Factor-join: A unique approach to compiling array languages for parallel machines

Chamberlain, Bradford L.; Choi, Sung‐Eun; Lewis, E. Christopher; Lin, Calvin; Snyder, Lawrence; Weathersby, Derrick

doi:10.1007/bfb0017271

Cited by 12 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many benefits to performing analyses and transformations at this array language level [42,12]. Some optimizations, such as message vectorization, become trivial [19], and others, such as array contraction, become more effective [31].…”

Section: Compilation Benefitsmentioning

confidence: 99%

“…Some optimizations, such as message vectorization, become trivial [19], and others, such as array contraction, become more effective [31]. Another advantage is the easy identification of communication operations, which facilitates the Factor-Join compilation strategy [12]. This strategy normalizes a program by decomposing it into factors, where each factor represents a class of operations that share a common communication pattern.…”

Section: Compilation Benefitsmentioning

confidence: 99%

See 1 more Smart Citation

ZPL: a machine independent programming language for parallel computers

Chamberlain

Choi

Lewis

et al. 2000

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

The goal of producing architecture-independent parallel programs is complicated by the competing need for high performance. The ZPL programming language achieves both goals by building upon an abstract parallel machine and by providing programming constructs that allow the programmer to "see" this underlying machine. This paper describes ZPL and provides a comprehensive evaluation of the language with respect to its goals of performance, portability, and programming convenience. In particular, we describe ZPL's machine-independent performance model, describe the programming benefits of ZPL's region-based constructs, summarize the compilation benefits of the language's high-level semantics, and summarize empirical evidence that ZPL has achieved both high performance and portability on diverse machines such as the IBM SP-2, Cray T3E, and SGI Power Challenge.

show abstract

Section: Compilation Benefitsmentioning

confidence: 99%

Section: Compilation Benefitsmentioning

confidence: 99%

ZPL: a machine independent programming language for parallel computers

Chamberlain

Choi

Lewis

et al. 2000

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

show abstract

“…ZPL is a highlevel machine-independent parallel programming language that has been ported to a wide variety of platforms. 2 Our decision to use it in the case study was arbitrary but logical, because we had access to the language designers and an actual implementation. The techniques described here apply equally well to other data-parallel languages, and we designed the debugger implementation so that adding support for additional languages is a straightforward process.…”

Section: Relative Debugging For Data-parallel Programs: a Zpl Case Studymentioning

confidence: 99%

“…Parallelism is derived from the Relative debugging is a high-level technique that lets us compare data in a reference program to that of a suspect program. 1,2 Often, programs derived from a reference program, perhaps through porting or some other form of an evolutionary software process, suffer from introduced errors. Relative debugging provides a powerful technique for locating porting errors quickly.…”

Section: Zplmentioning

confidence: 99%

Relative debugging for data-parallel programs: a ZPL case study

Watson

Abramson

2000

IEEE Concurrency

View full text Add to dashboard Cite

“…All compilers (ZPL and HPF) recognize this pattern well and employ optimizations such as message vectorization and storage preallocation for the nonlocal data [3,8,9,12]. Therefore, although the benchmark is rather complex, the initial indication is that both HPF and ZPL should be able to produce efficient parallel programs.…”

Section: Mgmentioning

confidence: 99%

Portable performance of data parallel languages

Ngo

Snyder

Chamberlain

1997

Proceedings of the 1997 ACM/IEEE Conference on Supercomputing (CDROM) - Supercomputing '97

Self Cite

View full text Add to dashboard Cite

A portable program executes on different platforms and yields consistent performance. With the focus on portability, this paper presents an in-depth study of the performance of three NAS benchmarks (EP, MG, FT) compiled with three commercial HPF compilers (APR, PGI, IBM) on the IBM SP2. Each benchmark is evaluated in two versions: using DO loops and using F90 constructs and/or HPF's Forall statement. Base-line comparison is provided by versions of the benchmarks written in Fortran/MPI and ZPL, a data parallel language developed at the University of Washington.While some F90/Forall programs achieve scalable performance with some compilers, the results indicate a considerable portability problem in HPF programs. Two sources for the problem are identified. First, Fortran's semantics require extensive analysis and optimization to arrive at a parallel program; therefore relying on the compiler's capability alone leads to unpredictable performance. Second, the wide differences in the parallelization strategies used by each compiler may require an HPF program to be customized for the particular compiler. While improving compiler optimizations may help to reduce some performance variations, the results suggest that Permission to make digital/hard copy of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage, the copyright notice, the title of the publication and its date appear, and notice is given that copying is by permission of ACM, Inc. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.(c) 1997 ACM 0-89791-985-8/97/0011 $3.50 the foremost criteria for portability is a concise performance model that the compiler must adhere to and that the users can rely on.

show abstract

Factor-join: A unique approach to compiling array languages for parallel machines

Cited by 12 publications

References 15 publications

ZPL: a machine independent programming language for parallel computers

ZPL: a machine independent programming language for parallel computers

Relative debugging for data-parallel programs: a ZPL case study

Portable performance of data parallel languages

Contact Info

Product

Resources

About