ENDURING DIFFERENTIATION Timothy Lanfear
|
|
- Cynthia Bruce
- 5 years ago
- Views:
Transcription
1 ENDURING DIFFERENTIATION Timothy Lanfear WHERE ARE WE? 2 LIFE AFTER DENNARD SCALING GPU-ACCELERATED PERFORMANCE Years of Microprocessor Trend Data Single-threaded perf Transistors (thousands) 1.5X per year 1.1X per year AMBER Performance (ns/day) AMBER 12 CUDA 4 K20 AMBER 14 CUDA 5 K40 AMBER 14 CUDA 6 K80 AMBER 16 CUDA 8 P GoogleNet Performance (i/s) cudnn 2 CUDA 6 8x K80 cudnn 4 CUDA 7 8x Maxwell cudnn 6 CUDA 8 NCCL 1.6 DGX-1 cudnn 7 CUDA 9 NCCL 2 DGX-1V Original data up to the year 2010 collected and plotted by M. Horowitz, F. Labonte, O. Shacham, K. Olukotun, L. Hammond, and C. Batten New plot and data collected for by K. Rupp
2 GFLOPS per Watt TESLA PLATFORM ADVANTAGE TESLA VALUE: $15-20M COST SAVINGS DELIVERED Delivered value grows over time GPU-ACCELERATED EFFICIENCY Life Sciences (AMBER) Oil & Gas (RTM) 13/13 Greenest Supercomputers Powered by Tesla P100 On Track To Meet Exascale Goal 35 10X Perf in 8 Years 6X Perf in 6 Years TSUBAME 3.0 Kukai AIST AI Cloud RAIDEN GPU subsystem Piz Daint Wilkes-2 GOSAT-2 (RCF2) DGX Saturn V Reedbush-H JADE Facebook Cluster Cedar DAVIDE Eurotech Aurora K Tsubame- KFC K20X 5.3 TiTech W780I K SaturnV P100 V TSUBAME 3.0 P GF/W Exascale Goal Amber performance: Nano Seconds Per Day delivered on 1xServer with GPUs and CPUS 5 Top GPU Systems in Green500 Lists and NVIDIA Projections for V100 6 HOW ARE WE DOING THIS? And, is our differentiation sustainable? What are the most important dimensions of our differentiation? Why are GPUs so much more efficient than CPUs? How can we continue scaling performance/efficiency as Moore s Law fades? ENERGY EFFICIENCY Why can t competitors replicate GPU efficiency, performance, scaling, etc., with lots of weak CPU cores? (e.g., Intel KNC/KNL/KNM) How is optimizing GPUs for AI affecting their suitability for HPC? 7 8
3 COMPUTATION VERSUS COMMUNICATIONS 64-bit DP 20 pj 26 pj 256 pj CPU 126 pj/flop (SP) GPU 28 pj/flop (SP) 256-bit access 8 kb SRAM 50 pj 256 bits pj DRAM Rd/Wr Optimized for Latency Deep Cache Hierarchy Optimized for Throughput Explicit Management of On-chip Memory 500 pj Efficient off-chip link 1000 pj 20mm 28nm IC 9 Broadwell E5 v4 14 nm Pascal 16 nm 10 ALU 6% Register File 11% HOW IS POWER SPENT IN A CPU? In Order, Embedded Data Supply 17% Clock + Control Logic 24% Instruction Supply 42% Out of Order, High Performance Issue 11% RF 14% ALU 4% Rename 10% Data Supply 5% Fetch 11% Clock + Pins 45% Payload Arithmetic 15pJ Overhead 985pJ Dally [2008] (Embedded in-order CPU) Natarajan [2003] (Alpha 21264) 11 12
4 SIMPLER CORES = ENERGY EFFICIENCY Payload Arithmetic 15pJ Overhead 15pJ Source: Azizi [PhD 2010] RISE OF LEAKAGE THROUGHPUT PROCESSORS 15 16
5 GFLOPS / watt FREQUENCY VS. LEAKAGE OPTIMIZED FOR DATACENTER EFFICIENCY 40% More Performance in a Rack V100 Max Performance V100 Max Efficiency Computer Vision Computer Vision Source: Gordon Moore, Intel; IEEE 17 80% Perf at Half the Power 13 KW Rack 4 Nodes of 8xV ResNet-50 Networks Trained Per Day 13 KW Rack 7 Nodes of 8xV ResNet-50 Networks Trained Per Day 19 ResNet-50 Training, Max Efficiency run with V100@160W V100 performance measured on pre-production hardware. 25 SP ENERGY 28 NM HETEROGENEOUS COMPUTING Fermi Kepler Maxwell 20 21
6 OPTIMIZING SERIAL/PARALLEL EXECUTION Application Code TWO TYPES OF ACCELERATORS GPU Parallel Work Majority of Ops Serial Work System and Sequential Ops CPU Many-Weak-Cores (MWC) Model Single CPU Core for Both Serial & Parallel Work Xeon Phi (And Others) Many Weak Serial Cores Heterogeneous Computing Model Complementary Processors Work Together CPU Optimized for Serial Tasks GPU Accelerator Optimized for Parallel Tasks NVLINK: A MEMORY FABRIC, NOT A NETWORK DGX-1: 8 NVLink-Connected GPUs EXTENSIBILITY 24 25
