6 Energy Efficient Scheduling for Multi-Core System
6.6 Summary
81
Remark 3: The DVC successfully decreases the power consumption for GEN_BLOCK redistribution.
Remark 4: The DVC provides more improvement on power consumption because the first level of the first part successfully avoids possible influence.
82
Chapter 7
Conclusions and Future Work
Parallel systems are good solutions to solve computation intensive scientific problems.
Distributing data according to the schemes not only keeps load balancing but improves the performance of GEN_BLOCK redistribution. Therefore, index generations and communication scheduling heuristics are proposed in this thesis. We first propose formulas to decompose multi-dimensional array and help node obtain information of data size, source node and destination node simply and independently. A two-phase scheduling heuristic is proposed to improve the communication cost. With the advancement of network, an optimization technique to adapt the heterogeneity of network and an efficient scheduling algorithm are proposed to avoid synchronization delay among clusters. Because the multi-core machines are popular recently, they become important elements of parallel systems. Therefore, a dynamic voltage communication scheduling technique is proposed for multi-core CPUs based grid systems. They successfully improve the communication cost and reduce power consumption.
With the improvement of computer architecture and network environment, new solutions are always required for performing GEN_BLOCK redistribution. It is trivial to image the huge change and great advancement of parallel systems in the future. For now, power saving is a good issue for such problems. Novel algorithms can be proposed for the characteristics of multi-core machines and various kinds of network protocols.
Research can be extended to dynamic grid system which allows nodes join or leave anytime. To make the system flexible becomes an important issue. Fault tolerance mechanism should handle the unexpected problems while the number of nodes in the
83
system changes anytime. Cloud systems require efficient redistribution strategies as well.
To create, suspend or delete virtual machines are methods to manage services on any host.
To prevent damages from all kinds of failures, image migrating is a method to back up the services. The way to migrate images and keep load balancing becomes important over the internet. The efficient distributing methods are required to migrate with better performance.
84
Current Publication Lists
Journal Papers
1. Ching-Hsien Hsu and Shih-Chang Chen, “Efficient Data Management Method for Scientific Application in Cloud,” Submitted to Journal of Universal Computer Science, 2010.
2. Ching-Hsien Hsu and Shih-Chang Chen, “Processor Reordering Techniques for Improving Data Locality in Heterogeneous Clusters,” Accepted by Journal of Supercomputing, 2010.
3. Ching-Hsien Hsu and Shih-Chang Chen, “Optimizing Communications of Data Parallel Programs in Scalable Cluster Systems,” Accepted by International Journal of High Performance Computing and Network, Inderscience Publishers, 2010.
4. Ching-Hsien Hsu and Shih-Chang Chen, “A Two-Level Scheduling Strategy for Optimizing Communications of Data Parallel Programs in Clusters ”, International Journal of Ad-Hoc and Ubiquitous Computing, Vol. 6, No. 4, pp. 263-269, 2010.
5. Ching-Hsien Hsu, Chi-Guey Hsu, Shih-Chang Chen and Tai-Lung Chen,
“Message Transmission Techniques for Low Traffic P2P Services,” International Journal of Communication Systems, Vol. 22, No. 9, pp. 1105-1122, September 2009.
6. Ching-Hsien Hsu, Shih-Chang Chen, Chia-Hao Yu and Jong Hyuk Park,
“Alleviating the Reader Collision Problem in Mobile and Wireless RFID Environments,” Journal of Personal and Ubiquitous Computing, Vol. 13, No 7, pp. 489-497, April 2009.
85
7. Ching-Hsien Hsu, Shih-Chang Chen and Chao-Yang Lan, “Scheduling Contention-Free Irregular Redistribution in Parallelizing Compilers,” The Journal of Supercomputing, Vol. 40, No. 3, pp. 229-247, June 2007.
8. Ching-Hsien Hsu, Shih-Chang Chen and Tzu-Tai Lo, “Locality Preserving Data Partitioning for SPMD Programs on Computational Grid,” Chung Hua Journal of Science and Engineering, Vol. 3, No. 1, pp. 121-128, January 2005.
Conference Papers
1. Tai-Lung Chen, Ching-Hsien Hsu and Shih-Chang Chen, “Scheduling of Job Combination and Dispatching Strategy for Grid and Cloud System,” Proceedings of the 5th International Grid and Pervasive Computing, LNCS 6104, pp. 612-621, Hualien, Taiwan, May 2010.
2. Shih-Chang Chen, Tai-Lung Chen and Ching-Hsien Hsu, “Message Clustering Technique towards Efficient Irregular Data Redistribution in Clusters and Grids,”
Proceedings of the 10th International Conference on Algorithms and Architectures for Parallel Processing, LNCS 6081, pp. 283-291, Busan, Korea, May 2010.
