Port, Develop, Tune on Linux on POWER8

Total Page:16

File Type:pdf, Size:1020Kb

Port, Develop, Tune on Linux on POWER8 May 22-25, 2017 | San Francisco Port, Develop, Tune on Linux on POWER8 Why Linux on POWER? ● Enterprise Class Hardware ● 2x price/performance ● Easy to port to, Easy to use ● Optimized for performance –High-performing, highly reliable platform, capable of handling large quantities of data more efficiently – Enables high speed off-load capabilities with technologies such as CAPI and GPUs. –Flexible, fast execution of analytics algorithms ● 4X threads per core vs. x86 (up to 1536 threads per system) ● Memory: Large, fast workspace maximizes business insight ● 4X memory bandwidth vs. x86 (up to 32 TB of memory) ● Cache Ensure continuous data load for fast responses ● 6X more cache vs x86 (>19 MB cache per core) Linux is Linux everywhere! Software: It's Linux! ▶Linux on POWER is Linux, with full distribution support from the major enterprise Linux distributions: – Red Hat Enterprise Linux (RHEL) from Red Hat, – Ubuntu from Canonical, and – SUSE Linux Enterprise Server (SLES) from SUSE. ● Thousands of open source binary packages are supported on the POWER platform ● Most standard packages are available directly from the major Linux distributions. ● Thousands of community maintained ppc64le packages that run on POWER ● Open Source POWER Availability Tool (OSPAT), searches ppc64le distros and ported apps The definitive guide to porting Linux applications to POWER ▶Research ▶Plan ▶Set up ▶Build ▶Resources Overview of Research Process ▶Plan for the port ▶Get started ▶Get hardware access ▶Choose Linux distribution ▶Prepare development environment ▶Determine database requirements ▶Gather test cases and tools ▶Are you ready to get started? Research May 22-25, 2017 San Francisco Researching your app – Getting Started ▶Many packages are trivial to port to POWER ▶often require a simple recompile or make command. ▶Some require minor tweaks to #ifdef configurations ▶Some have ppc64 – which implies big endian ▶Some need additional libraries, e.g. some math libraries ▶Some simply require identifying and loading the right dependencies ▶If the port is not trivial, we need to build a plan... AccesstoHardware May 22-25, 2017 San Francisco Access to POWER8 hardware ▶If you have your own hardware already, you are set ▶But if not... –There are POWER cloud resources available throughout the world –Use the OpenPOWER Developer Resources Map, ●https://developer.ibm.com/linuxonpower/cloud-resources/ Cloud centers available world wide Highlights of current clouds Highlights of current clouds ●Cloud Hardware Recommendations ● If you are an academic or open source developer consider these cloud resources: – Oregon State University- Open Source Lab (OSL) ● In partnership with IBM, the OSL provides access to IBM POWER based servers for developing and testing open source projects. Request access – Unicamp MiniCloud ● No-charge, access to Power virtual machines (VMs) for developing, testing or migrating applications to Linux on Power. Hosted by University of Campinas, Brazil. Request access ● If you are an ISV or need access to GPUs, CAPI, or NVlink technologies consider: – Nimbix ● The Nimbix Jarvice Cloud platform is the first commercial cloud environment to feature POWER8 with NVLink. It features ready to deploy instances for deep learning and NVLink application deployment and development. ● If you don’t have hardware and don’t want to use a cloud,use an emulator – QEMU (user-mode emulation) available in SDK – IBM Power Functional Simulator (full system simulation) are provided with the SDK. In this mode, you can develop and port applications without the need for Power hardware. May 22-25, 2017 San Francisco Hardware: Simulators ▶If you want to try the port through a simulator, consider: –Instal the IBM Software Developer Kit (SDK) for Linux on Power on your Linux laptop/desktop –run your Power binaries on the same desktop through emulation technologies ●Both QEMU (user-mode emulation) and the ●IBM Power Functional Simulator (full system simulation) –are provided with the SDK. In this mode, you can develop and port applications without the need for Power hardware. LinuxDistributions May 22-25, 2017 San Francisco Linux Distribution ● Do you need the latest and greatest technology? – Ubuntu, Debian, and Fedora typically have frequent releases that integrate the latest open source projects. They are good choices for initial development