Creación De Un Cluster Formado Por Tres Raspberry PI-3 Que Alojarán

Total Page:16

File Type:pdf, Size:1020Kb

Creación De Un Cluster Formado Por Tres Raspberry PI-3 Que Alojarán Máster en Ingeniería Computacional y Matemática Trabajo Final de Máster Creación de un cluster formado por tres Raspberry PI-3 que alojarán una base de datos NoSQL (Apache Cassandra) y motor de cálculo distribuido (Apache Spark), desplegado en contenedores (Docker). Eduardo Romero López Sistemas Distribuidos Coordinador: Félix Freitag Nombre Profesor/a responsable de la asignatura: Joan Manuel Marquès 10 de septiembre de 2017 GNU Free Documentation License (GNU FDL) Copyright © 2017 Eduardo Romero López. Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front- Cover Texts, and no Back-Cover Texts. A copy of the license is included in the section entitled "GNU Free Documentation License". DEDICADO A Lorena por su apoyo, paciencia y comprensión durante todo el periodo que duró el máster. AGRADECIMIENTO A todas las comunidades de desarrolladores y personas que comparten sus conocimientos en charlas y talleres sin miedo a que un tercero pueda aprenderlo, en especial a: @linux_malaga, @centrologic_es, @malaga_pythony @DataBeersMLG Ficha del Trabajo Fin de Máster Creación de un cluster formado por tres RaspberryPI-3 que alojarán una base de datos Título del trabajo NoSQL(Apache Cassandra) y motor de cálculo dis- tribuido(Apache Spark), alojado en un contenedor (Docker). Nombre del autor Eduardo Romero López Nombre del consultor/a Félix Freitag Nombre del PRA Joan Manuel Marquès Fecha de entrega 09/2017 Titulación Máster en Ingeniería Computacional y Matemática Área del Trabajo Final Sistemas Distribuidos Idioma del trabajo Español Palabras clave (máxi- Docker, Spark y Cassandra mo 3 palabras) Resumen del Trabajo (máximo 250 palabras): Este proyecto consiste en el ensamblaje e integración de todos los componentes hardware y software para formar un motor de cálculo distribuido sobre mini-PC (Raspberry PI-3), todo ello llevado a cabo desde un enfoque muy práctico. Así mismo, trata de dar continuidad y profundizar más en los conocimientos adquiridos en la asignatura del Máster Computación Distribuida. Abstract (in English, 250 words or less): This project consists in the assembly and integration of all the hardware and software components to form a distributed calculation engine over mini PC (Raspberry PI- 3), all realized from a very practical point of view. Also, it tries to give continuity and to deepen in the knowledge acquired in the subject of the Master Distributed Computing. Computación Distribuida iii Índice general Índice de figuras vi Índice de tablas viii Índice de Códigos ix 1 Introducción1 1.1 Contexto y justificación del Trabajo...................1 1.2 Objetivos del Trabajo...........................1 1.3 Enfoque y método seguido........................2 1.4 Planificación del Trabajo.........................2 1.5 Breve sumario del producto obtenido..................3 1.6 Breve descripción de los otros capítulos de la memoria........4 2 Hardware y sistema operativo utilizado5 2.1 Mini PC..................................5 2.2 Descripción del hardware a utilizar...................6 2.3 Sistema Operativo utilizado.......................8 2.3.1 Raspbian.............................9 2.3.2 Ubuntu Mate...........................9 3 Introducción de los componentes del sistema 12 3.1 Docker................................... 12 3.1.1 Imágenes en Docker........................ 13 3.1.2 Contenedores en Docker..................... 13 3.1.3 Volúmenes en Docker....................... 13 3.1.4 Arquitectura en Docker...................... 14 3.1.5 Herramientas de Docker..................... 14 3.2 Cassandra................................. 16 3.2.1 Arquitectura y características de Cassandra.......... 16 iv 3.2.2 Lenguaje CQL.......................... 17 3.2.3 Modelado de datos........................ 18 3.3 Spark................................... 19 3.3.1 Componentes del ecosistema Spark............... 19 3.3.2 La abstracción RDD....................... 21 4 Estado del arte 22 5 Puesta en marcha del sistema 24 5.1 Configuración inicial del sistema..................... 24 5.1.1 Creación imagen iso....................... 24 5.1.2 Instalación Ubuntu Mate..................... 26 5.1.3 Habilitar SSH en la Raspberry PI 3............... 28 5.1.4 Habilitar modo consola en la Raspberry PI 3.......... 