Converting high probability into nearly-constant time—with applications to parallel hashing
STOC '91 Proceedings of the twenty-third annual ACM symposium on Theory of computing
Fast randomized algorithms for distributed edge coloring
PODC '92 Proceedings of the eleventh annual ACM symposium on Principles of distributed computing
A brief survey of systems providing process or object migration facilities
ACM SIGOPS Operating Systems Review
The Tree Model for Hashing: Lower and Upper Bounds
SIAM Journal on Computing
The MOSIX multicomputer operating system for high performance cluster computing
Future Generation Computer Systems - Special issue on HPCN '97
Eliminating migration in multi-processor scheduling
Proceedings of the tenth annual ACM-SIAM symposium on Discrete algorithms
Scheduling to minimize average stretch without migration
SODA '00 Proceedings of the eleventh annual ACM-SIAM symposium on Discrete algorithms
Scheduling with unexpected machine breakdowns
Discrete Applied Mathematics
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
The Power of Migration in Multiprocessor Scheduling of Real-Time Systems
SIAM Journal on Computing
Minimizing the Flow Time Without Migration
SIAM Journal on Computing
Arachne: A Portable Threads System Supporting Migrant Threads on Heterogeneous Network Farms
IEEE Transactions on Parallel and Distributed Systems
An Adaptive, Fault-Tolerant Implementation of BSP for JAVA-Based Volunteer Computing Systems
Proceedings of the 11 IPPS/SPDP'99 Workshops Held in Conjunction with the 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing
STACS '92 Proceedings of the 9th Annual Symposium on Theoretical Aspects of Computer Science
User-Level Checkpointing for LinuxThreads Programs
Proceedings of the FREENIX Track: 2001 USENIX Annual Technical Conference
The Paderborn University BSP (PUB) library
Parallel Computing
Speed is as powerful as clairvoyance [scheduling problems]
FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
Hi-index | 0.01 |
Using idle times of the processors is a well-known approach to run coarse grained parallel algorithms for extremely complex problems. We present on-line algorithms for scheduling the processes of a parallel application that is known off-line on a dynamic network in which the idle times of the processors are dictated by an adversary. We also take communication and synchronization costs into account.Our first contribution consists of a formal model to restrict the adversary in a reasonable way. We then show a constant factor approximation for the off-line scheduling problem. As this problem has to take communication cost into account, it can be seen as a generalization of many NP-hard parallel machine scheduling problems. Finally, we present on-line algorithms for different models with constant or with "nearly constant" competitive ratio.