High-Throughput and High-Accuracy Classification with Convolutional Ternary Neural Networks. Frédéric Pétrot, Adrien Prost-Boucle, Alban Bourge
|
|
- Hope Skinner
- 5 years ago
- Views:
Transcription
1 High-Throughput and High-Accuracy Classification with Convolutional Ternary Neural Networks Frédéric Pétrot, Adrien Prost-Boucle, Alban Bourge International Workshop on Highly Efficient Neural Processing October 4th 2018
2 CNN Models : Accuracy, Operations and Parameters A. Canziani, E. Culurciello, A. Paszke, An Analysis of Deep Neural Network Models for Practical Applications, 2017 Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
3 CNN Models : Accuracy, Operations and Parameters Challenges in Embedded Neural Networks Limit number of parameters (weight values) Limit number of bits of weights and activations Integrate many memory cuts with processing elements Integrate computation into the memory itself Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
4 CNN Models : Accuracy, Operations and Parameters Challenges in Embedded Neural Networks Limit number of parameters (weight values) Limit number of bits of weights and activations Integrate many memory cuts with processing elements Integrate computation into the memory itself Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
5 CNN Models : Accuracy, Operations and Parameters Challenges in Embedded Neural Networks In other words,... Limit number of parameters (weight values) Limit number of bits of weights and activations Integrate many memory cuts with processing elements Integrate computation into the memory itself Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
6 CNN Models : Accuracy, Operations and Parameters Challenges in Embedded Neural Networks Limit number of parameters (weight values) Limit number of bits of weights and activations Integrate many memory cuts with processing elements Integrate computation into the memory itself In other words,... K. Usher, The Dwarf in the Dirt, Bones, 2009 Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
7 CNN Models : Accuracy, Operations and Parameters Challenges in Embedded Neural Networks Limit number of parameters (weight values) Limit number of bits of weights and activations Integrate many memory cuts with processing elements Integrate computation into the memory itself In other words,... K. Usher, The Dwarf in the Dirt, Bones, 2009 Let s Use Ternary { 1, 0, 1} weights and activations on FPGA FPGA : Great digital PIM Hardwiring ANN too risky New and better ANN every other day Ternarization Classification Error Rates on NN-64 (%) CIFAR-10 SVHN GTRSB Float Ternary H. Alemdar et al, Ternary neural networks for resource-efficient AI applications, IJCNN 17 Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
8 Why Ternary Convolutional Neural Networks? Objectives Energy efficient inference for AI tasks Without sacrifiying too much accuracy (Valid at a point in time : learning methods improve continuously) Solution Ternarize { 1, 0, 1} weights and activations a Sweet spot between resource usage and accuracy a. Perhaps the prettiest number system of all is the balanced ternary notation. Donald Knuth, The Art of Computer Programming, Volume 2 : Seminumerical algorithms. Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
9 Training Ternary Neural Networks : Teacher-Student Approach NN Teacher Student parameters { 1, 0, 1} neuron input activation function any any with ( 1, 1) 2-threshold step stochastic firing neuron output { 1, 0, 1} { 1, 0, 1} Teacher ρ = tanh(y i ) 1 with prob. ρ if ρ < 0 n i = 1 with prob. ρ if ρ > 0 0 otherwise Student 1 if y i < b lo n i = 1 if y i > b hi 0 otherwise Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
10 Ternary Neural Networks : Teacher-Student Individual Training Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
11 Experiments with Ternary Networks Multiple networks VGG-like networks two geometries : NN-64 and NN-128 multiple acceleration factors inside network (ranging 1 to 256) tradeoff area/throughput/energy Automation (kind of...) handmade generic hardware building blocks (vhdl) automatically generated networks customizable home-made tools (old school C and tcl) Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
12 Overview 12 theoretical layers 29 physical layers (+30 glue fifos) NN64 : 1930 neurons, 3.5 mega parameters NN128 : 3850 neurons, 14 mega parameters Goal of ternary : have parameters fit in FPGA distributed memories Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
13 Overview Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