28 5.1.5 Configuración de la red...................... 29 5.1.6 Asignación de partición Swap de intercambio.......... 30 5.2 Docker................................... 32 5.2.1 Instalación Docker........................ 32 5.2.2 Instalación Docker-Compose................... 34 5.2.3 Docker Swarm........................... 34 5.2.4 Instalación Portainer....................... 36 5.3 Cassandra................................. 38 5.3.1 Requerimientos previos...................... 38 5.3.2 Instalación de Cassandra..................... 38 5.3.3 Configuración de Cassandra para uso en Raspberry...... 39 5.3.3.1 Requerimientos de memoria.............. 39 5.3.3.2 Configuración de parámetros del cluster....... 39 5.3.4 Creación de una base de datos.................. 42 5.4 Spark................................... 46 5.4.1 Instalación y configuración de Spark en Raspberry Pi 3.... 46 5.4.2 Instalación Spark-Cassandra-Connector............. 50 5.4.3 Prueba de comunicación Spark-Cassandra-Connector..... 50 6 Análisis de resultados 52 6.1 Objetivo principal............................. 52 6.2 Objetivo secundario............................ 53 6.2.1 Proceso de ejecución de la aplicación.............. 55 6.2.2 Análisis de los resultados de la aplicación............ 56 7 Conclusiones y futuros trabajos 58 7.1 Conclusiones................................ 58 7.2 Futuros trabajos............................. 59 Bibliografía 60 Anexos 61 Web visitadas 62 Computación Distribuida v Presupuesto para realización del proyecto 64 Tabla comparativa de mini PC 65 Computación Distribuida vi Índice de figuras 1.1 Cluster raspberry pi-3..........................3 2.1 Componentes hardware del sistema...................7 2.2 Sistema Operativo Raspbian....................... 10 2.3 Sistema Operativo Ubuntu Mate.................... 10 3.1 Esquema del despliegue de aplicaciones con Docker.......... 12 3.2 Ejemplo de 2 imágenes con 3 contenedores en Docker......... 14 3.3 Docker Hub................................ 15 3.4 Esquema tipo de un sistema Docker multihost............. 16 3.5 Principales características de Cassandra................. 17 3.6 Modelo de datos en Cassandra...................... 18 3.7 Ecosistema Spark............................. 20 3.8 Flujograma de RDD en Spark...................... 20 5.1 Adaptador microSD a USB utilizado.................. 24 5.2 Crear la imagen iso de Ubuntu Mate.................. 25 5.3 Proceso de instalación Ubuntu Mate.................. 27 5.4 Diagrama red LAN montada....................... 29 5.5 Hardware Raspberry Pi 3 sin Swap................... 31 5.6 Hardware Raspberry Pi 3 con Swap................... 31 5.7 Añadir Docker al iniciar sesión...................... 33 5.8 Añadir el usuario al grupo de Docker.................. 34 5.9 Interfaz gráfica Portainer......................... 37 5.10 Estado cluster de Cassandra....................... 40 5.11 Consola de Cassandra.......................... 42 5.12 Usando Keyspace cotizaciones...................... 43 5.13 Registros de cotización de ING..................... 46 5.14 Clave RSA para acceso remoto...................... 47 5.15 Consola de Spark............................. 48 5.16 Panel web Cluster Spark......................... 50 vii Índice de figuras Índice de figuras 6.1 Imagen de Cassandra en Docker Hub.................. 53 6.2 Resultados obtenidos de la aplicación.................. 55 6.3 Consumo de la aplicación Python sobre una Raspberry Pi-3..... 57 7.1 UDOO X86 Ultra............................. 59 Computación Distribuida viii Índice de tablas 1.1 Planificación del proyecto........................2 2.1 Mini PC más usados para este tipo de proyectos............6 1 Presupuesto para la realización del proyecto.............. 64 2 Comparativa de mini PC......................... 77 ix Índice de Códigos 1 Contenido del archivo de configuración IP fija............. 30 2 Versión Docker instalada......................... 32 3 Crear nodo manager Swarm....................... 35 4 Cluster Swarm formado por rpi3..................... 35 5 Parámetros de Cassandra......................... 41 6 Creación de una keyspace en Cassandra................. 42 7 Parámetros de Cassandra......................... 43 8 Inserción de datos automatizados con Python............. 45 9 Consultas en Cassandra......................... 46 10 Configuración parámetro archivo slave................. 