MaJIC: Compiling MATLAB for speed and responsiveness

George Almási, David A Padua

Research output: Contribution to conferencePaper

Abstract

This paper presents and evaluates techniques to improve the execution performance of MATLAB. Previous efforts concentrated on source to source translation and batch compilation; MaJIC provides an interactive frontend that looks like MATLAB and compiles/optimizes code behind the scenes in real time, employing a combination of just-in-time and speculative ahead-of-time compilation. Performance results show that the proper mixture of these two techniques can yield near-zero response time as well as performance gains previously achieved only by batch compilers.

Original languageEnglish (US)
Pages294-303
Number of pages10
StatePublished - Jan 1 2002
EventProceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02) - Berlin, Germany
Duration: Jun 17 2002Jun 19 2002

Other

OtherProceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02)
CountryGermany
CityBerlin
Period6/17/026/19/02

Fingerprint

MATLAB

ASJC Scopus subject areas

  • Software

Cite this

Almási, G., & Padua, D. A. (2002). MaJIC: Compiling MATLAB for speed and responsiveness. 294-303. Paper presented at Proceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02), Berlin, Germany.

MaJIC : Compiling MATLAB for speed and responsiveness. / Almási, George; Padua, David A.

2002. 294-303 Paper presented at Proceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02), Berlin, Germany.

Research output: Contribution to conferencePaper

Almási, G & Padua, DA 2002, 'MaJIC: Compiling MATLAB for speed and responsiveness', Paper presented at Proceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02), Berlin, Germany, 6/17/02 - 6/19/02 pp. 294-303.
Almási G, Padua DA. MaJIC: Compiling MATLAB for speed and responsiveness. 2002. Paper presented at Proceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02), Berlin, Germany.
Almási, George ; Padua, David A. / MaJIC : Compiling MATLAB for speed and responsiveness. Paper presented at Proceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02), Berlin, Germany.10 p.
@conference{df4d6e7006d24a5b8d7ae50946537ca6,
title = "MaJIC: Compiling MATLAB for speed and responsiveness",
abstract = "This paper presents and evaluates techniques to improve the execution performance of MATLAB. Previous efforts concentrated on source to source translation and batch compilation; MaJIC provides an interactive frontend that looks like MATLAB and compiles/optimizes code behind the scenes in real time, employing a combination of just-in-time and speculative ahead-of-time compilation. Performance results show that the proper mixture of these two techniques can yield near-zero response time as well as performance gains previously achieved only by batch compilers.",
author = "George Alm{\'a}si and Padua, {David A}",
year = "2002",
month = "1",
day = "1",
language = "English (US)",
pages = "294--303",
note = "Proceedings of the ACM SIGPLAN 2002 Conference on Programming Language Design and Implementation (PLDI'02) ; Conference date: 17-06-2002 Through 19-06-2002",

}

TY - CONF

T1 - MaJIC

T2 - Compiling MATLAB for speed and responsiveness

AU - Almási, George

AU - Padua, David A

PY - 2002/1/1

Y1 - 2002/1/1

N2 - This paper presents and evaluates techniques to improve the execution performance of MATLAB. Previous efforts concentrated on source to source translation and batch compilation; MaJIC provides an interactive frontend that looks like MATLAB and compiles/optimizes code behind the scenes in real time, employing a combination of just-in-time and speculative ahead-of-time compilation. Performance results show that the proper mixture of these two techniques can yield near-zero response time as well as performance gains previously achieved only by batch compilers.

AB - This paper presents and evaluates techniques to improve the execution performance of MATLAB. Previous efforts concentrated on source to source translation and batch compilation; MaJIC provides an interactive frontend that looks like MATLAB and compiles/optimizes code behind the scenes in real time, employing a combination of just-in-time and speculative ahead-of-time compilation. Performance results show that the proper mixture of these two techniques can yield near-zero response time as well as performance gains previously achieved only by batch compilers.

UR - http://www.scopus.com/inward/record.url?scp=0036039844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036039844&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0036039844

SP - 294

EP - 303

ER -