Algorithmic strategies for optimizing the parallel reduction primitive in CUDA

Proceedings of the 2012 International Conference on High Performance Computing and Simulation, HPCS 2012

Volumn , Issue , 2012, Pages 511-519

  Martín, Pedro J ^a   Ayuso, Luis F ^a   Torres, Roberto ^a   Gavilanes, Antonio ^a  

^a UNIVERSIDAD COMPLUTENSE DE MADRID   (Spain)

Author keywords

CUDA; data parallel algorithms; GPGPU; parallel reduction; segmented parallel reduction

Indexed keywords

ALGORITHM PERFORMANCE; ALGORITHMIC OPTIMIZATION; CUDA; DATA PARALLEL; DATA SEQUENCES; EXPERIMENTAL STUDIES; GPGPU; GRAPHICS PROCESSING UNITS; ON CURRENTS; REDUCTION ALGORITHMS; SEQUENTIAL METHODS; SINGLE-VALUE; TREE-BASED; TREE-BASED ALGORITHMS;

COMPUTER GRAPHICS; FORESTRY; OPTIMIZATION; PROGRAM PROCESSORS; THROUGHPUT; TREES (MATHEMATICS);

ALGORITHMS;

ALGORITHMS; COMPUTER GRAPHICS; DATA PROCESSING; OPTIMIZATION; THROUGHPUT;

EID: 84867024407     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/HPCSim.2012.6266966     Document Type: Conference Paper

References (17)

1. T. Aila and S. Laine, "Understanding the efficiency of ray traversal on GPUs," Proc. High Performance Graphics (HPG 09), ACM, 2009, pp. 145-149, DOI=10.1145/1572769.1572792.
2. M. Bauer, H. Cook, and B. Khailany, "CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization," Proc. Int. Conference for High Performance Computing, Networking, Storage and Analysis (SC '11), ACM, November 2011, DOI=10.1145/2063384.2063400.
3. N. Bell and M. Garland, "Efficient Sparse Matrix-Vector Multiplication on CUDA," NVIDIA TR NVR-2008-004, Dec. 2008.
4. G. E. Blelloch, Vector Models for Data-Parallel Computing, MIT Press, 1990.
5. G. E. Blelloch, "Prefix sums and their applications," Tech. Rep. CMUCS-90-190, School of Computer Science, Carnegie Mellon University, 1993.
6. CUDA data parallel primitives library (CUDPP). http://gpgpu.org/ developer/cudpp.
7. Y. Dotsenko, N. K. Govindaraju, P. Sloan, C. Boyd, and J. Manferdelli, "Fast scan algorithms on graphics processors," Proc. international conference on Supercomputing (ICS 08), ACM, 2008, pp. 205-213, DOI=10.1145/1375527.1375559.
8. General-Purpose Computation on Graphics Hardware http://gpgpu.org/
9. A. Gress, M. Guthe and R. Klein, "GPU-based collision detection for deformable parameterized surfaces," Computer Graphics Forum 25, 2006, pp. 497-506, DOI: 10.1111/j.1467-8659.2006.00969.x.
10. M. Harris, Optimizing Parallel Reduction in CUDA, (2007),H http://developer.download.nvidia.com/compute/cuda/1-1/Website/projects/ reduction/doc/reduction.pdf.
11. D. Horn, "Stream reduction operations for GPGPU applications," GPU Gems 2, M. Pharr (ed.), Addison Wesley, 2005, pp. 573-589.
12. P. J. Martín, R. Torres, and A. Gavilanes,. "CUDA Solutions for the SSSP Problem," Proc. International Conference on Computational Science (ICCS 09), Springer-Verlag, 2009, pp. 904-913, DOI=10.1007/978-3-642- 01970-8-91.
13. S. Sengupta, A. E. Lefohn and J. D. Owens, "A work-efficient stepefficient prefix sum algorithm," Proc. Edge Computing Using New Commodity Architectures, 2006, pp. 26-27.
14. S. Sengupta, M. Harris, Y. Zhang, and J. Owens, "Scan Primitives for GPU Computing," Proc. Graphics Hardware (GH 07), ACM, 2007, pp. 97-106.
15. S. Sengupta, M. Harris, HM. GarlandH, "Efficient Parallel Scan Algorithms for GPUs," H NVIDIA TR NVR-2008-003H, Dec. 2008.
16. W. Wang, Y. Huang and S. Guo, "Design and Implementation of GPU-Based Prim's Algorithm," Modern Education and Computer Science, 4, MECS-Press, 2011, pp 55-62.
17. K. Zhou, Q. Hou, R. Wang and B. Guo, "Real-time kd-tree construction on graphics hardware," Proc. ACM SIGGRAPH Asia 2008, ACM, 2008, pp. 1-11, DOI=10.1145/1457515.1409079.