방송공학회논문지 (Journal of Broadcast Engineering)

  • 제10권1호
  • /
  • Pages.83-102
  • /
  • 2005
  • /
  • 1226-7953(pISSN)
  • /
  • 2287-9137(eISSN)
한국방송∙미디어공학회 (The Korean Institute of Broadcast and Media Engineers)
권호 표지

Parallel Video Processing Using Divisible Load Scheduling Paradigm

  • Suresh S. (Department of Aerospace Engineering, Indian Institute of Science) ;
  • Mani V. (Department of Aerospace Engineering, Indian Institute of Science) ;
  • Omkar S. N. (Department of Aerospace Engineering, Indian Institute of Science) ;
  • Kim H.J. (Department of Control and Instrumentation Engineering Kwangwon National University)
  • 발행 : 2005.03.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The problem of video scheduling is analyzed in the framework of divisible load scheduling. A divisible load can be divided into any number of fractions (parts) and can be processed/computed independently on the processors in a distributed computing system/network, as there are no precedence relationships. In the video scheduling, a frame can be split into any number of fractions (tiles) and can be processed independently on the processors in the network, and then the results are collected to recompose the single processed frame. The divisible load arrives at one of the processors in the network (root processor) and the results of the computation are collected and stored in the same processor. In this problem communication delay plays an important role. Communication delay is the time to send/distribute the load fractions to other processors in the network. and the time to collect the results of computation from other processors by the root processors. The objective in this scheduling problem is that of obtaining the load fractions assigned to each processor in the network such that the processing time of the entire load is a minimum. We derive closed-form expression for the processing time by taking Into consideration the communication delay in the load distribution process and the communication delay In the result collection process. Using this closed-form expression, we also obtain the optimal number of processors that are required to solve this scheduling problem. This scheduling problem is formulated as a linear pro-gramming problem and its solution using neural network is also presented. Numerical examples are presented for ease of understanding.

