Smart Containers and Skeleton Programming for GPU-Based Systems
2016 (English)In: International journal of parallel programming, ISSN 0885-7458, E-ISSN 1573-7640, Vol. 44, no 3, 506-530 p.Article in journal (Refereed) PublishedText
In this paper, we discuss the role, design and implementation of smart containers in the SkePU skeleton library for GPU-based systems. These containers provide an interface similar to C++ STL containers but internally perform runtime optimization of data transfers and runtime memory management for their operand data on the different memory units. We discuss how these containers can help in achieving asynchronous execution for skeleton calls while providing implicit synchronization capabilities in a data consistent manner. Furthermore, we discuss the limitations of the original, already optimizing memory management mechanism implemented in SkePU containers, and propose and implement a new mechanism that provides stronger data consistency and improves performance by reducing communication and memory allocations. With several applications, we show that our new mechanism can achieve significantly (up to 33.4 times) better performance than the initial mechanism for page-locked memory on a multi-GPU based system.
Place, publisher, year, edition, pages
SPRINGER/PLENUM PUBLISHERS , 2016. Vol. 44, no 3, 506-530 p.
SkePU; Smart containers; Skeleton programming; Memory management; Runtime optimizations; GPU-based systems
Computer and Information Science
IdentifiersURN: urn:nbn:se:liu:diva-128719DOI: 10.1007/s10766-015-0357-6ISI: 000374897200008OAI: oai:DiVA.org:liu-128719DiVA: diva2:933909
Funding Agencies|EU; SeRC2016-06-072016-05-302016-06-07