1 / 27

Modeling with Parallel DEVS

Modeling with Parallel DEVS. Serialization in DEVS models. Select function Implicit serialization of parallel models E-DEVS: internal transition first, external transition after Inadequate representation of DEVS models with parallel components. x b (5). y b (3).

palos
Download Presentation

Modeling with Parallel DEVS

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. Modeling with Parallel DEVS

  2. Serialization in DEVS models • Select function • Implicit serialization of parallel models • E-DEVS: internal transition first, external transition after • Inadequate representation of DEVS models with parallel components

  3. xb(5) yb(3) s’ = d ext (s,e,xb) (6a) s’ = d conf (s,e,xb) (6b) l (s) (2) s’ = d int (s) (4) s ta(s) (1) Parallel DEVS Atomic Models DEVS = < Xb, S, Yb, dint , dext , dconf , ta, l >

  4. yb(3) l (s) (2) s’ = d int (s) (4) s ta(s) (1) Parallel DEVS Atomic models DEVS = < Xb, S, Yb, dint , dext , dconf , ta, l >

  5. xb(5) s’ = d ext (s,e,xb) (6a) s ta(s) (1) Parallel DEVS Atomic models DEVS = < Xb, S, Yb, dint , dext , dconf , ta, l >

  6. xb(5) s’ = d conf (s,e,xb) (6b) s ta(s) (1) Parallel DEVS Atomic models DEVS = < Xb, S, Yb, dint , dext , dconf , ta, l >

  7. Ottawa-Toronto arrival Ottawa Fallowfield arrival Kingston departure departure passengers passengers passengers Parallel-DEVS Coupled models • Components • Couplings • Internal • External Inputs • External Outputs

  8. Simulation mechanism • Simulation advanced through message exchange • Synchronization messages TypeAction ( @, t ) Output execution ( *, t ) State transition ( done , t ) End of action • Content messages ( y , t ) Output event ( q , t ) External event

  9. Simulator • Drives atomic models • State tN = time of next transition tL = time of last transition message bag • Upon receiving Do • ( @, t ) y =l (s); send ( y, t ) • (q, t) Add q to message bag • ( *, t ) • if t < tN s =dext; tN = ta(s) ; tL = t • if t = tN  bag =  s = dint ; tN = ta(s) ; tL = t • if t = tN  bag   s= dconf ; tN = ta(s) ; tL = t

  10. ( @, 10) ( y, 10 ) ( done, 10 ) ( y, 10) ( y, 10) ( done, 10) ( @, 10) ( @, 10) ( done, 10) y =l (s) y =l (s) Coordinator • Coordinates processor’s activities Coordinator tN = 10 tN = 20 tN = 10

  11. ( *, 10) (q, 10) (done, 15) (q, 10) ( done, 20) (q, 10) ( *, 10) (done, 15) ( *, 10) ( done, 30) (*, 10) s =dint s =dconf s =dext Coordinator Coordinator tN = 10 tN = 10 tN = 20

  12. ( @, 15) Coordinator Coordinator tN = 20 tN = 30 tN = 15

  13. Parallel CD++ • A tool to execute Parallel DEVS and Parallel Cell-DEVS models in parallel/distributed environments • Layered architecture based on Warped Parallel CD++ Warped MPI (Message Passing Interface)

  14. Parallel - DEVS simulation • Independent of the modelling technique • Different simulators can be applied according to the needs. • Examples of existing simulators: • Hierarchical • Flat • Centralized • Distributed • Real-Time

  15. Parallel DEVS simulation Processors: 1 coordinator 16 simulators Cellular model : a coupled model of 16 cell Coord. Simulator Simulator Simulator Simulator • Processors • Simulator: Atomic model • Coordinator: Coupled model • Processor hierarchy= model hierarchy

  16. CD++ Parallel simulator CPU 1 CPU 2 Coord. Coord. Simulator Simulator Simulator Simulator • Model partitioned among available CPUs • Atomic models • Each atomic model assigned to a CPU • Coupled models • Coordinator is placed on each CPU where there is a component

  17. Parallel simulation mechanism (@,10) (done,10) (@,10) (@,10) (@,10) (y,10) (done,10) (y,10) (done,10) (y,10) (done,10) Simulator Simulator Simulator Simulator CPU 1 CPU 2 Slave coord. Master coord.

  18. (*,10) (done, min tN) (*,10) (q,10) (*,10) (q,10) (*,10) (done,tN) (done,tN) (done,tN) simulator simulator simulator simulator Parallel simulation mechanism CPU 1 CPU 2 Slave coord. Master coord.

  19. Extensions to CD++

  20. Extensions (cont.)

  21. Partition Files

  22. RADS (Carleton University) • Alpha network and Gamma network

  23. Simulation Results GPT in queue Generator out done in arrive solved out processor throughput transducer cpuusage • Generator- Processor-Transducer • Multiple instances (12, 48 and 96) • 1 to 12 CPUs (different machines)

  24. Results Generator - Processor - Transducer

  25. Results • Heat diffusion model • 100 x 100 surface • Each cell holds a temperature value • Temperature is update periodically • Partitions • 1, 2, 4 and 8 CPUs • Quantization • Quantum sizes: • 0 ; 0,001 ; 0,01 y 0,1 10000

  26. Results • Heat diffusion - Linux cluster

  27. Results • Heat diffusion - 4 processors SMP

More Related