3. Tai-Lung Chen, Shih-Chang Chen, Ching-Hsien Hsu, Kun-Ming Yu and Hsi-Ya Chang, “A Compound Scheduling Strategy for Irregular Array Redistribution in Cluster Based Parallel System,” Proceedings of the 2nd Russia-Taiwan Symposium on Methods and Tools of Parallel Programming Multicomputers, LNCS 6083, pp.xxx-xxx, Vladivostok, Russia, May 2010.
4. Shih-Chang Chen and Ching-Hsien Hsu, “Multi-Level Scheduling Technique for Optimizing Communications of Parallel Programs in Grids,” Proceedings of the 6th Workshop on Grid Technology and Applications, Taitung, December 2009.
5. Shih-Chang Chen and Ching-Hsien Hsu, “Multi-Level Communication
86
Scheduling for Irregular Data Redistribution,” Proceedings of 2009 National Computer Symposium, Taipei, Taiwan, November 2009.
6. Ching-Hsien Hsu and Shih-Chang Chen, “Data Distribution Methods for Communication Localization in Multi-Clusters with Heterogeneous Network,”
Proceeding of the 12th IEEE International Conference on Computational Science and Engineering, Vancouver, Canada, August 2009.
7. Chun-Ching Wang, Shih-Chang Chen, Ching-Hsien Hsu and Chao-Tung Yang,
“Optimizing Communications of Data Parallel Programs in Scalable Cluster Systems,” Proceedings of the 3rd International Conference on Grid and Pervasive Computing, Vol. 5036, pp. 29-37, May 2008.
8. Ching-Hsien Hsu, Chih-Hsun Chou, Chi-Guey Hsu and Shih-Chang Chen, “On Improving Message Passing in Unstructured Peer-to-Peer Overlay Networks,"
IEEE Proceedings of the 2nd International Workshop on Service, Security and its Data management technologies for Ubiquitous Computing, pp. 358-363, May 2008.
9. Shih-Chang Chen and Ching-Hsien Hsu, “ISO: Comprehensive Techniques Towards Efficient GEN_BLOCK Redistribution with Multidimensional Arrays,”
Parallel Computing Technologies - Lecture Notes in Computer Science, Vol. 4671, pp. 507-515, Springer-Verlag, September 2007.
10. Ching-Hsien Hsu, Chao-Yang Lan and Shih-Chang Chen, “Optimizing Scheduling Stability for Runtime Data Alignment,” Embedded System Optimization - Lecture Notes in Computer Science, Vol. 4097, pp. 825- 835, Springer-Verlag, August 2006.
11. Chao-Yang Lan, Shih-Chang Chen and Ching-Hsien Hsu, “On Improving Scheduling Length for Irregular Data Redistribution Based on Local Message
87
Reduction,” Proceedings of the 12th Workshop on Compiler Techniques for High-Performance Computing, pp. 203-211, March 2006.
12. Ching-Hsien Hsu, Shih-Chang Chen, Chao-Yang Lan, Chao-Tung Yang and Kuan-Ching Li, “Scheduling Convex Bipartite Communications Towards Efficient GEN_BLOCK Transformations,” Parallel and Distributed Processing and Applications - Lecture Notes in Computer Science, Vol. 3758, pp. 419-424, Springer-Verlag, November 2005.
13. Shih-Chang Chen, Ching-Hsien Hsu, Chao-Yang Lan, Chao-Tung Yang and Kuan-Ching Li, “Efficient Communication Scheduling Methods for Irregular Array Redistribution in Parallelizing Compilers,” Parallel Computing Technologies - Lecture Notes in Computer Science, Vol. 3606, pp. 216-225, Springer-Verlag, September 2005.
14. Ching-Hsien Hsu, Shih-Chang Chen, Kuan-Ching Li and Chao-Tung Yang,
“Optimizations of Data Distributions Localities in Cluster Grid Environments,”
Computational Science and its Applications - Lecture Notes in Computer Science, Vol. 3483, pp. 1017-1027, Springer-Verlag, May 2005.
15. Chao-Yang Lan, Ching-Hsien Hsu, and Shih-Chang Chen, “Scheduling Contention-Free Irregular Redistribution in Parallelizing Compilers,” Proceedings of the 11th Workshop on Compiler Techniques for High- Performance Computing, pp. 133-142, March 2005.
88
References
[1] Marcos Dias de Assuncao, Alexandre di Costanzo and Rajkumar Buyya, “Evaluating the cost-benefit of using cloud computing to extend the capacity of clusters,”
Proceedings of the 18th ACM international symposium on High Performance Distributed Computing, pp. 141-150, June 2009.
