Composing Parallel Software Efficiently with Lithe

TitleComposing Parallel Software Efficiently with Lithe
Publication TypeConference Paper
Year of Publication2010
AuthorsPan, H., Hindman B., & Asanovi´c K.
Conference NameProgramming Language Design and implementation (PLDI-2010)
Date Published06/2010
Conference LocationToronto, Canada

Applications composed of multiple parallel libraries perform
poorly when those libraries interfere with one another by oblivi-
ously using the same physical cores, leading to destructive resource oversubscription. This paper presents the design and implementation of Lithe, a low-level substrate that provides the basic primitives and a standard interface for composing parallel codes efficiently. Lithe can be inserted underneath the runtimes of legacy parallel libraries to provide bolt-on composability without needing to change existing application code. Lithe can also serve as the foundation for building new parallel abstractions and libraries that automatically interoperate with one another.
In this paper, we show versions of Threading Building Blocks
(TBB) and OpenMP perform competitively with their original im-
plementations when ported to Lithe. Furthermore, for two applica-
tions composed of multiple parallel libraries, we show that lever-
aging our substrate outperforms their original, even expertly tuned, implementations.

pldi285-pan.pdf2.29 MB