Proceedings Article10.1145/76263.76329
Event synchronization analysis for debugging parallel programs
Perry A. Emrath,S. Chosh,David Padua +2 more
- 01 Aug 1989
- pp 580-588
77
TL;DR: An algorithm is presented for automatically detecting non-determinacy in parallel programs that utilize event style synchronization instructions, using the Post, Wait, and Clear primitives.
read more
Abstract: One of the major difficulties of explicit parallel programming for a shared memory machine model is detecting the potential for nondeterminacy and identifying its causes. There will often be shared variables in a parallel program, and the tasks comprising the program may need to be synchronized when accessing these variables. This paper discusses this problem and presents a method for automatically detecting non-determinacy in parallel programs that utilize event style synchronization instructions, using the Post, Wait, and Clear primitives. With event style synchronization, especially when there are many references to the same event, the difficulty lies in computing the execution order that is guaranteed given the synchronization instructions and the sequential components of the program. The main result in this paper is an algorithm that computes such an execution order and yields a Task Graph upon which a nondeterminacy detection algorithm can be applied. We have focused on events because they are a frequently used synchronization mechanism in parallel versions of Fortran, including Cray [Cray87], IBM [IBM88], Cedar [GPHL88], and PCF Fortran [PCF88].
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Parallel Supercomputing Today and the Cedar Approach (並列処理ハ-ドウェアと言語特集)
David J. Kuck
- 01 Aug 1988
TL;DR: The Cedar supercomputer as discussed by the authors uses advanced system and applications developed at the University of Illinois during the past 12 years, which should allow the number of processors in Cedar to be doubled annually, providing rapid performance advances in the next decade.
236
The Cilk++ concurrency platform
TL;DR: Cilk++ as mentioned in this paper is a runtime system for multicore processors with a runtime compiler and a racedetection tool, which allows nonlocal variables to be mitigated without lock contention or substantial code restructuring.
Efficient detection of determinacy races in Cilk programs
Mingdong Feng,Charles E. Leiserson +1 more
- 01 Jun 1997
TL;DR: A provably efficient determinacy-race detector for Cilk, an algorithmic multithreaded programming language, that determines at least one location in the program that is subject to a determinacy race and certifies that the program is race free when run on the data set.
•Dissertation
Cilk: efficient multithreaded computing
Keith H. Randall,Charles E. Leiserson +1 more
- 01 Jan 1998
TL;DR: Borders on running time and communication are proved for a Cilk program executed on top of Backer, including all costs associated with Backer itself, which is believed to be the first of its kind in this regard.
137
Detecting data races in Cilk programs that use locks
Guang-Ien Cheng,Mingdong Feng,Charles E. Leiserson,Keith H. Randall,Andrew F. Stark +4 more
- 01 Jun 1998
TL;DR: The Nondeterminator-2’s two algorithms can verify the determinacy of a deadlock-free abelian program running on a given input, and it is proved that any “abelian” Cilk program, one whose critical sections commute, produces a determinate final state if it is deadlock free and if it generates any computation which is datarace free.
References
Parallel Supercomputing Today and the Cedar Approach (並列処理ハ-ドウェアと言語特集)
David J. Kuck
- 01 Aug 1988
TL;DR: The Cedar supercomputer as discussed by the authors uses advanced system and applications developed at the University of Illinois during the past 12 years, which should allow the number of processors in Cedar to be doubled annually, providing rapid performance advances in the next decade.
236
Parallel supercomputing today and the cedar approach
TL;DR: The Cedar supercomputer as mentioned in this paper uses advanced system and applications developed at the University of Illinois during the past 12 years, which should allow the number of processors in Cedar to be doubled annually, providing rapid performance advances in the next decade.
228
Compiler Algorithms for Synchronization
Samuel P. Midkiff,David Padua +1 more
TL;DR: Several loop synchronization techniques to generate synchronization instructions for singly-nested loops are presented and a technique for the elimination of redundant synchronization instructions is presented.
176
On-the-fly detection of access anomalies
D. Schonberg
- 21 Jun 1989
TL;DR: A general on-the-fly algorithm for access anomaly detection is presented, which can be applied to programs with both nested fork-join and synchronization operations and can be greatly reduced by data compression techniques and by discarding information as soon as it becomes obsolete.
135
Static analysis of low-level synchronization
David Callahan,Jaspal Sublok +1 more
- 01 Nov 1988
TL;DR: A new static analysis, suitable for inclusion in PTOOL, that identifies schedule-dependent operations in parallel programs with explicit synchronization, which exploits both control information and data flow information to provide an efficient mechanism for analyzing explicit synchronization.
121