[2] Sheng-Wen Bai and Chu-Sing Yang, “Essential Cycle Calculation Method for Irregular Array Redistribution,” IEICE Transactions on Information and Systems, Vol.
E89-D, No. 2, pp. 789-797, February 2006.
[3] Sheng-Wen Bai, Chu-Sing Yang and Tsung-Chuan Huang, “Packing/Unpacking using MPI User-Defined Datatypes for Efficient Data Redistribution,” IEICE Transactions on Information and Systems, Vol. E87-D, No.7, pp. 1721-1728, July 2004.
[4] Gerardo Bandera and E.L. Zapata, “Sparse Matrix Block-Cyclic Redistribution,”
Proceeding of IEEE International Parallel Processing Symposium, pp. 355-359, April 1999.
[5] Philippe Baptiste, Peter Brucker, Marek Chrobak, Christoph Dürr, Svetlana A.
Kravchenko and Francis Sourd, “The complexity of mean flow time scheduling problems with release times,” Journal of Scheduling, Vol. 10, No. 2, pp. 139-146, April 2007.
[6] Peter Brucker and Svetlana A. Kravchenko, “Scheduling jobs with equal processing times and time windows on identical parallel machines,” Journal of Scheduling, Vol.
11, No. 4, pp. 229-237, August 2008.
[7] EunJoung Byun, SungJin Choi, MaengSoon Baik, JoonMin Gil, ChanYeol Park and ChongSun Hwang, “MJSA: Markov job scheduler based on availability in desktop
89
grid computing environment,” Future Generation Computer Systems, Vol. 23, No. 4, pp. 616-622, May 2007.
[8] Claris Castillo, George N. Rouskas and Khaled Harfoush, “Efficient resource management using advance reservations for heterogeneous grids,” Proceedings of 21st IEEE International Parallel and Distributed Processing, pp. 1-12, April 2008.
[9] Ruay-Shiung Chang, Jih-Sheng Chang and Po-Sheng Lin, “An ant algorithm for balanced job scheduling in grids,” Future Generation Computer Systems, Vol. 25, No.
1, pp. 20-27, January 2009.
[10] Ruay-Shiung Chang, Jih-Sheng Chang and Shin-Yi Lin, “Job scheduling and data replication on data grids,” Future Generation Computer Systems, Vol. 23, No. 7, pp.
846-860, July 2007.
[11] Chieh-Wen Cheng, Jan-Jan Wu and Pangfeng Liu, “QoS-aware, access-efficient, and storage-efficient replica placements,” Journal of Supercomputing, Vol. 49, No. 1, pp.
42-63, July 2009.
[12] Johanne Cohen, Emmanuel Jeannot, Nicolas Padoy and and Frédéric Wagner,
“Messages Scheduling for Parallel Data Redistribution between Clusters,” IEEE Transactions on Parallel and Distributed Systems, Vol. 17, No. 10, pp. 1163-1175, October 2006.
[13] Frederic Desprez, Jack Dongarra and Antoine Petitet, “Scheduling Block-Cyclic Data redistribution,” IEEE Transactions on Parallel and Distributed Systems, Vol. 9, No. 2, pp. 192-205, February 1998.
[14] Nicolas G. Grounds, John K. Antonio and Jeff Muehring, “Cost-Minimizing Scheduling of Workflows on a Cloud of Memory Managed Multicore Machines,”
Proceedings of the 1st International Conference on Cloud Computing, LNCS Vol.
5931, December 2009.
90
[15] Minyi Guo, “Communication Generation for Irregular Codes,” The Journal of Supercomputing, Vol. 25, No. 3, pp. 199-214, 2003.
[16] Minyi Guo and Yi Pan, “Improving communication scheduling for array redistribution,” Journal of Parallel and Distributed Computing, Vol. 65, No. 5, pp.
553-563, May 2005.
[17] Minyi Guo, Yi Pan and Zhen Liu, “Symbolic Communication Set Generation for Irregular Parallel Applications,” The Journal of Supercomputing, Vol. 25, No. 3, pp.
199-214, July 2003.
[18] Ching-Hsien Hsu, Sheng-Wen Bai, Yeh-Ching Chung and Chu-Sing Yang, “A Generalized Basic-Cycle Calculation Method for Efficient Array Redistribution,”
IEEE Transactions on Parallel and Distributed Systems, Vol. 11, No. 12, pp.
1201-1216, December 2000.
