Programming support for reconfigurable custom vector architectures

Mehmet Ali Arslan, Krzysztof Kuchcinski, Flavius Gruian, Yangxurui Liu

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

1 Citation (SciVal)

Abstract

High performance requirements increased the popularity of unconventional architectures. While providing better performance, such architectures are generally harder to program and generate code for. In this paper, we present our approach to ease programmability and code generation for such architectures. We present a domain specific language (DSL) for the programming part, and a constraint programming approach to scheduling with memory allocation. Our experiments on implementing a kernel extracted from a DSP appli- cation on an example reconfigurable custom architecture shows that it is possible to achieve performance close to hand-written machine code that is scheduled without memory allocation.
Original languageEnglish
Title of host publicationProc. PPoPP, Principles and Practice of Parallel Programming
EditorsPavan Balaji, Minyi Guo, Zhiyi Huang
PublisherAssociation for Computing Machinery (ACM)
Pages49-57
Number of pages9
ISBN (Print)978-1-4503-3404-4
DOIs
Publication statusPublished - 2015
EventPMAM 2015: The 6th International Workshop on Programming Models and Applications for Multicores and Manycores in conjunction with PPoPP 2015, 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel - San Francisco, CA, United States
Duration: 2015 Feb 72015 Feb 11

Conference

ConferencePMAM 2015: The 6th International Workshop on Programming Models and Applications for Multicores and Manycores in conjunction with PPoPP 2015, 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel
Country/TerritoryUnited States
CitySan Francisco, CA
Period2015/02/072015/02/11

Subject classification (UKÄ)

  • Computer Science
  • Electrical Engineering, Electronic Engineering, Information Engineering

Fingerprint

Dive into the research topics of 'Programming support for reconfigurable custom vector architectures'. Together they form a unique fingerprint.

Cite this