Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Accelerated Deep Learning - Part 1

Accelerated Deep Learning - Part 1

Slide deck of Jeremy Purches and Alison Lowndes talk at the Deep Learning London event on 04 Nov 2015. Talk was focused on explaining how graphical processing units (GPUs) enable various deep learning techniques. He will include use cases across a wide area of industry plus the latest news on NVIDIAs toolkits and software, including DIGITS, their open-source Deep Learning platform. Further information can be found here: https://developer.nvidia.com/deep-learning

Deep Learning London Meetup

November 04, 2015
Tweet

More Decks by Deep Learning London Meetup

Other Decks in Technology

Transcript

  1. Jeremy Purches, Director - HPC & Deep Learning UK&I Alison

    B Lowndes, Deep Learning Solutions Architect & Community Manager Accelerated Deep Learning 4th November 2015
  2. 2 The World Leader in Visual Computing GAMING PRO VISUALIZATION

    HPC & BIG DATA MOBILE COMPUTING GeForce® Quadro® Tesla® Tegra®
  3. © NVIDIA Corporation 2013 The GPU is one of the

    most complex processors ever created, with more than 7 billion transistors. NVIDIA has shipped over 1 billion GPUs. NVIDIA GPU
  4. 4 CPU Optimized for Serial Tasks GPU Accelerator Optimized for

    Parallel Tasks GPU Accelerated Computing 10x Performance & 5x Energy Efficiency
  5. 6 Tesla K80 World’s Fastest Accelerator for Data Analytics, Scientific

    Computing and Deep Learning Caffe Benchmark: AlexNet training throughput based on 20 iterations, CPU: E5-2697v2 @ 2.70GHz. 64GB System Memory, CentOS 6.2 Maximum Performance Dynamically Maximize Perf for Every Application Double the Memory Designed for Big Data Apps 24GB Oil & Gas Data Analytics HPC Viz K40 12GB 2x Faster 2.9 TF| 4992 Cores | 480 GB/s 0x 5x 10x 15x 20x 25x CPU Tesla K40 Tesla K80 Deep Learning: Caffe GPU Boost
  6. 7 0.1 1 10 100 1000 10000 100000 1000000 10000000

    100000000 1E+09 1994 1996 1998 2000 2002 2004 2006 2008 2010 2012 2014 59.7 GFlop/s 400 MFlop/s 1.17 TFlop/s SUM N=1 N=500 1 Gflop/s 1 Tflop/s 100 Mflop/s 100 Gflop/s 100 Tflop/s 10 Gflop/s 10 Tflop/s 1 Pflop/s 100 Pflop/s 10 Pflop/s 1 Eflop/s 33.9 PFlop/s 274 PFlop/s 134 TFlop/s Super Computer Performance Development iPhone 6s (1.8 Gflop/s) Laptop (70 Gflop/s) GPU (2.9 Tflop/s) To Exascale and beyond….