Unimodular Loop Transformations with Source-to-Source Translation for GPUs

2013 ◽  
pp. 186-195
Author(s):  
Pasquale Cantiello ◽  
Beniamino Di Martino ◽  
Francesco Piccolo
Keyword(s):  
Loop Transformations

A Unified Framework for Systematic Loop Transformations

1990 ◽  
Author(s):  
Lee-Chung Lu ◽  
Marina Chen
Keyword(s):  
Unified Framework ◽  
Loop Transformations

Performance and area modeling of complete FPGA designs in the presence of loop transformations

2004 ◽  
Vol 53 (11) ◽  
pp. 1420-1435 ◽  
Author(s):  
Joonseok Park ◽  
P.C. Diniz ◽  
K.R. Shesha Shayee
Keyword(s):  
Loop Transformations

Automatic loop transformations and parallelization for Java

2000 ◽  
Author(s):  
Pedro V. Artigas ◽  
Manish Gupta ◽  
Samuel P. Midkiff ◽  
José E. Moreira
Keyword(s):  
Loop Transformations

CDA Loop Transformations

1996 ◽  
pp. 29-42 ◽  
Author(s):  
Dattatraya Kulkarni ◽  
Michael Stumm
Keyword(s):  
Loop Transformations

Loop transformations leveraging hardware prefetching

2018 ◽  
Author(s):  
Savvas Sioutas ◽  
Sander Stuijk ◽  
Henk Corporaal ◽  
Twan Basten ◽  
Lou Somers
Keyword(s):  
Loop Transformations ◽  
Hardware Prefetching

AUTOMATIC LOOP TRANSFORMATIONS AND PARALLELIZATION FOR JAVA

2000 ◽  
Vol 10 (02n03) ◽  
pp. 153-164 ◽  
Author(s):  
PEDRO V. ARTIGAS ◽  
MANISH GUPTA ◽  
SAMUEL P. MIKIFF ◽  
JOSÉ E. MOREIRA
Keyword(s):  
State Of The Art ◽  
Automatic Parallelization ◽  
High Order ◽  
Performance Levels ◽  
Loop Transformations ◽  
Current State ◽  
Fortran Code

This paper describes a prototype Java compiler that achieves performance levels approaching those of current state-of-the-art Fortran compilers on numerical codes. We present a new transformation called alias versioning that takes advantage of the simplicity of pointers in Java. This transformation, combined with other techniques that we have developed, enables the compiler to perform high order loop transformations and parallelization completely automatically. We believe that our compiler is the first to have such capabilities of optimizing numerical Java codes. By exploiting synergies between our compiler and the Array package for Java, we achieve between 80 and 100% of the performance of highly optimized Fortran code in a variety of benchmarks. Furthermore, automatic parallelization achieves speedups of up to 3.8 on four processors. Our compiler technology makes Java a serious contender for implementing numerical applications.

UNIMODULARITY AND THE PARALLELIZATION OF LOOPS

1992 ◽  
Vol 02 (02n03) ◽  
pp. 273-281 ◽  
Author(s):  
MICHAEL BARNETT ◽  
CHRISTIAN LENGAUER
Keyword(s):  
Algebraic Theory ◽  
Loop Transformations ◽  
Pros And Cons

The parallelization of loops can be made formal by basing it on an algebraic theory of loop transformations. In this theory, the concept of unimodularity arises. We discuss the pros and cons of insisting on unimodularity.

Sign in / Sign up

Export Citation Format

Share Document