DOCSLIB.ORG

Interconnect Your Future Enabling the Best Datacenter Return on Investment

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Interconnect Your Future Enabling the Best Datacenter Return on Investment Interconnect Your Future Enabling the Best Datacenter Return on Investment TOP500 Supercomputers, June 2017 InfiniBand Accelerates Majority of New Systems on TOP500 . InfiniBand connects 2.5 times more new systems versus OmniPath . EDR InfiniBand solutions grew 2.5X in six months . Mellanox accelerates the fastest supercomputer in the world . InfiniBand provides 1.7X Higher ROI for Petascale Platforms . Mellanox connects 39% of overall TOP500 systems (192 systems, InfiniBand and Ethernet) . InfiniBand connects 36% of the total TOP500 systems (179 systems) . InfiniBand connects 60% of the HPC TOP500 systems . InfiniBand accelerates 48% of the Petascale systems . Mellanox connects all of 40G Ethernet systems, connects the first 100G Ethernet system on the list InfiniBand is the Interconnect of Choice for HPC Infrastructures Enabling Machine Learning, High-Performance, Web 2.0, Cloud, Storage, Big Data Applications © 2017 Mellanox Technologies 2 Mellanox Connects the World’s Fastest Supercomputer National Supercomputing Center in Wuxi, China #1 on the TOP500 List . 93 Petaflop performance, 3X higher versus #2 on the TOP500 . 41K nodes, 10 million cores, 256 cores per CPU . Mellanox adapter and switch solutions * Source: “Report on the Sunway TaihuLight System”, Jack Dongarra (University of Tennessee) , June 20, 2016 (Tech Report UT-EECS-16-742) © 2017 Mellanox Technologies 3 InfiniBand Accelerates Artificial Intelligence (AI) and Deep Learning Facebook AI Supercomputer #31 on the TOP500 List NVIDIA AI Supercomputer #32 on the TOP500 List . EDR InfiniBand In-Network Computing technology key for scalable Deep Learning systems . RDMA accelerates Deep Learning performance by 2X, becomes de-facto solution for AI © 2017 Mellanox Technologies 4 Mellanox In the TOP500 . Mellanox accelerates the fastest supercomputer on the list . InfiniBand most used HPC interconnect in first half of 2017 . InfiniBand connects 2.5X more new end-user projects versus Omni-Path, and 3X more versus other proprietary products . Mellanox connects nearly 39 percent of overall TOP500 systems (192 systems, InfiniBand and Ethernet) . InfiniBand connects 36 percent of the total TOP500 systems (179 systems) . InfiniBand connects 60 percent of the HPC TOP500 systems . InfiniBand accelerates 48 percent of the Petascale systems . EDR InfiniBand installations grew 2.5X in six months . InfiniBand provides 1.7X higher system efficiency for Petascale systems versus OmniPath . Mellanox connects all of 40G Ethernet systems . Mellanox connects the first 100G Ethernet system on the list . InfiniBand is the most used Interconnect on the TOP500 for TOP100, TOP200, and TOP300 systems . InfiniBand is the preferred interconnect for Artificial Intelligence and Deep Learning systems . Mellanox solutions enable highest ROI for Machine Learning, High-Performance, Cloud, Storage, Big Data and more applications Paving The Road to Exascale Performance © 2017 Mellanox Technologies 5 TOP500 Interconnect Trends The TOP500 List has Evolved to Include Both HPC and Cloud / Web2.0 Hyperscale Platforms. For the HPC Platforms, InfiniBand Continues it’s Leadership as the Most Used Interconnect Solution for High-Performance Compute and Storage Infrastructures © 2017 Mellanox Technologies 6 TOP500 Petascale-Performance Systems InfiniBand is the Interconnect of Choice for Petascale Computing Accelerates 48% of the Petaflop Systems © 2017 Mellanox Technologies 7 InfiniBand Solutions – TOP100, 200, 300, 400, 500 InfiniBand is The Most Used Interconnect of the TOP100, 200, 300, 400 Supercomputers Superior Performance, Scalability, Efficiency