Latest revision as of 18:13, 3 February 2021

Abstract

In the last years, FPGAs became capable of performing complex floating-point based calculations. For many applications, highly parallel calculation units can be implemented which deliver a better performance than general-purpose processors. This paper focuses on applications where the calculations can be done in a pipeline, as it is often the case for simulations. A framework for rapid design of such calculation pipelines is described. The central part is a Perl based code generator, which automatically assembles floating-point operators into synthesizable hardware description code where the generator is directed by a pipeline description file. The framework is supplemented by various floating-point operators and support modules, which allow generating ready-to-use pipelines. The code generator dramatically reduces development time and produces high-quality results. The performance of the framework is demonstrated by the implementation of pipelines for gravitational forces and hydrodynamics.

Original document

The different versions of the original document can be found in:

• http://www.cecs.uci.edu/~papers/ipdps06/pdfs/039-RAW-paper-1.pdf

• http://xplorestaging.ieee.org/ielx5/10917/34366/01639439.pdf?arnumber=1639439,

http://dx.doi.org/10.1109/ipdps.2006.1639439

• https://dblp.uni-trier.de/db/conf/ipps/ipdps2006.html#LienhartKM06,

http://www.cecs.uci.edu/~papers/ipdps06/pdfs/039-RAW-paper-1.pdf,

http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.ieee-000001639439,

https://dl.acm.org/citation.cfm?id=1899135,

https://academic.microsoft.com/#/detail/2110398560