Profile-Driven Automated Mixed Precision
作者： Daniel J. Sorin , Helia Naeimi , Xiaobai Sun , Ralph Nathan
DOI:
关键词: Scheme (programming language) 、 Floating point 、 Measure (mathematics) 、 Mathematical optimization 、 Mixed precision 、 Algorithm 、 Set (abstract data type) 、 Computer science 、 Range (statistics)
摘要: We present a scheme to automatically set the precision of floating point variables in an application. design framework that profiles applications measure undesirable numerical behavior at operation level. use this perform mixed analysis heuristically all application based on their profiles. experimentally evaluate show it can generate range results with different accuracy and performance characteristics.
arxiv.org
harvard.edu参考文章(22)
Robert Strzodka, Dominik G, Mixed Precision Methods for Convergent Iterative Schemes ,(2006)
Hartwig Anzt, Björn Rocker, Vincent Heuveline, Energy Efficiency of Mixed Precision Iterative Refinement Methods using Hybrid Hardware Platforms: An Evaluation of different Solver and Hardware Configurations Computer Science - Research and Development. ,vol. 25, pp. 141- 148 ,(2010) , 10.1007/S00450-010-0124-2
Earl T. Barr, Thanh Vo, Vu Le, Zhendong Su, Automatic detection of floating-point exceptions Proceedings of the 40th annual ACM SIGPLAN-SIGACT symposium on Principles of programming languages - POPL '13. ,vol. 48, pp. 549- 560 ,(2013) , 10.1145/2429069.2429133
Dominik Goddeke, Robert Strzodka, Cyclic Reduction Tridiagonal Solvers on GPUs Applied to Mixed-Precision Multigrid IEEE Transactions on Parallel and Distributed Systems. ,vol. 22, pp. 22- 32 ,(2011) , 10.1109/TPDS.2010.61
Marc Baboulin, Alfredo Buttari, Jack Dongarra, Jakub Kurzak, Julie Langou, Julien Langou, Piotr Luszczek, Stanimire Tomov, Accelerating Scientific Computations with Mixed Precision Algorithms Computer Physics Communications. ,vol. 180, pp. 2526- 2533 ,(2009) , 10.1016/J.CPC.2008.11.005
T. G. Robertazzi, S. C. Schwartz, Best “ordering” for floating-point addition ACM Transactions on Mathematical Software. ,vol. 14, pp. 101- 110 ,(1988) , 10.1145/42288.42343
Florian Benz, Andreas Hildebrandt, Sebastian Hack, A dynamic program analysis to find floating-point accuracy problems programming language design and implementation. ,vol. 47, pp. 453- 462 ,(2012) , 10.1145/2254064.2254118
Tao Bao, Xiangyu Zhang, On-the-fly detection of instability problems in floating-point program execution conference on object oriented programming systems languages and applications. ,vol. 48, pp. 817- 832 ,(2013) , 10.1145/2509136.2509526
Xuejun Hao, Amitabh Varshney, Variable-precision rendering Proceedings of the 2001 symposium on Interactive 3D graphics - SI3D '01. pp. 149- 158 ,(2001) , 10.1145/364338.364384
J. D. Hogg, J. A. Scott, A fast and robust mixed-precision solver for the solution of sparse symmetric linear systems ACM Transactions on Mathematical Software. ,vol. 37, pp. 17- ,(2010) , 10.1145/1731022.1731027