and Return-On-Investment © 2017 Mellanox Technologies 8 InfiniBand Solutions – TOP100, 200, 300, 400, 500 HPC Systems Only (Excluding Cloud, Web2.0 etc. Systems) InfiniBand is The Most Used Interconnect For HPC Systems Superior Performance, Scalability, Efficiency and Return-On-Investment © 2017 Mellanox Technologies 9 Maximum Efficiency and Return on Investment . Mellanox smart interconnect solutions enable In-Network Computing and CPU-Offloading . Critical with CPU accelerators and higher scale deployments . Ensures highest system efficiency and overall return on investment InfiniBand Omni-Path System: NASA, System Efficiency: 84% System: CINECA, System Efficiency: 57% System: NCAR, System Efficiency: 90% System: Barcelona, System Efficiency: 62% System: US Army, System Efficiency: 94% System: TACC, System Efficiency: 53% 1.7X Higher System Efficiency! 43% System Resources not Utilized! © 2017 Mellanox Technologies 10 InfiniBand Delivers Best Return on Investment 30-100% Higher Return on Investment Up to 50% Saving on Capital and Operation Expenses Highest Applications Performance, Scalability and Productivity Molecular Genomics Weather Automotive Chemistry Dynamics 1.3X Better 2X Better 1.4X Better 1.7X Better 1.3X Better © 2017 Mellanox Technologies 11 InfiniBand Delivers Better Price/Performance Over Competition Example: Supercomputer for Other Vehicle Development (Memory, Chassis etc.) Omni-Path Other (Memory, Chassis etc.) 42% Reduction Other InfiniBand in System Cost! (Memory, Chassis etc.) 10 of Top 10 CPUs InfiniBand Automotive CPUs Manufacturers CPUs Use Mellanox ~2X Lower Cost for Similar System Performance! © 2017 Mellanox Technologies 12 The Advantages of HDR InfiniBand Solutions Maximum Performance and Highest Return on Investment World’s First World’s First 200G Switch 200G Adapter © 2017 Mellanox Technologies 13 The Generation of 200G HDR InfiniBand 40-Ports 200G 128K Nodes 4.6X Higher Scalability 80-Ports 100G 3-Level Fat Tree 15.6 Billion 200G Data Speed Messages / Sec 2X Higher Throughput Collective Operations MPI Tag Matching In-Network Computing 5-10X Faster 2X Faster World’s First World’s First 200G Switch 200G Adapter © 2017 Mellanox Technologies 14 Highest-Performance 100Gb/s and 200Gb/s Interconnect Solutions 200Gb/s Adapter, 0.6us latency 200 million messages per second (10 / 25 / 40 / 50 / 56 / 100 / 200Gb/s) 40 HDR (200Gb/s) InfiniBand Ports 80 HDR100 InfiniBand Ports Throughput of 16Tb/s, <90ns Latency 32 100GbE Ports, 64 25/50GbE Ports (10 / 25 / 40 / 50 / 100GbE) Throughput of 6.4Tb/s Transceivers Active Optical and Copper Cables (10 / 25 / 40 / 50 / 56 / 100 / 200Gb/s) VCSELs, Silicon Photonics and Copper © 2017 Mellanox Technologies 15 Interconnect Technology: The Need for Speed and Intelligence 400G NDR Homeland Cosmological Brain Security Simulations Mapping Human The Large Hadron 200G HDR Collider (CERN) Weather Genome OpenFOAM LS-DYNA (CFD) 100G EDR (FEA) SPEED 56G FDR 40G QDR SIZE 100 Nodes 1,000 Nodes 10,000 Nodes 100,000 Nodes 1,000,000 Nodes © 2017 Mellanox Technologies 16 The Intelligent Interconnect Overcomes Performance Bottlenecks CPU-Centric (Onload) Data-Centric (Offload) Must Wait for the Data Analyze Data as it Moves! Creates Performance Bottlenecks Faster Data Speeds and In-Network Computing Enable Higher Performance and Scale © 2017 Mellanox Technologies 17 In-Network Computing Enables Data-Centric Data Center Faster Data Speeds and In-Network Computing Enable Higher Performance and Scale © 2017 Mellanox Technologies 18 In-Network Computing Advantages with SHARP Technology Critical for High Performance Computing and Machine Learning Applications © 2017 Mellanox Technologies 19 SHIELD – Self Healing Interconnect Technology © 2017 Mellanox Technologies 20 Mellanox to Connect Future #1 HPC Systems (Coral) “Summit” System “Sierra” System