Presentation is loading. Please wait.

Presentation is loading. Please wait.

LOGO Parallel computing technique for EM modeling makai 天津大学电子信息工程学院 School of Electronic Information Engineering.

Similar presentations


Presentation on theme: "LOGO Parallel computing technique for EM modeling makai 天津大学电子信息工程学院 School of Electronic Information Engineering."— Presentation transcript:

1 LOGO Parallel computing technique for EM modeling makai 天津大学电子信息工程学院 School of Electronic Information Engineering

2 Company name Contents School of Electronic Information Engineering 1 、 background 2 、 Basic theory of parallel computing 3 、 An example 4 、 plan

3 Company name Background School of Electronic Information Engineering  Arificial neural network (ANN) techniques have been recognized as a powerful tool in electromagnetic(EM)-based modeling and design optimization of microwave passive components. ANN can learn EM responses versus geometrical variables through an automated training process, and the trained ANN can be used as accurate and fast models in the design optimization.

4 Company name Background School of Electronic Information Engineering “Efficient design optimization of microwave circuits using parallel computational methods,” European Microwave Conference, Amsterdam, the Netherlands, Nov. 2012. “Parallel automatic model generation technique for microwave modeling,” in IEEE MTT-S Int. Microw. Symp. Dig., Honolulu, Hawaii, June 2007.

5 Company name School of Electronic Information Engineering  Basic theory of parallel computing

6 Company name OpenMP Programming Model School of Electronic Information Engineering  Shared Memory Model Uniform Memory AccessNon-Uniform Memory Access  OpenMP is designed for multi processor/core, shared memory machines

7 Company name MPI(message passing interface) Programming Model School of Electronic Information Engineering distributed memory architecturehybrid distributed shared memory architecture  Distributed Memory Model  MPI was designed for distributed memory architectures.  Basic MPI Concepts:A set of processes executing in parallel. These processes have separate address space.

8 Company name Parallel computing environment School of Electronic Information Engineering Figure 1 A Windows HPC Server cluster of workstations

9 Company name Performance Measurement for Parallel Computing School of Electronic Information Engineering  Speedup factor  Efficiency when E is given as a percentage

10 Company name Parallel Algorithm Design process School of Electronic Information Engineering Problem Mapping Communication Partitioning Agglomeration Figure 2 PCAM process

11 Company name School of Electronic Information Engineering  An example of parallel computing

12 Company name An example of parallel computing School of Electronic Information Engineering  Problem description Sum =

13 Figure 3 Data flow chat

14 Company name Comparison of the running result School of Electronic Information Engineering CoreTime(s)SpeedupEfficiency 1196.7241.0100% 299.7351.995.0% 366.4522.996.7% 452.2353.895.0% 550.9413.978.0% 646.4064.270.0% 840.8954.860.0% Table1 Parallel on one computer

15 Company name Comparison of the running result School of Electronic Information Engineering CoreTime(s)SpeedupEfficiency 1196.7241.0100% 295.7222.0100% 448.9804.0100% 634.6805.795.0% 828.4686.986.2% 1025.4097.777.0% 1223.0538.570.8% Table2 Parallel on two computers

16 Company name Comparison of the running result School of Electronic Information Engineering CoreTime(s)SpeedupEfficiency 1196.7241.0100% 364.2213.0100% 632.6586.0100% 922.3538.895.0% 1218.11310.990.8% 1516.92511.677.3% 1815.46912.770.6% 2413.74814.359.6% Table3 Parallel on three computers

17 LOGO www.tju.edu.cn/seie/ www.themegallery.com 天津大学电子信息工程学院 School of Electronic Information Engineering


Download ppt "LOGO Parallel computing technique for EM modeling makai 天津大学电子信息工程学院 School of Electronic Information Engineering."

Similar presentations


Ads by Google