7 Speed-up vs 1 KNL Server Node Speed-up vs 1 KNL Server Node Speed-up vs 1x KNL Server LATENCY HIDING FOR LOAD/STORE/ATOMICS Where are the NICs? There are no NICs. STRONG SCALING GPU-Accelerated Server NVIDIA DGX-1 AlexNet Training DGX-1 Faster than 128 Knights Landing Servers 40x 30x 20x 10x GPU-Accelerated Server 0x Knights Landing Servers 1x DGX STRONG SCALING STRONG SCALING LAMMPS: Molecular Dynamics 8x Tesla P100 PCIe Server Faster than 32 KNL Servers GTC-P: Plasma Turbulence 8x Tesla P100 PCIe Server Faster than 64 KNL Servers Gflop/s LQCD- Higher Energy Physics SATURNV DGX Servers vs SuperMUC Supercomputer # of CPU Servers to Match Performance of SATURNV 40x 10x 25,000 35x 30x 25x 20x 15x 10x 5x 8x P100: 35x Faster 4x P100: 21x Faster 2x P100: 13x Faster 0x # of KNL Nodes 8x 6x 4x 2x 8x P100: 8x Faster 4x P100 2x P100 0x # of KNL Nodes 20,000 15,000 10,000 5, x DGX-1: 20K Gflop/s 2x DGX-1: 15K Gflop/s 1x DGX-1: 8K Gflop/s 3K Gflop/s 2K Gflop/s 5K Gflop/s 7K Gflop/s # of CPU Nodes (in SuperMUC Supercomputer) 2,300 CPU Servers S3D: Discovering New Fuel for Engines 3,800 CPU Servers SPECFEM3D: Simulating Earthquakes 28 QUDA version 0.9beta, using double-half mixed precision DDalphaAMG using double-single 29
8 NEW TENSOR CORE New CUDA TensorOp instructions and data formats 4 4 matrix processing array D FP32 = A FP16 B FP16 + C FP32 TESLA PLATFORM Optimized for deep learning Activation Inputs Weights Inputs Output Results TESLA IS A PLATFORM World s Leading Data Center Platform for Accelerating HPC and AI MULTIPLE GROWTH MARKETS APPLICATIONS INTERNET SERVICES Automotive Retail Defense Healthcare Manufacturing Finance ENTERPRISE APPLICATIONS HPC +450 Applications 10M Users 40 years of video/day GROWTH MARKETS INDUSTRY FRAMEWORKS & TOOLS FRAMEWORKS ECOSYSTEM TOOLS HPC AI Training AI Inference Desktop Virtualization Video Transcoding NVIDIA SDK cudnn TensorRT NCCL cublas cusparse DEEP LEARNING SDK DeepStream SDK COMPUTEWORKS TESLA PLATFORM TESLA GPU & SYSTEMS TESLA GPU NVIDIA DGX-1 NVIDIA HGX-1 SYSTEM OEM CLOUD 32 33
9 V100 Performance Normalized to P100 PASCAL TO VOLTA Architecture with Technology Area: ~600 mm 2 ~800 mm 2 (~33% more area) CONCLUSION Process: ~ small Pascal Volta improvement (a few percent) Clocks: similar dynamic range, power limited Memory BW (sustained): 50% improvement Communications (NVLink): 160 GB/s 300 GB/s (almost double!) AI (Tensor Cores): ~20 TFLOPS 120 TFLOPS (~6x!) REVOLUTIONARY PERFORMANCE FOR HPC AND AI Single Platform For Data Science and Computation Science 1.5X HPC Performance In 1 Year 3X AI Performance in 1 Year GPU PERFORMANCE COMPARISON P100 V100 Ratio Training acceleration 10 TOPS 120 TOPS 12x 2X CPU 15 Days Inference acceleration 21 TFLOPS 120 TOPS 6x FP64/FP32 5/10 TFLOPS 7.5/15 TFLOPS 1.5x 1X P Hours HBM2 Bandwidth 720 GB/s 900 GB/s 1.2x Molecular Dynamics (VMD) Physics (QUDA) Seismic (RTM) STREAM 1X V100 6 Hours LSTM ( Neural Machine Translation) NVLink Bandwidth 160 GB/s 300 GB/s 1.9x L2 Cache 4 MB 6 MB 1.5x L1 Caches 1.3 MB 10 MB 7.7x NMT Training for 13 Epochs German ->English, WMT15 subset System Config Info: CPU = 2x Xeon E V4 w/ P100s or V100s QUDA, RTM, STREAM System Config Info: 2X Xeon E v4, 2.6GHz, w/ 1X Tesla P100 or V100. VMD System Config Info: Xeon E5-2698v3 w/ 1x Tesla P100 and E5-2697Av4 w/ 1x Tesla V100 V100 measured on pre-production hardware
10 GPU TRAJECTORY APPLICATIONS ALGORITHMS SYSTEMS GPU-Computing perf 1.5X per year 1.1X per year 1000X by 2025 CUDA Single-threaded perf 1.5X per year ARCHITECTURE Original data up to the year 2010 collected and plotted by M. Horowitz, F. Labonte, O. Shacham, K. Olukotun, L. Hammond, and C. Batten New plot and data collected for by K. Rupp 38
ENDURING DIFFERENTIATION. Timothy Lanfear
ENDURING DIFFERENTIATION Timothy Lanfear WHERE ARE WE? 2 LIFE AFTER DENNARD SCALING 10 7 40 Years of Microprocessor Trend Data 10 6 10 5 10 4 Transistors (thousands) 1.1X per year 10 3 10 2 Single-threaded
More informationMACHINE LEARNING WITH NVIDIA AND IBM POWER AI
MACHINE LEARNING WITH NVIDIA AND IBM POWER AI July 2017 Joerg Krall Sr. Business Ddevelopment Manager MFG EMEA jkrall@nvidia.com A NEW ERA OF COMPUTING AI & IOT Deep Learning, GPU 100s of billions of devices
More informationPOWERING THE AI REVOLUTION JENSEN HUANG, FOUNDER & CEO GTC 2017
POWERING THE AI REVOLUTION JENSEN HUANG, FOUNDER & CEO GTC 2017 LIFE AFTER MOORE S LAW 10 7 40 Years of Microprocessor Trend Data 10 6 10 5 Transistors (thousands) 1.1X per year 10 4 10 3 1.5X per year
