Proceedings. 1998 International Conference on Parallel Processing (Cat. No.98EX205)
DOI: 10.1109/icpp.1998.708460
|View full text |Cite
|
Sign up to set email alerts
|

On-line configuration of a time warp parallel discrete event simulator

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
4
0

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(4 citation statements)
references
References 24 publications
0
4
0
Order By: Relevance
“…There are two policies on when to send anti-messages in order to nullify erroneously sent messages: aggressive (immediately when an out-of-order message is received) and lazy (delayed until necessary) cancellations. TWOS [15] employs a lazy policy as default, and WARPED [20] allows selecting either policy adaptively to achieve the optimal performance. Global Virtual Time (GVT) [13] maintains an event history so that earlier events (fossils) can be discarded.…”
Section: Related Workmentioning
confidence: 99%
“…There are two policies on when to send anti-messages in order to nullify erroneously sent messages: aggressive (immediately when an out-of-order message is received) and lazy (delayed until necessary) cancellations. TWOS [15] employs a lazy policy as default, and WARPED [20] allows selecting either policy adaptively to achieve the optimal performance. Global Virtual Time (GVT) [13] maintains an event history so that earlier events (fossils) can be discarded.…”
Section: Related Workmentioning
confidence: 99%
“…Alternatively, the optimistic approach allows execution of an event at a process (i.e., gate or ¯ip¯op) without guaranteeing that no other event with a smaller time stamp may later arrive at the same process [8,13]. If the chronological order is violated, the simulation must be rolled back in time to a safe state.…”
Section: Introductionmentioning
confidence: 99%
“…If the chronological order is violated, the simulation must be rolled back in time to a safe state. Therefore, an optimistic simulation algorithm requires a strategy for backing up the simulation [15]. This results in additional memory requirements and may be unacceptable for large VLSI simulation tasks.…”
Section: Introductionmentioning
confidence: 99%