Implementing an embedded GPU language by combining translation and generation
(2006) 2006 ACM Symposium on Applied Computing 2. p.1610-1614- Abstract
- Dynamic languages typically allow programs to be written at a very high level of abstraction. But their dynamic nature makes it very hard to compile such languages, meaning that a price has to be paid in terms of performance. However under certain restricted conditions compilation is possible. In this paper we describe how a domain specific language for image processing in Python can be compiled for execution on high speed graphics processing units. Previous work on similar problems have used either translative or generative compilation methods, each of which has its limitations. We propose a strategy which combine these two methods thereby achieving the benefits of both. Copyright 2006 ACM.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/617278
- author
- Lejdfors, Calle LU and Ohlsson, Lennart LU
- organization
- publishing date
- 2006
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Graphics processing units (GPU), Compilation, Dynamic languages, Generative techniques
- host publication
- Proceedings of the ACM Symposium on Applied Computing
- volume
- 2
- pages
- 1610 - 1614
- publisher
- Association for Computing Machinery (ACM)
- conference name
- 2006 ACM Symposium on Applied Computing
- conference location
- Dijon, France
- conference dates
- 2006-04-23 - 2006-04-27
- external identifiers
-
- scopus:33751050638
- ISBN
- 1595931082
- DOI
- 10.1145/1141277.1141654
- language
- English
- LU publication?
- yes
- id
- aa1129c9-7127-40a5-b19c-2a540b6d46ef (old id 617278)
- date added to LUP
- 2016-04-04 11:51:24
- date last changed
- 2022-01-29 22:31:09
@inproceedings{aa1129c9-7127-40a5-b19c-2a540b6d46ef, abstract = {{Dynamic languages typically allow programs to be written at a very high level of abstraction. But their dynamic nature makes it very hard to compile such languages, meaning that a price has to be paid in terms of performance. However under certain restricted conditions compilation is possible. In this paper we describe how a domain specific language for image processing in Python can be compiled for execution on high speed graphics processing units. Previous work on similar problems have used either translative or generative compilation methods, each of which has its limitations. We propose a strategy which combine these two methods thereby achieving the benefits of both. Copyright 2006 ACM.}}, author = {{Lejdfors, Calle and Ohlsson, Lennart}}, booktitle = {{Proceedings of the ACM Symposium on Applied Computing}}, isbn = {{1595931082}}, keywords = {{Graphics processing units (GPU); Compilation; Dynamic languages; Generative techniques}}, language = {{eng}}, pages = {{1610--1614}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{Implementing an embedded GPU language by combining translation and generation}}, url = {{http://dx.doi.org/10.1145/1141277.1141654}}, doi = {{10.1145/1141277.1141654}}, volume = {{2}}, year = {{2006}}, }