키워드

참고문헌

  1. D. T. Altilar and Y. Paker, 'Optimal Scheduling Algorithms for Communication Constrained Parallel Processing.' Lecture Notes in Computer Science. LNCS. Vol. 2400. pp. 197-206. Euro-Para. 2002. Springer-Verlag. Berlin Hidelberg. 2002 https://doi.org/10.1007/3-540-45706-2_25
  2. V. Bharadwaj. D. Ghose. V. Mani. and T. G. Robertazzi. Scheduling Divisible Loads in Parallel and Distributed Systems. Los Alamitos. California. IEEE Computer Society Press. 1996
  3. Special Issue on: Divisible Load Scheduling. Cluster Computing. Vol. 6, Jan 2003
  4. http://www.ee.sunysb.edu/tom/dlt.html
  5. Y. C. Cheng and T. G. Robertazzi, 'Distributed computation with communication delay.' IEEE Trans. Aerospace and Electronic Systems. Vol. 24. pp. 700-712, Nov. 1988 https://doi.org/10.1109/7.18637
  6. Y. C. Cheng and T. G. Robertazzi. 'Distributed computation for a tree network with communication delay.' IEEE Trans. Aerospace and Electronic Systems, Vol. 26. pp.511-516. May 1990 https://doi.org/10.1109/7.106129
  7. S. Bataineh and T.G. Robertazzi. 'Bus oriented load sharing for a network of sensor driven processors,' IEEE Trans. Systems Man Cybernetics. Vol. 21. PP. 1202-1205. Sep-Oct. 1991 https://doi.org/10.1109/21.120070
  8. V. Bharadwaj. D. Ghose. and V. Mani. 'Optimal sequencing and arrangement in single-level tree networks with communication delays,' IEEE Trans. Parallel and Distributed Systems. Vol. 5. pp. 968-976. 1994 https://doi.org/10.1109/71.308534
  9. H. J. Kim. G. I. Lee. and J. G. Lee. 'Optimal load distribution for tree network of processors,' IEEE Trans. Aerospace and Electronic SYstems. Vol. 32. no. 2. pp.607-612. 1996 https://doi.org/10.1109/7.489505
  10. S. Bataineh. T. Hsiung. and T. G. Robertazzi. 'Closed form solutions for bus and tree networks of processors sharing a divisible job,' IEEE Trans on Computers. Vol. 43. pp. 1184-1196. 1994 https://doi.org/10.1109/12.324544
  11. T.G. Robertazzi. 'Processor equivalence for daisy chain load sharing processors.' IEEE Trans. Aerospace and Electronic Systems. Vol. 29. pp. 1216-1221. Oct 1993 https://doi.org/10.1109/7.259524
  12. J. Sohn. and T. G. Robertazzi. 'Optimal divisible job load sharing on bus networks.' IEEE Trans. Aerospace and Electronic Systems, Vol. 32. pp. 34-40. Jan 1996 https://doi.org/10.1109/7.481247
  13. D. W. Tank and J. J. Hopfield. 'Simple 'neural' optimization networks: An A/D converter. signal decision circuit. and a linear programming circuit,' IEEE Trans. Circuits and Systems. Vol. CAS-33. pp. 533-541. May 1986
  14. A. CichOCki and R. Unbehauen. 'Neural networks for solving systems of linear equations and related problems.' IEEE Trans. Circuits and Systems-I: Fund. Theory App., Vol. 39. pp. 580-594. Feb. 1992
  15. M. P. Kennedy and L. O. Chua. 'Neural networks for nonlinear programming,' IEEE Trans Circuits and Systems. Vol. 35. pp. 554-562. May 1988 https://doi.org/10.1109/31.1783
  16. A. Rodriguez-Vazquez. R. Dominguer-Castro. A. Rueda. J.L.Huertas, and E, Sanchez-Sinencio, 'Nonlinear switched capacitor 'neural' networks for optimization problems,' IEEE Trans, Circuits and Systems, Vol. 37, pp. 384-397, March 1990 https://doi.org/10.1109/31.52732
  17. S, H. Zak, V, Upatising, and S, Hui, 'Solving linear programming problems with neural networks: A comparative study,' IEEE Trans. Neural Networks: Vol. 6, pp, 94-104. Jan. 1995 https://doi.org/10.1109/72.363446
  18. Y, Xia, and J. Wang, 'Neural networks for solving linear programming problems with bounded variables,' IEEE Trans Neural Networks, Vol. 6, pp. 515-519, March 1995 https://doi.org/10.1109/72.363493
  19. Y. Xia, 'A new neural network for solving linear pro gramming problems and its application,' IEEE Trans Neural Networks, Vol. 7, pp. 525-529, March 1996 https://doi.org/10.1109/72.485686
  20. K. V. Nguyan, 'A nonlinear neural network for solving linear programming problems,' ISMP-2000, International Symposium on Mathematical Programming, Aug. 7-11. Atlanta, GA. USA, 2000
  21. D. N. Zhou, V. Cherkassky, T. R. Baldwin, and D. E. Olson, ' A neural network approach to job-shop scheduling,' IEEE Trans. Neural Networks, Vol. 2, pp. 175-179, Jan. 1991 https://doi.org/10.1109/72.80311
  22. S. Cavalieri and O. :VIirabella, 'Neural networks for process scheduling in real-time communication systems,' IEEE Trans. Neural Networks, Vol. 7. pp.1272-1285, Sep. 1996
  23. V. Bharadwai. D. Ghose, and V. Mani, 'Multi installment load distribution in tree networks with delays,' IEEE Trans. on Aerospace and Electronic Systems, Vol. 31. pp. 555-567, 1995 https://doi.org/10.1109/7.381944
  24. V. Bharadwaj. D. Ghose, V. :viani, 'An efficient load dis tribution strategy for a linear network of processors with communication delays,' Computers and Mathematics with Applications, Vol. 29, pp. 9:1-112, 1995