48 11 Configuración parámetros Spark..................... 49 12 Consola Spark conectada con Cassandra................ 51 13 Aplicación cálculo correlaciones PySpark................ 55 1 1 Introducción 1.1 Contexto y justificación del Trabajo En la actualidad estamos inmersos en una revolución digital, cada vez hay más equipos o IOT (Internet of things) conectados a internet recabando y generando datos de diversas procedencia y naturaleza. Eso genera grandes volúmenes de datos que dificultan trabajar con ellos a través del modelo tradicional SGBDR (Sistema de Gestión de Bases de Datos Relacionales) y de ahí surgen nuevas tecnologías para dar solución a dicho problema, como las que se tratarán en este proyecto. 1.2 Objetivos del Trabajo Debido al carácter novedoso
Recommended publications
  • The Jon Peddie Research Gaming Market Press Conference
    The Jon Peddie Research Gaming Market Press Conference . All Gaming Hardware Peddie Research Peddie Jon The Gaming Hardware Market From handhelds to simulators Peddie Research Peddie Jon Jon Peddie Research Focus and emphasis on Visualization, Graphics, and forms of reality Consulting and market research - Advisor to industry leaders and investors Bi-weekly report, various Digital Technology Market Studies Product testing and benchmarking Conferences Chasing Pixels, Finding Visual Magic Peddie Research Peddie Jon Jon Peddie Research Communications “Whatever influences a pixel” & peripheral services Image Receiver(s) DVD Audio sensor Processor Local Memory Semiconductor Fabrication Image Front-end Input Video Graphics Display Processor Processor Processor Processor Processor System Memory Primary interest, CPU expertise, and tracking OS Drivers Application General interest, information Peddie Research Peddie Standards gathering, and limited tracking Jon Agenda – Why are we here? Introduce talking points for discussion . Brief history of computer graphics . The gaming platforms . Market size and growth . Thoughts and speculations on the future . Q&A Peddie Research Peddie Jon How long? . When do you think the game developer conference started? . Depending on who you ask, 1997 to 1999. Actually it was 1993 and was the GamePC Consortium, a loose confederation of hardware and software companies Peddie Research Peddie Jon Look How Far We Have Come Lora Croft from 1996 Lora Croft from 2013 In 1996 the best the industry By 2013 it was possible
    [Show full text]
  • Performance Analysis and Optimization Opportunities for NVIDIA Automotive Gpus
    Performance Analysis and Optimization Opportunities for NVIDIA Automotive GPUs Hamid Tabani∗, Fabio Mazzocchetti∗y, Pedro Benedicte∗y, Jaume Abella∗ and Francisco J. Cazorla∗ ∗ Barcelona Supercomputing Center y Universitat Politecnica` de Catalunya Abstract—Advanced Driver Assistance Systems (ADAS) and products such as Renesas R-Car H3 [1], NVIDIA Jetson Autonomous Driving (AD) bring unprecedented performance TX2 [20] and NVIDIA Jetson Xavier [35], [27] have already requirements for automotive systems. Graphic Processing Unit reached the market building upon GPU technology inherited (GPU) based platforms have been deployed with the aim of meeting these requirements, being NVIDIA Jetson TX2 and from the high-performance domain. Automotive GPUs have its high-performance successor, NVIDIA AGX Xavier, relevant inherited designs devised for the high-performance domain representatives. However, to what extent high-performance GPU with the aim of reducing costs in the design, verification and configurations are appropriate for ADAS and AD workloads validation process for chip manufacturers. remains as an open question. Unfortunately, reusability of high-performance hardware This paper analyzes this concern and provides valuable does not consider GPUs efficiency in the automotive domain insights on this question by modeling two recent automotive NVIDIA GPU-based platforms, namely TX2 and AGX Xavier. In and, to the best of our knowledge, the design space for GPUs, particular, our work assesses their microarchitectural parameters where resources are sized with the aim of optimizing specific against relevant benchmarks, identifying GPU setups delivering goals such as performance, has not been yet thoroughly increased performance within a similar cost envelope, or decreas- performed for the automotive domain. ing hardware costs while preserving original performance levels.
