Adaptive and transparent cache bypassing for GPUs

A. Li, G.-J. van den Braak, A. Kumar, H. Corporaal

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

32 Citations (Scopus)

Abstract

In the last decade, GPUs have emerged to be widely adopted for general-purpose applications. To capture on-chip locality for these applications, modern GPUs have integrated multilevel cache hierarchy, in an attempt to reduce the amount and latency of the massive and sometimes irregular memory accesses. However, inferior performance is frequently attained due to serious congestion in the caches results from the huge amount of concurrent threads. In this paper, we propose a novel compile-time framework for adaptive and transparent cache bypassing on GPUs. It uses a simple yet effective approach to control the bypass degree to match the size of applications' runtime footprints. We validate the design on seven GPU platforms that cover all existing GPU generations using 16 applications from widely used GPU benchmarks. Experiments show that our design can significantly mitigate the negative impact due to small cache sizes and improve the overall performance. We analyze the performance across different platforms and applications. We also propose some optimization guidelines on how to efficiently use the GPU caches.

Original languageEnglish
Title of host publicationProceedings of SC 2015: The International Conference for High Performance Computing, Networking, Storage and Analysis
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Number of pages12
ISBN (Electronic)978-1-4503-3723-6
DOIs
Publication statusPublished - 15 Nov 2015
Event27th International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2015), November 15-20, 2015, Austin, Texas, United States - Austin, United States
Duration: 15 Nov 201520 Nov 2015

Conference

Conference27th International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2015), November 15-20, 2015, Austin, Texas, United States
CountryUnited States
CityAustin
Period15/11/1520/11/15

Keywords

  • cache bypassing
  • GPUs
  • thread throttling

Fingerprint Dive into the research topics of 'Adaptive and transparent cache bypassing for GPUs'. Together they form a unique fingerprint.

  • Cite this

    Li, A., van den Braak, G-J., Kumar, A., & Corporaal, H. (2015). Adaptive and transparent cache bypassing for GPUs. In Proceedings of SC 2015: The International Conference for High Performance Computing, Networking, Storage and Analysis [17] Association for Computing Machinery, Inc. https://doi.org/10.1145/2807591.2807606