74470 81182 0 1>
Total Page:16
File Type:pdf, Size:1020Kb

Load more
Recommended publications
-
NVIDIA Opengl in 2012 Mark Kilgard
NVIDIA OpenGL in 2012 Mark Kilgard • Principal System Software Engineer – OpenGL driver and API evolution – Cg (“C for graphics”) shading language – GPU-accelerated path rendering • OpenGL Utility Toolkit (GLUT) implementer • Author of OpenGL for the X Window System • Co-author of Cg Tutorial Outline • OpenGL’s importance to NVIDIA • OpenGL API improvements & new features – OpenGL 4.2 – Direct3D interoperability – GPU-accelerated path rendering – Kepler Improvements • Bindless Textures • Linux improvements & new features • Cg 3.1 update NVIDIA’s OpenGL Leverage Cg GeForce Parallel Nsight Tegra Quadro OptiX Example of Hybrid Rendering with OptiX OpenGL (Rasterization) OptiX (Ray tracing) Parallel Nsight Provides OpenGL Profiling Configure Application Trace Settings Parallel Nsight Provides OpenGL Profiling Magnified trace options shows specific OpenGL (and Cg) tracing options Parallel Nsight Provides OpenGL Profiling Parallel Nsight Provides OpenGL Profiling Trace of mix of OpenGL and CUDA shows glFinish & OpenGL draw calls Only Cross Platform 3D API OpenGL 3D Graphics API • cross-platform • most functional • peak performance • open standard • inter-operable • well specified & documented • 20 years of compatibility OpenGL Spawns Closely Related Standards Congratulations: WebGL officially approved, February 2012 “The web is now 3D enabled” Buffer and OpenGL 4 – DirectX 11 Superset Event Interop • Interop with a complete compute solution – OpenGL is for graphics – CUDA / OpenCL is for compute • Shaders can be saved to and loaded from binary -
Fraps Windows 10
Fraps windows 10 Continue I noticed a person in the myst-Uru community point out that FRAPS doesn't work on their Windows 10 machine. I'm on the verge of upgrading my main machine to 10. So what's going on? First, visit the FRAPS website. FRAPS is advertised for Windows until version 7. The newest version of 3.5.99 was released in February 2013... two or more years ago. (By number 11/24/2018 there are still no updates.) Are they going to update it for Windows 10? I can't find any information to reliably answer that question. I've seen some people commenting that the latest pace of updates several times a year stopped in February 2013. Requests that use the contact form in FRAPS have largely gone unanswered. A June 2015 video shows FRAPS working in Win10 on older hardware. Some search shows people have problems with FRAPS on Win10. There is some discussion of this issue in the FRAPS Windows 10 Thread issues on Microsoft forums. Update 11/2018: No new FRAPS updates, 5 years. Now I find FRAPS dead. Exploring ways to get FRAPS working on Win10... I don't find good fixes or solutions. Tom's Hardware Review and other technology sites have no answers. In this topic, one person says they received an email back from FRAPS people saying an update to Windows 10 is in the process. (I take it as a rumor.) This one doesn't exist. This is from the post in August 2015. The date of the letter was not included. -
Developer Tools Showcase
Developer Tools Showcase Randy Fernando Developer Tools Product Manager NVISION 2008 Software Content Creation Performance Education Development FX Composer Shader PerfKit Conference Presentations Debugger mental mill PerfHUD Whitepapers Artist Edition Direct3D SDK PerfSDK GPU Programming Guide NVIDIA OpenGL SDK Shader Library GLExpert Videos CUDA SDK NV PIX Plug‐in Photoshop Plug‐ins Books Cg Toolkit gDEBugger GPU Gems 3 Texture Tools NVSG GPU Gems 2 Melody PhysX SDK ShaderPerf GPU Gems PhysX Plug‐Ins PhysX VRD PhysX Tools The Cg Tutorial NVIDIA FX Composer 2.5 The World’s Most Advanced Shader Authoring Environment DirectX 10 Support NVIDIA Shader Debugger Support ShaderPerf 2.0 Integration Visual Models & Styles Particle Systems Improved User Interface Particle Systems All-New Start Page 350Z Sample Project Visual