CULA: Hybrid GPU accelerated linear algebra routines

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 7705, Issue , 2010, Pages

  Humphrey, John R ^a   Price, Daniel K ^a   Spagnoli, Kyle E ^a   Paolini, Aaron L ^a   Kelmelis, Eric J ^a  

^a EM PHOTONICS INC   (United States)

Author keywords

Accelerated linear algebra; CULA; GPU; Graphics processing unit; Parallel computing

Indexed keywords

CODE SEGMENTS; EXECUTION MODEL; GPU; GRAPHICS PROCESSING UNIT; LEAST SQUARE; LINEAR ALGEBRA OPERATIONS; LU DECOMPOSITION; PARALLEL COMPUTING; PROCESSING MODEL; PROCESSING POWER; Q R DECOMPOSITION; SIMULTANEOUS OPERATION; SYSTEM SOLUTION;

ALGEBRA; COMPUTER SIMULATION; PARALLEL ARCHITECTURES; PERSONAL COMPUTERS; PROGRAM PROCESSORS; SINGULAR VALUE DECOMPOSITION;

COMPUTER GRAPHICS EQUIPMENT;

EID: 77953483096     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.850538     Document Type: Conference Paper

References (7)

1. www.netlib.org/blas/
2. www.netlib.org/lapack/
3. Volkov, V., and Demmel, J. W., "Benchmarking GPUs to tune dense linear algebra," In Proceedings of the 2008 ACM/IEEE Conference on Supercomputing. Conference on High Performance Networking and Computing. IEEE Press, Piscataway, NJ, 1-11.C. Jones, Director, Miscellaneous Optics Corporation, interview, Sept. 23, (2008
4. Price, D. K., Humphrey, J. R, Spagnoli, K. E., and Paolini, A. L. "Analyzing the Impact of Data Movement on GPU Computations," Presented at SPIE Defense and Security Symposium, April, (2010
5. http://developer.download.nvidia.com/compute/cuda/2-3/toolkit/docs/ CUBLAS-Library-2.3.pdf
6. Li, Y., Dongarra, J., Tomov, S. "A note on auto-tuning GEMM for GPUs," University of Tennessee Computer Science Technical Report, UT-CS-09-635, January 12, (2009
7. http://www.nvidia.com/object/fermi-architecture.html