Paving the Path to Exascale © 2017 Mellanox Technologies 21 End-to-End Interconnect Solutions for All Platforms Highest Performance and Scalability for X86, Power, GPU, ARM and FPGA-based Compute and Storage Platforms 10, 20, 25, 40, 50, 56, 100 and 200Gb/s Speeds X86 POWER GPU ARM FPGA Smart Interconnect to Unleash The Power of All Compute Architectures © 2017 Mellanox Technologies 22 InfiniBand The Smart Choice for HPC Platforms and Applications “We chose a co-design approach supporting in the “In HPC, the processor should be going 100% of “One of the big reasons we use InfiniBand and not best possible manner our key applications. The only the time on a science question, not on a an alternative is that we’ve got backwards communications question. This is why the compatibility with our existing solutions.” interconnect that really could offload capability of Mellanox‘s deliver that was Mellanox’s InfiniBand.” network is critical.” Watch Video Watch Video Watch Video “InfiniBand is the most advanced interconnect “We have users that move tens of terabytes of data “InfiniBand is the best that is required for our technology in the world, with dramatic and this needs to happen very, very rapidly. applications. It enhances and unlocks communication overhead reduction that fully InfiniBand is the way to do it.” the potential of the system.” unleashes cluster performance.” Watch Video Watch Video Watch Video © 2017 Mellanox Technologies 23 Proven Advantages . Scalable, intelligent, flexible, high performance, end-to-end connectivity . Standards-based (InfiniBand, Ethernet), supported by large eco-system . Supports all compute architectures: x86, Power, ARM, GPU, FPGA etc. Offloading architecture: RDMA, application acceleration engines, etc. Flexible topologies: Fat Tree, Mesh, 3D Torus, Dragonfly+, etc. Converged I/O: compute, storage, management on single fabric . Backward and future compatible The Future Depends On Smart Interconnect © 2017 Mellanox Technologies 24 TOP500 Mellanox Accelerated Supercomputers Examples © 2017 Mellanox Technologies 25 Wuxi Supercomputing Center – World’s
Load more

Recommended publications
  • Performance Evaluation of the Intel Sandy Bridge Based NASA
    Performance Evaluation of the Intel Sandy Bridge Based NASA Pleiades Using Scientific and Engineering Applications Subhash Saini, Johnny Chang, Haoqiang Jin NASA Advanced Supercomputing Division NASA Ames Research Center Moffett Field, California 94035-1000, USA {subhash.saini, johnny.chang, haoqiang.jin}@nasa.gov Abstract — We present a performance evaluation of Pleiades based based on the Many Integrated Core (code-named Knight’s on the Intel Xeon E5-2670 processor, a fourth-generation eight-core Corner) architecture and Yellowstone [1, 5, 6]. New and Sandy Bridge architecture, and compare it with the previous third extended features of Sandy Bridge architecture are: generation Nehalem architecture. Several architectural features have been incorporated in Sandy Bridge: (a) four memory channels as a) A ring to connect on-chip L3 cache with cores, system opposed to three in Nehalem; (b) memory speed increased from 1333 agent, memory controller, and QPI agent and I/O MHz to 1600 MHz; (c) ring to connect on-chip L3 cache with cores, controller to increase the scalability. L3 cache per core system agent, memory controller, and QPI agent and I/O controller to has been increased from 2 MB to 2.5 MB. increase the scalability; (d) new AVX unit with wider vector registers of 256 bit; (e) integration of PCI-Express 3.0 controllers into the I/O b) New micro-ops (L0) cache that caches instructions as subsystem on chip; (f) new Turbo Boost version 2.0 where base they are decoded. The cache is direct mapped and can frequency of processor increased from 2.6 to 3.2 GHz; and (g) QPI link store 1.5 K micro-ops.
