Sie verwenden einen Browser, in dem JavaScript deaktiviert ist. Dadurch wird verhindert, dass Sie die volle Funktionalität dieser Webseite nutzen können. Zur Navigation müssen Sie daher die Sitemap nutzen.

You are currently using a browser with deactivated JavaScript. There you can't use all the features of this website. In order to navigate the site, please use the Sitemap .

Scalable and Efficient Linear Algebra Kernel Mapping for Low Energy Consumption on the Layers CGRA

Authors:: Rákossy, Z. E. , Stengele, D. , Acosta Aponte, A. , Chafekar, S. , Bientinesi, P. , Chattopadhyay, A.
Editors:: Sano, K. , Soudris, D. , Hübner, M. , Diniz, P. C.
Book Title:: International Symposium on Applied Reconfigurable Computing
Publisher:: Springer International Publishing
Series:: Lecture Notes in Computer Science
Volume:: 9040
Pages:: p.p. 301-310
Address:: Bochum, Germany
Date:: Apr. 2015
DOI:: 0.1007/978-3-319-16214-0_25
Language:: English
Abstract:: The scalable coarse-grained reconfigurable archi- tecture, Layers, exploits functional parallelism of memory access, data movement and processing to gain high energy efficiency, while a functional reconfiguration-based programming model allows an easy programming model. In this paper, architecture- aware and scalable application mapping is proposed for 3 important kernels from the Numerical Linear Algebra domain, to exploit the architectural features to reach asymptotically optimal efficiency and a low energy consumption. Performance and power evaluations were done with input data set matrix sizes ranging from 64×64 to 16384×16384. 12 architectural variants with up to 10×10 processing elements were used to explore scalability of the mapping and the architecture, achieving < 10% energy increase for architectures up to 8×8 PEs coupled with performance speed- ups of more than an order of magnitude. This enables a clean area-performance trade-off while keeping energy constant over the variants.
Download:: BibTeX