Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Static Worksharing Strategies for Heterogeneous Computers with Unrecoverable Failures

Abstract : One has a large workload that is "divisible" (its constituent work's granularity can be adjusted arbitrarily) and one has access to p remote computers that can assist in computing the workload. How can one best utilize the computers? Two features complicate this question. First, the remote computers may differ from one another in speed. Second, each remote computer is subject to interruptions of known likelihood that kill all work in progress on it. One wishes to orchestrate sharing the workload with the remote computers in a way that maximizes the expected amount of work completed. We deal with three distinct problem instances. The simplest problem ignores communication costs, but considers a heterogeneous set of resources that may differ in speed. The other two problems account for communication costs, first with identical remote computers, and then with computers that may differ in speed. We provide exact expressions for the optimal work expectation for all three problems. For the first two problems we provide explicit, closed-form expressions; for the last (and most general) problem, we provide a recurrence for computing this optimal value.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Anne Benoit Connect in order to contact the contributor
Submitted on : Wednesday, July 15, 2009 - 4:55:05 PM
Last modification on : Thursday, September 29, 2022 - 2:58:07 PM
Long-term archiving on: : Monday, October 15, 2012 - 3:21:13 PM


Files produced by the author(s)


  • HAL Id : ensl-00404206, version 1



Anne Benoit, Yves Robert, Arnold Rosenberg, Frédéric Vivien. Static Worksharing Strategies for Heterogeneous Computers with Unrecoverable Failures. 2009. ⟨ensl-00404206⟩



Record views


Files downloads