article Free Access Share on Removal of redundant dependences in DOACROSS loops with constant dependences Authors: V. P. Krothapalli View Profile , P. Sadayappan View Profile Authors Info & Claims ACM SIGPLAN NoticesVolume 26Issue 7July 1991 pp 51–60https://doi.org/10.1145/109626.109632Online:01 April 1991Publication History 12citation195DownloadsMetricsTotal Citations12Total Downloads195Last 12 Months10Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

An efficient algorithm to remove redundant dependences in simple loops with constant dependences is presented. Dependences constrain the parallel execution of programs and are typically enforced by synchronization instructions. The synchronization instructions represent a significant part of the overhead in the parallel execution of a program. Some program dependences are redundant because they are covered by other dependences. It is shown that unlike with single loops, in the case of nested loops, a particular dependence may be redundant at some iterations but not redundant at others, so that the redundancy of a dependence may not be uniform over the entire iteration space. A sufficient condition for the uniformity of redundancy in a doubly nested loop is developed.>

This paper proposes an approach to minimally constrained synchronization for the parallel execution of imperative programs in a shared-memory environment. Anti-dependencies and output-dependencies arising from array references within loops are completely removed, using run-time analysis if necessary. A parallel reference-pattern generation scheme based on one proposed in [13] is used in conjunction with dynamic allocation and binding of storage, to completely remove non-intrinsic data dependencies during execution.