[19] Ching-Hsien Hsu, Ming-Hao Chen, Chao-Tung Yang and Kuan-Ching Li,
“Optimizing Communications of Dynamic Data Redistribution on Symmetrical Matrices in Parallelizing Compilers,” IEEE Transactions on Parallel and Distributed Systems, Vol. 17, No. 11, pp. 1226-1241, December 2006.
[20] Ching-Hsien Hsu, Shih-Chang Chen and Chao-Yang Lan, “Scheduling Contention-Free Irregular Redistributions in Parallelizing Compilers,” The Journal of Supercomputing, Vol. 40, No. 3, pp. 229-247, June 2007.
[21] Ching-Hsien Hsu, Dong-Lin Yang, Yeh-Ching Chung and Chyi-Ren Dow, “A Generalized Processor Mapping Technique for Array Redistribution,” IEEE Transactions on Parallel and Distributed Systems, Vol. 12, No. 7, pp. 743-757, July 2001.
[22] Jih-Woei Huang and Chih-Ping Chu, “A flexible processor mapping technique toward data localization for block-cyclic data redistribution,” The Journal of Supercomputing,
91
Vol. 45, No. 2, pp. 151-172, August 2008.
[23] Jih-Woei Huang and Chih-Ping Chu, “An Efficient Communication Scheduling Method for the Processor Mapping Technique Applied Data Redistribution,” The Journal of Supercomputing, Vol. 37, No.3, pp. 297-318, August 2006.
[24] Emmanuel Jeannot and Frédéric Wagner, “Scheduling Messages For Data Redistribution: An Experimental Study,” International Journal of High Performance Computing Applications, Vol. 20, No. 4, pp. 443-454, 2006.
[25] Edgar T. Kalns, and Lionel M. Ni, “Processor Mapping Technique Toward Efficient Data Redistribution,” IEEE Transactions on Parallel and Distributed Systems, Vol. 6, No. 12, pp. 1234-1247, December 1995.
[26] Konstantinos Kalpakis, Koustuv Dasgupta and Ouri Wolfson, “Optimal placement of replicas in trees with read, write, and storage costs,” IEEE Transactions on Parallel and Distributed Systems, Vol. 12, No. 6, pp. 628-637, June 2001.
[27] Amit Karwande, Xin Yuan and David K. Lowenthal, “An MPI prototype for compiled communication on ethernet switched clusters,” Journal of Parallel and Distributed Computing, Vol. 65, No. 10, pp. 1123-1133, October 2005.
[28] S. D. Kaushik, Chua-Huang Huang, J. Ramanujam and P. Sadayappan, “Multi-phase array redistribution: modeling and evaluation,” Proceeding of IEEE International Parallel Processing Symposium, pp. 441-445, April 1995.
[29] Saeri Lee, Hyun-Gyoo Yook, Mi-Soo Koo and Myong Park, “Processor reordering algorithms toward efficient GEN_BLOCK redistribution,” Proceedings of the ACM symposium on Applied computing, pp. 539-543, March 2001.
[30] Young Won Lim, Prashanth B. Bhat and Viktor K. Prasanna, “Efficient Algorithms for Block-Cyclic Redistribution of Arrays,” Algorithmica, Vol. 24, No. 3-4, pp. 298-330, July 1999.
92
[31] Chun-Yuan Lin and Yeh-Ching Chung, “Data distribution schemes of sparse arrays on distributed memory multicomputers,” The Journal of Supercomputing, Vol. 41, No. 1, pp. 63-87, July 2007.
[32] Ping-Yi Lin and Pangfeng Liu, “Job Scheduling Techniques for Distributed Systems with Temporal Constraints,” Proceedings of the 5th International Grid and Pervasive Computing, LNCS Vol. 6104, pp. 280-289, May 2010.
[33] Huan Liu and Dan Orban, “GridBatch: Cloud Computing for Large-Scale Data-Intensive Batch Applications,” Proceedings of the 2008 8th IEEE International Symposium on Cluster Computing and the Grid, pp. 295-304, May 2008.
[34] David Meisner, Brian T. Gold and Thomas F. Wenisch, “PowerNap: eliminating server idle power,” Proceeding of the 14th International Conference on Architectural Support for Programming Languages and Operation Systems, pp. 205-216, 2009.
[35] Neungsoo Park, Viktor K. Prasanna and Cauligi S. Raghavendra, “Efficient Algorithms for Block-Cyclic Data Redistribution Between Processor Sets,” IEEE Transactions on Parallel and Distributed Systems, Vol. 10, No. 12, pp. 1217-1240, December 1999.
[36] Antoine P. Petitet and Jack J. Dongarra, “Algorithmic Redistribution Methods for Block-Cyclic Decompositions,” IEEE Transactions on Parallel and Distributed Systems, Vol. 10, No. 12, pp. 1201-1216, December 1999.
