Knowledge discovery in auto-tuning parallel numerical library. (English) Zbl 1052.68668

Kuroda, Hisayasu; Katagiri, Takahiro; Kanada, Yasumasa

Arikawa, Setsuo (ed.) et al., Progress in discovery science. Final report of the Japanese discovery science project. Berlin: Springer (ISBN 3-540-43338-4). Lect. Notes Comput. Sci. 2281, 628-639 (2002).

Summary: This paper proposes the parallel numerical library called ILIB which realises auto-tuning facilities with selectable calculation kernels, communication methods between processors, and various number of unrolling for loop expansion. This auto-tuning methodology has advantage not only in usability of library but also in performance of library. In fact, results of the performance evaluation show that the auto-tuning or auto-correction feature for the parameters is a crucial technique to attain high performance. A set of parameters which are auto-selected by this auto-tuning methodology gives us several kinds of important knowledge for highly efficient program production. These kinds of knowledge will help us to develop some other high-performance programs, in general.
For the entire collection see [Zbl 0988.00034].

MSC:

68T05	Learning and adaptive systems in artificial intelligence
65Y99	Computer aspects of numerical algorithms

Software:

ScaLAPACK; ATLAS; PHiPAC