    [Show full text]
  • President Lands at Moffett Field During Silicon Valley Visit by Huong Nguyen and Jessica Culler President Barack Obama’S Arrival Onboard Air Force One on Sunday, Sept
    Fall 2011 - A Quarterly Publication Thousands turn out to tour airborne observatory at Ames The Stratospheric Observatory for In- frared Astronomy (SOFIA) visited NASA Ames and provided a rare opportunity to tour the airborne observatory in October. News media and Ames employees were invited to tour on Friday, Oct. 14 and the public on Saturday, Oct. 15. On Friday, an estimated 2,500 people, including representatives from CNET, Fox News, KQED (PBS), New Scientist, Space. com, Mountain View Patch and the San Mateo Daily Journal attended the event. On Saturday, an estimated 5,500 people visited Ames to tour SOFIA. See page 6 for a feature about the SOFIA visit. NASA photo by Doiminic Hart President lands at Moffett Field during Silicon Valley visit BY HUONG NGUYEN AND JESSICA CULLER President Barack Obama’s arrival onboard Air Force One on Sunday, Sept. 25, 2011, at Moffett Federal Airfield marked his first land- ing at NASA Ames. Center Director Pete Worden met President Barack Obama upon his arrival. "I had the honor to meet President Obama when he arrived at Moffett Federal Airfield," said Worden, who along with San Jose Mayor Chuck Reed and Mountain View Mayor Jac Siegel, greeted the president. "It was fitting that the president came to Silicon Valley to talk about his job creation plan, given how critical Silicon Valley is to the future of the U.S. economy," Worden said. NASA Ames is an integral com- ponent of the world-renowned inno- vation economy and actively partici- pates in the valley’s technological Photo credit: Official White House Photo by Pete Souza and scientific evolution.
    [Show full text]
  • The Outer Limits
    Welcome to the outer limits Budapest, March 19, 2013 M.Sc. Ji ří Hlavá č HPC consultant + sales manager for CEE [email protected] ©2012 Silicon Graphics International Corp. / Presented Only Under Non-Disclosure Agreement 1 Jiri Hlavac (by Czech Ji ří Hlavá č) 51 years old, 4 children … • MSc. Computers (1986) • Development of PC OSs for Tesla Czech (1986-1989) • Own SW company (1986-1991) • Owner SGI Distributor @ Czechoslovakia (1991-1995) • Employee @ SGI Czech office (1995-now) • Technical Director, Academic Sales, Enterprise Sales • HPC Consultant (2001-2011) • Sales Manager for Central + East Europe (2005-now) ©2012 Silicon Graphics International Corp. / Presented Only Under Non-Disclosure Agreement 2 SGI = Experts @ HPC Structural Mechanics Structural Mechanics Computational Fluid Electro-Magnetics Implicit Explicit Dynamics Computational Chemistry Computational Chemistry Computational Biology Seismic Processing Quantum Mechanics Molecular Dynamics Reservoir Simulation Rendering / Ray Tracing Climate / Weather Data Analytics Ocean Simulation ©2012 Silicon Graphics International Corp. / Presented Only Under Non-Disclosure Agreement 3 SGI = Focus on every detail (here Power Consumption) ©2012 Silicon Graphics International Corp. / Presented Only Under Non-Disclosure4 Agreement 4 SGI = Frontier @ Research SGI = Winner of last HPCwire Readers' Choice Award (Nov 2012) for "Top Supercomputing Achievement" for SGI contribution to the NASA Ames Pleiades supercomputer. SGI = Winner of last HPCwire Editor's Choice Award (Nov 2012) for "Best use of HPC in 'edge HPC‘ application" for Wikipedia historical mapping and exploration on UV 2000. SGI stock is growing 5 ©2012 Silicon Graphics International Corp. / Presented Only Under Non-Disclosure5 Agreement 5 Advanced Energy Exploration and Production Total: World's Largest Commercial HPC System (2.3 PF) SGI ICE ©2012 Silicon Graphics International Corp.
