Techniques of Parallelization : A Survey
DOI:
https://doi.org/10.26438/ijcse/v7i7.150153Keywords:
Shared Memory, Parallel programming, Parallelization techniquesAbstract
Parallel computing enables us to utilize hardware resources efficiently and to solve computationally intensive problems by dividing them into sub-problem using a shared-memory approach and solving them simultaneously. Emerging technologies are based on parallel computing as it involves complex simulations of real-world situations which are extremely computation-intensive and time-taking as well. Parallel programming is gaining significance due to the limitations of the hardware. Researchers are trying to enhance memory and bus speed to match the processor`s speed. Generating parallel code requires skill and a particular technique of parallelization. There are several parallelization techniques amongst which one needs to be shrewdly chosen for a particular task and architecture. A brief survey of existing parallelization procedures is provided through this paper. New hybrid techniques are required to be developed combining technical and architectural benefits two or more parallel models. A thorough revision of traditional parallelization techniques is required to derive new techniques.
References
[1] Prema, S.,and R. Jehadeesan,"Analysis of Parallelization Techniques and Tools," International Journal of Information and Computation Technology 3 (2013): 471-478.
[2] Jin, Ruoming, and Gagan Agrawal,"Shared memory parallelization of data mining algorithms: Techniques, programming interface, and performance" Proceedings of the 2002 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, 2002.
[3] John L. Hennessy, and David A. Patterson, “Computer Architecture: A Quantitative Approach”Morgan Kaufmann,Inc.,San Francisco,2nd edition,1996.
[4] Yu, Hao, and Lawrence Rauchwerger, "Adaptive reduction parallelization techniques" ACM International Conference on Supercomputing 25th Anniversary Volume. ACM, 2014.
[5] Chapman, Barbara, and Hans Zima, “Supercompilers for parallel and vector computers” Addison-wesley, 1990.
[6] Zhang, Ye, Lawrence Rauchwerger, and Josep Torrellas,"Hardware for speculative run-time parallelization in distributed shared-memory multiprocessor." Proceedings 1998 Fourth International Symposium on High-Performance Computer Architecture. IEEE, 1998.
[7] Rauchwerger, Lawrence, and David A. Padua,"The LRPD test: Speculative run-time parallelization of loops with privatization and reduction parallelization" IEEE Transactions on Parallel and Distributed Systems 10.2 (1999): 160-180.
[8] Yu, Hao, and L. Rauchwerger, "Run-time parallelization overhead reduction techniques" Proc. of the 9th Int. Conf. on Compiler Construction, Berlin, Germany. 2000.
[9] Banerjee, Utpal, et al, "Automatic program parallelization" Proceedings of the IEEE 81.2 (1993): 211-243.
[10] P.M. Behr, W.K. Giloi and H. Mfihlenbein, “SUPRENUM: The German supercomputer architecture—Rationaleand concepts, Proc” 1986 International Conference on Parallel Processing (1986).
[11] MJ. Flynn, “Some computer organizations and their effectiveness”, IEEE Trans. Computer. 21 (9) (1972) 948-960.
[12] U. Trottenberg, “SUPRENUM--an MIMD multiprocessor system for multi-level scientific computing”, in: W. H~indler et al., eds., CONPAR 86. Conference on Algorithms and Hardware for Parallel Processing, Lecture Notes in Computer Science 237 (Springer, Berlin, 1986) 48-52.
[13] H.P. Zima, H.-J. Bast, M. Gemdt, P.J. Hoppen, “Semi-automatic parallelization of Fortran programs”, in: W. Hgmdler et al., eds., CONPAR 86. Conference on Algorithms and Hardware for Parallel Processing, Lecture Notes in Computer Science 237 (Springer, Berlin, 1986) 287-294.
[14] H.P. Zima, H.-J. Bast, M. Gerndt, PJ. Hoppen, “SUPERB: The SUPRENUM Parallelizer Bonn”, Research Report SUPRENUM 861203, Bonn University, (1986).
[15] Ruchkin, Vladimir, et al, "Frame model of a compiler of cluster parallelism for embedded computing systems",2017 6th Mediterranean Conference on Embedded Computing (MECO). IEEE, 2017.
[16] Shin, Wongyu, et al, "Rank-Level Parallelism in DRAM",IEEE Transactions on Computers 66.7 (2017): 1274-1280.
[17] Liu, De-feng, Guo-teng Pan, and Lun-guo Xie, "Understanding how memory-level parallelism affects the processors performance",2011 IEEE 3rd International Conference on Communication Software and Networks. IEEE, 2011.
[18] Cheng, Shaoyi, et al, "Exploiting memory-level parallelism in reconfigurable accelerators", 2012 IEEE 20th International Symposium on Field-Programmable Custom Computing Machines. IEEE, 2012.
[19] Kumar, K. Ashwin, et al, "Hybrid approach for parallelization of sequential code with function level and block level parallelization”, International Symposium on Parallel Computing in Electrical Engineering (PARELEC`06). IEEE, 2006.
[20] Gasper, Pete, et al, "Automatic parallelization of sequential C code”, Midwest Instruction and Computing Symposium, Duluth, MN, USA. 2003.
[21] Wall, D,"Limits of instruction level parallelism. David W. Wall, Limits of Instruction Level Parallelism" Proc. 4th ASPLOS. 1991.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