Models & Styles Other Major Features Shader Creation Wizard Code Editor Quickly create common shaders Full editor with assisted Shader Library code generation Hundreds of samples Properties Panel Texture Viewer HDR Color Picker Materials Panel View, organize, and apply textures Even More Features Automatic Light Binding Complete Scripting Support Support for DirectX 10 (Geometry Shaders, Stream Out, Texture Arrays) Support for COLLADA, .FBX, .OBJ, .3DS, .X Extensible Plug‐in Architecture with SDK Customizable Layouts Semantic and Annotation Remapping Vertex Attribute Packing Remote Control Capability New Sample Projects 350Z Visual Styles Atmospheric Scattering DirectX 10 PCSS Soft Shadows Materials Post‐Processing Simple Shadows -
WWW 2013 22Nd International World Wide Web Conference
WWW 2013 22nd International World Wide Web Conference General Chairs: Daniel Schwabe (PUC-Rio – Brazil) Virgílio Almeida (UFMG – Brazil) Hartmut Glaser (CGI.br – Brazil) Research Track: Ricardo Baeza-Yates (Yahoo! Labs – Spain & Chile) Sue Moon (KAIST – South Korea) Practice and Experience Track: Alejandro Jaimes (Yahoo! Labs – Spain) Haixun Wang (MSR – China) Developers Track: Denny Vrandečić (Wikimedia – Germany) Marcus Fontoura (Google – USA) Demos Track: Bernadette F. Lóscio (UFPE – Brazil) Irwin King (CUHK – Hong Kong) W3C Track: Marie-Claire Forgue (W3C Training, USA) Workshops Track: Alberto Laender (UFMG – Brazil) Les Carr (U. of Southampton – UK) Posters Track: Erik Wilde (EMC – USA) Fernanda Lima (UNB – Brazil) Tutorials Track: Bebo White (SLAC – USA) Maria Luiza M. Campos (UFRJ – Brazil) Industry Track: Marden S. Neubert (UOL – Brazil) Proceedings and Metadata Chair: Altigran Soares da Silva (UFAM - Brazil) Local Arrangements Committee: Chair – Hartmut Glaser Executive Secretary – Vagner Diniz PCO Liaison – Adriana Góes, Caroline D’Avo, and Renato Costa Conference Organization Assistant – Selma Morais International Relations – Caroline Burle Technology Liaison – Reinaldo Ferraz UX Designer / Web Developer – Yasodara Córdova, Ariadne Mello Internet infrastructure - Marcelo Gardini, Felipe Agnelli Barbosa Administration– Ana Paula Conte, Maria de Lourdes Carvalho, Beatriz Iossi, Carla Christiny de Mello Legal Issues – Kelli Angelini Press Relations and Social Network – Everton T. Rodrigues, S2Publicom and EntreNós PCO – SKL Eventos -
Jim Allchin on Longhorn, Winfs, 64-Bit and Beyond Page 34 Jim
0805red_cover.v5 7/19/05 2:57 PM Page 1 4 Scripting Solutions to Simplify Your Life Page 28 AUGUST 2005 WWW.REDMONDMAG.COM MrMr WindowsWindows Jim Allchin on Longhorn, WinFS, 64-Bit and Beyond Page 34 > $5.95 05 • AUGUST Make Room for Linux Apps Page 43 25274 867 27 Active Directory Design Disasters Page 49 71 Project1 6/16/05 12:36 PM Page 1 Exchange Server stores & PSTs driving you crazy? Only $399 for 50 mailboxes; $1499 for unlimited mailboxes! Archive all mail to SQL and save 80% storage space! Email archiving solution for internal and external email Download your FREE trial from www.gfi.com/rma Project1 6/16/05 12:37 PM Page 2 Get your FREE trial version of GFI MailArchiver for Exchange today! GFI MailArchiver for Exchange is an easy-to-use email archiving solution that enables you to archive all internal and external mail into a single SQL database. Now you can provide users with easy, centralized access to past email via a web-based search interface and easily fulfill regulatory requirements (such as the Sarbanes-Oxley Act). GFI MailArchiver leverages the journaling feature of Exchange Server 2000/2003, providing unparalleled scalability and reliability at a competitive cost. GFI MailArchiver for Exchange features Provide end-users with a single web-based location in which to search all their past email Increase Exchange performance and ease backup and restoration End PST hell by storing email in SQL format Significantly reduce storage requirements for email by up to 80% Comply with Sarbanes-Oxley, SEC and other regulations. -
