High performance computing with MATLAB
Release time:2019-08-28Hits:
Course
Description:
This is a hands-on training course to learn the basic skills to accelerate your MATLAB programs using the MATLAB Parallel Computing Toolbox on regular desktop computers, GPU enabled computers, High-Performance Computing clusters, and cloud-based MATLAB parallel computing environment.
Objectives:
By the end of this course, participants will understand the structure of the MATLAB cluster, know how to log onto Xidian HPC cluster system from Linux, Mac, Windows operating systems, and know how to execute interactive and batch jobs on Xidian MATLAB HPC system.
ⅠTheory
CH1 Intorduction (2class hour)
HPC application.
CH2 MATLAB Parallel computing toolbox (2class hour)
MATLAB Parallel computingbasic commands, basic objects.
CH3 Parallel programming model and performancemeasurement(2class hour)
parallel programming method-PCAM，Amdahl law，Gustafson law，speedup ,etc.
CH4 Program Communicating Jobs (2class hour)
This section illustrates how to program communicating jobs for supported schedulers.
labindex,labReceive and labSend function.
CH5 Parallel for-Loops (parfor)（2class hour）
Profiling parfor-loops，Nested parfor and for-Loops,Example of parfor With different Parallel Overhead.
CH6 MATLAB and GPU computing (2class hour)
GPU software and hardware architecture ,GPUcomputing in MATLAB.
CH7 HPC and Deep learning (2class hour)
How to train, test, and evaluate neural networks for deep learning problems in MATLAB.
Slides
3、parallel computing
4、MPI
5、GPU
6、HPC+AI
7、Project
Learner Outcomes
At the end of the course the student will be able to:
Understand the architecture of MATLAB parallel computing toolbox and how this architecture influences the way programs should be written
Write parallel code, which exploits the MATLAB parallel computing toolbox to obtain a code with close to optimal performance
Analyze an existing program for OpenMP and MPI parallelization possibilities
Evaluate the possibilities of accelerators to speed up computational work
Teaching methods
Lecture, discussion and in-class exercises.
Instructor Biography
Huming Zhu received his Bachelor degree in Electronic Engineering, Master degree and Ph.D. degree in Communication and Information system from Xidian University, Xian, China, in 2001, 2004 and 2010,respectively. He is an associate professor at Xidian University. His research interests mainly include data mining,
pattern recognition, and High Performance Computing and image processing.
Publications:
(1) Huming Zhu, Peng Zhang, Libing Wang, Xiaohua Zhang & Licheng Jiao .A multiscale object detection approach for remote sensing images based on MSE-DenseNet and the dynamic anchor assignment, Remote Sensing Letters, 2019,10:10, 959-967.
(2) Huming Zhu, Duo Wang,Peng Zhang,Zheng Luo,Licheng Jiao,Hong Han. Parallel implementations of frame rate up-conversion algorithm using OpenCL on heterogeneous computing devices. Multimedia Tools and Applications, 2019, 78(7):9311–9334.
(3)Huming Zhu,Yanfei Wu,P Li,Peng Zhang,Zhe Ji,Maoguo Gong.A OPENCL-Accelerated Parallel Immunodominance Clone Selection Algorithm for Feature Selection, Concurrency and Computation: Practice and Experience, 2017,29(9):1-16
(4) Huming Zhu, Yanfei Wu, Pei Li,Duo Wang,Wei Shi, Peng Zhang, Licheng Jiao. A Parallel Non-Local Means Denoising Algorithm Implemtation with OpenMP and OpenCL on Intel Xeon Phi .Journal of Computational Science, 2016,17(3)591-598
(5) Huming Zhu, Yu Cao, Zhiqiang Zhou, Maoguo Gong, Licheng Jiao. Parallel Unsupervised SAR Image Change Detection on GPU. International Journal of High Performance Computing Applications, 2013, 27(2):109-122
(6)Huming Zhu, Zhong WQ, Jiao, L. C. Combination of Target Detection and Block-matching 3D Filter for Despeckling SAR Images. Electronics Letters.2013, 49(7):495-496
(7)Shuiping Gou,Xiong Zhuang, Huming Zhu. Parallel Sparse Spectral Clustering for SAR Image sengmention. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2013,6(4):1949-1962
(7) Huming Zhu, Jianing Kou,, Linyan Qiu, Yuqi Guo, Mingwei Niu, Maoguo Gong, Licheng Jiao.Distributed SAR image change detection with OpenCL-enabled spark, ETCD 2017 - Held in conjunction with 22nd ACM ASPLOS 2017,Xian, P.R. China, 2017:1-6
(8)Huming Zhu, Zheng Luo, Yanfei Wu, Pei Li, Peng Zhang, Shuiping Gou, L.C. Jiao.Accelerating Learning to Rank via SVM with OpenCL and OpenMP on Heterogeneous Platforms, 2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS), Wuhan, P.R. China, 2016:1199-1202
(9)H. Zhu, Y. Guo, M. Niu, L. Qiu, L. Jiao and M. Gong.SAR image change detection based on Spark-FLICM algorithm. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, P.R. China, 2016:3354-3357.
(10)H. Zhu, L. Lu, Y. Fan, P. Li, Q. Zhang and L. Jiao.Parallel implementation of the FLICM algorithm for SAR image change detection on intel MIC, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, P.R. China, 2016:2340-2343
(11)Huming Zhu, Yuqi Guo, Mingwei Niu, Guodong Yang, Licheng Jiao. Distributed SAR image change detection based on spark(IGARSS), Milan, Italy,2015:4149-4152
(12) Huming Zhu, Qingyu Zhang, Xinying Ren, Licheng Jiao. Parallel fast global K-means algorithm for synthetic aperture radar image change detection using OPENCL(IGARSS), Milan, Italy,2015:322-325
About MathWorks
MathWorks is the leading developer of mathematical computing software. Engineers and scientists worldwide rely on its products to accelerate the pace of discovery, innovation, and development.
MATLAB, the language of technical computing, is a programming environment for algorithm development, data analysis, visualization, and numeric computation. Simulink is a graphical environment for simulation and Model-Based Design for multidomain dynamic and embedded systems. MATLAB and Simulink are also fundamental teaching and research tools in the world's universities and learning institutions. Founded in 1984, MathWorks employs more than 5000 people in 16 countries, with headquarters in Natick, Massachusetts, USA.