in cloud, containers, cognitive, HPC, and other areas where the latest technology is absolutely necessary. ● Do you need the best support? – Red Hat Enterprise Linux (RHEL), SUSE Enterprise Linux (SLES), and Ubuntu, in partnership with IBM, provide long term distribution support and are a common target for key ISV applications that expect long term stability. ● Community supported distributions – Ubuntu (and its many variants, such as kubuntu), – CentOS, and – OpenSUSe provide community supported distributions, which provide much of the same application support as their enterprise versions but without the corresponding support costs. May 22-25, 2017 San Francisco Selecting a Distribution based on apps ● Are prerequisite and dependent packages available on the distribution of your choice? – Use the Open Source POWER Availability Tool (OSPAT) search engine to see if the correct packages and versions of packages are available on the distribution of your choice. May 22-25, 2017 San Francisco Open Source POWER Availability Tool (OSpat) May 22-25, 2017 San Francisco Ospat Search for Elasticsearch May 22-25, 2017 San Francisco Ospat Future Directions ▶Currently scans common distro contents ▶Adding pointers to all packages ported to POWER ▶Planning to add Ruby gems, Python pips, Node.js npms ▶Including HPC ported applications lists ▶Adding biobuilds.org contents ▶Working with OSU Center for Genome Research and Biocomputing (CGRB) –http://cgrb.oregonstate.edu/ –Listing their projects –Hosting build instructions at github.com/ppc64le/build-scripts ▶Working with Nimbix to build docker containers ▶Populating https://hub.docker.com/u/ppc64le/ with pre-built POWER containers ▶Tracking binaries when available ▶Many Bullets ▶Logo Colored Bullets May 22-25, 2017 San Francisco Other Distributions ● There are several other Linux distributions that support the POWER platform including: – Fedora (be sure to search for ppc64le packages) – Debian – CentOS May 22-25, 2017 San Francisco Languages May 22-25, 2017 San Francisco Application Programming Language ● What language is your application written in? – Power supports most but not all current languages (see list below) – Most compiled applications will simply require a re-build – Most interpreted languages will run without changes ● C# Clang++ ada Angular.js awk bash Clang Clojure (JVM) (Mono) (LLVM) Fixedhea GNU D (LLVM) DoT.js Erlang G++ GCC GNU Go der.js Fortran Java GNU GNU Objective Go Lang Haskell HHVM (OpenJD JQuery JRuby Objective C C++ K) Node.js/V Julia (LLVM) Lua Modula 2/3 OCaml Octave Perl Phantom.js 8S Rust Sala PHP pypy Python R Lang Ruby SpiderMonkey (LLVM) (JVM) SQL Swift (LLVM) May 22-25, 2017 San Francisco Porting a Compiled Language Compiled languages Effort required to port: Recompile and test* C, C++, and FORTRAN languages are compiled to instructions for a specific machine/platform. The C language in particular can expose more of the underlying machine architecture to the program and is thus, slightly less portable. That said, most applications written in a compiled language with no platform dependencies will only require a recompile to run on Power. *It’s estimated that less than 5% of Linux applications from any platform written in C/C++ will require source code changes. The Source Code Advisor, which is part of the IBM Software Developer Kit (SDK) for Linux on Power, can analyze your source code and show you which areas require changes. The SDK is discussed in more detail below. May 22-25, 2017 San Francisco C/C++ Applications Many of the most popular compilers are available and optimized for POWER, including the following: ● GNU Compiler Collection (GCC) ● Clang ● XL C/C++ for Linux ● XL Fortran for Linux May 22-25, 2017 San Francisco IBM Advanced Toolchain for Linux on POWER Install the Advance Toolchain for the latest open source compilers, runtime libraries, and tools enabled and optimized for POWER8. Current GCC compilers and language levels Languages: C/C++, FORTRAN, Go Includes cross compilers for SDK client Optimized POSIX runtime libraries: libc, libm, libpthread Extra libraries: Zlib, OpenSSL, Boost, Tcmalloc, Intel TBB, SPHDE Performance profiling tools: oprofile, valgrind Learn more about the Advance Toolchain for Linux on Power (including how to install it). ● https://www.ibm.com/developerworks/community/wikis/home?lang=en#!