Gaia Sky Documentation Release 1.5.0
Gaia Sky Documentation Release 1.5.0 Toni Sagrista Selles Jul 06, 2018 Contents 1 Main features 3 2 Contents 5 2.1 Download.................................................5 2.2 Requirements and Installation......................................5 2.2.1 System requirements......................................5 2.2.2 Installation and uninstallation..................................5 2.2.3 Running from source......................................7 2.3 Running Gaia Sky............................................7 2.3.1 Running from source......................................8 2.3.2 Running from downloaded package..............................9 2.4 Documentation.............................................. 10 2.4.1 Settings and configuration................................... 10 2.4.2 The configuration file...................................... 12 2.4.3 Graphics settings........................................ 13 2.4.4 Graphics performance..................................... 15 2.4.5 User Interface.......................................... 19 2.4.6 Controls............................................. 22 2.4.7 Camera modes......................................... 26 2.4.8 Cinematic camera........................................ 29 2.4.9 Stereoscopic (3D) mode.................................... 29 2.4.10 Planetarium mode........................................ 32 2.4.11 Panorama mode......................................... 32 2.4.12 Recording and playing camera paths.............................. 35 2.4.13 Performance.......................................... -
ETHAN KATZ-BASSETT [email protected]
ETHAN KATZ-BASSETT [email protected] http://www.columbia.edu/~ebk2141/ Research Interests networking: Internet reliability and performance, Internet-scale distributed systems, Internet measurement, routing, content delivery, system design and deployment I design systems to improve the reliability and performance of Internet services. To understand the problems, I look to the needs of operators and providers, and I conduct measurements. Based on what I learn, I design deployable systems to improve the Internet and services that run over it. Education Ph.D., Computer Science and Engineering, University of Washington, Seattle, WA (March 2012) Advisors: Tom Anderson and Arvind Krishnamurthy Dissertation: Systems for Improving Internet Availability and Performance Won the department’s 2012 William Chan Memorial Dissertation Award B.A., Computer Science & Mathematics, Williams College, Williamstown, MA (June 2001) Magna Cum Laude Employment Associate Professor [tenure track but without tenure] (2017-current) Department of Electrical Engineering, Columbia University, New York, NY. Andrew and Erna Viterbi Early Career Chair (2016-2017) Assistant Professor (2012-2017) Computer Science Department, University of Southern California, Los Angeles, CA. Software Engineer (2011-2012) Mobile performance, Google Inc., Seattle, WA. Honors and Awards · Andrew and Erna Viterbi Early Career Chair, 2016 · Facebook Faculty Award, 2016, 2017 · Google Faculty Research Award, 2013, 2014, 2015, 2016 · Applied Networking Research Prize, IRTF/IETF, TCP Gentle -
Winter 2006-2007
UNIVERSITY OF NEBRASKA–LINCOLN COLLEGE OF JOURNALISM AND MASS COMMUNICATIONS ALUMNI MAGAZINE WINTER 2006-2007 Q&A With Steve Pederson Pages 44–51 Photo courtesy Lincoln Journal Star M E D I A Wesley G. Pippert ‘JUST POLITICS’ The nation has been reminded in recent days of the quality of There had been jokes that Ford had played football too long President Gerald R. Ford’s life and the easy, comfortable rela- without a helmet, making light of his presumed lack of wit — tionship he had with members of the press corps. even though he finished in the top third of his class both at In many ways, this relationship was another demonstration Michigan and the Yale law school. So during the speech Ford of Ford’s general friendliness with everyone. And