1 / 1

General-Purpose vs. GPU: A Comparison of Many-Core Performance on Irregular Workloads

This analysis by the University of Maryland examines the performance of general-purpose many-core platforms compared to GPUs, particularly for irregular workloads. Highlighting Intel's challenges with programming for 100-core processors, the paper discusses the proposed XMT (eXplicit Multi-Threading) solution. It emphasizes the ease of parallel programming and the benefits of abstraction for developers. The findings show a significant performance boost on irregular applications, achieving 6.05x speedup over CUDA GPUs, while noting the trade-offs in performance on regular applications.

bryce
Télécharger la présentation

General-Purpose vs. GPU: A Comparison of Many-Core Performance on Irregular Workloads

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. General-Purpose vs. GPU:Comparison of Many-Cores on Irregular WorkloadsUniversity of Maryland, College Park • ..we will not bring these [100 core] products to market until we have good solutions to the programming problem J. Rattner, Intel CTO 3/2006 • Proposed solutionXMT (eXplicitMulti Threading) • General-Purpose Many-Core platform • Issue: ease of parallel programming • Abstraction: (any) next instruction(s) execute immediately • Means: PRAM theory, programmer’s workflow, HW+SW • Unmatched on: abstraction, teachability, and support by algorithms/theory, foundation of CS • How much performance does one need to sacrifice for ease of programming? Surprise. Performance bonuswhen using similar chip area: • 6.05x average speedup over CUDA GPU on irregular applications • 2.07x slowdown on regular applications G.C. Caragea F. Keceli A. Tzannes U.Vishkin

More Related