    [Show full text]
  • NASA Announces a New Approach to Earth Science Data Analysis 20 April 2010
    NASA Announces A New Approach To Earth Science Data Analysis 20 April 2010 (PhysOrg.com) -- The way we analyze planet Earth than ten hours. will never be the same, thanks to a new initiative at NASA that integrates supercomputers with global NEX uses a new approach for collaboration among satellite observations and sophisticated models of scientists and science teams working to model the the Earth system in an online collaborative Earth system and analyze large Earth observation environment. As part of its celebration of Earth datasets. Using on-line collaboration technologies, Week, NASA unveiled the NASA Earth Exchange NEX will bring together geographically dispersed (NEX) at a “Green Earth” public forum held at the multi-disciplinary groups of scientists focused on NASA Exploration Center, Moffett Field, Calif. global change research. Scientists will be able to build custom project environments containing the By making NEX available, NASA expects to better datasets and software components needed to solve enable scientists to collaboratively conduct complex Earth science problems. These project research and address the impacts of changes in environments, built using virtualization technology, climate and land use patterns on ecosystems. NEX will be highly portable and reusable and will will link NASA’s supercomputing resources with automatically capture the entire analysis process, massive Earth system data sets, and provide a including the data and processing steps required to collection of tools for analysis and visualization. replicate the results in an open and transparent way. For example, results from the processing of "Currently, it can require months for scientists to the global Landsat data would be available to gather and analyze global-scale data sets, due to scientists with the additional expertise required to computing limitations, data storage requirements analyze rates of urbanization, deforestation, or and network bandwidth constraints”, said biodiversity impacts.
    [Show full text]
  • Performance Evaluation of the Intel Sandy Bridge Based NASA
    NAS Technical Report: NAS-2015-05 Performance Evaluation of the Intel Sandy Bridge Based NASA Pleiades Using Scientific and Engineering Applications Subhash Saini, Johnny Chang, Haoqiang Jin NASA Advanced Supercomputing Division NASA Ames Research Center Moffett Field, California 94035-1000, USA {subhash.saini, johnny.chang, haoqiang.jin}@nasa.gov Abstract — We present a performance evaluation of Pleiades based based on the Many Integrated Core (code-named Knight’s on the Intel Xeon E5-2670 processor, a fourth-generation eight-core Corner) architecture and Yellowstone [1, 5, 6]. New and Sandy Bridge architecture, and compare it with the previous third extended features of Sandy Bridge architecture are: generation Nehalem architecture. Several architectural features have been incorporated in Sandy Bridge: (a) four memory channels as a) A ring to connect on-chip L3 cache with cores, system opposed to three in Nehalem; (b) memory speed increased from 1333 agent, memory controller, and QPI agent and I/O MHz to 1600 MHz; (c) ring to connect on-chip L3 cache with cores, controller to increase the scalability. L3 cache per core system agent, memory controller, and QPI agent and I/O controller to has been increased from 2 MB to 2.5 MB. increase the scalability; (d) new AVX unit with wider vector registers of 256 bit; (e) integration of PCI-Express 3.0 controllers into the I/O b) New micro-ops (L0) cache that caches instructions as subsystem on chip; (f) new Turbo Boost version 2.0 where base they are decoded. The cache is direct mapped and can frequency of processor increased from 2.6 to 3.2 GHz; and (g) QPI link store 1.5 K micro-ops.