[37] Loic Prylli and Bernard Touranchean, “Fast runtime block cyclic data redistribution on multiprocessors,” Journal of Parallel and Distributed Computing, Vol. 45, No. 1, pp. 63-72, August 1997.
[38] Shankar Ramaswamy, Barbara Simons, and Prithviraj Banerjee, “Optimizations for Efficient Array Redistribution on Distributed Memory Multicomputers,” Journal of Parallel and Distributed Computing, Vol. 38, No. 2, pp. 217-228, November 1996.
93
[39] Thomas Rauber and Gudula Rünger, “A Data Re-Distribution Library for Multi-Processor Task Programming,” International Journal of Foundations of Computer Science, Vol 17, No. 2, pp.251-270, 2006.
[40] Ravi Reddy and Alexey Lastovetsky, “HeteroMPI+ScaLAPACK: Towards a ScaLAPACK (Dense Linear Solvers) on Heterogeneous Networks of Computers,”
Proceedings of the 13th IEEE International Conference on High Performance Computing, Vol 4297, pp. 242-253, December 2006.
[41] Dongkun Shin and Jihong Kim, “Power-Aware Communication Optimization for Networks-on-Chips with Voltage Scalable Links,” Proceeding of the International Conference on Hardware/Software Codesign and System Synthesis, pp. 170-175, 2004.
[42] Seung Woo Son, Guangyu Chen, Ozcan Ozturk Mahmut Kandemir and Alok Choudhary, “Compiler-Directed Energy Optimization for Parallel-Disk-Based Systems,” IEEE Transactions on Parallel and Distributed Systems, Vol. 18, No. 9, pp.
1241-1257, September 2007.
[43] Stavros Souravlas and Manos Roumeliotis, “A message passing strategy for array redistributions in a torus network,” The Journal of Supercomputing, Vol. 46, No. 1, pp.
40-57, October 2008.
[44] Rajesh Sudarsan and Calvin J. Ribbens, “Efficient Multidimensional Data Redistribution for Resizable Parallel Computations,” Fifth International Symposium on Parallel and Distributed Processing and Applications, Vol. 4742, pp. 182-194, August 2007.
[45] Manghui Tu, Peng Li, Qingkai Ma, I-Ling Yen and Farokh B. Bastani, “On the Optimal Placement of Secure Data Objects over Internet,” Proceedings of 19th IEEE International Parallel and Distributed Processing, pp. 14-14, April 2005.
94
[46] Akiyoshi Wakatani and Michael Wolfe, “Optimization of array redistribution for distributed memory multicomputers,” Parallel Computing, Vol. 21, No. 9, pp.
1485-1490, September 1995.
[47] Hui Wang, Minyi Guo and Daming Wei, “A Divide-and-conquer Algorithm for Irregular Redistributions in Parallelizing Compilers,” The Journal of Supercomputing, Vol. 29, No. 2, pp.157-170, August 2004.
[48] Hui Wang, Minyi Guo and Daming Wei, “Message Scheduling for Irregular Data Redistribution in Parallelizing Compilers,” IEICE Transactions on Information and Sysmtes, Vol. E89-D, No. 2, pp. 418-424, February 2006.
[49] Sewook Wee and Huan Liu, “Client-side load balancer using cloud,” Proceedings of the 2010 ACM Symposium on Applied Computing, pp. 399-405, March 2010.
[50] Jan-Jan Wu, Yi-Fang Lin and Pangfeng Liu, “Optimal replica placement in hierarchical Data Grids with locality assurance,” Journal of Parallel and Distributed Computing, Vol. 68, No. 12, pp. 1517-1538, December 2008.
[51] Yun Yang, Ke Liu, Jinjun Chen, Xiao Liu, Dong Yuan and Hai Jin, “An Algorithm in SwinDeW-C for Scheduling Transaction-Intensive Cost-Constrained Cloud Workflows,” Proceedings of the 4th IEEE International Conference on eScience, pp.
374-375, December 2008.
[52] Hyun-Gyoo Yook and Myung-Soon Park, “Scheduling GEN_BLOCK Array Redistribution,” The Journal of Supercomputing, Vol. 22, No. 3, pp. 251-267, July 2002.
[53] Chang Wu Yu, “On the Complexity of the Max-Edge-Coloring Problem with Its Variants,” International Symposium on Combinatorics, Algorithms, Probabilistic and Experimental Methodologies, Vol.4614, pp. 350-361, September 2007.
[54] XianGrong Zhou, ChenJie Yu and Peter Petrov, “Temperature-Aware Register