/wiki/W51a7ffcf4dfd_4b40_9d82_44 6ebc23c550/page/IBM%20Advance%20Toolchain%20for%20PowerLinux%20Documentation?section=insta llation May 22-25, 2017 San Francisco IBM Software Development Kit (SDK) for Linux on Power If you’re porting an application written in C/C++, consider using the the SDK for Linux on Power, which is a free, Eclipse-based integrated development environment (IDE) that includes powerful tools to aid developers porting to Linux on Power: ● Migration Advisor ● Build Advisor ● Source Code Advisor Each of these tools, and many others (including the IBM Advance Toolchain) are integrated into the SDK, which you can download from here: https://developer.ibm.com/linuxonpower/sdk-download/ or in source form from here: https://github.com/open-power-sdk May 22-25, 2017 San Francisco Migration Advisor The Migration Advisor scans
Recommended publications
  • 16 Inspiring Women Engineers to Watch
    Hackbright Academy Hackbright Academy is the leading software engineering school for women founded in San Francisco in 2012. The academy graduates more female engineers than UC Berkeley and Stanford each year. https://hackbrightacademy.com 16 Inspiring Women Engineers To Watch Women's engineering school Hackbright Academy is excited to share some updates from graduates of the software engineering fellowship. Check out what these 16 women are doing now at their companies - and what languages, frameworks, databases and other technologies these engineers use on the job! Software Engineer, Aclima Tiffany Williams is a software engineer at Aclima, where she builds software tools to ingest, process and manage city-scale environmental data sets enabled by Aclima’s sensor networks. Follow her on Twitter at @twilliamsphd. Technologies: Python, SQL, Cassandra, MariaDB, Docker, Kubernetes, Google Cloud Software Engineer, Eventbrite 1 / 16 Hackbright Academy Hackbright Academy is the leading software engineering school for women founded in San Francisco in 2012. The academy graduates more female engineers than UC Berkeley and Stanford each year. https://hackbrightacademy.com Maggie Shine works on backend and frontend application development to make buying a ticket on Eventbrite a great experience. In 2014, she helped build a WiFi-enabled basal body temperature fertility tracking device at a hardware hackathon. Follow her on Twitter at @magksh. Technologies: Python, Django, Celery, MySQL, Redis, Backbone, Marionette, React, Sass User Experience Engineer, GoDaddy 2 / 16 Hackbright Academy Hackbright Academy is the leading software engineering school for women founded in San Francisco in 2012. The academy graduates more female engineers than UC Berkeley and Stanford each year.
    [Show full text]
  • Automated Analysis of Speculation Windows in Spectre Attacks
    Barbara Gigerl Automated Analysis of Speculation Windows in Spectre Attacks MASTER'S THESIS to achieve the university degree of Diplom-Ingenieurin Master's degree programme: Software Engineering and Management submitted to Graz University of Technology Supervisor: Daniel Gruss Institute for Applied Information Processing and Communication Graz, May 2019 i AFFIDAVIT I declare that I have authored this thesis independently, that I have not used other than the declared sources/resources, and that I have explicitly indicated all material which has been quoted either literally or by content from the sources used. The text document uploaded to TUGRAZonline is identical to the present master's thesis. Date Signature EIDESSTATTLICHE ERKLARUNG¨ Ich erkl¨arean Eides statt, dass ich die vorliegende Arbeit selbstst¨andig verfasst, andere als die angegebenen Quellen/Hilfsmittel nicht benutzt, und die den benutzten Quellen w¨ortlich und inhaltlich entnommenen Stellen als solche kenntlich gemacht habe. Das in TUGRAZonline hochgeladene Textdokument ist mit der vorliegenden Masterarbeit identisch. Datum Unterschrift Abstract Speculative execution is a feature integrated into most modern CPUs. Although intro- duced as a way to enhance the performance of processors, the release of Spectre attacks showed that it is a significant security risk. Since CPUs from various vendors, includ- ing Intel, AMD, ARM, and IBM, implement speculative execution, all different kinds of devices are affected by Spectre attacks, for example, desktop PCs and smartphones. Spectre attacks exploit the branch prediction mechanisms of the CPU and then use a cache covert channel to leak secret data. Several attack variants have been discovered since the release, including Spectre-PHT which targets the Pattern History Table of the CPU.