    [Show full text]
  • Cash Flow Comparison
    國立政治大學商學院國際經營管理 英語碩士學位學程 International MBA Program College of Commerce National Chengchi University 碩士論文 治 Master政 ’s Thesis大 立 學 國 三大電腦晶片製造商之財務比較‧ ‧ A ComparisonN of Major Computer Chipset Vendors a y t t i Inio Financial Point of View s n r a e i v l C n heng chi U Student: Roger Chang Advisor: Professor James Liu 中華民國一百年六月 June 2011 三大電腦晶片製造商之財務比較 A Comparison of Major Computer Chipset Vendors In Financial Point of View 研究生: 張鼎昱 Student: Roger Chang 指導教授: 劉助 Advisor: Prof. James Liu 治 政 大 立 國立政治大學 商學院國際經營管理英語碩士學 學位學程 國 碩士論文 ‧ ‧ N a y t t A Thesis i i s o r Sunbmitted to International MBAe Program a i v l NationalC Chengchi nUniversity he i U in partial fulfillmentngch of the Requirements for the degree of Master in Business Administration 中華民國一百年六月 June 2011 i Abstract A Comparison of Major Computer Chipset Vendors In Financial Point of View By Roger Chang The goal of this master thesis is to analyze the治 three major chipset players in today’s Personal 政 大 Computer (PC) industry, while立 providing recommendations in different perspectives. One of the perspectives is from the investor’s point of view to single out a 學company with the most long term 國 investment value. The other is from each company’s management point of view to suggest for the ‧ areas of improvement for the companies. Two of the three companies discussed in this thesis are ‧ American-based global companiesN namely, Intel and AMD, while the other is a Taiwanese company: a y t t i VIA Technology.
    [Show full text]
  • Video Games Review DRAFT5-16
    Video Games: History, Technology, Industry, and Research Agendas Table of Contents I. Overview ....................................................................................................................... 1 II. Video Game History .................................................................................................. 7 III. Academic Approaches to Video Games ................................................................. 9 1) Game Studies ....................................................................................................................... 9 2) Video Game Taxonomy .................................................................................................... 11 IV. Current Status ........................................................................................................ 12 1) Arcade Games ................................................................................................................... 12 2) Console Games .................................................................................................................. 13 3) PC Standalone Games ...................................................................................................... 14 4) Online Games .................................................................................................................... 15 5) Mobile Games .................................................................................................................... 16 V. Recent Trends ..........................................................................................................
    [Show full text]
  • A Low-Cost Deep Neural Network-Based Autonomous Car
    DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car Michael G. Bechtely, Elise McEllhineyy, Minje Kim?, Heechul Yuny y University of Kansas, USA. fmbechtel, elisemmc, [email protected] ? Indiana University, USA. [email protected] Abstract—We present DeepPicar, a low-cost deep neural net- task may be directly linked to the safety of the vehicle. This work based autonomous car platform. DeepPicar is a small scale requires a high computing capacity as well as the means to replication of a real self-driving car called DAVE-2 by NVIDIA. guaranteeing the timings. On the other hand, the computing DAVE-2 uses a deep convolutional neural network (CNN), which takes images from a front-facing camera as input and produces hardware platform must also satisfy cost, size, weight, and car steering angles as output. DeepPicar uses the same net- power constraints, which require a highly efficient computing work architecture—9 layers, 27 million connections and 250K platform. These two conflicting requirements complicate the parameters—and can drive itself in real-time using a web camera platform selection process as observed in [25]. and a Raspberry Pi 3 quad-core platform. Using DeepPicar, we To understand what kind of computing hardware is needed analyze the Pi 3’s computing capabilities to support end-to-end deep learning based real-time control of autonomous vehicles. for AI workloads, we need a testbed and realistic workloads. We also systematically compare other contemporary embedded While using a real car-based testbed would be most ideal, it computing platforms using the DeepPicar’s CNN-based real-time is not only highly expensive, but also poses serious safety control workload.