14 FPGA Design for Ternary Convolutional Neural Networks Neurones and Parallelism Max NN-64 acceleration factor that fits on a VC709 : 128 Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
15 Acceleration factors Base implementation : at most 1 activation transfered between layers in 1 cycle But some layers take more time than others to compute stalls Use parallelism at layer level : Transfering several activations in 1 cycle in/out of bootleneck layers NN Acc. Parallelism per layer (in/out) size factor NL1 NL2 MPL1 NL3 NL4 MPL2 NL5 NL6 MPL3 NL7 NL8 NL / / / / 1-2 / 1 4 / / / 2 16 / 2 2 / 1 4 / 1 8 / 1-2 / 1 4 / / 4 32 / 4 4 / 1 8 / 2 16 / 2 2 / 1 4 / 1 8 / / 8 64 / 8 8 / 2 16 / 4 32 / 4 4 / 1 8 / 2 16 / 2 2 / / / / 4 32 / 8 64 / 8 8 / 2 16 / 4 32 / 4 4 / / / / 8 64 / / / 4 32 / 8 64 / 8 8 / 2 2/1 - - Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
16 Squeezing High-Efficiency TCNN in FPGA : Adder Trees Ternary Adders Sum of trits Sum of bits With (x, y) { 1, 0, 1} 2, x + y { 2, 1, 0, 1, 2} LUT savings with optimized ternary adder tree Number of inputs Generic 2-bit radix-2 adder tree (LUT) Optimized ternary adder (LUT) Savings 33.3% 57.1% 52.3% 51.1% 50.3% 51.6% 51.8% 51.0% Overall LUT savings when using optimized ternary adder trees Acc. factor Savings for NN % 1.38% 4.61% 10.9% 17.3% 24.1% 32.0% Savings for NN % 1.71% 5.63% 12.9% 19.6% 25.7% Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
17 Squeezing High-Efficiency TCNN in FPGA : Weight Compression Trits encoding Naïve encoding : 2 bits to encode 1 trit suboptimal Ex. : 3 trits encoded on 6 bits while 3 3 = 27 combinations encodable on 5 bits Optimal number of bits per trits : b = log 2 ( 3 T ) = T log 2 (3) Minimal number of bits per trits : b/t log 2 (3) bits Maximum saving % (Shannon limit) Interesting cases 3 trits / 5 bits 16 % saving 5 trits / 8 bits 20 % saving Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
18 Squeezing High-Efficiency TCNN in FPGA : Weight Compression Compression of weights Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
19 Squeezing High-Efficiency TCNN in FPGA : Weight Compression Trading-off BRAM vs logic : Ressources Breakdown and Power Analysis NN-64 with compression 3t5b NN-64 with compression 5t8b y-axis : % of change wrt same degree of parallelism without compression Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
20 Measured Results for NN-64 on Xilinx MHz (VC709) Acc. Resource usage factor LUT (logic) LUTRAM BRAM 18k FF (39.4%) (21.47%) 1410 (48.0%) (37.1%) 256* (69.9%) (60.9%) 2920 (96.7%) (74.0%) NN-64 with parallelism degree 128 Uses half of the FPGA resources, reaches max throughput of 60.2k fps (32 32) (LUT+B)RAM throughput of 18.7 Tb/s (290 Gb/s for FC layers only a ) End to end latency including PCIe + RIFFA : 135 µs Max performance : 18.7 T(T)OP/s (9.33 T(T)MAC/s) max performance : 11.5 W (Idle FPGA 2 W) Peak efficiency of 5226 fps per Watt 1.62 T(T)OP/s/W or 810 G(T)MAC/s/W a. VC709 DRAM throughput 204 Gb/s Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
21 Take away FPGAs are a very good fit for ANN if weights fit in internal memory Extreme quantization needed Huge weight access throughput possible FPGAs are reconfigurable! Who would be mad enough to hardwire a given ANN architecture anyway? ASICs follow a very different (but equally useful) architectural path Creative low level optimizations help squeeze-in high-efficiency networks (NN-64 ) High-throughput : up to 60.2k fps Low latency : k fps High power efficiency : 1.62 T(T)OP/s/W or k fps Pétrot, Prost-Boucle, Bourge HENP 18 October 4 th / 16
Accelerating Binarized Convolutional Neural Networks with Software-Programmable FPGAs
Accelerating Binarized Convolutional Neural Networks with Software-Programmable FPGAs Ritchie Zhao 1, Weinan Song 2, Wentao Zhang 2, Tianwei Xing 3, Jeng-Hau Lin 4, Mani Srivastava 3, Rajesh Gupta 4, Zhiru
More informationScaling Convolutional Neural Networks on Reconfigurable Logic Michaela Blott, Principal Engineer, Xilinx Research
Scaling Convolutional Neural Networks on Reconfigurable Logic Michaela Blott, Principal Engineer, Xilinx Research Nick Fraser (Xilinx & USydney) Yaman Umuroglu (Xilinx & NTNU) Giulio Gambardella (Xilinx)
More informationRevolutionizing the Datacenter
Power-Efficient Machine Learning using FPGAs on POWER Systems Ralph Wittig, Distinguished Engineer Office of the CTO, Xilinx Revolutionizing the Datacenter Join the Conversation #OpenPOWERSummit Top-5
More informationFINN: A Framework for Fast, Scalable Binarized Neural Network Inference
FINN: A Framework for Fast, Scalable Binarized Neural Network Inference Yaman Umuroglu (XIR & NTNU), Nick Fraser (XIR & USydney), Giulio Gambardella (XIR), Michaela Blott (XIR), Philip Leong (USydney),
More informationBrainchip OCTOBER
Brainchip OCTOBER 2017 1 Agenda Neuromorphic computing background Akida Neuromorphic System-on-Chip (NSoC) Brainchip OCTOBER 2017 2 Neuromorphic Computing Background Brainchip OCTOBER 2017 3 A Brief History
More informationFINN: A Framework for Fast, Scalable Binarized Neural Network Inference
FINN: A Framework for Fast, Scalable Binarized Neural Network Inference Yaman Umuroglu (NTNU & Xilinx Research Labs Ireland) in collaboration with N Fraser, G Gambardella, M Blott, P Leong, M Jahre and
More informationDNNBuilder: an Automated Tool for Building High-Performance DNN Hardware Accelerators for FPGAs
IBM Research AI Systems Day DNNBuilder: an Automated Tool for Building High-Performance DNN Hardware Accelerators for FPGAs Xiaofan Zhang 1, Junsong Wang 2, Chao Zhu 2, Yonghua Lin 2, Jinjun Xiong 3, Wen-mei
More informationSDA: Software-Defined Accelerator for Large- Scale DNN Systems
SDA: Software-Defined Accelerator for Large- Scale DNN Systems Jian Ouyang, 1 Shiding Lin, 1 Wei Qi, Yong Wang, Bo Yu, Song Jiang, 2 1 Baidu, Inc. 2 Wayne State University Introduction of Baidu A dominant
More informationarxiv: v2 [cs.ar] 15 May 2018
[DL] A Survey of FPGA Based Neural Network Accelerator arxiv:1712.08934v2 [cs.ar] 15 May 2018 KAIYUAN GUO, SHULIN ZENG, JINCHENG YU, YU WANG AND HUAZHONG YANG, Tsinghua University, China Recent researches
More informationProfiling the Performance of Binarized Neural Networks. Daniel Lerner, Jared Pierce, Blake Wetherton, Jialiang Zhang
Profiling the Performance of Binarized Neural Networks Daniel Lerner, Jared Pierce, Blake Wetherton, Jialiang Zhang 1 Outline Project Significance Prior Work Research Objectives Hypotheses Testing Framework
More informationdirect hardware mapping of cnns on fpga-based smart cameras
direct hardware mapping of cnns on fpga-based smart cameras Workshop on Architecture of Smart Cameras Kamel ABDELOUAHAB, Francois BERRY, Maxime PELCAT, Jocelyn SEROT, Jean-Charles QUINTON Cordoba, June
More informationECE5775 High-Level Digital Design Automation, Fall 2018 School of Electrical Computer Engineering, Cornell University
ECE5775 High-Level Digital Design Automation, Fall 2018 School of Electrical Computer Engineering, Cornell University Lab 4: Binarized Convolutional Neural Networks Due Wednesday, October 31, 2018, 11:59pm
More informationTowards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA
Towards a Uniform Template-based Architecture for Accelerating 2D and 3D CNNs on FPGA Junzhong Shen, You Huang, Zelong Wang, Yuran Qiao, Mei Wen, Chunyuan Zhang National University of Defense Technology,
More informationScalable and Modularized RTL Compilation of Convolutional Neural Networks onto FPGA
Scalable and Modularized RTL Compilation of Convolutional Neural Networks onto FPGA Yufei Ma, Naveen Suda, Yu Cao, Jae-sun Seo, Sarma Vrudhula School of Electrical, Computer and Energy Engineering School
More informationImplementing Long-term Recurrent Convolutional Network Using HLS on POWER System
Implementing Long-term Recurrent Convolutional Network Using HLS on POWER System Xiaofan Zhang1, Mohamed El Hadedy1, Wen-mei Hwu1, Nam Sung Kim1, Jinjun Xiong2, Deming Chen1 1 University of Illinois Urbana-Champaign
More informationIndex. Springer Nature Switzerland AG 2019 B. Moons et al., Embedded Deep Learning,
Index A Algorithmic noise tolerance (ANT), 93 94 Application specific instruction set processors (ASIPs), 115 116 Approximate computing application level, 95 circuits-levels, 93 94 DAS and DVAS, 107 110
More informationSDA: Software-Defined Accelerator for Large- Scale DNN Systems
SDA: Software-Defined Accelerator for Large- Scale DNN Systems Jian Ouyang, 1 Shiding Lin, 1 Wei Qi, 1 Yong Wang, 1 Bo Yu, 1 Song Jiang, 2 1 Baidu, Inc. 2 Wayne State University Introduction of Baidu A
More informationDeepLearning on FPGAs
DeepLearning on FPGAs Introduction to FPGAs Sebastian Buschjäger Technische Universität Dortmund - Fakultät Informatik - Lehrstuhl 8 October 24, 2017 1 Recap: Convolution Observation 1 Even smaller images
More informationScalable and Dynamically Updatable Lookup Engine for Decision-trees on FPGA
Scalable and Dynamically Updatable Lookup Engine for Decision-trees on FPGA Yun R. Qu, Viktor K. Prasanna Ming Hsieh Dept. of Electrical Engineering University of Southern California Los Angeles, CA 90089
More informationLab 4: Convolutional Neural Networks Due Friday, November 3, 2017, 11:59pm
ECE5775 High-Level Digital Design Automation, Fall 2017 School of Electrical Computer Engineering, Cornell University Lab 4: Convolutional Neural Networks Due Friday, November 3, 2017, 11:59pm 1 Introduction
More informationThroughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks
Throughput-Optimized OpenCL-based FPGA Accelerator for Large-Scale Convolutional Neural Networks Naveen Suda, Vikas Chandra *, Ganesh Dasika *, Abinash Mohanty, Yufei Ma, Sarma Vrudhula, Jae-sun Seo, Yu
More informationOptimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Zhezhi He Department of ECE University of Central Florida Elliot.he@knights.ucf.edu Boqing Gong Tencent AI Lab Bellevue, WA 98004
More informationOptimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Zhezhi He, Boqing Gong, and Deliang Fan Department of Electrical and Computer Engineering, University of Central Florida, Orlando,
More informationarxiv: v1 [cs.cv] 11 Feb 2018
arxiv:8.8v [cs.cv] Feb 8 - Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms ABSTRACT Jong Hwan Ko, Taesik Na, Mohammad Faisal Amir,
More informationarxiv: v1 [cs.lg] 17 Jan 2019
CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs Mohammad Samragh, Mojan Javaheripi, Farinaz Koushanfar Department of Electrical and Computer Engineering, University of California
More informationA Lightweight YOLOv2:
FPGA2018 @Monterey A Lightweight YOLOv2: A Binarized CNN with a Parallel Support Vector Regression for an FPGA Hiroki Nakahara, Haruyoshi Yonekawa, Tomoya Fujii, Shimpei Sato Tokyo Institute of Technology,
More informationNeural Computer Architectures
Neural Computer Architectures 5kk73 Embedded Computer Architecture By: Maurice Peemen Date: Convergence of different domains Neurobiology Applications 1 Constraints Machine Learning Technology Innovations
More informationRecurrent Neural Networks. Deep neural networks have enabled major advances in machine learning and AI. Convolutional Neural Networks
Deep neural networks have enabled major advances in machine learning and AI Computer vision Language translation Speech recognition Question answering And more Problem: DNNs are challenging to serve and
More informationAn FPGA Based Adaptive Viterbi Decoder
An FPGA Based Adaptive Viterbi Decoder Sriram Swaminathan Russell Tessier Department of ECE University of Massachusetts Amherst Overview Introduction Objectives Background Adaptive Viterbi Algorithm Architecture
More informationUnified Deep Learning with CPU, GPU, and FPGA Technologies
Unified Deep Learning with CPU, GPU, and FPGA Technologies Allen Rush 1, Ashish Sirasao 2, Mike Ignatowski 1 1: Advanced Micro Devices, Inc., 2: Xilinx, Inc. Abstract Deep learning and complex machine
More informationTHE NVIDIA DEEP LEARNING ACCELERATOR
THE NVIDIA DEEP LEARNING ACCELERATOR INTRODUCTION NVDLA NVIDIA Deep Learning Accelerator Developed as part of Xavier NVIDIA s SOC for autonomous driving applications Optimized for Convolutional Neural
More informationLecture 12: Model Serving. CSE599W: Spring 2018
Lecture 12: Model Serving CSE599W: Spring 2018 Deep Learning Applications That drink will get you to 2800 calories for today I last saw your keys in the store room Remind Tom of the party You re on page
More informationarxiv: v3 [cs.lg] 27 Mar 2018
ReBNet: Residual Binarized Neural Network Mohammad Ghasemzadeh, Mohammad amragh, and Farinaz Koushanfar Department of Electrical and Computer Engineering, University of California an Diego {mghasemzadeh,
More informationDeep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations, and Hardware Implications
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations, and Hardware Implications Jongsoo Park Facebook AI System SW/HW Co-design Team Sep-21 2018 Team Introduction
More informationImplementation of 14 bits floating point numbers of calculating units for neural network hardware development
International Conference on Recent Trends in Physics 206 (ICRTP206) Journal of Physics: Conference Series 755 (206) 000 doi:0.088/742-6596/755//000 Implementation of 4 bits floating numbers of calculating
More informationUtilizing SDSoC to Port Convolutional Neural Network to a Space-grade FPGA
Utilizing SDSoC to Port Convolutional Neural Network to a Space-grade FPGA Josh Anderson joshua.anderson@swri.org Southwest Research Institute 1 Objective Compress MASPEX instrument data Produces ~80MB
More informationCan FPGAs beat GPUs in accelerating next-generation Deep Neural Networks? Discussion of the FPGA 17 paper by Intel Corp. (Nurvitadhi et al.
Can FPGAs beat GPUs in accelerating next-generation Deep Neural Networks? Discussion of the FPGA 17 paper by Intel Corp. (Nurvitadhi et al.) Andreas Kurth 2017-12-05 1 In short: The situation Image credit:
More informationSemantic Image Search. Alex Egg
Semantic Image Search Alex Egg Inspiration Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing
More informationSwitched by Input: Power Efficient Structure for RRAMbased Convolutional Neural Network
Switched by Input: Power Efficient Structure for RRAMbased Convolutional Neural Network Lixue Xia, Tianqi Tang, Wenqin Huangfu, Ming Cheng, Xiling Yin, Boxun Li, Yu Wang, Huazhong Yang Dept. of E.E., Tsinghua
More informationSpaceWire Technologies deliver multi-gigabit data rates for on-board Spacecraft. SpaceTech Expo Gregor Cranston Business Development Manager
SpaceWire Technologies deliver multi-gigabit data rates for on-board Spacecraft SpaceTech Expo 2013 Gregor Cranston Business Development Manager 1 Introducing SpaceFibre A very high-speed serial data-link
More informationRFNoC Neural-Network Library using Vivado HLS (rfnoc-hls-neuralnet) EJ Kreinar Team E to the J Omega
RFNoC Neural-Network Library using Vivado HLS (rfnoc-hls-neuralnet) EJ Kreinar Team E to the J Omega Overview An RFNoC out-of-tree module that can be used to simulate, synthesize, and run a neural network
More informationFast Flexible FPGA-Tuned Networks-on-Chip
This work was funded by NSF. We thank Xilinx for their FPGA and tool donations. We thank Bluespec for their tool donations. Fast Flexible FPGA-Tuned Networks-on-Chip Michael K. Papamichael, James C. Hoe
More informationXPU A Programmable FPGA Accelerator for Diverse Workloads
XPU A Programmable FPGA Accelerator for Diverse Workloads Jian Ouyang, 1 (ouyangjian@baidu.com) Ephrem Wu, 2 Jing Wang, 1 Yupeng Li, 1 Hanlin Xie 1 1 Baidu, Inc. 2 Xilinx Outlines Background - FPGA for
More informationXilinx ML Suite Overview
Xilinx ML Suite Overview Yao Fu System Architect Data Center Acceleration Xilinx Accelerated Computing Workloads Machine Learning Inference Image classification and object detection Video Streaming Frame
More informationFrequency Domain Acceleration of Convolutional Neural Networks on CPU-FPGA Shared Memory System
Frequency Domain Acceleration of Convolutional Neural Networks on CPU-FPGA Shared Memory System Chi Zhang, Viktor K Prasanna University of Southern California {zhan527, prasanna}@usc.edu fpga.usc.edu ACM
More informationBinary Convolutional Neural Network on RRAM
Binary Convolutional Neural Network on RRAM Tianqi Tang, Lixue Xia, Boxun Li, Yu Wang, Huazhong Yang Dept. of E.E, Tsinghua National Laboratory for Information Science and Technology (TNList) Tsinghua
More informationA New Era of Hardware Microservices in the Cloud. Doug Burger Distinguished Engineer, Microsoft UW Cloud Workshop March 31, 2017
A New Era of Hardware Microservices in the Cloud Doug Burger Distinguished Engineer, Microsoft UW Cloud Workshop March 31, 2017 Moore s Law Dennard Scaling has been dead for a decade Moore s La is o er
More informationElasticFlow: A Complexity-Effective Approach for Pipelining Irregular Loop Nests
ElasticFlow: A Complexity-Effective Approach for Pipelining Irregular Loop Nests Mingxing Tan 1 2, Gai Liu 1, Ritchie Zhao 1, Steve Dai 1, Zhiru Zhang 1 1 Computer Systems Laboratory, Electrical and Computer
More informationTracking Acceleration with FPGAs. Future Tracking, CMS Week 4/12/17 Sioni Summers
Tracking Acceleration with FPGAs Future Tracking, CMS Week 4/12/17 Sioni Summers Contents Introduction FPGAs & 'DataFlow Engines' for computing Device architecture Maxeler HLT Tracking Acceleration 2 Introduction
More informationExploring Automatically Generated Platforms in High Performance FPGAs
Exploring Automatically Generated Platforms in High Performance FPGAs Panagiotis Skrimponis b, Georgios Zindros a, Ioannis Parnassos a, Muhsen Owaida b, Nikolaos Bellas a, and Paolo Ienne b a Electrical
More informationResolve: Generation of High Performance Sorting Architectures from High Level Synthesis
Resolve: Generation of High Performance Sorting Architectures from High Level Synthesis Janarbek Matai, Dustin Richmond, Dajung Lee, Zac Blair, Qiongzhi Wu, Amin Abazari, Ryan Kastner Department of Computer
More informationPRIME: A Novel Processing-in-memory Architecture for Neural Network Computation in ReRAM-based Main Memory
Scalable and Energy-Efficient Architecture Lab (SEAL) PRIME: A Novel Processing-in-memory Architecture for Neural Network Computation in -based Main Memory Ping Chi *, Shuangchen Li *, Tao Zhang, Cong
More informationMaximizing Server Efficiency from μarch to ML accelerators. Michael Ferdman
Maximizing Server Efficiency from μarch to ML accelerators Michael Ferdman Maximizing Server Efficiency from μarch to ML accelerators Michael Ferdman Maximizing Server Efficiency with ML accelerators Michael
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 informationHow to Estimate the Energy Consumption of Deep Neural Networks
How to Estimate the Energy Consumption of Deep Neural Networks Tien-Ju Yang, Yu-Hsin Chen, Joel Emer, Vivienne Sze MIT 1 Problem of DNNs Recognition Smart Drone AI Computation DNN 15k 300k OP/Px DPM 0.1k
More informationefpga for Neural Network based Image Recognition
efpga for Neural Network based Image Recognition June 26, 2018 Yoan Dupret Managing Director Menta yoan.dupret@menta-efpga.com Copyright @ 2018 Menta S.A.S. Menta Overview 17 employees 11 years of R&D
More informationGRVI Phalanx. A Massively Parallel RISC-V FPGA Accelerator Accelerator. Jan Gray
GRVI Phalanx A Massively Parallel RISC-V FPGA Accelerator Accelerator Jan Gray jan@fpga.org Introduction FPGA accelerators are hot MSR Catapult. Intel += Altera. OpenPOWER + Xilinx FPGAs as computers Massively
More informationComputer Engineering Mekelweg 4, 2628 CD Delft The Netherlands MSc THESIS. Exploring Convolutional Neural Networks on the
Computer Engineering Mekelweg 4, 2628 CD Delft The Netherlands http://ce.et.tudelft.nl/ 2018 MSc THESIS Exploring Convolutional Neural Networks on the ρ-vex architecture Jonathan Tetteroo Abstract As machine
More informationDEEP LEARNING ACCELERATOR UNIT WITH HIGH EFFICIENCY ON FPGA
DEEP LEARNING ACCELERATOR UNIT WITH HIGH EFFICIENCY ON FPGA J.Jayalakshmi 1, S.Ali Asgar 2, V.Thrimurthulu 3 1 M.tech Student, Department of ECE, Chadalawada Ramanamma Engineering College, Tirupati Email
More informationExtending the PCIe Interface with Parallel Compression/Decompression Hardware for Energy and Performance Optimization
Extending the PCIe Interface with Parallel Compression/Decompression Hardware for Energy and Performance Optimization Mohd Amiruddin Zainol Department of Electrical and Electronic Engineering, University
More informationM.Tech Student, Department of ECE, S.V. College of Engineering, Tirupati, India
International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue 5 ISSN : 2456-3307 High Performance Scalable Deep Learning Accelerator
More informationDEEP NEURAL NETWORKS FOR OBJECT DETECTION
DEEP NEURAL NETWORKS FOR OBJECT DETECTION Sergey Nikolenko Steklov Institute of Mathematics at St. Petersburg October 21, 2017, St. Petersburg, Russia Outline Bird s eye overview of deep learning Convolutional
More informationESE: Efficient Speech Recognition Engine for Sparse LSTM on FPGA
ESE: Efficient Speech Recognition Engine for Sparse LSTM on FPGA Song Han 1,2, Junlong Kang 2, Huizi Mao 1, Yiming Hu 3, Xin Li 2, Yubin Li 2, Dongliang Xie 2, Hong Luo 2, Song Yao 2, Yu Wang 2,3, Huazhong
More informationBHNN: a Memory-Efficient Accelerator for Compressing Deep Neural Network with Blocked Hashing Techniques
BHNN: a Memory-Efficient Accelerator for Compressing Deep Neural Network with Blocked Hashing Techniques Jingyang Zhu 1, Zhiliang Qian 2*, and Chi-Ying Tsui 1 1 The Hong Kong University of Science and
More informationOpenCL on FPGAs - Creating custom accelerated solutions
OpenCL on FPGAs - Creating custom accelerated solutions Manuel Greisinger Channel Manager, Central & Eastern Europe Oct 13 th, 2015 ESSEI Technology Day, Gilching, Germany Industry Trends Increasing product
More informationVersal: AI Engine & Programming Environment
Engineering Director, Xilinx Silicon Architecture Group Versal: Engine & Programming Environment Presented By Ambrose Finnerty Xilinx DSP Technical Marketing Manager October 16, 2018 MEMORY MEMORY MEMORY
More information"On the Capability and Achievable Performance of FPGAs for HPC Applications"
"On the Capability and Achievable Performance of FPGAs for HPC Applications" Wim Vanderbauwhede School of Computing Science, University of Glasgow, UK Or in other words "How Fast Can Those FPGA Thingies
More informationAn Adaptable Deep Learning Accelerator Unit (DLAU) for FPGA
An Adaptable Deep Learning Accelerator Unit (DLAU) for FPGA N. Sireesha 1 & P.Malleswari 2 1PG Scholar, Dept of ECE, Narsaraopeta Institute of Technology, Yellamanda, Narsaraopeta, Guntur district, Andhra
More informationUser Manual for FC100
Sundance Multiprocessor Technology Limited User Manual Form : QCF42 Date : 6 July 2006 Unit / Module Description: IEEE-754 Floating-point FPGA IP Core Unit / Module Number: FC100 Document Issue Number:
More informationDRAF: A Low-Power DRAM-based Reconfigurable Acceleration Fabric
DRAF: A Low-Power DRAM-based Reconfigurable Acceleration Fabric Mingyu Gao, Christina Delimitrou, Dimin Niu, Krishna Malladi, Hongzhong Zheng, Bob Brennan, Christos Kozyrakis ISCA June 22, 2016 FPGA-Based
More informationReconfigurable Acceleration of 3D-CNNs for Human Action Recognition with Block Floating-Point Representation
Reconfigurable Acceleration of 3D-CNNs for Human Action Recognition with Block Floating-Point Representation Hongxiang Fan, Ho-Cheung Ng, Shuanglong Liu, Zhiqiang Que, Xinyu Niu, Wayne Luk Dept. of Computing,
More informationHow to Build Optimized ML Applications with Arm Software
How to Build Optimized ML Applications with Arm Software Arm Technical Symposia 2018 ML Group Overview Today we will talk about applied machine learning (ML) on Arm. My aim for today is to show you just
More informationComPEND: Computation Pruning through Early Negative Detection for ReLU in a Deep Neural Network Accelerator
ICS 28 ComPEND: Computation Pruning through Early Negative Detection for ReLU in a Deep Neural Network Accelerator June 3, 28 Dongwoo Lee, Sungbum Kang, Kiyoung Choi Neural Processing Research Center (NPRC)
More informationThe Lekha 3GPP LTE FEC IP Core meets 3GPP LTE specification 3GPP TS V Release 10[1].
