Transparent Distributed Cross-State Synchronization in Optimistic Parallel Discrete Event Simulation

Matteo Principe (), Alessandro Pellegrini (), Francesco Quaglia () and Bruno Ciciani ()
Additional contact information
Matteo Principe: Department of Computer, Control and Management Engineering Antonio Ruberti (DIAG), University of Rome La Sapienza, Rome, Italy
Alessandro Pellegrini: Department of Computer, Control and Management Engineering Antonio Ruberti (DIAG), University of Rome La Sapienza, Rome, Italy
Francesco Quaglia: Department DICII, University Tor Vergata, Rome, Italy
Bruno Ciciani: Department of Computer, Control and Management Engineering Antonio Ruberti (DIAG), University of Rome La Sapienza, Rome, Italy

No 2017-12, DIAG Technical Reports from Department of Computer, Control and Management Engineering, Universita' degli Studi di Roma "La Sapienza"

Abstract: In this report we tackle transparent deploy and seamless execution of sequentially-coded Parallel Discrete Event Simulation (PDES) models on distributed computing architectures. We present an innovative distributed synchronization protocol which allows, in conjunction with ad-hoc Operating System memory management facilities, to access the simulation state of any concurrent Logical Process (LP) running on any node of the distributed computing environment, as if it were locally hosted by a unique node - more specifically, by a unique address space. By relying on our facilities, the simulation model developer is not required to implement neither explicit message passing, nor to rely on annotations or specific programming constructs. He can simply code the accesses to the LPs' states in place (e.g. via pointers), which significantly simplifies the software development process. The burden of synchronization and correct handling of these accesses is demanded from our user-space and kernel-space runtime environment. Our proposal targets Linux on x86 64 systems and has been integrated within the ROOT-Sim open-source optimistic simulation platform, although its design principles, and most parts of the developed software, are of general relevance.

Keywords: Distributed Simulation; High-Performance Computing; PDES; Programming Models (search for similar items in EconPapers)
Date: 2017
New Economics Papers: this item is included in nep-cmp
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://wwwold.dis.uniroma1.it/~bibdis/RePEc/aeg/report/2017-12.pdf First version, 2017 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 500 Can't connect to wwwold.dis.uniroma1.it:80 (No such host is known. )

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aeg:report:2017-12

Access Statistics for this paper

More papers in DIAG Technical Reports from Department of Computer, Control and Management Engineering, Universita' degli Studi di Roma "La Sapienza" Contact information at EDIRC.
Bibliographic data for series maintained by Antonietta Angelica Zucconi ( this e-mail address is bad, please contact ).