    [Show full text]
  • Compulab Document
    Hayetsira St. 17, Yokneam, Israel Tel: +972-48-290-100 Fax: +972-48-325-251 www.compulab.co.il 14-July-2013 CompuLab introduces Utilite – a single-core to quad-core ARM Linux desktop starting at $99 Yokneam, Israel - 14-July-2013 - CompuLab is introducing Utilite – a miniature ARM-based desktop computer. Powered by Freescale i.MX6 system-on-chip, Utilite is the next generation of CompuLab’s highly acclaimed Trim-Slice computer. Featuring a quad-core ARM Cortex-A9 CPU, up-to 4GB RAM and dual-head 1080p display output, Utilite expands the 2011 Trim-Slice offering with up-to twice the performance and less than half the starting price of $99. Designed into an elegant “zero-screws” housing and measuring only 5.3” x 3.9” x 0.8”, Utilite provides unprecedentedly rich I/O with dual GbE, 5 USB ports, 802.11 WiFi and Bluetooth. High performance, low-power, rich I/O and miniature form-factor position the Utilite as an attractive solution for a variety of applications such as media player, IPTV, infotainment systems, digital signage, thin client and small-footprint desktop replacement. Utilite will be offered with fully featured, desktop-grade Ubuntu Linux or Android operating systems delivering rich multimedia and PC-like user experience. “In 2011 CompuLab’s Trim-Slice has pioneered the market of ARM-based computers,” said Igor Vaisbein, VP Business Development at CompuLab. “Utilite pushes the boundaries of ARM desktops even further by doubling the performance and providing more connectivity while maintaining the same tiny form-factor and drastically reducing cost.” Utilite is particularly attractive to software developers since it is a high-performance, open platform designed into a commercial grade product.
    [Show full text]
  • Procurement of Electric-Electronic
    REQUEST FOR QUOTATION (RFQ) Procurement of Electric-Electronic Laboratory Equipment and Supplies for Adana and Mersin Innovation Centers Adana ve Mersin Yenilik Merkezleri için Elektrik-Elektronik Laboratuvarları Ekipman ve Sarf Malzemeleri Alım İhalesi Please enter Name, Address & Contact Details of your Firm DATE: February 10, 2020 Lütfen Firma Adı, Adresi ve İrtibat Bilgilerini buraya giriniz TARİH: 10 Şubat 2020 REFERENCE: UNDP-TUR-RFQ(MC1)-2020/07 Dear Sir / Madam: Sayın İlgili: We kindly request you to submit your Teklife Davet Ek 1’deki Teknik Şartnamede ve Ek quotation for “Procurement of Electric-Electronic 2’de yer alan Malzeme Listesi’nde detayları verilmiş Laboratory Equipment and Supplies for Adana and olan “Adana ve Mersin Yenilik Merkezleri için Mersin Innovation Centers”, as detailed in Technical Elektrik-Elektronik Laboratuvarları Ekipman ve Sarf Specifications and Supplies List provided as Annex Malzemeleri Alım İhalesi” için teklifinizi sunmanızı 1 and Annex 2 (respectively) of this RFQ. When rica ederiz. preparing your quotation, please be guided by the forms attached hereto as ANNEX 1, ANNEX 2 and Teklifinizi lütfen EK 1, EK 2 ve EK 3’de sunulmuş ANNEX 3. formların rehberliğinde hazırlayınız. Quotations shall be submitted on or before 27 Teklifler aşağıda belirtilen adrese, 27 Şubat 2020, February 2020, 14:00 hrs. Turkey Local Time, via Türkiye saati ile 14:00’a kadar elden, e-posta veya hand delivery, e-mail or courier mail to the address kargo yolu ile teslim edilmelidir: below: United Nations Development Programme Birleşmiş Milletler Kalkınma Programı (UNDP) (UNDP) Yıldız Kule, Yukarı Dikmen Mahallesi, Turan Güneş Yıldız Kule, Yukarı Dikmen Mahallesi, Turan Bulvarı, No:106, 06550, Çankaya, Ankara/Türkiye Güneş Bulvarı, No:106, 06550, Çankaya, İlgili Kişi: Ümit ALSAÇ Ankara/Turkey Satın Alma Yetkilisi, UNDP Attn: Mr.