More informationACCELERATED COMPUTING: THE PATH FORWARD. Jensen Huang, Founder & CEO SC17 Nov. 13, 2017
ACCELERATED COMPUTING: THE PATH FORWARD Jensen Huang, Founder & CEO SC17 Nov. 13, 2017 COMPUTING AFTER MOORE S LAW Tech Walker 40 Years of CPU Trend Data 10 7 GPU-Accelerated Computing 10 5 1.1X per year
More informationTimothy Lanfear, NVIDIA HPC
GPU COMPUTING AND THE Timothy Lanfear, NVIDIA FUTURE OF HPC Exascale Computing will Enable Transformational Science Results First-principles simulation of combustion for new high-efficiency, lowemision
More informationTHE PATH TO EXASCALE COMPUTING. Bill Dally Chief Scientist and Senior Vice President of Research
THE PATH TO EXASCALE COMPUTING Bill Dally Chief Scientist and Senior Vice President of Research The Goal: Sustained ExaFLOPs on problems of interest 2 Exascale Challenges Energy efficiency Programmability
More informationEfficiency and Programmability: Enablers for ExaScale. Bill Dally Chief Scientist and SVP, Research NVIDIA Professor (Research), EE&CS, Stanford
Efficiency and Programmability: Enablers for ExaScale Bill Dally Chief Scientist and SVP, Research NVIDIA Professor (Research), EE&CS, Stanford Scientific Discovery and Business Analytics Driving an Insatiable
More informationHETEROGENEOUS HPC, ARCHITECTURAL OPTIMIZATION, AND NVLINK STEVE OBERLIN CTO, TESLA ACCELERATED COMPUTING NVIDIA
HETEROGENEOUS HPC, ARCHITECTURAL OPTIMIZATION, AND NVLINK STEVE OBERLIN CTO, TESLA ACCELERATED COMPUTING NVIDIA STATE OF THE ART 2012 18,688 Tesla K20X GPUs 27 PetaFLOPS FLAGSHIP SCIENTIFIC APPLICATIONS
More informationGPU COMPUTING AND THE FUTURE OF HPC. Timothy Lanfear, NVIDIA
GPU COMPUTING AND THE FUTURE OF HPC Timothy Lanfear, NVIDIA ~1 W ~3 W ~100 W ~30 W 1 kw 100 kw 20 MW Power-constrained Computers 2 EXASCALE COMPUTING WILL ENABLE TRANSFORMATIONAL SCIENCE RESULTS First-principles
More informationTESLA V100 PERFORMANCE GUIDE May 2018
TESLA V100 PERFORMANCE GUIDE May 2018 TESLA V100 The Fastest and Most Productive GPU for AI and HPC Volta Architecture Tensor Core Improved NVLink & HBM2 Volta MPS Improved SIMT Model Most Productive GPU
More informationA NEW COMPUTING ERA JENSEN HUANG, FOUNDER & CEO GTC CHINA 2017
A NEW COMPUTING ERA JENSEN HUANG, FOUNDER & CEO GTC CHINA 2017 TWO FORCES DRIVING THE FUTURE OF COMPUTING 10 7 Transistors (thousands) 10 6 10 5 1.1X per year 10 4 10 3 10 2 1.5X per year Single-threaded
More informationA NEW COMPUTING ERA. Shanker Trivedi Senior Vice President Enterprise Business at NVIDIA
A NEW COMPUTING ERA Shanker Trivedi Senior Vice President Enterprise Business at NVIDIA THE ERA OF AI AI CLOUD MOBILE PC 2 TWO FORCES DRIVING THE FUTURE OF COMPUTING 10 7 Transistors (thousands) 10 5 1.1X
More informationTESLA PLATFORM. Jan 2018
TESLA PLATFORM Jan 2018 A NEW ERA OF COMPUTING AI & IOT Deep Learning, GPU 100s of billions of devices MOBILE-CLOUD iphone, Amazon AWS 2.5 billion mobile users PC INTERNET WinTel, Yahoo! 1 billion PC users
More informationSYNERGIE VON HPC UND DEEP LEARNING MIT NVIDIA GPUS
SYNERGIE VON HPC UND DEEP LEARNING MIT NVIDIA S Axel Koehler, Principal Solution Architect HPCN%Workshop%Goettingen,%14.%Mai%2018 NVIDIA - AI COMPUTING COMPANY Computer Graphics Computing Artificial Intelligence
More informationTOWARDS ACCELERATED DEEP LEARNING IN HPC AND HYPERSCALE ARCHITECTURES Environnement logiciel pour l apprentissage profond dans un contexte HPC
TOWARDS ACCELERATED DEEP LEARNING IN HPC AND HYPERSCALE ARCHITECTURES Environnement logiciel pour l apprentissage profond dans un contexte HPC TERATECH Juin 2017 Gunter Roth, François Courteille DRAMATIC
More informationNVIDIA PLATFORM FOR AI
NVIDIA PLATFORM FOR AI João Paulo Navarro, Solutions Architect - Linkedin i am ai HTTPS://WWW.YOUTUBE.COM/WATCH?V=GIZ7KYRWZGQ 2 NVIDIA Gaming VR AI & HPC Self-Driving Cars GPU Computing 3 GPU COMPUTING
More informationCME 213 S PRING Eric Darve
CME 213 S PRING 2017 Eric Darve Summary of previous lectures Pthreads: low-level multi-threaded programming OpenMP: simplified interface based on #pragma, adapted to scientific computing OpenMP for and
More informationWorld s most advanced data center accelerator for PCIe-based servers
