Performance models for asynchronous data transfers on consumer Graphics Processing Units

Journal of Parallel and Distributed Computing

Volumn 72, Issue 9, 2012, Pages 1117-1126

  Gómez Luna, Juan ^a   González Linares, José María ^b   Benavides, José Ignacio ^a   Guil, Nicolás ^b  

^a UNIVERSITY OF CÓRDOBA   (Spain)

^b UNIVERSITY OF MÁLAGA   (Spain)

Author keywords

Asynchronous transfers; CUDA; GPU; Overlapping of communication and computation; Streams

Indexed keywords

APPLICATION PROGRAMMING INTERFACES (API); APPLICATION PROGRAMS; COMPUTER GRAPHICS; COMPUTER GRAPHICS EQUIPMENT; DATA TRANSFER; MEMORY ARCHITECTURE; PROGRAM PROCESSORS; SOFTWARE DESIGN;

ASYNCHRONOUS DATA TRANSFERS; ASYNCHRONOUS TRANSFERS; COMPUTE UNIFIED DEVICE ARCHITECTURE(CUDA); CUDA; HIGH-PERFORMANCE COMPUTING APPLICATIONS; PERFORMANCE BOTTLENECKS; SOFTWARE DEVELOPMENT KIT; STREAMS;

GRAPHICS PROCESSING UNIT;

EID: 84865705401     PISSN: 07437315     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jpdc.2011.07.011     Document Type: Article

References (20)

1. Sara S. Baghsorkhi, Matthieu Delahaye, Sanjay J. Patel, William D. Gropp, Wen-mei W. Hwu, An adaptive performance modeling tool for GPU architectures, in: Proceedings of the 15th ACM SIGPLAN Smposium on Principles and Practice of Parallel Programming, PPoPP'10, ACM, New York, NY, USA, 2010, pp. 105-114.
2. Juan Gómez-Luna, José María González-Linares, José Ignacio Benavides, Nicolás Guil, Parallelization of a video segmentation algorithm on CUDAenabled graphics processing units, in: Proc. of the Int'l Euro-Par Conference on Parallel Processing, EuroPar'09, 2009, pp. 924-935.
3. Juan Gómez-Luna, José María González-Linares, José Ignacio Benavides, Nicolás Guil, Performance models for CUDA streams on NVIDIA GeForce series, Technical Report, University of Málaga, 2011. http://www.ac.uma.es/~vip/publications/UMA-DAC-11-02.pdf.
4. Wan Han, Gao Xiaopeng, Wang Zhiqiang, Li Yi, Using GPU to accelerate cache simulation, in: IEEE International Symposium on Parallel and Distributed Processing with Applications, 2009, pp. 565-570.
5. Sunpyo Hong, Hyesoon Kim, An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness, in: Proceedings of the 36th Annual International Symposium on Computer Architecture, ISCA'09, ACM, New York, NY, USA, 2009, pp. 152-163.
6. Amir H. Hormati, Mehrzad Samadi, Mark Woh, Trevor Mudge, Scott Mahlke, Sponge: portable stream programming on graphics engines, in: Proceedings of the Sixteenth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS'11, ACM, New York, NY, USA, 2011, pp. 381-392.
7. Khronos Group, OpenCL. http://www.khronos.org/opencl/.
8. Supada Laosooksathit, Chokchai B. Leangsuksun, Abdelkader Baggag, Clayton F. Chandler, Stream experiments: toward latency hiding in GPGPU, in: Proceedings of the 9th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN'10, 2010, pp. 240-248.
9. Vladimir Marjanović, Jesús Labarta, Eduard Ayguadé, Mateo Valero, Overlapping communication and computation by using a hybrid MPI/SMPSS approach, in: Proceedings of the 24th ACM International Conference on Supercomputing, ICS'10, ACM, New York, NY, USA, 2010, pp. 5-16.
10. MPI Forum, The Message Passing Interface Standard. http://www.mpiforum. org/.
11. NVIDIA, CUDA C best practices guide 3.2, August 2010. http://developer.download.nvidia.com/compute/cuda/3-2/toolkit/docs/ CUDA-C-Best-Practices-Guide.pdf.
12. NVIDIA, CUDA C programming guide 3.2, September 2010. http://developer.download.nvidia.com/compute/cuda/3-2/toolkit/docs/ CUDA-C-Programming-Guide.pdf.
13. NVIDIA, CUDA SDK code samples: matrix multiplication. http://developer.download.nvidia.com/compute/cuda/sdk/website/samples. html#matrixMul.
14. NVIDIA, CUDA Zone. http://www.nvidia.com/object/cuda-home-new.html.
15. Peripheral Component Interconnect Special Interest Group, PCI Express. http://www.pcisig.com/.
16. James C. Phillips, John E. Stone, Klaus Schulten, Adapting a message-driven parallel application to GPU-accelerated clusters, in: Proceedings of the 2008 ACM/IEEE Conference on Supercomputing, SC'08, IEEE Press, Piscataway, NJ, USA, 2008, pp. 8:1-8:9.
17. V. Podlozhnyuk, Histogram calculation in CUDA, White Paper, 2007. http://developer.download.nvidia.com/compute/cuda/1-1/Website/projects/ histogram256/doc/histogram.pdf.
18. Abhishek Udupa, R. Govindarajan, Matthew J. Thazhuthaveetil, Synergistic execution of stream programs on multicores with accelerators, in: Proceedings of the 2009 ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems, LCTES'09, ACM, New York, NY, USA, 2009, pp. 99-108.
19. Ta Quoc Viet, Tsutomu Yoshinaga, Improving linpack performance on SMP clusters with asynchronous MPI programming, IPSJ Digital Courier 2 (2006) 598-606.
20. Yao Zhang, John D. Owens, A quantitative performance analysis model for GPU architectures, in: Proceedings of the 17th IEEE International Symposium on High-Performance Computer Architecture, HPCA 17, February 2011.