Using Coarrays to Parallelize Legacy Fortran Applications: Strategy and Case Study
Abstract
This paper summarizes a strategy for parallelizing a legacy Fortran 77 program using the object-oriented (OO) and coarray features that entered Fortran in the 2003 and 2008 standards, respectively. OO programming (OOP) facilitates the construction of an extensible suite of model-verification and performance tests that drive the development. Coarray parallel programming facilitates a rapid evolution from a serial application to a parallel application capable of running on multicore processors and many-core accelerators in shared and distributed memory. We delineate 17 code modernization steps used to refactor and parallelize the program and study the resulting performance. Our initial studies were done using the Intel Fortran compiler on a 32-core shared memory server. Scaling behavior was very poor, and profile analysis using TAU showed that the bottleneck in the performance was due to our implementation of a collective, sequential summation procedure. We were able to improve the scalability and achieve nearly linear speedup by replacing the sequential summation with a parallel, binary tree algorithm. We also tested the Cray compiler, which provides its own collective summation procedure. Intel provides no collective reductions. With Cray, the program shows linear speedup even in distributed-memory execution. We anticipate similar results with other compilers once theymore »
- Authors:
-
- EXA High Performance Computing, 1087 Nicosia, Cyprus
- Stanford University, Stanford, CA 94305, USA
- Sandia National Laboratories, Livermore, CA 94550, USA
- University of Oregon, Eugene, OR 97403, USA
- Computational Sciences Laboratory (UCY-CompSci), University of Cyprus, 1678 Nicosia, Cyprus
- Publication Date:
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1197693
- Grant/Contract Number:
- AC02-05CH11231; AC04-94-AL85000
- Resource Type:
- Published Article
- Journal Name:
- Scientific Programming
- Additional Journal Information:
- Journal Name: Scientific Programming Journal Volume: 2015; Journal ID: ISSN 1058-9244
- Publisher:
- Hindawi Publishing Corporation
- Country of Publication:
- Egypt
- Language:
- English
Citation Formats
Radhakrishnan, Hari, Rouson, Damian W. I., Morris, Karla, Shende, Sameer, and Kassinos, Stavros C.. Using Coarrays to Parallelize Legacy Fortran Applications: Strategy and Case Study. Egypt: N. p., 2015.
Web. doi:10.1155/2015/904983.
Radhakrishnan, Hari, Rouson, Damian W. I., Morris, Karla, Shende, Sameer, & Kassinos, Stavros C.. Using Coarrays to Parallelize Legacy Fortran Applications: Strategy and Case Study. Egypt. https://doi.org/10.1155/2015/904983
Radhakrishnan, Hari, Rouson, Damian W. I., Morris, Karla, Shende, Sameer, and Kassinos, Stavros C.. Thu .
"Using Coarrays to Parallelize Legacy Fortran Applications: Strategy and Case Study". Egypt. https://doi.org/10.1155/2015/904983.
@article{osti_1197693,
title = {Using Coarrays to Parallelize Legacy Fortran Applications: Strategy and Case Study},
author = {Radhakrishnan, Hari and Rouson, Damian W. I. and Morris, Karla and Shende, Sameer and Kassinos, Stavros C.},
abstractNote = {This paper summarizes a strategy for parallelizing a legacy Fortran 77 program using the object-oriented (OO) and coarray features that entered Fortran in the 2003 and 2008 standards, respectively. OO programming (OOP) facilitates the construction of an extensible suite of model-verification and performance tests that drive the development. Coarray parallel programming facilitates a rapid evolution from a serial application to a parallel application capable of running on multicore processors and many-core accelerators in shared and distributed memory. We delineate 17 code modernization steps used to refactor and parallelize the program and study the resulting performance. Our initial studies were done using the Intel Fortran compiler on a 32-core shared memory server. Scaling behavior was very poor, and profile analysis using TAU showed that the bottleneck in the performance was due to our implementation of a collective, sequential summation procedure. We were able to improve the scalability and achieve nearly linear speedup by replacing the sequential summation with a parallel, binary tree algorithm. We also tested the Cray compiler, which provides its own collective summation procedure. Intel provides no collective reductions. With Cray, the program shows linear speedup even in distributed-memory execution. We anticipate similar results with other compilers once they support the new collective procedures proposed for Fortran 2015.},
doi = {10.1155/2015/904983},
journal = {Scientific Programming},
number = ,
volume = 2015,
place = {Egypt},
year = {Thu Jan 01 00:00:00 EST 2015},
month = {Thu Jan 01 00:00:00 EST 2015}
}
https://doi.org/10.1155/2015/904983
Web of Science