NVIDIA TESLA P100 GPU ACCELERATOR World s most advanced data center accelerator for PCIe-based servers HPC data centers need to support the ever-growing demands of scientists and researchers while staying
More informationDeep Learning and HPC. Bill Dally, Chief Scientist and SVP of Research January 17, 2017
Deep Learning and HPC Bill Dally, Chief Scientist and SVP of Research January 17, 2017 A Decade of Scientific Computing with GPUs World s First Atomic Model of HIV Capsid GPU-Trained AI Machine Beats World
More informationGPUS FOR NGVLA. M Clark, April 2015
S FOR NGVLA M Clark, April 2015 GAMING DESIGN ENTERPRISE VIRTUALIZATION HPC & CLOUD SERVICE PROVIDERS AUTONOMOUS MACHINES PC DATA CENTER MOBILE The World Leader in Visual Computing 2 What is a? Tesla K40
More informationRECENT TRENDS IN GPU ARCHITECTURES. Perspectives of GPU computing in Science, 26 th Sept 2016
RECENT TRENDS IN GPU ARCHITECTURES Perspectives of GPU computing in Science, 26 th Sept 2016 NVIDIA THE AI COMPUTING COMPANY GPU Computing Computer Graphics Artificial Intelligence 2 NVIDIA POWERS WORLD
More informationA NEW COMPUTING ERA. DAVID B. KIRK, FELLOW NVIDIA AI Conference Singapore 2017
A NEW COMPUTING ERA DAVID B. KIRK, FELLOW NVIDIA AI Conference Singapore 2017 TWO FORCES DRIVING THE FUTURE OF COMPUTING 10 7 Transistors (thousands) 10 5 1.1X per year 10 3 1.5X per year Single-threaded
More informationObject recognition and computer vision using MATLAB and NVIDIA Deep Learning SDK
Object recognition and computer vision using MATLAB and NVIDIA Deep Learning SDK 17 May 2016, Melbourne 24 May 2016, Sydney Werner Scholz, CTO and Head of R&D, XENON Systems Mike Wang, Solutions Architect,
More informationDEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE. Dennis Lui August 2017
DEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE Dennis Lui August 2017 THE RISE OF GPU COMPUTING APPLICATIONS 10 7 10 6 GPU-Computing perf 1.5X per year 1000X by 2025 ALGORITHMS 10 5 1.1X
More informationAccelerating High Performance Computing.
Accelerating High Performance Computing http://www.nvidia.com/tesla Computing The 3 rd Pillar of Science Drug Design Molecular Dynamics Seismic Imaging Reverse Time Migration Automotive Design Computational
More informationTESLA P100 PERFORMANCE GUIDE. HPC and Deep Learning Applications
TESLA P PERFORMANCE GUIDE HPC and Deep Learning Applications MAY 217 TESLA P PERFORMANCE GUIDE Modern high performance computing (HPC) data centers are key to solving some of the world s most important
More informationTESLA V100 PERFORMANCE GUIDE. Life Sciences Applications
TESLA V100 PERFORMANCE GUIDE Life Sciences Applications NOVEMBER 2017 TESLA V100 PERFORMANCE GUIDE Modern high performance computing (HPC) data centers are key to solving some of the world s most important
More informationGTC Jensen Huang Founder & CEO
GTC 2018 Jensen Huang Founder & CEO 2 3 4 SCREEN-SPACE AMBIENT OCCLUSION BAKED LIGHTING 5 GLOBAL ILLUMINATION 6 SCREEN-SPACE REFLECTIONS ENVIRONMENT MAPS 7 RAY TRACED REFLECTIONS 8 SCREEN-SPACE REFRACTION
More informationGPUs and the Future of Accelerated Computing Emerging Technology Conference 2014 University of Manchester
NVIDIA GPU Computing A Revolution in High Performance Computing GPUs and the Future of Accelerated Computing Emerging Technology Conference 2014 University of Manchester John Ashley Senior Solutions Architect
More informationNEW NVIDIA PLATFORM FOR AI
NEW NVIDIA PLATFORM FOR AI Pedro Mario Cruz e Silva (pcruzesilva@nvidia.com) LinkedIn Solution Architect Manager Enterprise Latin America Global Oil & Gas Team "GTC 2017: 'I AM AI' OPENING IN KEYNOTE"
More informationApril 4-7, 2016 Silicon Valley INSIDE PASCAL. Mark Harris, October 27,
April 4-7, 2016 Silicon Valley INSIDE PASCAL Mark Harris, October 27, 2016 @harrism INTRODUCING TESLA P100 New GPU Architecture CPU to CPUEnable the World s Fastest Compute Node PCIe Switch PCIe Switch
More informationNVIDIA TESLA V100 GPU ARCHITECTURE THE WORLD S MOST ADVANCED DATA CENTER GPU
NVIDIA TESLA V100 GPU ARCHITECTURE THE WORLD S MOST ADVANCED DATA CENTER GPU WP-08608-001_v1.1 August 2017 WP-08608-001_v1.1 TABLE OF CONTENTS Introduction to the NVIDIA Tesla V100 GPU Architecture...
