Lecture Notes in Computer Science, 2006, Volume 3984/2006, 762-771, DOI: 10.1007/11751649_84

Compiler-Optimized Kernels: An Efficient Alternative to Hand-Coded Inner Kernels

José R. Herrero and Juan J. Navarro

View Related Documents

Abstract

The use of highly optimized inner kernels is of paramount importance for obtaining efficient numerical algorithms. Often, such kernels are created by hand. In this paper, however, we present an alternative way to produce efficient matrix multiplication kernels based on a set of simple codes which can be parameterized at compilation time. Using the resulting kernels we have been able to produce high performance sparse and dense linear algebra codes on a variety of platforms.
This work was supported by the Ministerio de Ciencia y Tecnología of Spain (TIN2004-07739-C02-01).

Fulltext Preview

Image of the first page of the fulltext document