    [Show full text]
  • Project Status Report High End Computing Capability Strategic Capabilities Assets Program December 10, 2014
    Project Status Report High End Computing Capability Strategic Capabilities Assets Program December 10, 2014 Dr. Rupak Biswas – Project Manager NASA Ames Research Center, Moffett Field, CA [email protected] (650) 604-4411 www.nasa.gov Pleiades Achieves 3.38 Petaflops, Ranks 7th in U.S. and 11th Worldwide on TOP500 List • On the November 2014 TOP500 list of the world’s Mission Impact: Enhancing NASA’s most powerful most power supercomputers, Pleiades ranked 7th in supercomputer and running subsequent diagnostic the U.S. and 11th worldwide, with an impressive tests enables HECC to validate the entire system, improving stability for all jobs. efficiency of 84.6%. The new list was released on November 17 at the SC14 conference in New Orleans (see slide 11). • The HECC Systems team worked with SGI engineers to complete system-wide testing on Pleiades, including a LINPACK benchmark run, prior to the release of new Intel Haswell processors for general production on October 27. • During the LINPACK run, Pleiades delivered a sustained performance of 3.38 petaflops using 73% of its compute nodes, representing 89% of the theoretical peak of the overall system. The benchmark was run on 1,024 Haswell nodes, 5,365 Pleiades’ increased LINPACK benchmark performance since 2008, when Ivy Bridge nodes, and 1,792 Sandy Bridge nodes. the original system was installed at the NASA Advanced Supercomputing (NAS) facility. The initial configuration achieved a sustained performance • In addition to measuring performance, the of 0.487 petaflops and 80% efficiency in benchmark testing. With the latest LINPACK run helped the Systems team detect upgrade, Pleiades achieved 84.6% efficiency on the LINPACK benchmark.
    [Show full text]
  • Pleiades • the NASA Workload • System Build Strategy • Operational Strategy • Tools and Analysis Software • Issues Do We See • Whats Lustre Does • What We Want
    NASA SuperComputing A Ground Based Instrument for Exploration and Discovery LUG 2015 Bob Ciotti Chief Architect/Supercomputing Systems Lead LUG 2015 - Denver LUG - Denver Apr 2015 Discussion • What is Pleiades • The NASA Workload • System Build Strategy • Operational Strategy • Tools and Analysis Software • Issues Do We See • Whats Lustre Does • What We Want LUG - Denver Apr 2015 Supercomputing Support for NASA Missions Jet aircraft wake vortices Jet engine • Agency wide resource noise • Production Supercomputing emissions • Focus on availability • Machines mostly run large ensembles • Some very large calculations (50k) Orbiting, Spinning – Typically o500 jobs running Detailed CLV Black Holes Geometry • Example applications • ARMD – LaRC: Jet wake vortex simulations, to increase airport capacity and safety – GRC: Understanding jet noise simulations, to decrease airport noise • ESMD – ARC: Launch pad flame trench simulations for Ares vehicle safety analysis – MSFC: Correlating wind tunnel tests and simulations of Solar surface Ares I-X test vehicle – ARC/LaRC: High-fidelity CLV flight simulation with convection detailed protuberances • SMD – Michigan State: Ultra-high-resolution solar surface convection simulation – GSFC: Gravity waves from the merger of orbiting, spinning black holes • SOMD – JSC/ARC: Ultra-high-resolution Shuttle ascent analysis • NESC – KSC/ARC: Initial analysis of SRB burn risk in Vehicle 2-SRB Burn Assembly Building in VAB Shuttle Ascent Configuration 3 LUG - Denver Apr 2015 LUG - Denver Apr 2015 ECCO – Ocean Modeling
    [Show full text]
  • NASA Advanced Supercomputing Division
    Fold here Fold here CMYK logo 8.5 x 17 Trifold Modeling & Simulation NAS High-End Computing Environment Facts National Aeronautics and Space Administration NAS expertise in fundamental and applied Pleiades modeling and simulation is essential to creating • Primary production system for all NASA mission directorates large-scale simulations supporting critical • SGI ICE X cluster connected via InfiniBand in an 11D hypercube topology NASA engineering and design decisions. Our • 126,720 cores (Intel Xeon quad-, six-, and eight-core processors) fundamental research advances numerical • 1.75 petaflop/s peak; 1.24 petaflop/s sustained performance (June 2012) methods, algorithms, and code development • 233 terabytes total memory for aeronautics research, while