HeteroSync: A benchmark suite for fine-grained synchronization on tightly coupled GPUs

Matthew D. Sinclair, Johnathan Alsop, Sarita V. Adve

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Traditionally GPUs focused on streaming, data-parallel applications, with little data reuse or sharing and coarse-grained synchronization. However, the rise of general-purpose GPU (GPGPU) computing has made GPUs desirable for applications with more general sharing patterns and fine-grained synchronization, especially for recent GPUs that have a unified address space and coherent caches. Prior work has introduced microbenchmarks to measure the impact of these changes, but each paper uses its own set of microbenchmarks. In this work, we combine several of these sets together in a single suite, HeteroSync. HeteroSync includes several synchronization primitives, data sharing at different levels of the memory hierarchy, and relaxed atomics. We characterize the scalability of HeteroSync for different coherence protocols and consistency models on modern, tightly coupled CPU-GPU systems and show that certain algorithms, coherence protocols, and consistency models scale better than others.

Original languageEnglish (US)
Title of host publicationProceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages239-249
Number of pages11
ISBN (Electronic)9781538612323
DOIs
StatePublished - Dec 5 2017
Event2017 IEEE International Symposium on Workload Characterization, IISWC 2017 - Seattle, United States
Duration: Oct 1 2017Oct 3 2017

Publication series

NameProceedings of the 2017 IEEE International Symposium on Workload Characterization, IISWC 2017
Volume2017-January

Other

Other2017 IEEE International Symposium on Workload Characterization, IISWC 2017
CountryUnited States
CitySeattle
Period10/1/1710/3/17

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems and Management

Fingerprint Dive into the research topics of 'HeteroSync: A benchmark suite for fine-grained synchronization on tightly coupled GPUs'. Together they form a unique fingerprint.

Cite this