More informationVOLTA: PROGRAMMABILITY AND PERFORMANCE. Jack Choquette NVIDIA Hot Chips 2017
VOLTA: PROGRAMMABILITY AND PERFORMANCE Jack Choquette NVIDIA Hot Chips 2017 1 TESLA V100 21B transistors 815 mm 2 80 SM 5120 CUDA Cores 640 Tensor Cores 16 GB HBM2 900 GB/s HBM2 300 GB/s NVLink *full GV100
More informationCSE 591/392: GPU Programming. Introduction. Klaus Mueller. Computer Science Department Stony Brook University
CSE 591/392: GPU Programming Introduction Klaus Mueller Computer Science Department Stony Brook University First: A Big Word of Thanks! to the millions of computer game enthusiasts worldwide Who demand
More informationThe Exascale Era Has Arrived
Technology Spotlight The Exascale Era Has Arrived Sponsored by NVIDIA Steve Conway, Earl Joseph, Bob Sorensen, and Alex Norton November 2018 EXECUTIVE SUMMARY Earlier this year, scientists broke the exascale
More informationNVIDIA GTX200: TeraFLOPS Visual Computing. August 26, 2008 John Tynefield
NVIDIA GTX200: TeraFLOPS Visual Computing August 26, 2008 John Tynefield 2 Outline Execution Model Architecture Demo 3 Execution Model 4 Software Architecture Applications DX10 OpenGL OpenCL CUDA C Host
More informationFra superdatamaskiner til grafikkprosessorer og
Fra superdatamaskiner til grafikkprosessorer og Brødtekst maskinlæring Prof. Anne C. Elster IDI HPC/Lab Parallel Computing: Personal perspective 1980 s: Concurrent and Parallel Pascal 1986: Intel ipsc
More informationGPU ACCELERATED COMPUTING. 1 st AlsaCalcul GPU Challenge, 14-Jun-2016, Strasbourg Frédéric Parienté, Tesla Accelerated Computing, NVIDIA Corporation
GPU ACCELERATED COMPUTING 1 st AlsaCalcul GPU Challenge, 14-Jun-2016, Strasbourg Frédéric Parienté, Tesla Accelerated Computing, NVIDIA Corporation GAMING PRO ENTERPRISE VISUALIZATION DATA CENTER AUTO
More informationGPU Architecture. Alan Gray EPCC The University of Edinburgh
GPU Architecture Alan Gray EPCC The University of Edinburgh Outline Why do we want/need accelerators such as GPUs? Architectural reasons for accelerator performance advantages Latest GPU Products From
More informationGPU FOR DEEP LEARNING. 周国峰 Wuhan University 2017/10/13
GPU FOR DEEP LEARNING chandlerz@nvidia.com 周国峰 Wuhan University 2017/10/13 Why Deep Learning Boost Today? Nvidia SDK for Deep Learning? Agenda CUDA 8.0 cudnn TensorRT (GIE) NCCL DIGITS 2 Why Deep Learning
More informationBuilding the Most Efficient Machine Learning System
Building the Most Efficient Machine Learning System Mellanox The Artificial Intelligence Interconnect Company June 2017 Mellanox Overview Company Headquarters Yokneam, Israel Sunnyvale, California Worldwide
More informationIBM CORAL HPC System Solution
IBM CORAL HPC System Solution HPC and HPDA towards Cognitive, AI and Deep Learning Deep Learning AI / Deep Learning Strategy for Power Power AI Platform High Performance Data Analytics Big Data Strategy
More informationThe Future of GPU Computing
The Future of GPU Computing Bill Dally Chief Scientist & Sr. VP of Research, NVIDIA Bell Professor of Engineering, Stanford University November 18, 2009 The Future of Computing Bill Dally Chief Scientist
More informationCSCI 402: Computer Architectures. Parallel Processors (2) Fengguang Song Department of Computer & Information Science IUPUI.
