters the most powerful dedicated, non-classified geospatial system in the world, capable of bringing unprecedented speed and efficiency to global mapping, and fundamentally changing the way humans view the Earth.

    This collaboration will be a continuation of the existing Blue Waters machine and will leverage the Blue Waters Project’s domain expertise in optimizing workflows, applications, and complex data analysis, The Ohio State University’s programming domain expertise, and the University of Minnesota’s data flow domain expertise.

    “The NGA is one of the primary organizations whose mission is to keep the United States secure and safe,” said Bill Kramer, Blue Waters director at NCSA and research professor at Illinois’s Department of Computer Science. “They are pioneering new methods to understand the surface of our planet with advanced remote-sensing technology.”

    The first major project between the NGA and NCSA will be EarthDEM, a follow-up to the very successful ArcticDEM project, which was conducted on Blue Waters by the Polar Geospatial Center at the University of Minnesota. Now, with the help of Blue Waters and the NGA, EarthDEM seeks to apply the same mapping and data processing techniques to the rest of the Earth, producing planet-wide DEM data sets. Once completed, these elevation models will be available to the public and have applications in areas that directly benefit society, from community planning to water resources, landslide, and seismic activity assessments.

    EarthDEM and the data processed on Blue Waters will allow researchers a path to assess various research areas where major geological changes are occurring, no matter how remote the region, but what’s more, it will begin to create an ecosystem where geospatial modeling can be done quickly, efficiently and repeatedly.

    ArcticDEM was spurred by a 2015 Presidential Executive Order, bringing together researchers from The Ohio State University and the University of Minnesota. They used Blue Waters to interpret over 187,000 satellite images, ultimately taking these raw data, processing them, and producing the first-ever publicly available high-resolution digital elevation models of the entire Arctic. Furthermore, this collaboration expanded on ArcticDEM by performing the same process in the Antarctic, resulting in Reference Elevation Model of Antarctica (REMA), also publicly available.

    “ArcticDEM and REMA really showed what’s possible, taking the poles from the worst to the best mapped regions of Earth,” said Ian Howat, Director of Ohio State’s Byrd Polar and Climate Research Center. “With EarthDEM, we will take this transformative new capability to where most of us live, to cities and coastlines, that will directly impact their lives.”

    In turn, this research has allowed scientists to accurately track changes in the Arctic and Antarctic landscape and environment, which helps to quantify a changing landscape in one of the most remote and scientifically-impactful regions of Earth.

    “This agreement between NSF and NGA provides processing power that never before has been applied to geospatial data. The production of EarthDEM will change the way we see and measure the Earth’s surface,” said Paul Morin, Director of the Polar Geospatial Center at the University of Minnesota. “The continued operation of Blue Waters brings the dream of a global high-resolution digital surface model closer to reality.”

    Because of the importance and utility of these data sets, this new collaboration seeks to build and refine the pipeline for producing digital elevation models, leveraging different skills to greatly cut down on the time and cost to produce this impactful data.

    “In the past three and a half years, the ability to create production-quality digital elevation models from satellite data has revolutionized the way highly-accurate maps can be created, and with this collaboration we hope to build on that progress even further,” concluded Kramer.”

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 8:22 am on August 2, 2019 Permalink | Reply
    Tags: insideHPC, , Oregon State University   

    From insideHPC: “Oregon State University Invests $2.6 million in AI Computing Resources” 

    From insideHPC

    August 1, 2019

    1

    Oregon State University’s College of Engineering is accelerating its work in artificial intelligence, robotics, driverless vehicles and other areas by acquiring six advanced NVIDIA systems that give the college some of the most powerful computing resources among universities worldwide.

    “The computing power we now possess will accelerate our research in artificial intelligence and machine learning, while exposing our computer science students to the most advanced technology available in higher education,” said Scott Ashford, Kearney Professor and dean of the College of Engineering. “We are committed to continue to drive innovation in both research and education and will do so by providing faculty and students with the state-of-the-art capabilities needed.”

    The college has invested $2.6 million in a high-performance artificial intelligence computing cluster built using NVIDIA DGX-2 systems, which are in operation within OSU’s Kelley Engineering Center. NVIDIA, a world leader in computing systems for AI and machine learning, was founded by OSU alumnus Jensen Huang.

    The new infrastructure will allow computer science students access to the top tier of technology. In addition to AI and machine learning, the high-performance computing made possible by the graphical processing power will enhance the college’s work in parallel programming and medical imaging among other fields of study, Ashford added.

    “Researchers doing groundbreaking science demand the right instruments,” said Huang, NVIDIA’s chief executive officer. “For AI researchers, that instrument is a graphics processing supercomputer. Today’s announcement reflects OSU’s commitment to its researchers and seriousness to lead in AI research.”

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
  • richardmitnick 9:16 am on July 27, 2019 Permalink | Reply
    Tags: Accelerating High-Resolution Weather Models with Deep-Learning Hardware., insideHPC   

    From insideHPC: “Accelerating High-Resolution Weather Models with Deep-Learning Hardware” 

    From insideHPC

    July 26, 2019


    29:28
    In this video from PASC 2019, Sam Hatfield from the University of Oxford presents: Accelerating High-Resolution Weather Models with Deep-Learning Hardware.

    1

    “The next generation of weather and climate models will have an unprecedented level of resolution and model complexity, and running these models efficiently will require taking advantage of future supercomputers and heterogeneous hardware. In this paper, we investigate the use of mixed-precision hardware that supports floating-point operations at double-, single- and half-precision. In particular, we investigate the potential use of the NVIDIA Tensor Core, a mixed-precision matrix-matrix multiplier mainly developed for use in deep learning, to accelerate the calculation of the Legendre transforms in the Integrated Forecasting System (IFS), one of the leading global weather forecast models. In the IFS, the Legendre transform is one of the most expensive model components and dominates the computational cost for simulations at a very high resolution. We investigate the impact of mixed-precision arithmetic in IFS simulations of operational complexity through software emulation. Through a targeted but minimal use of double-precision arithmetic we are able to use either half-precision arithmetic or mixed half/single-precision arithmetic for almost all of the calculations in the Legendre transform without affecting forecast skill.”

    See the full article here .

    five-ways-keep-your-child-safe-school-shootings

    Please help promote STEM in your local schools.

    Stem Education Coalition

    Founded on December 28, 2006, insideHPC is a blog that distills news and events in the world of HPC and presents them in bite-sized nuggets of helpfulness as a resource for supercomputing professionals. As one reader said, we’re sifting through all the news so you don’t have to!

    If you would like to contact me with suggestions, comments, corrections, errors or new company announcements, please send me an email at rich@insidehpc.com. Or you can send me mail at:

    insideHPC
    2825 NW Upshur
    Suite G
    Portland, OR 97239

    Phone: (503) 877-5048

     
c
Compose new post
j
Next post/Next comment
k
Previous post/Previous comment
r
Reply
e
Edit
o
Show/Hide comments
t
Go to top
l
Go to login
h
Show/Hide help
shift + esc
Cancel
%d bloggers like this: