4K HEVC Video Processing with GPU Optimization on Jetson TX1
|
|
- George Robbins
- 6 years ago
- Views:
Transcription
1 4K HEVC Video Processing with GPU Optimization on Jetson TX1 Tobias Kammacher Matthias Frei Hans Gelke Institute of Embedded Systems / High Performance Multimedia Research Group Zurich University of Applied Sciences
2 Goal 1. 4K Video Realtime 2. Capturing 3. Scaling, Mixing 4. Encoding H.265/HEVC 2
3 Requirements Streaming Use Case 2nd Video Source Gbps Mbps Video Input Color Space Conversion Scaling Picture in Picture H.264/H.265 Encoder Audio Audio/Video Mux Encryption Transport Protocol Packer Forward Error Correction Ethernet Output Recorder 3
4 Requirements Hardware Limitations Nvidia Jetson TX1 Development Board Gigabit Ethernet Video Output HDMI x Hz WIFI 802.1ac 2x2 Video Input 4 Images: anandtech.com, wccftech.com
5 Video Input MIPI CSI-2 Video Interface (Camera Serial Interface) 1-4 Lanes Images: wccftech.com, nvidia.com 5
6 Video Input Use Case / Hardware Design Capture HDMI sources 4K p and process them CSI HDMI 4K HDMI 1080p Toshiba TC TC Jetson TX1 Dev Board Process Video Ethernet Stream 4K* requires 8 CSI lanes in our case (hardware limitation) * 2160p30 YUV422 6
7 Video Input Hardware Design Nvidia Jetson TX1 Development Board HDMI2CSI module 7
8 Video Input Capture Driver Development Driver Overview Bridge: tc Host: tegra_vi2 Features Capture 720p60, 1080p60, 2160p30 Capture custom formats Available Open Source: 8
9 Video Rendering Frameworks GStreamer Pipeline-based Multimedia Framework OpenGL Graphics API with GPU Acceleration Plugins for Gstreamer available GStreamer is free software available under the terms of the LGPL license OpenGL and the oval logo are trademarks or registered trademarks of Silicon Graphics, Inc 9
10 Video Processing Example: Scaling, Mixing Gstreamer Pipeline V4L2 Source V4L2 Source Format Convert Scale Mix (PiP) Render HDMI Mixing two sources (4K and 1080p) 10
11 Video Processing Example: Scaling, Mixing Logo 1080p Video 4K Video Images: CC BY-SA Wikimedia 11
12 Video Processing Example: Scaling, Mixing Gstreamer Pipeline V4L2 Source V4L2 Source Format Convert Scale Mix (PiP) Render HDMI Mixing two sources (4K and 1080p) CPU: Using compositor element: 1.2 FPS gst-launch-1.0 v4l2src! 'video/x-raw, format=uyvy, framerate=30/1, width=3840, height=2160'! compositor name=comp sink_0::alpha=1 sink_1::alpha=0.5! xvimagesink sync=false videotestsrc pattern=1! 'video/xraw,format=uyvy, framerate=30/1, width=1000, height=1000'! comp. OpenGL (glvideomixer & glimagesink): 6.8 FPS PiP Pipeline FPS? CPU OpenGL Required Need a solution with better performance => GPU 12
13 GPU Processing GPU Memory Access Methods Unified Virtual Addressing TX1 Zero Copy TX1 Managed Memory TX1 CPU GPU CPU GPU CPU GPU L2 Cache L2 Cache L2 Cache L2 Cache L2 Cache L2 Cache Memory Controller DRAM 4GB Memory Controller DRAM 4GB Memory Controller DRAM 4GB CPU Buffer GPU Buffer Shared Buffer Shared Buffer 13
14 GPU Processing Results Tested use cases PiP Dynamic Logo Fixed Images: CC BY-SA Wikimedia 14
15 GPU Processing PiP Test (GPU Data Transfer and Kernel Execution) Unified Virtual Addressing Step 1: cudamemcpy() to GPU * 12.5 ms Step 2: Execute kernel 9-11 ms Step 3: cudamemcpy() to host * 7.2 ms Step 1: Zero Copy cudamallochost(): Allocate memory on host ** Step 2: Execute kernel ms - Total: 30 ms Total: 25 ms * Upload 4K p, Download 4K ** One time only operation Step 1: Managed Memory cudamallocmanaged(): Allocate shared memory ** Step 2: Execute kernel 9-11 ms Step 3: synchronize with CPU 0.2 ms - Total: 10 ms 15
16 GPU Processing Results PiP pipeline achieves 30 FPS Using managed memory Logo pipeline achieves 30 FPS Using UVA, copy once Additional: Consecutive kernels executed faster PiP Pipeline FPS CPU OpenGL GPU 16
17 Conclusion Hardware Mapping 2nd Video Source Gbps Mbps Video Input Color Space Conversion Scaling Picture in Picture H.264/H.265 Encoder Audio Audio/Video Mux Encryption Transport Protocol Packer Forward Error Correction Ethernet Output GPU Recorder HW Block CPU 17
18 Conclusion Driver for 4K HDMI capturing Video processing on GPU Shared Memory Data transfer mode TX1 for 4K video Capturing Processing Streaming 18
19 Find us on the web: Blog: Github: Hardware Board: 19
4K Video Processing and Streaming Platform on TX1
4K Video Processing and Streaming Platform on TX1 Tobias Kammacher Dr. Matthias Rosenthal Institute of Embedded Systems / High Performance Multimedia Research Group Zurich University of Applied Sciences
More informationEfficient Video Processing on Embedded GPU
Efficient Video Processing on Embedded GPU Tobias Kammacher Armin Weiss Matthias Frei Institute of Embedded Systems High Performance Multimedia Research Group Zurich University of Applied Sciences (ZHAW)
More information4K Video Processing and Streaming Platform on TX1
4K Video Processing and Streaming Platform on TX1 Tobias Kammacher Dr. Matthias Rosenthal Institute of Embedded Systems / High Performance Multimedia Research Group Zurich University of Applied Sciences
More informationUsing mobile processors for general purpose industrial signal processing
Using mobile processors for general purpose industrial signal processing Hans-Joachim Gelke hans.gelke@zhaw.ch Tobias Kammacher tobias.kammacher@zhaw.ch Matthias Rosenthal matthias.rosenthal@zhaw.ch Amin
More informationRealtime Signal Processing on Nvidia TX2 using CUDA
Realtime Signal Processing on Nvidia TX2 using CUDA Armin Weiss Dr. Amin Mazloumian Dr. Matthias Rosenthal Institute of Embedded Systems High Performance Multimedia Research Group Zurich University of
More informationRealtime Signal Processing on Embedded GPUs
Realtime Signal Processing on Embedded s Dr. Matthias Rosenthal Armin Weiss Dr. Amin Mazloumian Institute of Embedded Systems Realtime Platforms Research Group Zurich University of Applied Sciences Motivation
More informationMultimedia SoC System Solutions
Multimedia SoC System Solutions Presented By Yashu Gosain & Forrest Picket: System Software & SoC Solutions Marketing Girish Malipeddi: IP Subsystems Marketing Agenda Zynq Ultrascale+ MPSoC and Multimedia
More informationGstShark profiling: a real-life example. Michael Grüner - David Soto -
GstShark profiling: a real-life example Michael Grüner - michael.gruner@ridgerun.com David Soto - david.soto@ridgerun.com Introduction Michael Grüner Technical Lead at RidgeRun Digital signal processing
More informationGStreamer Conference 2013, Edinburgh 22 October Sebastian Dröge Centricular Ltd
The never-ending story: GStreamer and hardware integration GStreamer Conference 2013, Edinburgh 22 October 2013 Sebastian Dröge Centricular Ltd Who is speaking? Sebastian Dröge,
More informationEmbedded Streaming Media with GStreamer and BeagleBoard. Presented by Todd Fischer todd.fischer (at) ridgerun.com
Embedded Streaming Media with GStreamer and BeagleBoard Presented by Todd Fischer todd.fischer (at) ridgerun.com 1 Agenda BeagleBoard-XM multimedia features GStreamer concepts GStreamer hands on exercises
More informationTHE LEADER IN VISUAL COMPUTING
MOBILE EMBEDDED THE LEADER IN VISUAL COMPUTING 2 TAKING OUR VISION TO REALITY HPC DESIGN and VISUALIZATION AUTO GAMING 3 BEST DEVELOPER EXPERIENCE Tools for Fast Development Debug and Performance Tuning
More informationEmbedded Computing without Compromise. Evolution of the Rugged GPGPU Computer Session: SIL7127 Dan Mor PLM -Aitech Systems GTC Israel 2017
Evolution of the Rugged GPGPU Computer Session: SIL7127 Dan Mor PLM - Systems GTC Israel 2017 Agenda Current GPGPU systems NVIDIA Jetson TX1 and TX2 evaluation Conclusions New Products 2 GPGPU Product
More informationIntelligent Surveillance
Intelligent Surveillance About Me 9 Years experience developing on Linux based platforms. Prior to that, worked as a system admin in hardware and networking. Google Summer of Code 2015: Developed RootFS
More informationMCN Streaming. An Adaptive Video Streaming Platform. Qin Chen Advisor: Prof. Dapeng Oliver Wu
MCN Streaming An Adaptive Video Streaming Platform Qin Chen Advisor: Prof. Dapeng Oliver Wu Multimedia Communications and Networking (MCN) Lab Dept. of Electrical & Computer Engineering, University of
More informationA176 Cyclone. GPGPU Fanless Small FF RediBuilt Supercomputer. IT and Instrumentation for industry. Aitech I/O
The A176 Cyclone is the smallest and most powerful Rugged-GPGPU, ideally suited for distributed systems. Its 256 CUDA cores reach 1 TFLOPS, and it consumes less than 17W at full load (8-10W at typical
More informationPorting Tizen-IVI 3.0 to an ARM based SoC Platform. Damian Hobson-Garcia, IGEL Co., Ltd.
