Reducing thread divergence in a GPU-accelerated branch-and-bound algorithm

Concurrency and Computation: Practice and Experience

Volumn 25, Issue 8, 2013, Pages 1121-1136

  Chakroun, I ^a   Mezmaz, M ^b   Melab, N ^a   Bendjoudi, A ^c  

^a UNIV LILLE   (France)

^b UNIVERSITY OF MONS   (Belgium)

^c CERIST RESEARCH CENTER   (Algeria)

Author keywords

branch and bound algorithms; data parallelism; GPU computing; thread divergence

Indexed keywords

BRANCH AND BOUND METHOD; COMPUTER HARDWARE; PARALLEL ARCHITECTURES; PROGRAM PROCESSORS;

BRANCH-AND-BOUND ALGORITHMS; DATA PARALLELISM; DESIGN AND IMPLEMENTATIONS; FLOW-SHOP SCHEDULING; GPU COMPUTING; GRAPHICAL PROCESSING UNITS; SINGLE INSTRUCTION MULTIPLE DATA; THREAD DIVERGENCES;

GRAPHICS PROCESSING UNIT;

EID: 84876674988     PISSN: 15320626     EISSN: 15320634     Source Type: Journal    
DOI: 10.1002/cpe.2931     Document Type: Conference Paper

References (25)

1. Allen R, Cinque L, Tanimoto S, Shapiro L, Yasuda D,. A parallel algorithm for graph matching and its MasPar implementation. IEEE Transactions on Parallel and Distributed Systems 1997; 8 (5): 490-501.
2. Quinn MJ,. Analysis and implementation of branch-and-bound algorithms on a hypercube multicomputer. IEEE Transactions on Computers 1990; 39 (3): 384-387.
3. Casadoa LG, Martneza JA, Garcaa I, Hendrixb EMT,. Branch-and-bound interval global optimization on shared memory multiprocessors. Optimization Methods and Software 2008; 23 (5): 689-701.
4. Dongarra JJ, Bader DA, Kurzak J,. Scientific Computing with Multicore and Accelerators. CRC Press Inc, 2010. ISBN-10 143982536X, ISBN-13: 978-1439825365.
5. Luong TV, Melab N, Talbi E-G,. GPU computing for parallel local search metaheuristic algorithms. IEEE Transactions on Computers 2011. DOI: ieeecomputersociety.org/ 10.1109/TC.2011.206. IEEE Computer Society.
6. Taillard E,. Benchmarks for basic scheduling problems. Journal of Operational Research 1993; 64: 278-285.
7. Chakroun I, Bendjoudi A, Melab N,. Reducing thread divergence in GPU-based B&B applied to the Flow-shop problem. 9th International Conference on Parallel Processing and Applied Mathematics PPAM'11, Poland, Torun, September 11-14, 2011. (To appear).
8. Ryoo S, Rodrigues CI, Stone SS, Stratton JA, Ueng S-Z, Baghsorkhi SS, Hwu W-MW,. Program optimization carving for GPU computing. Journal of Parallel and Distributed Computing 2008; 68 (10): 1389-1401.
9. Fung W, Sham I, Yuan G, Aamodt T,. Dynamic warp formation and scheduling for efficient gpu control flow. MICRO '07: Proceedings of the 40th Annual IEEE/ACM International Symposium on Micro-architecture, Washington, DC, USA, 2007; 407-420.
10. Meng J, Tarjan D, Skadron K,. Dynamic warp subdivision for integrated branch and memory divergence tolerance. Proceedings of the 37th Annual International Symposium on Computer Architecture ISCA, New York, USA, 2010; 235-246.
11. Zhang EZ, Jiang Y, Guo Z, Shen X,. Streamlining GPU applications on the fly: thread divergence elimination through runtime thread-data remapping. In Proceedings of the 24th ACM International Conference on Supercomputing (ICS'10). ACM: New York, NY, USA, 2010; 115-126.
12. Han T, Abdelrahman TS,. Reducing branch divergence in GPU programs. In Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units (GPGPU-4). ACM: New York, USA, 2011; 1-8.
13. Garey MR, Johnson DS, Sethi R,. The complexity of flow-shop and job-shop scheduling. Mathematics of Operations Research 1976; 1: 117-129.
14. Lenstra JK, Lageweg BJ, Rinnooy Kan AHG,. A General bounding scheme for the permutation flow-shop problem. Operations Research 1978; 26 (1): 53-67.
15. Johnson SM,. Optimal two and three-stage production schedules with setup times included. Naval Research Logistis Quarterly 1954; 1: 61-68.
16. Melab N,. Contributions à la résolution de problèmes d'optimisation combinatoire sur grilles de calcul. HDR thesis, LIFL, USTL, Novembre 2005.
17. Nvidia CUDA C Programming Best Practices Guide. Available from: http://developer.download.Nvidia.com/compute/cuda/2\-3/toolkit/docs/Nvidia\ -CUDA\-BestPracticesGuide\-2.3.pdf [accessed on 19 January 2011].
18. Melab N, Chakroun I, Bendjoudi A,. GPU-accelerated bounding for branch-and-bound applied to a permutation problem using data access optimization. under submission in concurrency and computation: practice and experience-manuscript CPE-12-0085.
19. Mezmaz M, Melab N, Talbi E-G,. A grid-enabled branch and bound algorithm for solving challenging combinatorial optimization problems. Proceedings of 21th IEEE International Parallel and Distributed Processing Symposium (IPDPS), Long Beach, California, March 26th-30th, 2007.
20. Chakroun I, Melab N,. An adaptative multi-GPU-based branch-and-bound. A case study: the flow-shop scheduling problem. The 14th IEEE International Conference on High Performance Computing and Communications (HPCC-2012), Liverpool, England.
21. COMPUTE VISUAL PROFILER User Guide. Available from: http://developer. Nvidia.com/Nvidia-gpu-computing-documentation#VisualProfiler [accessed on 3 October 2011].
22. Alerstam E, Chun Yip Lo W, David Han T, Rose J, Andersson-Engels S, Lilge L,. Next-generation acceleration and code optimization for light transport in turbid media using GPUs. Biomedical Optics Express 2010; 1: 658-675.
23. Available from: http://www.Nvidia.com/docs/IO/43395/NV\-DS\-Tesla\-C2050\ -C2070\-jul10\-lores.pdf [accessed on 12 May 2012].
24. Available from: http://ark.intel.com/products/47933/Intel-Core-i7-970- Processor-\%2812M-Cache-3\-20-GHz-4\-80-GTs-Intel-QPI\%29 [accessed on 12 May 2012].
25. Available from: http://download.intel.com/support/processors/corei7/sb/ core\-i7-900\-d.pdf [accessed on 12 May 2012].