CSCI 402: Computer Architectures Parallel Processors (2) Fengguang Song Department of Computer & Information Science IUPUI 6.6 - End Today s Contents GPU Cluster and its network topology The Roofline performance
More informationTESLA P100 PERFORMANCE GUIDE. Deep Learning and HPC Applications
TESLA P PERFORMANCE GUIDE Deep Learning and HPC Applications SEPTEMBER 217 TESLA P PERFORMANCE GUIDE Modern high performance computing (HPC) data centers are key to solving some of the world s most important
More informationACCELERATED COMPUTING: THE PATH FORWARD. Jen-Hsun Huang, Co-Founder and CEO, NVIDIA SC15 Nov. 16, 2015
ACCELERATED COMPUTING: THE PATH FORWARD Jen-Hsun Huang, Co-Founder and CEO, NVIDIA SC15 Nov. 16, 2015 COMMODITY DISRUPTS CUSTOM SOURCE: Top500 ACCELERATED COMPUTING: THE PATH FORWARD It s time to start
More informationNVIDIA GPU TECHNOLOGY UPDATE
NVIDIA GPU TECHNOLOGY UPDATE May 2015 Axel Koehler Senior Solutions Architect, NVIDIA NVIDIA: The VISUAL Computing Company GAMING DESIGN ENTERPRISE VIRTUALIZATION HPC & CLOUD SERVICE PROVIDERS AUTONOMOUS
More informationS THE MAKING OF DGX SATURNV: BREAKING THE BARRIERS TO AI SCALE. Presenter: Louis Capps, Solution Architect, NVIDIA,
S7750 - THE MAKING OF DGX SATURNV: BREAKING THE BARRIERS TO AI SCALE Presenter: Louis Capps, Solution Architect, NVIDIA, lcapps@nvidia.com A TALE OF ENLIGHTENMENT Basic OK List 10 for x = 1 to 3 20 print
More informationBuilding the Most Efficient Machine Learning System
Building the Most Efficient Machine Learning System Mellanox The Artificial Intelligence Interconnect Company June 2017 Mellanox Overview Company Headquarters Yokneam, Israel Sunnyvale, California Worldwide
More informationHybrid KAUST Many Cores and OpenACC. Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS
+ Hybrid Computing @ KAUST Many Cores and OpenACC Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS + Agenda Hybrid Computing n Hybrid Computing n From Multi-Physics
More informationCUDA Accelerated Linpack on Clusters. E. Phillips, NVIDIA Corporation
CUDA Accelerated Linpack on Clusters E. Phillips, NVIDIA Corporation Outline Linpack benchmark CUDA Acceleration Strategy Fermi DGEMM Optimization / Performance Linpack Results Conclusions LINPACK Benchmark
More informationEFFICIENT INFERENCE WITH TENSORRT. Han Vanholder
EFFICIENT INFERENCE WITH TENSORRT Han Vanholder AI INFERENCING IS EXPLODING 2 Trillion Messages Per Day On LinkedIn 500M Daily active users of iflytek 140 Billion Words Per Day Translated by Google 60
More informationSteve Scott, Tesla CTO SC 11 November 15, 2011
Steve Scott, Tesla CTO SC 11 November 15, 2011 What goal do these products have in common? Performance / W Exaflop Expectations First Exaflop Computer K Computer ~10 MW CM5 ~200 KW Not constant size, cost
More informationNVIDIA Tesla P100. Whitepaper. The Most Advanced Datacenter Accelerator Ever Built. Featuring Pascal GP100, the World s Fastest GPU
Whitepaper NVIDIA Tesla P100 The Most Advanced Datacenter Accelerator Ever Built Featuring Pascal GP100, the World s Fastest GPU NVIDIA Tesla P100 WP-08019-001_v01.2 1 Table of Contents Introduction...
More informationThe Tesla Accelerated Computing Platform
The Tesla Accelerated Computing Platform Axel Koehler, Principal Solution Architect HPC Advisory Council Meeting Lugano 22 March 2016 Introduction TESLA Platform for HPC Agenda TESLA Platform for HYPERSCALE
More informationPerformance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA
Performance Evaluation of a Vector Supercomputer SX-Aurora TSUBASA Kazuhiko Komatsu, S. Momose, Y. Isobe, O. Watanabe, A. Musa, M. Yokokawa, T. Aoyama, M. Sato, H. Kobayashi Tohoku University 14 November,
More informationFast Hardware For AI
Fast Hardware For AI Karl Freund karl@moorinsightsstrategy.com Sr. Analyst, AI and HPC Moor Insights & Strategy Follow my blogs covering Machine Learning Hardware on Forbes: http://www.forbes.com/sites/moorinsights
More informationGPGPU, 1st Meeting Mordechai Butrashvily, CEO GASS
GPGPU, 1st Meeting Mordechai Butrashvily, CEO GASS Agenda Forming a GPGPU WG 1 st meeting Future meetings Activities Forming a GPGPU WG To raise needs and enhance information sharing A platform for knowledge
More informationCSE 591: GPU Programming. Introduction. Entertainment Graphics: Virtual Realism for the Masses. Computer games need to have: Klaus Mueller
Entertainment Graphics: Virtual Realism for the Masses CSE 591: GPU Programming Introduction Computer games need to have: realistic appearance of characters and objects believable and creative shading,
More informationIBM Deep Learning Solutions
IBM Deep Learning Solutions Reference Architecture for Deep Learning on POWER8, P100, and NVLink October, 2016 How do you teach a computer to Perceive? 2 Deep Learning: teaching Siri to recognize a bicycle
More informationFinite Element Integration and Assembly on Modern Multi and Many-core Processors
Finite Element Integration and Assembly on Modern Multi and Many-core Processors Krzysztof Banaś, Jan Bielański, Kazimierz Chłoń AGH University of Science and Technology, Mickiewicza 30, 30-059 Kraków,
More informationS8901 Quadro for AI, VR and Simulation
S8901 Quadro for AI, VR and Simulation Carl Flygare, PNY Quadro Product Marketing Manager Allen Bourgoyne, NVIDIA Senior Product Marketing Manager The question of whether a computer can think is no more
