Optimizations on Array Skeletons in a Shared Memory Environment

Clemens Grelck


Map- and fold-like skeletons are a suitable abstractions to guide parallel program execution in functional array processing. However, when it comes to achieving high performance, it turns out that confining compilation efforts to individual skeletons is insufficient. This paper proposes compilation schemes which aim at reducing runtime overhead due to communication and synchronization by embedding multiple array skeletons within a so-called spmd meta skeleton. Whereas the meta skeleton exclusively takes responsibility for the organization of parallel program execution, the original array skeletons are focussed to their individual numerical operation. While concrete compilation schemes assume multithreading in a shared memory environment as underlying execution model, ideas can be carried over to other settings straightforwardly. Preliminary performance investigations help to quantify potential benefits.

Original languageEnglish
Title of host publicationIFL 2001: Implementation of Functional Languages
Number of pages9
PublisherSpringer Verlag
Publication date01.01.2002
ISBN (Print)978-3-540-43537-2
ISBN (Electronic)978-3-540-43537-2
Publication statusPublished - 01.01.2002
Event13th International Workshop on Implementation of Functional Languages
- Stockholm, Sweden
Duration: 24.08.200126.08.2001
Conference number: 121759


Dive into the research topics of 'Optimizations on Array Skeletons in a Shared Memory Environment'. Together they form a unique fingerprint.

Cite this