Devito: Towards a generic finite difference DSL using symbolic python

TitleDevito: {Towards} a generic finite difference {DSL} using symbolic python
Publication TypeConference
Year of Publication2016
AuthorsMichael Lange, Navjot Kukreja, Mathias Louboutin, Fabio Luporini, Felippe Vieira Zacarias, Vincenzo Pandolfo, Paulius Velesko, Paulius Kazakas, Gerard Gorman
Conference Name6th Workshop on Python for High-Performance and Scientific Computing
Page67-75
Month11
Keywordsacoustic, finite differences, HPC, inversion, Modelling, python, software optimization
Abstract

Domain specific languages (DSL) have been used in a variety of fields to express complex scientific problems in a concise manner and provide automated performance optimization for a range of computational architectures. As such DSLs provide a powerful mechanism to speed up scientific Python computation that goes beyond traditional vectorization and pre-compilation approaches, while allowing domain scientists to build applications within the comforts of the Python software ecosystem. In this paper we present Devito, a new finite difference DSL that provides optimized stencil computation from high-level problem specifications based on symbolic Python expressions. We demonstrate Devito's symbolic API and performance advantages over traditional Python acceleration methods before highlighting its use in the scientific context of seismic inversion problems.

Notes

(PyHPC, Utah)

URLhttps://www.slim.eos.ubc.ca/Publications/Public/Conferences/PyHPC/2016/lange2016dtg/lange2016dtg.pdf
DOI10.1109/PyHPC.2016.9
URL1

https://www.slim.eos.ubc.ca/Publications/Public/Conferences/PyHPC/2016/l...

Citation Keylange2016dtg