    [Show full text]
  • Magento on HHVM Speeding up Your Webshop with a Drop-In PHP Replacement
    Magento on HHVM Speeding up your webshop with a drop-in PHP replacement. Daniel Sloof [email protected] What is HHVM? ● HipHop Virtual Machine ● Created by engineers at Facebook ● Essentially a reimplementation of PHP ● Originally translated PHP to C++, now translates PHP to bytecode ● Just-in-time compiler, turning generated bytecode into machine code ● In some cases 5 to 10 times faster than regular PHP So what’s the problem? ● HHVM not entirely compatible with PHP ● Magento’s PHP triggering many of these incompatibilities ● Choosing between ○ Forking Magento to work around HHVM ○ Fixing issues within the extensive HHVM C++ codebase Resulted in... fixing HHVM ● Already over 100 commits fixing Magento related HHVM bugs; ○ SimpleXML (majority of bugfixes) ○ sessions ○ number_format ○ __get and __set ○ many more... ● Most of these fixes already merged back into the official (github) repository ● Community Edition running (relatively) stable! Benchmarks Before we go to the results... ● Magento 1.8 with sample data ● Standard Apache2 / php-fpm / MySQL stack (with APC opcode cache). ● Standard HHVM configuration (repo-authoritative mode disabled, JIT enabled) ● Repo-authoritative mode has potential to increase performance by a large margin ● Tool of choice: siege Benchmarks: Response time Average across 50 requests Benchmarks: Transaction rate While increasing siege concurrency until avg. response time ~2 seconds What about <insert caching mechanism here>? ● HHVM does not get in the way ● Dynamic content still needs to be generated ● Replaces PHP - not Varnish, Redis, FPC, Block Cache, etc. ● As long as you are burning CPU cycles (always), you will benefit from HHVM ● Think about speeding up indexing, order placement, routing, etc.
    [Show full text]
  • Defeating Invisible Enemies:Firmware Based
    Defeating Invisible Enemies: Firmware Based Security in OpenPOWER Systems — Linux Security Summit 2017 — George Wilson IBM Linux Technology Center Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation Agenda Introduction The Case for Firmware Security What OpenPOWER Is Trusted Computing in OpenPOWER Secure Boot in OpenPOWER Current Status of Work Benefits of Open Source Software Conclusion Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation 2 Introduction Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation 3 Disclaimer These slides represent my views, not necessarily IBM’s All design points disclosed herein are subject to finalization and upstream acceptance The features described may not ultimately exist or take the described form in a product Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation 4 Background The PowerPC CPU has been around since 1990 Introduced in the RS/6000 line Usage presently spans embedded to server IBM PowerPC servers traditionally shipped with the PowerVM hypervisor and ran AIX and, later, Linux in LPARs In 2013, IBM decided to open up the server architecture: OpenPOWER OpenPOWER runs open source firmware and the KVM hypervisor with Linux guests Firmware and software designed and developed by the IBM Linux Technology Center “OpenPOWER needs secure and trusted boot!” Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation 5 The Case for Firmware Security Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation 6 Leaks Wikileaks Vault 7 Year 0 Dump NSA ANT Catalog Linux Security Summit / Defeating Invisible Enemies / September 14, 2017 / © 2017 IBM Corporation 7 Industry Surveys UEFI Firmware Rootkits: Myths and Reality – Matrosov Firmware Is the New Black – Analyzing Past Three Years of BIOS/UEFI Security Vulnerabilities – Branco et al.
    [Show full text]
  • Automated Program Transformation for Improving Software Quality
    Automated Program Transformation for Improving Software Quality Rijnard van Tonder CMU-ISR-19-101 October 2019 Institute for Software Research School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee: Claire Le Goues, Chair Christian Kästner Jan Hoffmann Manuel Fähndrich, Facebook, Inc. Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Software Engineering. Copyright 2019 Rijnard van Tonder This work is partially supported under National Science Foundation grant numbers CCF-1750116 and CCF-1563797, and a Facebook Testing and Verification research award. The views and conclusions contained in this document are those of the author and should not be interpreted as representing the official policies, either expressed or implied, of any sponsoring corporation, institution, the U.S. government, or any other entity. Keywords: syntax, transformation, parsers, rewriting, crash bucketing, fuzzing, bug triage, program transformation, automated bug fixing, automated program repair, separation logic, static analysis, program analysis Abstract Software bugs are not going away. Millions of dollars and thousands of developer-hours are spent finding bugs, debugging the root cause, writing a patch, and reviewing fixes. Automated techniques like static analysis and dynamic fuzz testing have a proven track record for cutting costs and improving software quality. More recently, advances in automated program repair have matured and see nascent adoption in industry. Despite the value of these approaches, automated techniques do not come for free: they must approximate, both theoretically and in the interest of practicality. For example, static analyzers suffer false positives, and automatically produced patches may be insufficiently precise to fix a bug.
