PARALLEL PROCESSING PROBLEM AND SOLUTION - A CASE STUDY ON MATLAB PARALLEL COMPUTING TOOLBOX PERFORMANCE PROFILING

Ayu Fazillah Alias #1, Mohamed Faidz Mohamed Said #2

# Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA 
70300 Seremban, Negeri Sembilan, MALAYSIA

1 ayufazillahalias@gmail.com
2 faidzms@ieee.org


 
Abstract—Forecasting the execution time of computer programs is an important but challenging problem in the society of computer systems. Code analysis tools are indispensable to comprehend program behaviour. Profile tools utilize the aftereffects of time estimations in the execution of a program to increase comprehension and in this way help in the advancement of the code. This research paper is about a case study on MATLAB parallel computing toolbox performance profiling. The parallel profiler runs an extension of the profile command and the profile viewer exclusively for communicating jobs, to allow users to see how much time each worker spends estimating each function and how much time communicating or waiting for communications with the other workers. Thus, the programmers can improve their system so that the system can run smoothly. Besides, it can increase the quality of code to become better than before. This will conclude how important the profiling whiles doing the programming. 

Keyword: MATLAB, parallel, computing, toolbox, profiling



REFERENCES

[1]	A. Egyed, "Automatically Detecting and Tracking Inconsistencies in Software Design Models," IEEE Transactions on Software Engineering, vol. 37, 2011.

[2]	A. Rubio and F. de Villar, "Code Profiling in R: A Review of Existing Methods and an Introduction to Package GUIProfiler," R JOURNAL, vol. 7, pp. 275-287, 	2015.

[3]	(June 14, 2017). Profile to Improve Performance. Available: https://www.mathworks.com/help/matlab/matlab_prog/profiling-for-improving-	performance.html#responsive_offcanvas

[4]	C. Moler. (2014). The Origins of MATLAB. Available: https://www.mathworks.com/company/newsletters/articles/the-origins-of-matlab.html

[5]	S. L. Graham, P. B. Kessler, and M. K. McKusick, "gprof," ACM SIGPLAN Notices, vol. 39, p. 49, 2004.

[6]	I. Manousakis, F. S. Zakkak, P. Pratikakis, and D. S. Nikolopoulos, "TProf: An energy profiler for task-parallel programs," Sustainable Computing: Informatics 	and Systems, 2013.

[7]	L. Huang, J. Jia, B. Yu, B.-G. Chun, P. Maniatis, and M. Naik, "Predicting execution time of computer programs using sparse polynomial regression," in Advances 	in neural information processing systems, 2010, pp. 883-891.

[8]	R. J. Lisle, J. L. Fernández Martínez, N. Bobillo-Ares, O. Menéndez, J. Aller, and F. Bastida, "FOLD PROFILER: A MATLAB ®—based program for fold shape 	classification," Computers and Geosciences, vol. 32, pp. 102-108, 2006.

[9]	K. Whipple, C. Wobus, B. Crosby, E. Kirby, and D. Sheehan, "New tools for quantitative geomorphology: extraction and interpretation of stream profiles from 	digital topographic data," GSA Short Course, vol. 506, 2007.

[10]	B. Vermeulen, A. J. F. Hoitink, and M. G. Sassi, "On the use of horizontal acoustic Doppler profilers for continuous bed shear stress monitoring," 	International Journal of Sediment Research, vol. 28, pp. 260-268, 2013.

[11]	C. Sharmistha, K. N. Jukka, and S. Matti, "Design of energy-efficient location-based cloud services using cheap sensors," International Journal of Pervasive 	Computing and Communications, vol. 9, pp. 115-138, 2013.

[12]	G. Pryor, B. Lucey, S. Maddipatla, C. McClanahan, J. Melonakos, V. Venugopalakrishnan, et al., "High-level GPU computing with Jacket for MATLAB and C/C++," in 	SPIE Defense, Security, and Sensing, 2011, pp. 806005-806005-6.

[13]	D. S. Mueller, "extrap: Software to assist the selection of extrapolation methods for moving-boat ADCP streamflow measurements," Computers and Geosciences, 	vol. 54, pp. 211-218, 2013.

[14]	S. Kosta, A. Aucinas, P. Hui, R. Mortier, and X. Zhang, "Thinkair: Dynamic resource allocation and parallel execution in the cloud for mobile code offloading," 	in Infocom, 2012 Proceedings IEEE, 2012, pp. 945-953.

[15]	A. Klöckner, N. Pinto, Y. Lee, B. Catanzaro, P. Ivanov, and A. Fasih, "PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation," 	Parallel Computing, vol. 38, pp. 157-174, 2012.

[16]	M. Garg and L. Dewan, "Non-recursive Haar Connection Coefficients Based Approach for Linear Optimal Control," Journal of Optimization Theory and Applications, 	vol. 153, pp. 320-337, 2012.

[17]	A. F. Alias. (2017, May 23). 170525 CSC580 AFA. Retrieved from https://www.youtube.com/watch?v=1jhQVK2qx8I