Härdtlein J, Linke A, Pflaum C (2005)
Publication Type: Conference contribution, Conference Contribution
Publication year: 2005
Publisher: Springer-verlag
Edited Volumes: Lecture Notes in Computer Science
Series: Lecture Notes in Computer Science
Book Volume: 3515
Pages Range: 1055-1063
Conference Proceedings Title: Computational Science - ICCS 2005
Event location: Atlanta
ISBN: 3-540-26043-9
URI: https://www10.informatik.uni-erlangen.de/Publications/Papers/2005/Haerdtlein_ICCS05.pdf
Expression templates (ET) can significantly reduce the implementation effort of mathematical software. For some compilers, especially for those of supercomputers, however, it can be observed that classical ET implementations do not deliver the expected performance. This is because aliasing of pointers in combination with the complicated ET constructs becomes much more difficult. Therefore, we introduced the concept of enumerated variables, which are provided with an additional integer template parameter. Based on this new implementation of ET we obtain a C++ code whose performance is very close to the handcrafted C code. The performance results of these so-called Fast ET are presented for the Hitachi SR8000 supercomputer and the NEC SX6, both with automatic vectorization and parallelization. Additionally we studied the combination of Fast ET and OpenMP on a high performance Opteron cluster. © Springer-Verlag Berlin Heidelberg 2005.
APA:
Härdtlein, J., Linke, A., & Pflaum, C. (2005). Fast expression templates. Object-oriented high performance computing. In Dongarra J.J.; Sunderam V.S.; Sloot P.M.A.; Albada G.D. (Eds.), Computational Science - ICCS 2005 (pp. 1055-1063). Atlanta: Springer-verlag.
MLA:
Härdtlein, Jochen, Alexander Linke, and Christoph Pflaum. "Fast expression templates. Object-oriented high performance computing." Proceedings of the Fifth International Conference on Computational Science, Atlanta Ed. Dongarra J.J.; Sunderam V.S.; Sloot P.M.A.; Albada G.D., Springer-verlag, 2005. 1055-1063.
BibTeX: Download