Lekha IP 3GPP LTE FEC Encoder IP Core V1.0 The Lekha 3GPP LTE FEC IP Core meets 3GPP LTE specification 3GPP TS 36.212 V 10.5.0 Release 10[1]. 1.0 Introduction The Lekha IP 3GPP LTE FEC Encoder IP Core
More informationIn Live Computer Vision
EVA 2 : Exploiting Temporal Redundancy In Live Computer Vision Mark Buckler, Philip Bedoukian, Suren Jayasuriya, Adrian Sampson International Symposium on Computer Architecture (ISCA) Tuesday June 5, 2018
More informationConvolutional Neural Networks: Applications and a short timeline. 7th Deep Learning Meetup Kornel Kis Vienna,
Convolutional Neural Networks: Applications and a short timeline 7th Deep Learning Meetup Kornel Kis Vienna, 1.12.2016. Introduction Currently a master student Master thesis at BME SmartLab Started deep
More informationNVIDIA FOR DEEP LEARNING. Bill Veenhuis
NVIDIA FOR DEEP LEARNING Bill Veenhuis bveenhuis@nvidia.com Nvidia is the world s leading ai platform ONE ARCHITECTURE CUDA 2 GPU: Perfect Companion for Accelerating Apps & A.I. CPU GPU 3 Intro to AI AGENDA
More informationIntroduction to Field Programmable Gate Arrays
Introduction to Field Programmable Gate Arrays Lecture 1/3 CERN Accelerator School on Digital Signal Processing Sigtuna, Sweden, 31 May 9 June 2007 Javier Serrano, CERN AB-CO-HT Outline Historical introduction.
More informationTETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory
TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory Mingyu Gao, Jing Pu, Xuan Yang, Mark Horowitz, Christos Kozyrakis Stanford University Platform Lab Review Feb 2017 Deep Neural
More informationComputer Architectures for Deep Learning. Ethan Dell and Daniyal Iqbal
Computer Architectures for Deep Learning Ethan Dell and Daniyal Iqbal Agenda Introduction to Deep Learning Challenges Architectural Solutions Hardware Architectures CPUs GPUs Accelerators FPGAs SOCs ASICs
More informationDeep Learning Accelerators
Deep Learning Accelerators Abhishek Srivastava (as29) Samarth Kulshreshtha (samarth5) University of Illinois, Urbana-Champaign Submitted as a requirement for CS 433 graduate student project Outline Introduction
More informationDeep Learning Processing Technologies for Embedded Systems. October 2018
Deep Learning Processing Technologies for Embedded Systems October 2018 1 Neural Networks Architecture Single Neuron DNN Multi Task NN Multi-Task Vehicle Detection With Region-of-Interest Voting Popular
More informationSimple and Powerful Animation Compression. Nicholas Fréchette Programming Consultant for Eidos Montreal
Simple and Powerful Animation Compression Nicholas Fréchette Programming Consultant for Eidos Montreal Contributors Frédéric Zimmer, co-designer Luke Mamacos, consultant Thank you Eidos Montreal! Presentation
More informationIntroduction to Neural Networks
ECE 5775 (Fall 17) High-Level Digital Design Automation Introduction to Neural Networks Ritchie Zhao, Zhiru Zhang School of Electrical and Computer Engineering Rise of the Machines Neural networks have
More informationBandwidth-Centric Deep Learning Processing through Software-Hardware Co-Design
Bandwidth-Centric Deep Learning Processing through Software-Hardware Co-Design Song Yao 姚颂 Founder & CEO DeePhi Tech 深鉴科技 song.yao@deephi.tech Outline - About DeePhi Tech - Background - Bandwidth Matters
More informationOptimizing CNN-based Object Detection Algorithms on Embedded FPGA Platforms
Optimizing CNN-based Object Detection Algorithms on Embedded FPGA Platforms Ruizhe Zhao 1, Xinyu Niu 1, Yajie Wu 2, Wayne Luk 1, and Qiang Liu 3 1 Imperial College London {ruizhe.zhao15,niu.xinyu10,w.luk}@imperial.ac.uk
More informationResource Efficient Real-Time Processing of Contrast Limited Adaptive Histogram Equalization
Resource Efficient Real-Time Processing of Contrast Limited Adaptive Histogram Equalization Burak Ünal, Ali Akoglu Reconfigurable Computing Lab Department of Electrical and Computer Engineering The University