Porting Tizen-IVI 3.0 to an ARM based SoC Platform Damian Hobson-Garcia, IGEL Co., Ltd. Current State of Affairs Intel architecture (x86) system Tizen IVI 2.0alpha, Tizen IVI 3.0 ARM architecture based
More informationCase Study: Building a High Quality Video Pipeline Using GStreamer and V4Linux on an i.mx6
Case Study: Building a High Quality Video Pipeline Using GStreamer and V4Linux on an i.mx6 Sean Hudson Embedded Linux Architect & Member of Technical Staff Android is a trademark of Google Inc. Use of
More informationMAPPING VIDEO CODECS TO HETEROGENEOUS ARCHITECTURES. Mauricio Alvarez-Mesa Techische Universität Berlin - Spin Digital MULTIPROG 2015
MAPPING VIDEO CODECS TO HETEROGENEOUS ARCHITECTURES Mauricio Alvarez-Mesa Techische Universität Berlin - Spin Digital MULTIPROG 2015 Video Codecs 70% of internet traffic will be video in 2018 [CISCO] Video
More informationPorting Tizen-IVI 3.0 to an ARM based SoC Platform
Porting Tizen-IVI 3.0 to an ARM based SoC Platform Damian Hobson-Garcia Automotive Linux Summit July 1-2, 2014 Tokyo, Japan Tizen IVI support Until recently Intel architecture (x86) system Tizen IVI 2.0alpha,
More informationMemory Management in Tizen. SW Platform Team, SW R&D Center
Memory Management in Tizen SW Platform Team, SW R&D Center Contents Tizen Kernel Overview Memory Management in Tizen Kernel Memory Size Optimization 2 Tizen Kernel Overview 3 Tizen Kernel Overview Core
More informationSimple Plugin API. Wim Taymans Principal Software Engineer October 10, Pinos Wim Taymans
Simple Plugin API Wim Taymans Principal Software Engineer October 10, 2016 1 In the begining 2 Pinos DBus service for sharing camera Upload video and share And then... Extend scope Add audio too upload,
More informationTowards Automatic Heterogeneous Computing Performance Analysis. Carl Pearson Adviser: Wen-Mei Hwu
Towards Automatic Heterogeneous Computing Performance Analysis Carl Pearson pearson@illinois.edu Adviser: Wen-Mei Hwu 2018 03 30 1 Outline High Performance Computing Challenges Vision CUDA Allocation and
More informationEmbedded Vision Solutions
FLEXIBLE SOLUTIONS FOR EMBEDDED VISION PROCESSING AT THE EDGE Embedded Vision Solutions Embedded vision offers a promising future with many exciting new applications entering the market. These systems
More informationGStreamer Daemon - Building a media server under 30min. Michael Grüner - David Soto -
GStreamer Daemon - Building a media server under 30min Michael Grüner - michael.gruner@ridgerun.com David Soto - david.soto@ridgerun.com Introduction Michael Grüner Technical Lead at RidgeRun Digital signal
More informationConnecting the uvcvideo driver of the PHYTEC USB-CAM-104H
Application Note No. LAN-056e Version: 1.0 Author: D. Heer Date: 06.10.2011 Historie: Version Changes Date Author 1.0 Creation of the document 06.10.2011 D. Heer Connecting the uvcvideo driver of the PHYTEC
More informationEGLSTREAMS: INTEROPERABILITY FOR CAMERA, CUDA AND OPENGL. Debalina Bhattacharjee Sharan Ashwathnarayan
53023 - EGLSTREAMS: INTEROPERABILITY FOR CAMERA, CUDA AND OPENGL Debalina Bhattacharjee Sharan Ashwathnarayan Tegra SOC and typical use-cases Why Interops EGLStream and Its Key Features Agenda Examples
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 informationTBS8510 Transcoder Server User Guide
