Presentation is loading. Please wait.

Presentation is loading. Please wait.

MSE Presentation 3 By Lakshmikanth Ganti Under the Guidance of Dr. Virgil Wallentine – Major Professor Dr. Paul Smith – Committee Member Dr. Mitch Neilsen.

Similar presentations


Presentation on theme: "MSE Presentation 3 By Lakshmikanth Ganti Under the Guidance of Dr. Virgil Wallentine – Major Professor Dr. Paul Smith – Committee Member Dr. Mitch Neilsen."— Presentation transcript:

1 MSE Presentation 3 By Lakshmikanth Ganti Under the Guidance of Dr. Virgil Wallentine – Major Professor Dr. Paul Smith – Committee Member Dr. Mitch Neilsen – Committee Member

2 Introduction Overview Revised Artifacts Component Design Assessment Evaluation Project Evaluation User Manual Conclusion

3 Overview Goals: To develop a parallel program for the simulation of a group of molecules using Molecular Dynamics Simulation. To implement various parallel algorithms and compare their performance. To produce good documentation of the design and the overall system.

4 Revised Artifacts Architecture Design Revised with design descriptions for each of the parallel programming paradigms used.

5 Revised Artifacts Object Model

6 Component Design Classes Atom Barrier ObjBuf EnergyWriter ParThread MdPar MdConstants

7 Component Design Classes LineReader IO_Utils Semaphore BinarySemaphore CountingSemaphore

8 Assessment Evaluation Feature Testing Read Data from files Read Program Arguments Format Values for output

9 Assessment Evaluation Functional Testing Program executed with different number of threads. Velocities read from a file each time instead of calculating using Random Gaussian Distribution.

10 Assessment Evaluation Performance Evaluation Initial Design 3-D grid shaped pattern of thread creation Message passing by Bounded Buffers Number of threads is 512; Each thread is assigned one partition No Speedup achieved

11 Assessment Evaluation Performance Evaluation Design I 3-D grid shaped pattern of thread creation Message passing by bounded buffers Number of threads can 2x2x2 or 4x4x4 3-D array of partitions are assigned to each thread

12 Assessment Evaluation Performance Evaluation Design I, Fine Grained Number of ThreadsTime TakenSpeed-upEfficiency 1179625-- 81743931.0325.75 642164150.8320.75

13 Assessment Evaluation Performance Evaluation Design I, Coarse Grained Number of ThreadsTime TakenSpeed-upEfficiency 11726549-- 816762611.0325.75 6421055470.8220.5

14 Assessment Evaluation Performance Evaluation Design I

15 Performance Evaluation Design II Vertical Pipeline shaped pattern of thread creation Message Passing through Bounded Buffers Layers of partitions assigned to each thread rather than a 3-D array of partitions Number of threads created can be 1, 2, 4 or 8. Assessment Evaluation

16 Performance Evaluation Design II, Fine Grained Number of ThreadsTime TakenSpeed-upEfficiency 1170062-- 21589361.0726.75 41047961.6240.5 81269111.3433.5

17 Assessment Evaluation Performance Evaluation Design II, Coarse Grained Number of ThreadsTime TakenSpeed-upEfficiency 11699526-- 215591981.0927.25 49823841.7343.25 811968491.4235.5

18 Assessment Evaluation Performance Evaluation Design II

19 Performance Evaluation Final Design Vertical Pipeline shaped pattern of thread creation Synchronization by Barrier. No message passing Layers of partitions assigned to each thread rather than a 3-D array of partitions Number of threads created can be 1, 2, 4 or 8. Assessment Evaluation

20 Performance Evaluation Final Design, Fine Grained Number of ThreadsTime TakenSpeed-upEfficiency 1162653-- 21378411.1829.5 4628002.5964.75 8669352.4360.75

21 Assessment Evaluation Performance Evaluation Final Design, Coarse Grained Number of ThreadsTime TakenSpeed-upEfficiency 11684963-- 213061721.2932.25 45912152.8571.25 86406702.6365.75

22 Assessment Evaluation Performance Evaluation Final Design

23 Project Evaluation Problems encountered JPF Debugging Parallel Programs Limited Processing power of available systems

24 Project Evaluation Accuracy of Estimates Estimated duration of the project ~ 8 Months Actual duration of the project ~ 7 months Estimated LOCActual LOC Sequential1435504 Parallel15451271

25 Project Evaluation Lessons Learnt Methodology Reviews

26 User Manual Data Formats Program usage User Commands System Configuration

27 Conclusion Various parallel algorithms based on 1) Synchronization mechanism, 2) the pattern of thread creation and 3) Granularity, are implemented The above implementations are compared for speedup and efficiencies Documentation of the design and the overall system is produced.

28 Questions/Comments


Download ppt "MSE Presentation 3 By Lakshmikanth Ganti Under the Guidance of Dr. Virgil Wallentine – Major Professor Dr. Paul Smith – Committee Member Dr. Mitch Neilsen."

Similar presentations


Ads by Google