    [Show full text]
  • Nástroje Pro Sjednocení Datových Zdrojů Projektu Gloffer Tools for Unification of Data Sources Project Gloffer
    VŠB – Technická univerzita Ostrava Fakulta elektrotechniky a informatiky Katedra informatiky Nástroje pro sjednocení datových zdrojů projektu Gloffer Tools for unification of data sources project Gloffer 2018 Bc. Jakub Malchárek Rád bych poděkoval panu Ing. Radoslavu Fasugovi, Ph.D. za odbornou pomoc a konzultaci při zpracování této diplomové práce a cenné rady v průběhu implementace. Abstrakt V této diplomové práci se zabývám analýzou dostupných technologií pro implementaci webo- vého portálu Gloffer. Jsou zde popsány databáze (MySQL, Redis, MongoDB, Aerospike, Apache HBase, Apache Cassandra, Google Bigtable, Memcached), vyhledávače (Solr, Lucene, Elastic Search), webové servery (Apache HTTP server, Apache Tomcat), zprostředkovatelé zpráv (Rab- bit MQ), distribuované výpočetní technologie (Apache Hadoop) a vývojové technologie (PHP 7, Nette Framework, Java, Spring Framework). Cílem je nejen popis těchto technologií, ale také ná- vrh a implementace rozhraní pro sjednocení datových zdrojů projektu Gloffer v programovacím jazyce Java s využitím Spring Frameworku. Výstupem práce je inteligentní nástroj zpřístupňující data z více datových zdrojů. Závěr práce obsahuje výkonové testování vyvinutého nástroje. Klíčová slova: Aerospike, Apache Cassandra, Apache Hadoop, Apache HBase, Apache HTTP server, Apache Tomcat, aplikační rozhraní, datové zdroje, Elastic Search, fulltext, Google Bi- gtable, index, Java, Lucene, Memcached, MongoDB, MySQL, Nette Framework, PHP, Rabbit MQ, Redis, REST, Solr, Spring Framework Abstract In this diploma thesis I deal with analysis of the available technologies for implementation of the Gloffer web portal. There are described databases (MySQL, Redis, MongoDB, Aerospike, Apache HBase, Apache Cassandra, Google Bigtable, Memcached), search engines (Solr, Lucene, Elastic Search), web servers (Apache HTTP server, Apache Tomcat), message brokers (Rabbit MQ), distributed computing technologies (Apache Hadoop) and develop technologies (PHP 7, Nette Framework, Java, Spring Framework).
    [Show full text]
  • Openbsd Gaming Resource
    OPENBSD GAMING RESOURCE A continually updated resource for playing video games on OpenBSD. Mr. Satterly Updated August 7, 2021 P11U17A3B8 III Title: OpenBSD Gaming Resource Author: Mr. Satterly Publisher: Mr. Satterly Date: Updated August 7, 2021 Copyright: Creative Commons Zero 1.0 Universal Email: [email protected] Website: https://MrSatterly.com/ Contents 1 Introduction1 2 Ways to play the games2 2.1 Base system........................ 2 2.2 Ports/Editors........................ 3 2.3 Ports/Emulators...................... 3 Arcade emulation..................... 4 Computer emulation................... 4 Game console emulation................. 4 Operating system emulation .............. 7 2.4 Ports/Games........................ 8 Game engines....................... 8 Interactive fiction..................... 9 2.5 Ports/Math......................... 10 2.6 Ports/Net.......................... 10 2.7 Ports/Shells ........................ 12 2.8 Ports/WWW ........................ 12 3 Notable games 14 3.1 Free games ........................ 14 A-I.............................. 14 J-R.............................. 22 S-Z.............................. 26 3.2 Non-free games...................... 31 4 Getting the games 33 4.1 Games............................ 33 5 Former ways to play games 37 6 What next? 38 Appendices 39 A Clones, models, and variants 39 Index 51 IV 1 Introduction I use this document to help organize my thoughts, files, and links on how to play games on OpenBSD. It helps me to remember what I have gone through while finding new games. The biggest reason to read or at least skim this document is because how can you search for something you do not know exists? I will show you ways to play games, what free and non-free games are available, and give links to help you get started on downloading them.