TBS8510 Transcoder Server User Guide Copyright TBS Technologies 2005-2019 All Rights Reserved 2019-01-08 1 / 53 TBS8510 User Guide Catalog 1. Product Overview... 4 1.1 Product Presentation... 4 1.2 Product
More informationSolid State Graphics (SSG) SDK Setup and Raw Video Player Guide
Solid State Graphics (SSG) SDK Setup and Raw Video Player Guide PAGE 1 Radeon Pro SSG SDK Setup To enable you to access the capabilities of the Radeon Pro SSG card, it comes with extensions for Microsoft
More informationProfiling and Debugging OpenCL Applications with ARM Development Tools. October 2014
Profiling and Debugging OpenCL Applications with ARM Development Tools October 2014 1 Agenda 1. Introduction to GPU Compute 2. ARM Development Solutions 3. Mali GPU Architecture 4. Using ARM DS-5 Streamline
More informationE9171-based Graphics/Compute Engine
Product Overview E9171-based Graphics/Compute Engine Compact, Power Efficient DO-254 Certifiable GPU Module IP Features and Benefits Part of the COTS-D family of safety certifiable modules A compact GPU
More informationA176 C clone. GPGPU Fanless Small FF RediBuilt Supercomputer. Aitech
The A176 Cyclone is the smallest and most powerful Rugged-GPGPU, ideally suited for distributed systems. Its 256 CUDA cores reach 1 TFLOPS at a remarkable level of energy efficiency, providing all the
More informationYafit Snir Arindam Guha Cadence Design Systems, Inc. Accelerating System level Verification of SOC Designs with MIPI Interfaces
Yafit Snir Arindam Guha, Inc. Accelerating System level Verification of SOC Designs with MIPI Interfaces Agenda Overview: MIPI Verification approaches and challenges Acceleration methodology overview and
More informationarm MULTICORE PLATFORMS FOR ADVANCED APPLICATIONS Product Longevity
The new i.mx B processor series builds on 15+ years of cutting-edge technology, robust software, and broad ecosystem support to continue the NXP tradition of helping customers find the right balance between
More informationRemote Access and Output Sharing Between Multiple ECUs for Automotive
Remote Access and Output Sharing Between Multiple ECUs for Automotive 20/6/2018 Harunobu KUROKAWA Open system development center, Automotive information solution business division Renesas Electronics Corporation
More informationSOM PRODUCTS BRIEF. S y s t e m o n M o d u l e. Engicam. SOMProducts ver
SOM S y s t e m o n M o d u l e PRODUCTS BRIEF GEA M6425IB ARM9 TM Low cost solution Reduced Time to Market Very small form factor Low cost multimedia solutions Industrial Automotive Consumer Single power
More informationSpeed Sign Detection Using Convolutional Neural Network Accelerator IP User Guide
Speed Sign Detection Using Convolutional Neural Network Accelerator IP FPGA-RD-02035-1.0 May 2018 Contents Acronyms in This Document... 3 Introduction... 4 Reference Design Overview... 5 Block diagram...
More informationDesigning with NXP i.mx8m SoC
Designing with NXP i.mx8m SoC Course Description Designing with NXP i.mx8m SoC is a 3 days deep dive training to the latest NXP application processor family. The first part of the course starts by overviewing
More informationAMD HD5450 PCIe ADD-IN BOARD. Datasheet AEGX-A3T5-01FST1
AMD HD5450 PCIe ADD-IN BOARD Datasheet AEGX-A3T5-01FST1 CONTENTS 1. Feature... 3 2. Functional Overview... 4 2.1. Memory Interface... 4 2.2. Acceleration Features... 4 2.3. Avivo Display System... 5 2.4.