  25. D. Ghose, and V. Mani, 'Distributed computation with communication delays: Asymptotic performance analysis,' Journal of Parallel and Distributed Computing, Vol. 23, pp. 293-30;), 1994 https://doi.org/10.1006/jpdc.1994.1141
  26. J. Blazewicz, and :M. Drozdowski, 'The performance limits of a two dimensional network of load sharing processors,' Foundatkms of Computing and Decision Sciences, Vol. 21. pp. 3-15, 1996
  27. J. Blazewicz, and ;vI. Drozdowski, 'Scheduling divisible jobs on hypercube,' Parallel Computing, Vol. 21. pp. 1945-1956, 1995 https://doi.org/10.1016/0167-8191(95)00046-1
  28. W. Glazek, 'A multistage load distribution strategy for three dimensional meshes,' Cluster Computing, Special Issue on: Divisible Load Scheduling, Vol. 6, pp. 31-39, 2003
  29. Keqin Li, 'Parallel processing of divisible loads on par titionable static interconnection networks,' Cluster Computing, Special Issue on: Divisible Load Scheduling, Vol. 6, pp. 47-55, 2003
  30. Keqin Li, 'Improved methods for divisible load distribution on k-dimensional meshes using pipelined communications,' IEEE Transactions on Parallel and Distributed Systems, Vol. 14. pp. 1250-1261. 2003 https://doi.org/10.1109/TPDS.2003.1255637
  31. S. Bataineh, and M. Alibraham, 'Effect of fault tolerance and communication delay on response time in a multiprocessor system with a bus topology,' Computer Commufllcations, Vol. 17, 1994
  32. J. Sohn, and T. G. .Robertazzi, 'Optimal timevarying load sharing divisible jobs,' IEEE Trans. on Aerospace and Electronic Systems, Vol. 34. 1988
  33. J. Sohn, T. G. Robertazzi, and S. Luryi, 'Optimizing com puting costs using divisible load analysis,' IEEE Trans. on Parallel and Distributed Systems, Vol. 9, pp. 225-231. 1998 https://doi.org/10.1109/71.674315
  34. X. Li, V. Bharadwaj, and C. C. Ko, 'Divisible load scheduling on single-level tree networks with buffer constraints,' IEEE Trans. on Aerospace and Electronic Systems, Vol. 36, pp.1298-1308, 2000 https://doi.org/10.1109/7.892677
  35. M. Drozdowski, and P. Wolniewicz, 'Divisible load scheduling in systems with limited memory,' Cluster Computing, Special Issue on: Divisible Load Scheduling, Vol. 6, pp. 19-29, 2003
  36. V. Bharadwaj, H. F. Li. and T. Radhakrishnan, 'Scheduling divisible loads in bus networks with arbitrary processor release times,' Computers and klathematics with Applications, Vol.32, pp. 57-77, 1996
  37. V. Bharadwaj, and G. Barlas, 'Scheduling divisible loads with processor release times and finite size buffer capacity constraints in bus networks,' Cluster Computing, Special Issue on: Divisible Load Scheduling, Vol. 6, pp, 63-74, 2003
  38. H, J. Kim, 'A novel optimal load distribution algorithm for divisible loads,' Cluster Computing, Special Issue on: Divisible Load Scheduling, Vol. 6, pp. 41-46, 2003
  39. H. J. Kim, and V. Mani, 'Divisible load scheduling in single level tree networks: Optimal sequencing and arrangement in the non-blocking mode of communication,' Computers and Mathematics with Applications, Vol. 46, pp. 161- 623, 2003
  40. S. K. Chan, V. Bharadwaj, and D. Ghose, 'Large matrix vector products on distributed bus networks with commu nication delays using the divisible load paradigm: Performance analysis and simulation,' Mathematics and Computer Simulation. Vol. 58, pp. 71-92, 2001 https://doi.org/10.1016/S0378-4754(01)00329-9
  41. D. Ghose, and H. J. Kim, 'Load partitioning and trade off study for large matrix-vector computations in multicast bus networks with communication delays,' Journal of Parallel and Distributed Computing, Vol. 55, pp. 32-59, 1998 https://doi.org/10.1006/jpdc.1998.1494
  42. J. Blazewicz, and M. Drozdowski. 'Distributed processing of divisible jobs with communication startup costs,' Discrete Applied Mathematics, Vol. 76, pp. 21-41. 1997 https://doi.org/10.1016/S0166-218X(96)00115-1
  43. V. Bharadwaj, X. Li, and C. C. Ko, 'On the influence of start -up costs in scheduling divisible loads on bus networks,' IEEE Trans. Parallel and Distributed Systems, Vol. 11. pp. 1288-1305, 2000 https://doi.org/10.1109/71.895794
  44. S. Suresh, V. Mani. and S. N. Omkar. 'The effect of start up delays in scheduling divisible loads on bus networks: An alternate approach,' Computers and Mathematics with Applications, Vol. 46, pp. 1545-1557, 2003 https://doi.org/10.1016/S0898-1221(03)90190-8
  45. R. Agrawal, and H, V. Jagadish, 'Partitioning techniques for large-grained parallelism,' IEET Trans. Computers, Vol. 37, pp. 1627-1634, 1988 https://doi.org/10.1109/12.9739
  46. D. Ghose, and H.J, Kim, 'A generalized linear programming approach to optimal divisible load scheduling,' Technical Report KNU/CI/MSL/001/2004, Kangwon National University, Department of Control and Instrumentation, Chunchon, 200-701. Korea, 2004
  47. T. G. Robertazzi, 'Ten reasons to use divisible load theory,' IEEE Computer, pp. 63-68, May 2003