    [Show full text]
  • Ipsos Poll Conducted for Reuters Video Games 9.27.13
    Ipsos Poll Conducted for Reuters Video Games 9.27.13 These are findings from an Ipsos poll conducted for Thomson Reuters from September 23-27, 2013 . For the survey, a sample of 1,297 Americans ages 18+ were interviewed online. The precision of the Reuters/Ipsos online polls is measured using a credibility interval. In this case, the poll has a credibility interval of plus or minus 3.1 percentage points . For more information about credibility intervals, please see the appendix. The data were weighted to the U.S. current population data by gender, age, education, and ethnicity. Statistical margins of error are not applicable to online polls. All sample surveys and polls may be subject to other sources of error, including, but not limited to coverage error and measurement error. Figures marked by an asterisk (*) indicate a percentage value of greater than zero but less than one half of one per cent. Where figures do not sum to 100, this is due to the effects of rounding. To see more information on this and other Reuters/Ipsos polls, please visit http://polling.reuters.com/. VIDEO GAMES Q1. Which of the following gaming devices do personally use to play games? Please select all that apply. Nintendo Wii 23% Android Devices (Android tablet or Smartphone) 21% Xbox 360 20% PC / MAC 20% PlayStation 3 (PS3) 18% iOS Devices (iPod, iPhone, etc.) 12% Nintendo DS (DS lite, DSi) 10% Nintendo 3DS 6% Sony PSP/PSP Go 3% Nintendo Wii U 3% PS Vita 2% Nvidia Shield 1% Ouya 1% OnLive *% Other 2% None of the above 38% Q2.
    [Show full text]
  • NVIDIA Jetson TX2 Module
    ® ™ NVIDIA JETSON TX2 SUPERCOMPUTER ON A MODULE FOR AI AT THE EDGE TAKE REAL-TIME AI PERFORMANCE FARTHER WITH THE HIGH-PERFORMANCE, LOW-POWER JETSON TX2. The most innovative technology for AI computing and visual computing comes in a supercomputer the size of a credit card. Its small form factor and power envelope make the Jetson TX2 module ideal for intelligent edge devices like robots, drones, smart cameras, and portable medical devices. CONTENTS Jetson TX2 features a variety of standard hardware interfaces that make it easy to integrate it into a wide range of products and form factors. Plus, it comes with the complete Jetpack > NVIDIA Jetson TX2 > Attached Thermal Transfer Plate (TTP) SDK, which includes the BSP, libraries for deep learning, computer vision, GPU computing, multimedia processing, and much more to accelerate your software development. And it’s TECHNICAL SPECIFICATIONS supported by the Jetson developer site, which includes documentation, tutorials, and an FEATURES JETSON TX2 ecosystem of partners and developers. It’s never been easier to get started with AI. Graphics NVIDIA Pascal™, 256 NVIDIA For detailed specifications, design guides, Jetpack, and everything else you need to develop CUDA® cores with Jetson, go to developer.nvidia.com/embedded-computing. CPU HMP Dual Denver 2/2MB L2 + Quad ARM® A57/2MB L2 KEY FEATURES Video 4K x 2K 60 Hz Encode (HEVC) 4K x 2K 60 Hz Decode (12-bit Jetson TX2 Module I/O support) > NVIDIA Pascal™ architecture GPU > USB 3.0 Type A Memory 8 GB 128-bit LPDDR4 > Dual-core Denver 2 64-bit CPU
    [Show full text]
  • Jetson TX2 Developer Kit User Guide
    JETSON TX2 DEVELOPER KIT DA_09452-005 | December 17, 2019 ````` User Guide DOCUMENT CHANGE HISTORY DA_09452-005 Version Date Authors Description of Change Revision for Jetson Linux Driver 2.0 March 28, 2019 jsachs, plawrence Package r32.1. Revision for SDK Manager and Jetson 3.0 July 8, 2019 jsachs, plawrence Linux Driver Package r32.2. Revision for Jetson Linux Driver 4.0 December 17, 2019 ssheshadri Package r32.3.1. NOTE Welcome to the NVIDIA Jetson platform! There two key things you should do right away: 1. Sign up for the NVIDIA Developer Program – this enables you to ask questions and contribute on the NVIDIA Jetson Forums, gives access to all documentation and collateral on the Jetson Download Center, and more. 2. Read this User Guide! After that, check out these important links: • Jetson FAQ – Please read the FAQ. • Support Resources – This web page links to important resources, including the Jetson Forum and the Jetson Ecosystem page. • Jetson Linux Driver Package Release Notes – Jetson Linux Driver Package (L4T) is a key component of the Jetson platform, and provides the sample filesystem for your developer kit. Please read the latest release notes. • Thanks, The NVIDIA Jetson team Jetson TX2 Developer Kit DA_09452-005 | ii TABLE OF CONTENTS Note .........................................................................................ii Jetson TX2 Developer Kit ............................................................... 1 Included in the box ............................................................................. 1 Developer