More informationThe Mobile Internet: The Potential of Handhelds to Bring Internet to the Masses. April 2008
The Mobile Internet: The Potential of Handhelds to Bring Internet to the Masses April 2008 Agenda Today s Mobile Internet Market Mobile Convergence Products Internet Browsing on a Handheld Separating Fact
More informationSpeed Sign Detection Using Convolutional Neural Network Accelerator IP Reference Design
Speed Sign Detection Using Convolutional Neural Network Accelerator IP FPGA-RD-02035 Version 1.1 September 2018 Contents Acronyms in This Document... 3 1. Introduction... 4 2. Overview... 5 2.1. Block
More informationHugo Cunha. Senior Firmware Developer Globaltronics
Hugo Cunha Senior Firmware Developer Globaltronics NB-IoT Product Acceleration Platforms 2018 Speaker Hugo Cunha Project Developper Agenda About us NB IoT Platforms The WIIPIIDO The Gateway FE 1 About
More informationGPM0002 E9171-based Graphics/Compute Engine
GPM0002 E9171-based Graphics/Compute Engine Compact, Power Efficient DO-254/ED-80 Certifiable GPU Module IP Features and Benefits Part of the COTS-D family of safety certifiable modules A compact GPU module
More informationMustang-200 Accelerate to the Future
Mustang-200 Accelerate to the Future Multiple Applications & Tasking (6) Micro-Server 1-1 Big Data computing Micro-Server 1-2 Face recognition (5) Micro-Server 1-1 Big Data computing Micro-Server 1-2 Face
More informationA Linux multimedia platform for SH-Mobile processors
A Linux multimedia platform for SH-Mobile processors Embedded Linux Conference 2009 April 7, 2009 Abstract Over the past year I ve been working with the Japanese semiconductor manufacturer Renesas, developing
More informationTEGRA LINUX DRIVER PACKAGE R23.2
TEGRA LINUX DRIVER PACKAGE R23.2 RN_05071-R23 February 25, 2016 Advance Information Subject to Change Release Notes RN_05071-R23 TABLE OF CONTENTS 1.0 ABOUT THIS RELEASE... 3 1.1 What s New... 3 1.2 Login
More informationAccelerating Cloud Graphics
Accelerating Cloud Graphics Franck DIARD, Ph. D. SW Architect Distinguished Engineer, NVIDIA Agenda 30 minute talk 10 minute demo 10 minute Q&A GeForce GRID Lower Latency Higher Density Higher Quality
More informationACCELERATED GSTREAMER USER GUIDE
` ACCELERATED GSTREAMER USER GUIDE DA_07303-3.9 November 2, 2018 Release 31.1 DOCUMENT CHANGE HISTORY DA_07303-3.9 Version Date Authors Description of Change v1.0 01 May 2015 NVIDIA Initial release. v1.1
More informationAccelerate to the Future
Accelerate to the Future 1 Mustang-200 Overview 10Gbps Network Based x86 Computing Accelerator 10 Gigabit Ethernet based x86 computing nodes support decentralized computing architecture Perfectly integrated
More informationAdhocracy Innovation with Imaging technology. Socionext Inc. Hiroyuki Komori July 5th, 2017
Adhocracy Innovation with Imaging technology Socionext Inc. Hiroyuki Komori July 5th, 2017 Video Steaming in the world Video uploading : 65,000 clip/min, 300 hour/min on YouTube Video viewing : billions
More informationExporting virtual memory as dmabuf. Nikhil Devshatwar Texas Instruments, India
1 Exporting virtual memory as dmabuf Nikhil Devshatwar Texas Instruments, India 2 About author Embedded Linux developer @Texas Instruments Video subsystem Camera drivers Base port support Contributions
More informationNETPC-BD6C User s Manual BASED ON VERSION AMD DRIVER
NETPC-BD6C User s Manual BASED ON VERSION 9.001 AMD DRIVER The purpose of this document is to discuss the uses and various setups for the Technovare Multiport computer (NETPC-BD6C). The NETPC-BD6C consists
More informationGPGPU introduction and network applications. PacketShaders, SSLShader
GPGPU introduction and network applications PacketShaders, SSLShader Agenda GPGPU Introduction Computer graphics background GPGPUs past, present and future PacketShader A GPU-Accelerated Software Router
More informationWhat s cooking in GStreamer. FOSDEM, Brussels 1 February Tim-Philipp Müller Sebastian Dröge
What s cooking in GStreamer FOSDEM, Brussels 1 February 2014 Tim-Philipp Müller Sebastian Dröge Introduction who are we? what is GStreamer? What is GStreamer?
More informationBringing display and 3D to the C.H.I.P computer
Embedded Linux Conference 2016 Bringing display and 3D to the C.H.I.P computer Maxime Ripard maxime@bootlin.com Copyright 2004-2018, Bootlin. Creative Commons BY-SA 3.0 license. embedded Linux and kernel
More informationTBS8520 Transcoder Server User Guide
TBS8520 Transcoder Server User Guide Copyright TBS Technologies 2005-2018 All Rights Reserved 2018-06-21 1 / 37 TBS8520 User Guide Catalog 1. Product Overview... 3 1.1 Product Presentation... 3 1.2 Product
More informationNVJPEG. DA _v0.1.4 August nvjpeg Libary Guide
NVJPEG DA-06762-001_v0.1.4 August 2018 Libary Guide TABLE OF CONTENTS Chapter 1. Introduction...1 Chapter 2. Using the Library... 3 2.1. Single Image Decoding... 3 2.3. Batched Image Decoding... 6 2.4.