More informationTECHNICAL OVERVIEW ACCELERATED COMPUTING AND THE DEMOCRATIZATION OF SUPERCOMPUTING
TECHNICAL OVERVIEW ACCELERATED COMPUTING AND THE DEMOCRATIZATION OF SUPERCOMPUTING Table of Contents: The Accelerated Data Center Optimizing Data Center Productivity Same Throughput with Fewer Server Nodes
More informationScalable Distributed Training with Parameter Hub: a whirlwind tour
Scalable Distributed Training with Parameter Hub: a whirlwind tour TVM Stack Optimization High-Level Differentiable IR Tensor Expression IR AutoTVM LLVM, CUDA, Metal VTA AutoVTA Edge FPGA Cloud FPGA ASIC
More informationS8688 : INSIDE DGX-2. Glenn Dearth, Vyas Venkataraman Mar 28, 2018
S8688 : INSIDE DGX-2 Glenn Dearth, Vyas Venkataraman Mar 28, 2018 Why was DGX-2 created Agenda DGX-2 internal architecture Software programming model Simple application Results 2 DEEP LEARNING TRENDS Application
More informationBuilding NVLink for Developers
Building NVLink for Developers Unleashing programmatic, architectural and performance capabilities for accelerated computing Why NVLink TM? Simpler, Better and Faster Simplified Programming No specialized
More informationCharacterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager
Characterization and Benchmarking of Deep Learning Natalia Vassilieva, PhD Sr. Research Manager Deep learning applications Vision Speech Text Other Search & information extraction Security/Video surveillance
More informationEfficient Communication Library for Large-Scale Deep Learning
IBM Research AI Efficient Communication Library for Large-Scale Deep Learning Mar 26, 2018 Minsik Cho (minsikcho@us.ibm.com) Deep Learning changing Our Life Automotive/transportation Security/public safety
More informationS WHAT THE PROFILER IS TELLING YOU: OPTIMIZING GPU KERNELS. Jakob Progsch, Mathias Wagner GTC 2018
S8630 - WHAT THE PROFILER IS TELLING YOU: OPTIMIZING GPU KERNELS Jakob Progsch, Mathias Wagner GTC 2018 1. Know your hardware BEFORE YOU START What are the target machines, how many nodes? Machine-specific
More informationCOMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface. 5 th. Edition. Chapter 6. Parallel Processors from Client to Cloud
COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface 5 th Edition Chapter 6 Parallel Processors from Client to Cloud Introduction Goal: connecting multiple computers to get higher performance
More informationIntroduction: Modern computer architecture. The stored program computer and its inherent bottlenecks Multi- and manycore chips and nodes
Introduction: Modern computer architecture The stored program computer and its inherent bottlenecks Multi- and manycore chips and nodes Motivation: Multi-Cores where and why Introduction: Moore s law Intel
More informationHPC future trends from a science perspective
HPC future trends from a science perspective Simon McIntosh-Smith University of Bristol HPC Research Group simonm@cs.bris.ac.uk 1 Business as usual? We've all got used to new machines being relatively
More informationTuring Architecture and CUDA 10 New Features. Minseok Lee, Developer Technology Engineer, NVIDIA
Turing Architecture and CUDA 10 New Features Minseok Lee, Developer Technology Engineer, NVIDIA Turing Architecture New SM Architecture Multi-Precision Tensor Core RT Core Turing MPS Inference Accelerated,
More informationSupercomputing with Commodity CPUs: Are Mobile SoCs Ready for HPC?
Supercomputing with Commodity CPUs: Are Mobile SoCs Ready for HPC? Nikola Rajovic, Paul M. Carpenter, Isaac Gelado, Nikola Puzovic, Alex Ramirez, Mateo Valero SC 13, November 19 th 2013, Denver, CO, USA
More informationStan Posey, NVIDIA, Santa Clara, CA, USA
Stan Posey, sposey@nvidia.com NVIDIA, Santa Clara, CA, USA NVIDIA Strategy for CWO Modeling (Since 2010) Initial focus: CUDA applied to climate models and NWP research Opportunities to refactor code with
More informationNvidia Jetson TX2 and its Software Toolset. João Fernandes 2017/2018
Nvidia Jetson TX2 and its Software Toolset João Fernandes 2017/2018 In this presentation Nvidia Jetson TX2: Hardware Nvidia Jetson TX2: Software Machine Learning: Neural Networks Convolutional Neural Networks
More informationNVIDIA DGX SYSTEMS PURPOSE-BUILT FOR AI
NVIDIA DGX SYSTEMS PURPOSE-BUILT FOR AI Overview Unparalleled Value Product Portfolio Software Platform From Desk to Data Center to Cloud Summary AI researchers depend on computing performance to gain
More informationTo hear the audio, please be sure to dial in: ID#
Introduction to the HPP-Heterogeneous Processing Platform A combination of Multi-core, GPUs, FPGAs and Many-core accelerators To hear the audio, please be sure to dial in: 1-866-440-4486 ID# 4503739 Yassine
More informationINVESTOR UPDATE. September 2018
INVESTOR UPDATE September 2018 SAFE HARBOR Forward-Looking Statements Except for the historical information contained herein, certain matters in this presentation including, but not limited to, statements
More informationGeneral Purpose GPU Computing in Partial Wave Analysis
JLAB at 12 GeV - INT General Purpose GPU Computing in Partial Wave Analysis Hrayr Matevosyan - NTC, Indiana University November 18/2009 COmputationAL Challenges IN PWA Rapid Increase in Available Data
More informationn N c CIni.o ewsrg.au
@NCInews NCI and Raijin National Computational Infrastructure 2 Our Partners General purpose, highly parallel processors High FLOPs/watt and FLOPs/$ Unit of execution Kernel Separate memory subsystem GPGPU
