SkePU 2: Flexible and Type-Safe Skeleton Programming for Heterogeneous Parallel Systems

In this article we present SkePU 2 , the next generation of the SkePU C++ skeleton programming framework for heterogeneous parallel systems. We critically examine the design and limitations of the SkePU 1 programming interface. We present a new, flexible and type-safe, interface for skeleton program...

Full description

Saved in:
Bibliographic Details
Published in:International journal of parallel programming Vol. 46; no. 1; pp. 62 - 80
Main Authors: Ernstsson, August, Li, Lu, Kessler, Christoph
Format: Journal Article
Language:English
Published: New York Springer US 01.02.2018
Springer Nature B.V
Subjects:
Computer Science
Parallel processing
Parallel programming
Processor Architectures
Software Engineering/Programming and Operating Systems
Theory of Computation
Transformations (mathematics)
SkePU
Source-to-source transformation
Portability
Skeleton programming
Heterogeneous parallel systems
C++11
ISSN:0885-7458, 1573-7640, 1573-7640
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this article we present SkePU 2 , the next generation of the SkePU C++ skeleton programming framework for heterogeneous parallel systems. We critically examine the design and limitations of the SkePU 1 programming interface. We present a new, flexible and type-safe, interface for skeleton programming in SkePU 2, and a source-to-source transformation tool which knows about SkePU 2 constructs such as skeletons and user functions. We demonstrate how the source-to-source compiler transforms programs to enable efficient execution on parallel heterogeneous systems. We show how SkePU 2 enables new use-cases and applications by increasing the flexibility from SkePU 1, and how programming errors can be caught earlier and easier thanks to improved type safety. We propose a new skeleton, Call , unique in the sense that it does not impose any predefined skeleton structure and can encapsulate arbitrary user-defined multi-backend computations. We also discuss how the source-to-source compiler can enable a new optimization opportunity by selecting among multiple user function specializations when building a parallel program. Finally, we show that the performance of our prototype SkePU 2 implementation closely matches that of SkePU 1.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-7458
1573-7640
1573-7640
DOI:10.1007/s10766-017-0490-5