More informationAMD HD7750 PCIe ADD-IN BOARD. Datasheet (GFX-A3T2-01FST1)
AMD HD7750 PCIe ADD-IN BOARD Datasheet (GFX-A3T2-01FST1) CONTENTS 1. Feature... 3 2. Functional Overview... 4 2.1. Memory Interface... 4 2.2. Memory Aperture Size... 4 2.3. Avivo Display System... 5 2.4.
More informationThunderbolt 3 USER GUIDE. For more information visit
Thunderbolt 3 USER GUIDE For more information visit www.caldigit.com Table of Contents Section 1 : General Information General Use Warnings Safety Warnings System Requirements In the Box Thunderbolt 3
More informationCSE 599 I Accelerated Computing - Programming GPUS. Advanced Host / Device Interface
CSE 599 I Accelerated Computing - Programming GPUS Advanced Host / Device Interface Objective Take a slightly lower-level view of the CPU / GPU interface Learn about different CPU / GPU communication techniques
More informationApril 4-7, 2016 Silicon Valley VISIONWORKS A CUDA ACCELERATED COMPUTER VISION LIBRARY S6783. Elif Albuz, April 4, 2016
April 4-7, 2016 Silicon Valley VISIONWORKS A CUDA ACCELERATED COMPUTER VISION LIBRARY S6783 Elif Albuz, April 4, 2016 Motivation Introduction to VisionWorks AGENDA VisionWorks Software Stack VisionWorks
More informationModule Introduction. Content 15 pages 2 questions. Learning Time 25 minutes
Purpose The intent of this module is to introduce you to the multimedia features and functions of the i.mx31. You will learn about the Imagination PowerVR MBX- Lite hardware core, graphics rendering, video
More informationAMD HD7750 2GB PCIEx16
AMD HD7750 2GB PCIEx16 ADVANTECH MODEL: GFX-AH7750L16-5J MPN number: 1A1-E000130ADP Performance PCIe Graphics 4 x Mini DP CONTENTS 1. Specification... 3 2. Functional Overview... 4 2.1. Memory Interface...
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 informationBringing display and 3D to the C.H.I.P computer
Embedded Linux Conference 2016 Bringing display and 3D to the C.H.I.P computer Maxime Ripard Free Electrons maxime@free-electrons.com Free Electrons Embedded Linux Developers c Copyright 2004-2016, Free
More informationNVIDIA AI BRAIN OF SELF DRIVING AND HD MAPPING. September 13, 2016
NVIDIA AI BRAIN OF SELF DRIVING AND HD MAPPING September 13, 2016 AI FOR AUTONOMOUS DRIVING MAPPING KALDI LOCALIZATION DRIVENET Training on DGX-1 NVIDIA DGX-1 NVIDIA DRIVE PX 2 Driving with DriveWorks
More informationObject Counting Using Convolutional Neural Network Accelerator IP Reference Design
Object Counting Using Convolutional Neural Network Accelerator IP FPGA-RD-02036 Version 1.1 September 2018 Contents Acronyms in This Document... 3 1. Introduction... 4 2. Related Documentation... 5 2.1.
More informationedix Data Sheet XTRMX January 2018 XTRMX.com/edix
xview 2.1 PreRequisites edix Data Sheet XTRMX January 2018 XTRMX.com/edix edix 2.2 Remote Editing Proxy-free workflow Integrated with Adobe Premiere Pro Audio Support up to 8 tracks Storage agnostic XTRMX
More informationTR An Overview of NVIDIA Tegra K1 Architecture. Ang Li, Radu Serban, Dan Negrut
TR-2014-17 An Overview of NVIDIA Tegra K1 Architecture Ang Li, Radu Serban, Dan Negrut November 20, 2014 Abstract This paperwork gives an overview of NVIDIA s Jetson TK1 Development Kit and its Tegra K1
More informationEfficient Data Transfers
Efficient Data fers Slide credit: Slides adapted from David Kirk/NVIDIA and Wen-mei W. Hwu, 2007-2016 PCIE Review Typical Structure of a CUDA Program Global variables declaration Function prototypes global
More informationWindowing System on a 3D Pipeline. February 2005
Windowing System on a 3D Pipeline February 2005 Agenda 1.Overview of the 3D pipeline 2.NVIDIA software overview 3.Strengths and challenges with using the 3D pipeline GeForce 6800 220M Transistors April
More informationFOSDEM 3 February 2018, Brussels. Tim-Philipp Müller < >
WHAT'S NEW IN GSTREAMER? FOSDEM 3 February 2018, Brussels Tim-Philipp Müller < > tim@centricular.com INTRODUCTION WHO AM I? GStreamer core developer, maintainer, backseat release manager Centricular co-founder
More informationFace Tracking Using Convolutional Neural Network Accelerator IP Reference Design
Face Tracking Using Convolutional Neural Network Accelerator IP FPGA-RD-02037-1.0 May 2018 Contents 1. Introduction... 4 2. Related Documentation... 5 2.1. Soft IP Document... 5 2.2. Diamond Document...