    [Show full text]
  • Artificial Intelligence for Understanding Large and Complex
    Artificial Intelligence for Understanding Large and Complex Datacenters by Pengfei Zheng Department of Computer Science Duke University Date: Approved: Benjamin C. Lee, Advisor Bruce M. Maggs Jeffrey S. Chase Jun Yang Dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of Computer Science in the Graduate School of Duke University 2020 Abstract Artificial Intelligence for Understanding Large and Complex Datacenters by Pengfei Zheng Department of Computer Science Duke University Date: Approved: Benjamin C. Lee, Advisor Bruce M. Maggs Jeffrey S. Chase Jun Yang An abstract of a dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Department of Computer Science in the Graduate School of Duke University 2020 Copyright © 2020 by Pengfei Zheng All rights reserved except the rights granted by the Creative Commons Attribution-Noncommercial Licence Abstract As the democratization of global-scale web applications and cloud computing, under- standing the performance of a live production datacenter becomes a prerequisite for making strategic decisions related to datacenter design and optimization. Advances in monitoring, tracing, and profiling large, complex systems provide rich datasets and establish a rigorous foundation for performance understanding and reasoning. But the sheer volume and complexity of collected data challenges existing techniques, which rely heavily on human intervention, expert knowledge, and simple statistics. In this dissertation, we address this challenge using artificial intelligence and make the case for two important problems, datacenter performance diagnosis and datacenter workload characterization. The first thrust of this dissertation is the use of statistical causal inference and Bayesian probabilistic model for datacenter straggler diagnosis.
    [Show full text]
  • Facebook Messenger Engineering
    SED 1037 Transcript EPISODE 1037 [INTRODUCTION] [00:00:00] JM: Facebook Messenger is a chat application that millions of people use every day to talk to each other. Over time, Messenger has grown to include group chats, video chats, animations, facial filters, stories and many more features. Messenger is a tool for utility as well as for entertainment. Messengers used on both mobile and desktop, but the size of the mobile application is particularly important. There are many users who are on devices that do not have much storage space. As Messenger has accumulated features, the iOS codebase has grown larger and larger. Several generations of Facebook engineers have rotated through the company with responsibility of working on Facebook Messenger, and that has led to different ways of managing information within the same codebase. The iOS codebase had room for improvement and Project LightSpeed was a project within Facebook that had the goal of making Messenger on iOS much smaller. Mohsen Agsen and is an engineer with Facebook and he joins the show to talk about the process of rewriting the Messenger app. This is a great deep dive into how to rewrite a mission- critical iOS application, and this team became very large at a certain point within Facebook. It's a great story and I hope you enjoy it as well. [SPONSOR MESSAGE] [00:01:27] JM: When I’m building a new product, G2i is the company that I call on to help me find a developer who can build the first version of my product. G2i is a hiring platform run by engineers that matches you with React, React Native, GraphQL and mobile engineers who you can trust.
    [Show full text]
  • DVD-Libre 2005-04 Y 2 Pr W W Pr B - 3 T T T T S De Ca SI 5 Sc Re Ra Q 1 Po 3 Ph I Sa Dic Dic 2 4 W Ex ( H N C T
