Optimized implementations of blocking and nonblocking collective operations are most important for scalable high-performance applications. Offloading such collective operations into the communication layer can improve performance and asynchronous progression of the operations. However, it is most important that such offloading schemes remain flexible in order to support user-defined (sparse neighbor) collective communications. In this work, we describe an operating system kernel-based architecture for implementing an interpreter for the flexible Group Operation Assembly Language (GOAL) framework to offload collective communications. We describe an optimized scheme to store the schedules that define the collective operations and show an extension to profile the performance of the kernel layer. Our microbenchmarks demonstrate the effectiveness of the approach and we show performance improvements over traditional progression in user-space. We also discuss complications with the design and offloading strategies in general.

Identiferoai:union.ndltd.org:DRESDEN/oai:qucosa.de:bsz:ch1-qucosa-67745
Date18 May 2011
CreatorsSchneider, Timo, Eckelmann, Sven
ContributorsTU Chemnitz, Fakultät für Informatik, Dipl. Inf. Nico Mittenzwey, Professor Dr.-Ing. Wolfgang Rehm
PublisherUniversitätsbibliothek Chemnitz
Source SetsHochschulschriftenserver (HSSS) der SLUB Dresden
LanguageEnglish
Detected LanguageEnglish
Typedoc-type:StudyThesis
Formatapplication/pdf, text/plain, application/zip

Page generated in 0.003 seconds