More informationHLS Authoring Update. Media #WWDC17. Eryk Vershen, AVFoundation Engineer
Session Media #WWDC17 HLS Authoring Update 515 Eryk Vershen, AVFoundation Engineer 2017 Apple Inc. All rights reserved. Redistribution or public display not permitted without written permission from Apple.
More informationShareable Camera Framework for Multiple Computer Vision Applications
669 Shareable Camera Framework for Multiple Computer Vision Applications Hayun Lee, Gyeonghwan Hong, Dongkun Shin Department of Electrical and Computer Engineering, Sungkyunkwan University, Korea lhy920806@skku.edu,
More informationKhronos and the Mobile Ecosystem
Copyright Khronos Group, 2011 - Page 1 Khronos and the Mobile Ecosystem Neil Trevett VP Mobile Content, NVIDIA President, Khronos Copyright Khronos Group, 2011 - Page 2 Topics It s not just about individual
More informationNVJPEG. DA _v0.2.0 October nvjpeg Libary Guide
NVJPEG DA-06762-001_v0.2.0 October 2018 Libary Guide TABLE OF CONTENTS Chapter 1. Introduction...1 Chapter 2. Using the Library... 3 2.1. Single Image Decoding... 3 2.3. Batched Image Decoding... 6 2.4.
More informationGTC 2013 March San Jose, CA The Smartest People. The Best Ideas. The Biggest Opportunities. Opportunities for Participation:
GTC 2013 March 18-21 San Jose, CA The Smartest People. The Best Ideas. The Biggest Opportunities. Opportunities for Participation: SPEAK - Showcase your work among the elite of graphics computing - Call
More informationTEGRA LINUX DRIVER PACKAGE R24.1
TEGRA LINUX DRIVER PACKAGE R24.1 RN_05071-R24 June 15, 2016 Advance Information Subject to Change Release Notes RN_05071-R24 TABLE OF CONTENTS 1.0 ABOUT THIS RELEASE... 3 1.1 What s New... 3 1.2 Login
More informationNXP-Freescale i.mx6 MicroSoM i4pro. Quad Core SoM (System-On-Module) Rev 1.3
NXP-Freescale i.mx6 MicroSoM i4pro Quad Core SoM (System-On-Module) Rev 1.3 Simple. Robust. Computing Solutions SolidRun Ltd. 3 Dolev st., 3rd floor, P.O. Box 75 Migdal Tefen 2495900, Israel. www.solid-run.com
More informationGPU Fundamentals Jeff Larkin November 14, 2016
GPU Fundamentals Jeff Larkin , November 4, 206 Who Am I? 2002 B.S. Computer Science Furman University 2005 M.S. Computer Science UT Knoxville 2002 Graduate Teaching Assistant 2005 Graduate
More informationInspiron Setup and Specifications
Inspiron 15 7000 Setup and Specifications Computer Model: Inspiron 15-7560 Regulatory Model: P61F Regulatory Type: P61F001 Notes, cautions, and warnings NOTE: A NOTE indicates important information that
More informationBefore you use your Point Grey Zebra2 camera, we recommend that you are aware of the following resources:
1.1 Subject Technical Application Note (TAN2012006): 1.2 Applicable Product(s) Point Grey Zebra2 camera products 1.3 Application Note Description Technical Application Note TAN2012006 Revised November
More information. SMARC 2.0 Compliant
MSC SM2S-IMX8 NXP i.mx8 ARM Cortex -A72/A53 Description The new MSC SM2S-IMX8 module offers a quantum leap in terms of computing and graphics performance. It integrates the currently most powerful i.mx8
More informationHow to achieve low latency audio/video streaming over IP network?