    (continuación) - CDCheck 3.1.4.0 - CDex 1.51 - Celestia 1.3.2 - Centarsia 1.3 - Chain Reaction - Check4me 2.03 - Checky 2.5 - Chomp 1.4.5 - ClamWin 0.83 - Clan Bomber 1.05 - Cobian Backup 6.1.1.264 - Cobian Internet Tools 1.0.0.10 - ColorCop 5.3 - ColorWiz 1.0 - Combinaisons Junior Plus 2.70 - Continental 2.1 - Crack Attack! 1.1.08 - Crimson Editor 3.70 - CubeTest 0.9.3 - DBDesigner 4.0.5.6 - DeepBurner 1.3.6.168 - Deslizzzp 3.3 - Dev-C++ 4.9.9.2 - Dia Win32 0.94 - DirGraph 2.0 - DVD-Libre Disk Imager 1.4 - Domino Puzzle 0.1a - DominOSA 1.71 - DomiSol 1.2 - Doxygen 1.4.1 - Dragonboard 0.8c - Drawing for children 2.0 - DVD Identifier 3.6.2 - e-Counter 3.1.2004 - EasyISO 1.3 - EasyPHP cdlibre.org 1.8 - Eclipse 3.0.1 - Eclipse Language Pack 3.0.x - Eclipse Modeling Framework 2.0.1 - Eclipse Visual Editor 1.0.2 - Emilia Pinball 0.30c - Enigma 0.81 - EQTabla 4.0.050208 - Eraser 5.7 - Everest 2005-04 Dictionary 3.10 beta - Everest Dictionary 3.10 beta Completo - Exact Audio Copy 0.95 prebeta 5 - Exodus 0.9.0.0 - Fall - FileMenu Tools 4.1 - FileZilla 2.2.12a - Find Favorites 1.11 - Firebird 1.5.2 - Flexible Renamer 7.3 - FloboPuyo 0.20 - FolderQuote 1.0 - foobar2000 0.8.3 - FooBilliard 3.0 - Foxit PDF Reader 1.2.0.115 - FractalExplorer 2.02 - FractalForge 2.8.2 - FrameFun 1.0.5.0 - Free Download DVD-Libre es una recopilación de programas para Windows: Manager 1.5.256 - Free Pascal 1.0.10 - FreeCiv 1.14.2 - FreeMind 0.7.1 - Frozen Bubble Enhanced ● libres / gratuitos al menos para uso personal o educativo 1.0 - Gaim 1.1.4 - GanttProject 1.10.3
    [Show full text]
  • Unicorn: a System for Searching the Social Graph
    Unicorn: A System for Searching the Social Graph Michael Curtiss, Iain Becker, Tudor Bosman, Sergey Doroshenko, Lucian Grijincu, Tom Jackson, Sandhya Kunnatur, Soren Lassen, Philip Pronin, Sriram Sankar, Guanghao Shen, Gintaras Woss, Chao Yang, Ning Zhang Facebook, Inc. ABSTRACT rative of the evolution of Unicorn's architecture, as well as Unicorn is an online, in-memory social graph-aware index- documentation for the major features and components of ing system designed to search trillions of edges between tens the system. of billions of users and entities on thousands of commodity To the best of our knowledge, no other online graph re- servers. Unicorn is based on standard concepts in informa- trieval system has ever been built with the scale of Unicorn tion retrieval, but it includes features to promote results in terms of both data volume and query volume. The sys- with good social proximity. It also supports queries that re- tem serves tens of billions of nodes and trillions of edges quire multiple round-trips to leaves in order to retrieve ob- at scale while accounting for per-edge privacy, and it must jects that are more than one edge away from source nodes. also support realtime updates for all edges and nodes while Unicorn is designed to answer billions of queries per day at serving billions of daily queries at low latencies. latencies in the hundreds of milliseconds, and it serves as an This paper includes three main contributions: infrastructural building block for Facebook's Graph Search • We describe how we applied common information re- product. In this paper, we describe the data model and trieval architectural concepts to the domain of the so- query language supported by Unicorn.
    [Show full text]
  • Foundation Overview February 2014
    OpenPOWER Overview May 2015 Keith Brown Director, IBM Systems Technical Strategy & Product Security [email protected] http://openpowerfoundation.org/ © 2015 OpenPOWER Foundation What is the OpenPOWER Ecosystem? Cloud Software Existing ISV community of 800+ Standard Operating Open Environment Source All major Linux distros (System Mgmt) Software Communities Operating Open sourced Power8 System / KVM firmware stack New OSS Firmware OpenPOWER Resources for porting and Firmware Community optimizing on Hardware OpenPOWER OpenPOWERFoundation.org Technology 2 © 2015 OpenPOWER Foundation A Fast Start for OpenPOWER! The year • Collaborative solutions, standards, and reference designs available • Independent members solutions and systems ahead • Sector growth in technical computing and cloud • Global growth with increasing depth in all layers • Broad adoption across hardware, software, and end users 3 © 2015 OpenPOWER Foundation Fueling an Open Development Community 4 © 2015 OpenPOWER Foundation Critical workloads run on Linux on Power Web, Java Apps and Infrastructure Analytics & Research HPC applications for Life Sciences • Highly threaded • Compute intensive • Throughput oriented • High memory bandwidth • Scale out capable • Floating point • High quality of service • High I/O rates Business Applications Database • High quality of service • Handle peak workloads • Scalability • Scalability • Flexible infrastructure • High quality of service • Large memory footprint • Resiliency and security 5 © 2015 OpenPOWER Foundation IBM, Mellanox, and NVIDIA
    [Show full text]