1 / 10

Parallel Simulation System

Parallel Simulation System. Victor V. Okol’nishnikov E-mail: okoln@kti.nsc.ru Institute of Computational Mathematics and Mathematical Geophysics of SB RAS Russia, Novosibirsk. Simulation System. Source language. C++ based process-oriented discrete event simulation language

kyria
Download Presentation

Parallel Simulation System

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Parallel Simulation System Victor V. Okol’nishnikov E-mail: okoln@kti.nsc.ru Institute of Computational Mathematics and Mathematical Geophysics of SB RAS Russia, Novosibirsk

  2. Simulation System. Source language • C++ based process-oriented discrete event simulation language • Interaction between processes through message passing • Possibility of construction of hierarchical models • Possibility of dynamically exchanging structure of the model • Possibility of parallel execution

  3. Simulation System. Branches • The sequential branch is realized for Windows 95/98/NT • The distributed branch is realized for a local network of personal computer under the control of the real time operating system QNX 4.25 • The parallel branch is realized for the supercomputer RM600-E30 that is an SMP system under Reliant UNIX.

  4. Goals of developing of the parallel simulation system • Portability • High-performance

  5. Portability of simulation system • Realization of model processes with help operating system standard technique - Threads • Interaction of parallel model processeswith help standard package MPI (Message Passing Interface)

  6. Run-time system consists of • Communication subsystem • Simulation subsystem

  7. Communication subsystem • Message passing between processes • Synchronization of execution of parallel model parts in model time.

  8. Model1 Model2 Processes Processes Inputs Inputs Outputs Outputs Local time Local time Parallel execution of model parts Communication subsystems

  9. Methods of synchronization • Conservative • Optimistic

  10. Future directions of research • Realization parallel simulation system for supercomputer MBC-1000/M • Development library of synchronization methods both conservative and optimistic • Large-scale simulation of large systems

More Related