Automatic CPU-GPU communication management and optimization

Thomas B. Jablin, Prakash Prabhu, James A. Jablin, Nick P. Johnson, Stephen R. Beard, David I. August

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

128 Scopus citations


The performance benefits of GPU parallelism can be enormous, but unlocking this performance potential is challenging. The applicability and performance of GPU parallelizations is limited by the complexities of CPU-GPU communication. To address these communications problems, this paper presents the first fully automatic system for managing and optimizing CPU-GPU communcation. This system, called the CPU-GPU Communication Manager (CGCM), consists of a run-time library and a set of compiler transformations that work together to manage and optimize CPU-GPU communication without depending on the strength of static compile-time analyses or on programmer-supplied annotations. CGCM eases manual GPU parallelizations and improves the applicability and performance of automatic GPU parallelizations. For 24 programs, CGCM-enabled automatic GPU parallelization yields a whole program geomean speedup of 5.36x over the best sequential CPU-only execution.

Original languageEnglish (US)
Title of host publicationPLDI'11 - Proceedings of the 2011 ACM Conference on Programming Language Design and Implementation
PublisherAssociation for Computing Machinery
Number of pages10
ISBN (Print)9781450306638
StatePublished - 2011
Event32nd ACM Conference on Programming Language Design and Implementation, PLDI 2011 - San Jose, United States
Duration: Jun 4 2011Jun 8 2011

Publication series

NameProceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI)


Conference32nd ACM Conference on Programming Language Design and Implementation, PLDI 2011
Country/TerritoryUnited States
CitySan Jose

All Science Journal Classification (ASJC) codes

  • Software


  • communication
  • gpu
  • management
  • optimization


Dive into the research topics of 'Automatic CPU-GPU communication management and optimization'. Together they form a unique fingerprint.

Cite this