GithubHelp home page GithubHelp logo

ensq / warp-paper Goto Github PK

View Code? Open in Web Editor NEW
0.0 2.0 1.0 7.38 MB

'Accelerating GPU Workload Simulation using Microsoft WARP'; a study into the performance of WARP (Windows Advanced Rasterization Platform) - a high-speed software rasterizer introduced by Microsoft in the Direct3D 11 runtime.

Home Page: http://bit.ly/MicrosoftWarpPdf

Gnuplot 2.62% TeX 95.65% Perl 1.73%

warp-paper's Introduction

warp-paper

'Accelerating GPU Workload Simulation using Microsoft WARP'; a study into the performance of WARP (Windows Advanced Rasterization Platform) - a high-speed software rasterizer introduced by Microsoft in the Direct3D 11 runtime.


Click here for a compiled version of the article.

Abstract

A convenient approach toward more transparent debugging and profiling of GPU-accelerated applications is to simulate GPU-bound workloads on CPUs. This approach is also applicable in situations where target hardware is simply not available, as is often the case with server-side applications, or would require too many system resources to initialize. However, when simulating GPU-bound workloads on CPUs, one may experience severe performance losses due to computational overhead.

Consequently, the subject of this study is performance variations between three device drivers of the DirectX framework; using DirectCompute and the high speed software rasterizer WARP (Windows Advanced Rasterization Platform). The performance of WARP is compared to that of traditional GPU hardware acceleration and the standard driver for software rasterization - the Reference Device Driver.

Experimental results show a major performance boost when compared to that of software rasterization using the reference device driver, indicating that performance losses traditionally obstructing simulation of throughput-oriented workloads on CPUs may be sufficiently amended by technologies, such as WARP, to the degree that simulation may be considered viable for extended use above and beyond that of current in-development utilities.

BibTeX

@inproceedings{nilsson:warp:2014,
    author = {Nilsson, Eric},
    title = {Accelerating GPU Workload Simulation using Microsoft WARP},
    editor = {Dickinson, Patrick},
    booktitle = {15th International Conference on Intelligent Games and Simulation},
    number = {15},
    pages = {115--120},
    month = {September},
    year = {2014},
    organization = {University of Lincoln},
    isbn = {978-90-77381-85-4},
    publisher = {EUROSIS-ETI},
    series = {GAME-ON},
}

warp-paper's People

Contributors

ensq avatar

Watchers

James Cloos avatar  avatar

Forkers

zhuguoping

warp-paper's Issues

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.