applied • 64 nodes enhanced with Nvidia graphics processing units modeling enables large-scale numerical simulations in several important mission areas. hyperwall-2 • 128-screen, tiled LCD wall displays, processes, and shares data—can display a single image across In support of NASA’s project to design the all screens, or can display unique images in selected “cells” heavy-lift Space Launch System, NAS compu- • Custom Colfax International system connected to Pleiades via InfiniBand NASA ADVANCED SUPERCOMPUTING DIVISION tational fluid dynamics experts developed (over 100 gigabytes-per-second connectivity) specialized software and performed thousands • 128 nodes; 2 quad-core (AMD Opteron 2354) processors per node of simulations to analyze aerodynamic • 136 Nvidia Fermi GTX 480 processors
    [Show full text]
  • NASA, Intel, SGI Plan to 'Soup Up' Supercomputer
    May 7, 2008 NASA, Intel, SGI Plan to 'Soup Up' Supercomputer MOFFETT FIELD, Calif.--(BUSINESS WIRE)-- NASA, Intel Corp., and SGI today announced the signing of an agreement establishing intentions to collaborate on significantly increasing the space agency's supercomputer performance and capacity. Under the terms of a Space Act Agreement, NASA will work closely with Intel and SGI to increase computational capabilities for modeling and simulation at the NASA Advanced Supercomputing (NAS) facility at NASA's Ames Research Center, Moffett Field, Calif. "Achieving such a monumental increase in performance will help fulfill NASA's increasing need for additional computing capacity and will enable us to provide the computational performance and capacity needed for future missions," said Ames Director S. Pete Worden. "This additional computational performance is necessary to help us achieve breakthrough scientific discoveries." NASA Ames, Intel and SGI will work together on a project called Pleiades to develop a computational system with a capacity of one Petaflops peak performance (1,000 trillion operations per second) by 2009 and a system with a peak performance of 10 Petaflops (10,000 trillion operations per second) by 2012. "Throughout its history, NASA has sought to explore the most compelling questions about mankind, Earth, and the worlds that await our discovery," said Robert "Bo" Ewald, chief executive officer of SGI. "SGI is proud to be part of this effort. These groundbreaking new systems powered by SGI and fueled by the latest multi-core Intel processors, offer a platform for new discoveries that will help us all achieve the most promising future for the human race.
    [Show full text]
  • An Automated Bolide Detection Pipeline for GOES GLM
    Highlights An Automated Bolide Detection Pipeline for GOES GLM Jeffrey C. Smith,Robert L. Morris,Clemens Rumpf,Randolph Longenbaugh,Nina McCurdy,Christopher Henze,Jessie Dotson • GOES Geostationary Lightning Mappers can be used to detect bolides. • A Random Forest detection algorithm has been deployed on the NASA Advanced Supercomputing facility Pleiades supercomputer. • Bolide light curves are promptly published on a NASA hosted publicly accessible website, https://neo-bolide.ndc.nasa.gov. arXiv:2106.09189v1 [astro-ph.EP] 17 Jun 2021 An Automated Bolide Detection Pipeline for GOES GLM a,b < a,b b,c d Jeffrey C. Smith , , Robert L. Morris , Clemens Rumpf , Randolph Longenbaugh , b b b Nina McCurdy , Christopher Henze and Jessie Dotson aThe SETI Institute, 189 Bernardo Ave, Suite 200, Mountain View, CA 94043, USA bNASA Ames Research Center, Moffett Field, CA 94035, USA cSTC, NASA Research Park, Moffett Field, CA 94035, USA dSandia National Laboratories, Albuquerque, NM 87185, USA ARTICLEINFO ABSTRACT Keywords: The Geostationary Lightning Mapper (GLM) instrument onboard the GOES 16 and 17 satellites Bolide detection has been shown to be capable of detecting bolides (bright meteors) in Earth’s atmosphere. Due to GOES GLM its large, continuous field of view and immediate public data availability, GLM provides a unique Random forest classifier opportunity to detect a large variety of bolides, including those in the 0.1 to 3 m diameter range and complements current ground-based bolide detection systems, which are typically sensitive to smaller events. We present a machine learning-based bolide detection and light curve generation pipeline being developed at NASA Ames Research Center as part of NASA’s Asteroid Threat Assessment Project (ATAP).