More informationGPGPUs in HPC. VILLE TIMONEN Åbo Akademi University CSC
GPGPUs in HPC VILLE TIMONEN Åbo Akademi University 2.11.2010 @ CSC Content Background How do GPUs pull off higher throughput Typical architecture Current situation & the future GPGPU languages A tale of
More informationHPC with GPU and its applications from Inspur. Haibo Xie, Ph.D
HPC with GPU and its applications from Inspur Haibo Xie, Ph.D xiehb@inspur.com 2 Agenda I. HPC with GPU II. YITIAN solution and application 3 New Moore s Law 4 HPC? HPC stands for High Heterogeneous Performance
More informationCUDA Experiences: Over-Optimization and Future HPC
CUDA Experiences: Over-Optimization and Future HPC Carl Pearson 1, Simon Garcia De Gonzalo 2 Ph.D. candidates, Electrical and Computer Engineering 1 / Computer Science 2, University of Illinois Urbana-Champaign
More informationIntel Many Integrated Core (MIC) Matt Kelly & Ryan Rawlins
Intel Many Integrated Core (MIC) Matt Kelly & Ryan Rawlins Outline History & Motivation Architecture Core architecture Network Topology Memory hierarchy Brief comparison to GPU & Tilera Programming Applications
More informationPerformance Analysis of Memory Transfers and GEMM Subroutines on NVIDIA TESLA GPU Cluster
Performance Analysis of Memory Transfers and GEMM Subroutines on NVIDIA TESLA GPU Cluster Veerendra Allada, Troy Benjegerdes Electrical and Computer Engineering, Ames Laboratory Iowa State University &
More informationDEEP LEARNING ALISON B LOWNDES. Deep Learning Solutions Architect & Community Manager EMEA
DEEP LEARNING ALISON B LOWNDES Deep Learning Solutions Architect & Community Manager EMEA 1 THE GPU-ACCELERATED WORLD HPC DEEP LEARNING PC VIRTUALIZATION CLOUD GAMING RENDERING 2 3 Why is Deep Learning
More informationLecture 1: Gentle Introduction to GPUs
CSCI-GA.3033-004 Graphics Processing Units (GPUs): Architecture and Programming Lecture 1: Gentle Introduction to GPUs Mohamed Zahran (aka Z) mzahran@cs.nyu.edu http://www.mzahran.com Who Am I? Mohamed
More informationProfiling DNN Workloads on a Volta-based DGX-1 System
Profiling DNN Workloads on a Volta-based DGX-1 System Saiful A. Mojumder 1, Marcia S Louis 1, Yifan Sun 2, Amir Kavyan Ziabari 3, José L. Abellán 4, John Kim 5, David Kaeli 2, Ajay Joshi 1 1 ECE Department,
More informationMathematical computations with GPUs
Master Educational Program Information technology in applications Mathematical computations with GPUs Introduction Alexey A. Romanenko arom@ccfit.nsu.ru Novosibirsk State University How to.. Process terabytes
More informationLecture 8: GPU Programming. CSE599G1: Spring 2017
Lecture 8: GPU Programming CSE599G1: Spring 2017 Announcements Project proposal due on Thursday (4/28) 5pm. Assignment 2 will be out today, due in two weeks. Implement GPU kernels and use cublas library
More informationDeep Learning: Transforming Engineering and Science The MathWorks, Inc.
Deep Learning: Transforming Engineering and Science 1 2015 The MathWorks, Inc. DEEP LEARNING: TRANSFORMING ENGINEERING AND SCIENCE A THE NEW RISE ERA OF OF GPU COMPUTING 3 NVIDIA A IS NEW THE WORLD S ERA
More informationMay 8-11, 2017 Silicon Valley CUDA 9 AND BEYOND. Mark Harris, May 10, 2017
May 8-11, 2017 Silicon Valley CUDA 9 AND BEYOND Mark Harris, May 10, 2017 INTRODUCING CUDA 9 BUILT FOR VOLTA FASTER LIBRARIES Tesla V100 New GPU Architecture Tensor Cores NVLink Independent Thread Scheduling
More informationWhat is GPU? CS 590: High Performance Computing. GPU Architectures and CUDA Concepts/Terms
CS 590: High Performance Computing GPU Architectures and CUDA Concepts/Terms Fengguang Song Department of Computer & Information Science IUPUI What is GPU? Conventional GPUs are used to generate 2D, 3D
More informationCisco UCS C480 ML M5 Rack Server Performance Characterization
White Paper Cisco UCS C480 ML M5 Rack Server Performance Characterization The Cisco UCS C480 ML M5 Rack Server platform is designed for artificial intelligence and machine-learning workloads. 2018 Cisco
More informationHPC Technology Trends
HPC Technology Trends High Performance Embedded Computing Conference September 18, 2007 David S Scott, Ph.D. Petascale Product Line Architect Digital Enterprise Group Risk Factors Today s s presentations
More informationGPU-centric communication for improved efficiency
GPU-centric communication for improved efficiency Benjamin Klenk *, Lena Oden, Holger Fröning * * Heidelberg University, Germany Fraunhofer Institute for Industrial Mathematics, Germany GPCDP Workshop
More information(software agnostic) Computational Considerations
(software agnostic) Computational Considerations The Issues CPU GPU Emerging - FPGA, Phi, Nervana Storage Networking CPU 2 Threads core core Processor/Chip Processor/Chip Computer CPU Threads vs. Cores
More informationWhen MPPDB Meets GPU:
When MPPDB Meets GPU: An Extendible Framework for Acceleration Laura Chen, Le Cai, Yongyan Wang Background: Heterogeneous Computing Hardware Trend stops growing with Moore s Law Fast development of GPU
More informationIBM Power AC922 Server
IBM Power AC922 Server The Best Server for Enterprise AI Highlights More accuracy - GPUs access system RAM for larger models Faster insights - significant deep learning speedups Rapid deployment - integrated
More information