Institute for Communication Technologies and Embedded Systems

Graph-based Kernel Recognition for Compiler Guidance

Authors:
Rodriguez Blanco, M. H.
Book Title:
Proceedings of the Tenth International Summer School on Advanced Computer Architecture and Compilation for High-Performance and Embedded Systems (ACACES)
Publisher:
HIPEAC
Pages:
p.p. 137-140
Address:
L'Aquila, Italy
Date:
Jul. 2014
Note:

-Abstract-

ISBN:
978-8-89058-062-8
Language:
English
Abstract:
Functional and performance portability as well as maintainability have become dominant issues when developing embedded software, mainly due to the increasing use of heterogenous processor architectures in modern designs. Compilers had to evolve as well to cope with this trend. For example, auto-parallelizing, source-to-source and auto-tuning compilers are active research areas. In this work we present an approach that can supply these kinds of compilers with additional information useful to guide the selection of proper optimization techniques. The approach tries to recognize a known algorithmic kernel for which an optimization technique is proven to be beneficial, even though its implementation differs from the original model of the kernel. To that end, our approach uses a graph-based representation for the kernels to perform the analysis.
Download:
BibTeX

Copyright © by ICE
rodriguezblanco14.pdf
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.