Array resizing for scientific code debugging, maintenance and reuse

Ancourt, Corinne; Nguyen, Thi Viet Nga

doi:10.1145/379605.379656

Cited by 4 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PIPS has proved over the years to be a fertile ground for the polyhedral model [21], data transformations [13], communication synthesis [4,7], compilation for distributed memory machines [9,23], ILP [37], code maintenance [29,6], program verification [25], scratchpad management [8], offload compilers [14,1,10], and task parallelism [18,33].…”

Section: Discussionmentioning

confidence: 99%

Author retrospective for semantical interprocedural parallelization

Irigoin

Jouvelot

Triolet³

2014

25th Anniversary International Conference on Supercomputing Anniversary Volume -

View full text Add to dashboard Cite

The PIPS project was started in 1988 to investigate the automatic detection of medium-and large-grain parallelism in scientific programs thanks to summarization techniques based on convex array regions. By 1992 the PIPS system had reached its original goals, but it has morphed into a comprehensive, open-source platform still in use today. What were the key scientific and engineering decisions that made this possible in spite of some inevitable shortcomings?

show abstract

Section: Discussionmentioning

confidence: 99%

Author retrospective for semantical interprocedural parallelization

Irigoin

Jouvelot

Triolet³

2014

25th Anniversary International Conference on Supercomputing Anniversary Volume -

View full text Add to dashboard Cite

show abstract

“…This optimization is an array resizing transformation [40]. Unlike Fortran, which supports array declaration from any starting point or without any explicit size, arrays in C must always start at 0 and must have a size that is known numerically, or symbolically in C99 standard.…”

Section: Optimizationsmentioning

confidence: 99%

Automatic Code Generation of Distributed Parallel Tasks

Lossing

Ancourt

Irigoin

2016

2016 IEEE Intl Conference on Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Co

Self Cite

View full text Add to dashboard Cite

Abstract-With the advent of clustered systems, more and more parallel computing is required. However a lot of programming skills is needed to write a parallel codes, especially when you want to benefit from the various parallel architectural resources, with heterogeneous units and complex memory organizations. We present in this paper a method that generates automatically, step by step, a task-parallel distributed code from a sequential program. It has been implemented in an existing source-to-source compiler PIPS. Our approach provides two main advantages 1) all the program transformations are simple and applied on source code, thus are visible by the user, 2) a proof of correctness of the parallelization process can be made. This ensures that we end up with a correct distributed-task program for distributed-memory machines. To our knowledge, it is the first tool that automatically generates a distributed code for task parallelization.

show abstract

“…In Ancourt and Nguyen [2001], the problem of calculating the exact size of FORTRAN arrays that have the REAL(1) or REAL(*) declarations is considered. The article discusses a method based on array region analysis to determine the set of array elements referenced during program execution.…”

Section: Alternate Approachesmentioning

confidence: 99%

“…While the article outlines a scheme for the analysis, it isn't clear how effective this would be in an APL or MATLAB setting. The primary motivation for the work was to clean up and tighten the large number of imprecise array declarations in legacy FORTRAN code, declarations that would otherwise hinder program analysis, parallelization, verification, and code readability [Ancourt and Nguyen 2001].…”

Section: Alternate Approachesmentioning

confidence: 99%

An algebraic array shape inference system for MATLAB®

Joisha

Banerjee

2006

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

The problem of inferring array shapes ahead of time in languages that exhibit both implicit and dynamic typing is a critical one because the ramifications of its solution are the better organization of array storage through compaction and reuse, and the generation of high-performance code through specialization by shape. This article addresses the problem in a prototypical implicitly and dynamically typed array language called MATLAB. The approach involves modeling the language's shape semantics using an algebraic system, and applying term rewriting techniques to evaluate expressions under this algebra. Unlike prior efforts at array shape determination, this enables the deduction of valuable shape information even when array extents are compile-time unknowns. Furthermore, unlike some previous methods, our approach doesn't impose monotonicity requirements on an operator's shape semantics. The work also describes an inference methodology and reports measurements from a type inference engine called . In a benchmark suite of 17 programs, the shape inference subsystem in detected the equivalence of over 61% of the symbolic shapes in six programs, and over 57% and 37% of the symbolic shapes in two others. In the remaining nine programs, all array shapes were inferred to be compile-time constants.

show abstract

Array resizing for scientific code debugging, maintenance and reuse

Cited by 4 publications

References 7 publications

Author retrospective for semantical interprocedural parallelization

Author retrospective for semantical interprocedural parallelization

Automatic Code Generation of Distributed Parallel Tasks

An algebraic array shape inference system for MATLAB®

Contact Info

Product

Resources

About