it seems to me tried to put on an old helmet he had worn — but it wouldn’t fit. that it also was the result of his having worked on a frequent, “Heads tend to swell in Washington,” he said, a remark that daily basis with reporters during a quarter of a century in brought down the house. Congress. It was something of a surprise, then, when in 1974 Ford In times past, reporters gathered on the floor of the Senate a vetoed a bill that would have strengthened the 1966 Freedom of few minutes before the start of the session for what was called Information Act. (FOIA gives any citizen the right to gain access “dugout chatter,” a time when the majority leader would answer to government documents, with certain exceptions such as questions. -
Manycore GPU Architectures and Programming, Part 1
Lecture 19: Manycore GPU Architectures and Programming, Part 1 Concurrent and Mul=core Programming CSE 436/536, [email protected] www.secs.oakland.edu/~yan 1 Topics (Part 2) • Parallel architectures and hardware – Parallel computer architectures – Memory hierarchy and cache coherency • Manycore GPU architectures and programming – GPUs architectures – CUDA programming – Introduc?on to offloading model in OpenMP and OpenACC • Programming on large scale systems (Chapter 6) – MPI (point to point and collec=ves) – Introduc?on to PGAS languages, UPC and Chapel • Parallel algorithms (Chapter 8,9 &10) – Dense matrix, and sorng 2 Manycore GPU Architectures and Programming: Outline • Introduc?on – GPU architectures, GPGPUs, and CUDA • GPU Execuon model • CUDA Programming model • Working with Memory in CUDA – Global memory, shared and constant memory • Streams and concurrency • CUDA instruc?on intrinsic and library • Performance, profiling, debugging, and error handling • Direc?ve-based high-level programming model – OpenACC and OpenMP 3 Computer Graphics GPU: Graphics Processing Unit 4 Graphics Processing Unit (GPU) Image: h[p://www.ntu.edu.sg/home/ehchua/programming/opengl/CG_BasicsTheory.html 5 Graphics Processing Unit (GPU) • Enriching user visual experience • Delivering energy-efficient compung • Unlocking poten?als of complex apps • Enabling Deeper scien?fic discovery 6 What is GPU Today? • It is a processor op?mized for 2D/3D graphics, video, visual compu?ng, and display. • It is highly parallel, highly multhreaded mulprocessor op?mized for visual -
Because Sustainability
Change Making Simplified Addressing technology- business transformation in the COVID-era Contents Foreword 03 Thriving on Data 36 Applying TechnoVision 73 Leveraging data and algorithms as an asset to Introduction 04 increase the "Corporate IQ". A Few More Things 84 TechnoVision and COVID-19 06 Process on the Fly 43 TechnoVision 2020 Team 88 Building, managing, and running processes that Simplify 11 match the dynamics of the digital outside world. About Capgemini 90 You Experience 50 Being Architects of Positive Futures 15 Creating seamless user experiences for decisive, Overview of TechnoVision 18 magical moments. We Collaborate 57 Invisible Infostructure 22 Tapping into the power of the connected and Evolving the IT Infrastructure into the simple, collaborative "everything". pluggable utility it was always supposed to be. Design for Digital 64 Applications Unleashed 29 Overarching design principles to be followed and Liberating the legacy application landscape and checked throughout the journey of becoming a unleashing the next generation of powerful, agile, Technology Business. cloud-based apps. Invisible Infostructure Applications Unleashed Thriving on Data Process on the Fly You Experience We Collaborate Design for Digital Applying TechnoVision Special Foreword Patrick Nicolet Group Executive Board Member and Group CTO “Future Thinking, Change Making” businesses to operate, retailers to sell and companies to deliver. While The theme of this edition is ‘Simplify’ because, in a world where data the value of traditional ‘safe’ commodities has dropped exponentially, seems to overwhelm us all, we recognize that technology should It’s a sobering thought that, only a few months ago, when we were the popularity of technology and technological companies has soared aim to make the lives of consumers, colleagues and citizens easier. -