More informationDNN ENGINE: A 16nm Sub-uJ DNN Inference Accelerator for the Embedded Masses
DNN ENGINE: A 16nm Sub-uJ DNN Inference Accelerator for the Embedded Masses Paul N. Whatmough 1,2 S. K. Lee 2, N. Mulholland 2, P. Hansen 2, S. Kodali 3, D. Brooks 2, G.-Y. Wei 2 1 ARM Research, Boston,
More informationCS 61C: Great Ideas in Computer Architecture Performance and Floating-Point Arithmetic
CS 61C: Great Ideas in Computer Architecture Performance and Floating-Point Arithmetic Instructors: Nick Weaver & John Wawrzynek http://inst.eecs.berkeley.edu/~cs61c/sp18 3/16/18 Spring 2018 Lecture #17
More informationCore Facts. Documentation Design File Formats. Verification Instantiation Templates Reference Designs & Application Notes Additional Items
(ULFFT) November 3, 2008 Product Specification Dillon Engineering, Inc. 4974 Lincoln Drive Edina, MN USA, 55436 Phone: 952.836.2413 Fax: 952.927.6514 E-mail: info@dilloneng.com URL: www.dilloneng.com Core
More informationScaling Throughput Processors for Machine Intelligence
Scaling Throughput Processors for Machine Intelligence ScaledML Stanford 24-Mar-18 simon@graphcore.ai 1 MI The impact on humanity of harnessing machine intelligence will be greater than the impact of harnessing
More informationFPGA BASED IMPLEMENTATION OF DEEP NEURAL NETWORKS USING ON-CHIP MEMORY ONLY. Jinhwan Park and Wonyong Sung
FPGA BASED IMPLEMENTATION OF DEEP NEURAL NETWORKS USING ON-CHIP MEMORY ONLY Jinhwan Park and Wonyong Sung Department of Electrical and Computer Engineering Seoul National University Seoul 151-744 Korea
More informationRe-Examining Conventional Wisdom for Networks-on-Chip in the Context of FPGAs
This work was funded by NSF. We thank Xilinx for their FPGA and tool donations. We thank Bluespec for their tool donations. Re-Examining Conventional Wisdom for Networks-on-Chip in the Context of FPGAs
More informationIndustry Collaboration and Innovation
Industry Collaboration and Innovation Industry Landscape Key changes occurring in our industry Historical microprocessor technology continues to deliver far less than the historical rate of cost/performance
More informationXilinx DNN Processor An Inference Engine, Network Compiler + Runtime for Xilinx FPGAs
ilinx DNN Proceor An Inference Engine, Network Compiler Runtime for ilinx FPGA Rahul Nimaiyar, Brian Sun, Victor Wu, Thoma Branca, Yi Wang, Jutin Oo, Elliott Delaye, Aaron Ng, Paolo D'Alberto, Sean Settle,
More informationFPGA Matrix Multiplier
FPGA Matrix Multiplier In Hwan Baek Henri Samueli School of Engineering and Applied Science University of California Los Angeles Los Angeles, California Email: chris.inhwan.baek@gmail.com David Boeck Henri
More informationParallel Reconfigurable Hardware Architectures for Video Processing Applications
Parallel Reconfigurable Hardware Architectures for Video Processing Applications PhD Dissertation Presented by Karim Ali Supervised by Prof. Jean-Luc Dekeyser Dr. HdR. Rabie Ben Atitallah Parallel Reconfigurable
More informationInference Engine compiler and SDK FWDNXT 2018
Inference Engine compiler and SDK 1 Deep Learning processor Best performance per power Best utilization Efficient use of memory bandwidth Low latency Scalability: IoT to cloud 2 Deep Learning processor
More informationTwo FPGA-DNN Projects: 1. Low Latency Multi-Layer Perceptrons using FPGAs 2. Acceleration of CNN Training on FPGA-based Clusters
Two FPGA-DNN Projects: 1. Low Latency Multi-Layer Perceptrons using FPGAs 2. Acceleration of CNN Training on FPGA-based Clusters *Argonne National Lab +BU & USTC Presented by Martin Herbordt Work by Ahmed
More informationDRAF: A Low-Power DRAM-based Reconfigurable Acceleration Fabric
DRAF: A Low-Power DRAM-based Reconfigurable Acceleration Fabric Mingyu Gao, Christina Delimitrou, Dimin Niu, Krishna Malladi, Hongzhong Zheng, Bob Brennan, Christos Kozyrakis ISCA June 22, 2016 FPGA-Based
More information