    [Show full text]
  • 33Rd TOP500 List
    33rd TOP500 List ISC’ 09, Hamburg Agenda • Welcome and Introduction (H.W. Meuer) • TOP10 and Awards (H.D. Simon) • Hig hlig hts of the 30th TOP500 (E. ShiStrohmaier) • HPC Power Consumption (J. Shalf) • Multicore and Manycore and their Impact on HPC (J. J. Dongarra) • Discussion 33rd List: The TOP10 Rmax Power Rank Site Manufacturer Computer Country Cores [Tflops] [MW] Roadrunner 1 DOE/NNSA/LANL IBM USA 129,600 1,105.0 2.48 BladeCenter QS22/LS21 Oak Ridge National Jaguar 2 Cray Inc. USA 150,152 1,059.0 6.95 Laboratory Cray XT5 QC 2.3 GHz Forschungszentrum Jugene 3 IBM Germany 294,912 825.50 2.26 Juelich (FZJ) Blue Gene/P Solution NASA/Ames Pleiades 4 Research SGI USA 51,200 487.0 2.09 SGI Altix ICE 8200EX Center/NAS BlueGene/L 5 DOE/NNSA/LLNL IBM USA 212,992 478.2 2.32 eServer Blue Gene Solution University of Kraken 6 Cray USA 66,000 463.30 Tennessee Cray XT5 QC 2.3 GHz ANtilArgonne National ItIntrep id 7 IBM USA 163,840 458.61 1.26 Laboratory Blue Gene/P Solution Ranger 8 TACC/U. of Texas Sun USA 62,976 433.2 2.0 SunBlade x660420 Dawn 9 DOE/NNSA/LANL IBM USA 147,456 415.70 1.13 Blue Gene/P Solution Forschungszentrum JUROPA 10 Sun/Bull SA Germany 26,304 274.80 1.54 Juelich (FZJ) NovaScale /Sun Blade The TOP500 Project • Listing the 500 most powerful computers in the world • Yardstick: Rmax of Linpack – Solve Ax=b, dense problem, matrix is random • Update twice a year: – ISC’ xy in June in Germany • SCxy in November in the U.S.
    [Show full text]
  • NASA HEC BDTF V2-Tagged
    National Aeronautics and Space Administration NASA Supercomputing, Big Data, and a Vision for the Future Compute Services Presented at NASA Big Data Task Force Meeting January 16, 2016 Tsengdar Lee – [email protected], NASA Headquarters High Performance Computing Program Manager with HECC and NCCS teams www.nasa.gov Agenda • NASA Supercomputing Program • Changing Workload from Big Compute to Big Data • Big Compute + Big Data = New Compute Service 2 High-end Computing at NASA • The mission of NASA's High-End Computing (HEC) Program is to: • Plan and provision HEC systems and services to support NASA's mission needs. • Operate and manage these HEC resources for the benefit of agency users, customers, and stakeholders. •The HEC Program manages two projects, which serve all three NASA Mission Directorates: Aeronautics (ARMD), Human Exploration and Operations (HEOMD), Science (SMD), and Space Technology (STMD). HECC provides world-class NCCS offers an integrated set high-end computing, of supercomputing, storage, and associated visualization, and data services to enable scientists interaction technologies to and engineers supporting enhance NASA capabilities in NASA missions to broadly weather and climate and productively employ prediction and enable future large-scale modeling, scientific discoveries that will simulation, and analysis to benefit humankind. It serves achieve successful mission hundreds of users at NASA outcomes. It supports 1,200 centers, laboratories, and users from NASA and universities across the U.S. around the U.S. HECC is NCCS is run by the run by the NASA Advanced Computational and Supercomputing (NAS) Information Sciences and Division at Ames Research Technology Office (CISTO) at Center.
    [Show full text]