Advanced tools and techniques for automatic parallelization

Kremer, Ulrich; Bast, Heinz-J; Gerndt, Michael; Zima, Hans P.

doi:10.1016/0167-8191(88)90057-9

Cited by 19 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic parallelization tools are studied since many years [12,8]. They usually work as meta-compilers [20,2], producing a parallel source code from a sequential source code, or as compilers [6], producing directly an executable.…”

Section: Related Workmentioning

confidence: 99%

Static Loop Parallelization Decision Using Template Metaprogramming

Pereda

Hill

Mazel

et al. 2018

2018 International Conference on High Performance Computing &Amp; Simulation (HPCS)

View full text Add to dashboard Cite

This article proposes to use C++ template metaprogramming techniques to decide at compile-time which parts of a code sequence in a loop can be parallelized. The approach focuses on characterizing the way a variable is accessed in a loop (reading or writing), first to decide how the loop should be split to enable the analysis for parallelization on each part, and then to decide if the iterations inside each loop are independent so that they can be run in parallel. The conditions that enable the parallelization of a loop are first explained to justify the proposed decision algorithm exposed. Then, a C++ library-based solution is presented that uses expression templates to get the relevant information necessary for the parallelization decision of a loop, and metaprograms to decide whether to parallelize the loop and generate a parallel code.

show abstract

Section: Related Workmentioning

confidence: 99%

Static Loop Parallelization Decision Using Template Metaprogramming

Pereda

Hill

Mazel

et al. 2018

2018 International Conference on High Performance Computing &Amp; Simulation (HPCS)

View full text Add to dashboard Cite

show abstract

“…Interactive tools have been around for a long time now [19,23,10,24,16,3,4,131. Most of them are based on menus proposing to the user lists of program transformations such as loop unrolling, loop interchange, etc.…”

Section: Ics 98 Melbourne Australiamentioning

confidence: 99%

A user level program transformation tool

Bodin

Mével

Quiniou

1998

Proceedings of the 12th International Conference on Supercomputing

View full text Add to dashboard Cite

Updating distributed variables in local computations

Gerndt

1990

Concurrency: Pract. Exper.

Self Cite

View full text Add to dashboard Cite

This paper describes special aspects of MlMD parallelization in SUPERB. SUPERB is an interactive SIMDMIMD parallelizing system for the SUPRENUM machine. The main topic of this paper is the updating of distributed variables in parallelized applications. The intended applications perform local computations on a large data domain. KEY WORDS Multiprocessors Analysis of algorithms Program transformations

show abstract

Advanced tools and techniques for automatic parallelization

Cited by 19 publications

References 12 publications

Static Loop Parallelization Decision Using Template Metaprogramming

Static Loop Parallelization Decision Using Template Metaprogramming

A user level program transformation tool

Updating distributed variables in local computations

Contact Info

Product

Resources

About