Software-Based Undervolting Faults in AMD Zen Processors Fehler in AMD Zen Prozessoren Durch Software-Basierte Unterspannung
Software-based Undervolting Faults in AMD Zen Processors Fehler in AMD Zen Prozessoren durch Software-basierte Unterspannung Bachelorarbeit im Rahmen des Studiengangs IT-Sicherheit der Universität zu Lübeck vorgelegt von Anja Rabich ausgegeben und betreut von Prof. Dr. Thomas Eisenbarth mit Unterstützung von Luca Wilke Lübeck, den 31. August 2020 Abstract Dynamic Voltage and Frequency Scaling (DVFS) is a powerful performance enhance- ment method used by modern processors, allowing them to scale voltage or frequency as needed based on the power requirements of the CPU. This not only saves power, but also prevents processors from overheating. However, the continued integration of soft- ware interfaces giving a user direct access to this functionality has been shown to be a potential security risk, allowing a privileged adversary to indirectly tamper with sensitive computations. This thesis summarizes the results of various papers showing that using DVFS features, unsuitable voltage/frequency values can be set for the processor leading to hardware faults and calculation errors which can be used to undermine the integrity of Trusted Execution Environments (TEE). Results are partially replicated for Intel’s TEE implementation SGX, followed by extending the same methodology to AMD’s Zen Pro- cessors, on which there is currently no information. Results show that undervolting is an unlikely attack vector. iii Zusammenfassung Dynamische Spannungs- und Frequenzskalierung (engl. DVFS) ist ein in modernen Prozessoren vorhandener Leistungs- und Stromverwaltungsmechanismus, womit Span- nung und Frequenz der CPU je nach Bedarf skaliert werden können. Somit wird nicht nur Strom gespart, sondern auch zusätzlich verhindert, dass der Prozessor überhitzt. Die zunehmende Integration von Softwareschnittstellen zu diesen Mechanismen die dem Nutzer Einstellungsmöglichkeiten anbieten, haben sich zunehmend als potenzielle Sicherheitslücke erwiesen. -
High Performance Linpack Benchmark on AMD EPYC™ Processors
High Performance Linpack Benchmark on AMD EPYC™ Processors This document details running the High Performance Linpack (HPL) benchmark using the AMD xhpl binary. HPL Implementation: The HPL benchmark presents an opportunity to demonstrate the optimal combination of multithreading (via the OpenMP library) and MPI for scientific and technical high-performance computing on the EPYC architecture. For MPI applications where the per-MPI-rank work can be further parallelized, each L3 cache is an MPI rank running a multi-threaded application. This approach results in fewer MPI ranks than using one rank per core, and results in a corresponding reduction in MPI overhead. The ideal balance is for the number of threads per MPI rank to be less than or equal to the number of CPUs per L3 cache. The exact maximum thread count per MPI rank depends on both the specific EPYC SKU (e.g. 32 core parts have 4 physical cores per L3, 24 core parts have 3 physical cores per L3) and whether SMT is enabled (e.g. for a 32 core part with SMT enabled there are 8 CPUs per L3). HPL performance is primarily determined by DGEMM performance, which is in turn primarily determined by SIMD throughput. The Zen microarchitecture of the EPYC processor implements one SIMD unit per physical core. Since HPL is SIMD limited, when SMT is enabled using a second HPL thread per core will not directly improve HPL performance. However, leaving SMT enabled may indirectly allow slightly higher performance (1% - 2%) since the OS can utilize the SMT siblings as needed without pre-empting the HPL threads.