February 2018 How to achieve low latency audio/video streaming over IP network? Jean-Marie Cloquet, Video Division Director, Silex Inside Gregory Baudet, Marketing Manager, Silex Inside Standard audio
More informationMobile AR Hardware Futures
Copyright Khronos Group, 2010 - Page 1 Mobile AR Hardware Futures Neil Trevett Vice President Mobile Content, NVIDIA President, The Khronos Group Two Perspectives NVIDIA - Tegra 2 mobile processor Khronos
More informationVT988. Key Features. Benefits. High speed 16 ADC at 3 GSPS with Synchronous Capture VT ADC for synchronous capture
Key Features VT988 High speed 16 ADC at 3 GSPS with Synchronous Capture 16 ADC for synchronous capture Xilinx Virtex-7 XC7VX485T FPGA NVidia Jetson TX2 System on Module TI ADC08B3000 8-bit @ 3 GSPS Managed
More informationDiscover Video. StreamEngine. User Guide. Version 1.0. Discover Video LLC 8/5/2016
Discover Video User Guide Version 1.0 8/5/2016 Discover Video LLC www.discovervideo.com Contents General Description...3 Installation...4 Getting Started...5 Edit Settings...8 File Output Settings...9
More informationARM Multimedia IP: working together to drive down system power and bandwidth
ARM Multimedia IP: working together to drive down system power and bandwidth Speaker: Robert Kong ARM China FAE Author: Sean Ellis ARM Architect 1 Agenda System power overview Bandwidth, bandwidth, bandwidth!
More informationOptimizing Film, Media with OpenCL & Intel Quick Sync Video
Optimizing Film, Media with OpenCL & Intel Quick Sync Video Petter Larsson, Senior Software Engineer Ryan Tabrah, Product Manager The Intel Vision Enriching the lives of every person on earth through technology
More informationINTEGRATING COMPUTER VISION SENSOR INNOVATIONS INTO MOBILE DEVICES. Eli Savransky Principal Architect - CTO Office Mobile BU NVIDIA corp.
INTEGRATING COMPUTER VISION SENSOR INNOVATIONS INTO MOBILE DEVICES Eli Savransky Principal Architect - CTO Office Mobile BU NVIDIA corp. Computer Vision in Mobile Tegra K1 It s time! AGENDA Use cases categories
More informationInspiron Setup and Specifications
Inspiron 22 3000 Setup and Specifications Computer Model: Inspiron 22-3264 Regulatory Model: W17B Regulatory Type: W17B003 Notes, cautions, and warnings NOTE: A NOTE indicates important information that
More informationElaborazione dati real-time su architetture embedded many-core e FPGA
Elaborazione dati real-time su architetture embedded many-core e FPGA DAVIDE ROSSI A L E S S A N D R O C A P O T O N D I G I U S E P P E T A G L I A V I N I A N D R E A M A R O N G I U C I R I - I C T
More informationBuild cost-effective, reliable signage solutions with the 8 display output, single slot form factor NVIDIA NVS 810
WEB COPY NVIDIA NVS 810 for Eight DP Displays Part No. VCNVS810DP-PB Overview Build cost-effective, reliable signage solutions with the 8 display output, single slot form factor NVIDIA NVS 810 The NVIDIA
More informationDistributing Computation to Large GPU Clusters
Distributing Computation to Large GPU Clusters What is this about? DiCE: Software library for writing applications scaling to many GPUs and CPUs in a cluster What is this about? DiCE: Software library
More informationECE 574 Cluster Computing Lecture 17
ECE 574 Cluster Computing Lecture 17 Vince Weaver http://web.eece.maine.edu/~vweaver vincent.weaver@maine.edu 28 March 2019 HW#8 (CUDA) posted. Project topics due. Announcements 1 CUDA installing On Linux
More informationPacketShader: A GPU-Accelerated Software Router
PacketShader: A GPU-Accelerated Software Router Sangjin Han In collaboration with: Keon Jang, KyoungSoo Park, Sue Moon Advanced Networking Lab, CS, KAIST Networked and Distributed Computing Systems Lab,
More informationSpring 2009 Prof. Hyesoon Kim
Spring 2009 Prof. Hyesoon Kim Application Geometry Rasterizer CPU Each stage cane be also pipelined The slowest of the pipeline stage determines the rendering speed. Frames per second (fps) Executes on
More informationHezi Saar, Sr. Staff Product Marketing Manager Synopsys. Powering Imaging Applications with MIPI CSI-2
Hezi Saar, Sr. Staff Product Marketing Manager Powering Imaging Applications with MIPI CSI-2 Agenda Implementation of MIPI interfaces in mobile applications and beyond Advantages of implementing MIPI camera
More informationG3399 Single Board Computer Introduction
G3399 Single Board Computer Introduction Shenzhen Graperain Technology Co., Ltd. http://www.graperain.com/ Copyright Statement Copyrights of this manual belong to Shenzhen Graperain Technology Co., Ltd.
More information