    [Show full text]
  • Superdataresearch Deliverable Digital
    2013 Game Changers 2013 GAME CHANGERS How will the next generation of consoles affect your business? Compliments of SUPERDATA RESEARCH, INC. | www.superdataresearch.com | August 2013 1 2013 Game Changers INDEX INTRODUCTION & MOTIVATION 3 METHODOLOGY 4 LANDSCAPE 6 Current console ownership ‣ Console ownership in the United States (U.S.), 2013 ‣ Per capita spend on interactive entertainment in the U.S. Changing audience CONSUMER 10 Consumer behavior and devices ‣ Aggregated platform usage among U.S. gamers ‣ Primary platform usage among U.S. gamers, 2008 versus 2013 New dedicated devices: familiarity and interest ‣ Q: Which one have you heard of? ‣ Q: Which one do you plan on buying? PUBLISHER 14 Consoles don’t sell consoles. Titles sell consoles. ‣ Physical versus digital sales for Electronic Arts ABOUT & CONTACT 17 SUPERDATA RESEARCH, INC. | www.superdataresearch.com | August 2013 2 2013 Game Changers INTRODUCTION & MOTIVATION The next generation of consoles presents a renewal of an important part of the interactive entertainment industry. Recent announcements of the PlayStation 4 and Xbox One as well as the smaller, new market entrants have fueled a vigorous discussion within the industry. In particular, the position of the incumbents, and their ability to maintain it, has been a hot topic of discussion. For example, Daniel Thomas at VentureBeat recently criticized Xbox One for throwing out “its only good idea with [the console’s] DRM policy reversal.” Elsewhere, Gamasutra’s editor-at-large Leigh Alexander called Sony’s showing at E3 a “spiritual victory” and reminded gamers not to forget about the GameStick. And lead Portal designer Kim Swift adamantly supported OUYA as the exclusive console for her new game Soul Fjord, while both the likes of Square- Enix and indie developer Supergiant Games will find a home on the PS4.
    [Show full text]
  • The ITRS Design Technology and System Drivers Roadmap: Process and Status
    The ITRS Design Technology and System Drivers Roadmap: Process and Status Andrew B. Kahng CSE and ECE Depts., Univ. of California at San Diego [email protected] ABSTRACT progress of design technology. The Design technology working group (TWG) is one of 16 working • Understanding of contexts and needs for technology. Con- groups in the International Technology Roadmap for Semiconduc- texts ranging from process technology to market forces affect tors (ITRS) effort. It is responsible for the ITRS’ Design Chap- the need for technology. For example, the trajectory of mo- ter, which roadmaps design technology requirements and poten- bile consumer SOC products has driven rapid innovation in tial solutions for elements of the semiconductor supply chain that low-power design techniques spanning embedded memory are produced by the electronic design automation (EDA) indus- design, power and clock gating, dynamic voltage scaling, try. The Design TWG is also responsible for the ITRS’ System etc. At the same time, these low-power design techniques Drivers Chapter, which roadmaps the key product classes that drive must acknowledge process and material attributes such as the leading-edge requirements for process and design technolo- discreteness of FinFET device widths starting at the 16nm gies. Through these activities, the Design TWG sets a number foundry node, or increasingly dominant reliability and aging of fundamental parameters in the overall ITRS: layout density, die mechanisms. size, maximum on-chip clock frequency, total chip power, SOC and • Holistic selection of potential solutions. Technology roadmap- MPU architecture models, etc. This paper reviews the process by ping must holistically model and predict impacts of potential which the Design TWG evolves its roadmap content, and some of technology solutions, at many levels.
    [Show full text]