skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: StreamJIT: a commensal compiler for high-performance stream programming

Abstract

There are many domain libraries, but despite the performance benefits of compilation, domain-specific languages are comparatively rare due to the high cost of implementing an optimizing compiler. We propose commensal compilation, a new strategy for compiling embedded domain-specific languages by reusing the massive investment in modern language virtual machine platforms. Commensal compilers use the host language's front-end, use host platform APIs that enable back-end optimizations by the host platform JIT, and use an autotuner for optimization selection. The cost of implementing a commensal compiler is only the cost of implementing the domain-specific optimizations. We demonstrate the concept by implementing a commensal compiler for the stream programming language StreamJIT atop the Java platform. Our compiler achieves performance 2.8 times better than the StreamIt native code (via GCC) compiler with considerably less implementation effort.

Authors:
 [1];  [2];  [2];  [1]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  2. National Univ. of Singapore (Singapore)
Publication Date:
Research Org.:
Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
OSTI Identifier:
1557583
Grant/Contract Number:  
SC0008923
Resource Type:
Accepted Manuscript
Journal Name:
ACM SIGPLAN Notices
Additional Journal Information:
Journal Volume: 49; Journal Issue: 10; Journal ID: ISSN 0362-1340
Publisher:
ACM
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; domain-specific languages; embedded domain-specific languages

Citation Formats

Bosboom, Jeffrey, Rajadurai, Sumanaruban, Wong, Weng -Fai, and Amarasinghe, Saman. StreamJIT: a commensal compiler for high-performance stream programming. United States: N. p., 2014. Web. doi:10.1145/2714064.2660236.
Bosboom, Jeffrey, Rajadurai, Sumanaruban, Wong, Weng -Fai, & Amarasinghe, Saman. StreamJIT: a commensal compiler for high-performance stream programming. United States. doi:10.1145/2714064.2660236.
Bosboom, Jeffrey, Rajadurai, Sumanaruban, Wong, Weng -Fai, and Amarasinghe, Saman. Wed . "StreamJIT: a commensal compiler for high-performance stream programming". United States. doi:10.1145/2714064.2660236. https://www.osti.gov/servlets/purl/1557583.
@article{osti_1557583,
title = {StreamJIT: a commensal compiler for high-performance stream programming},
author = {Bosboom, Jeffrey and Rajadurai, Sumanaruban and Wong, Weng -Fai and Amarasinghe, Saman},
abstractNote = {There are many domain libraries, but despite the performance benefits of compilation, domain-specific languages are comparatively rare due to the high cost of implementing an optimizing compiler. We propose commensal compilation, a new strategy for compiling embedded domain-specific languages by reusing the massive investment in modern language virtual machine platforms. Commensal compilers use the host language's front-end, use host platform APIs that enable back-end optimizations by the host platform JIT, and use an autotuner for optimization selection. The cost of implementing a commensal compiler is only the cost of implementing the domain-specific optimizations. We demonstrate the concept by implementing a commensal compiler for the stream programming language StreamJIT atop the Java platform. Our compiler achieves performance 2.8 times better than the StreamIt native code (via GCC) compiler with considerably less implementation effort.},
doi = {10.1145/2714064.2660236},
journal = {ACM SIGPLAN Notices},
number = 10,
volume = 49,
place = {United States},
year = {2014},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 5 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Using machine learning to partition streaming programs
journal, September 2013

  • Wang, Zheng; O'boyle, Michael F. P.
  • ACM Transactions on Architecture and Code Optimization, Vol. 10, Issue 3
  • DOI: 10.1145/2512436

Some scheduling techniques and an easily schedulable horizontal architecture for high performance scientific computing
journal, December 1981