Automatically tuned linear algebra software

DMCA

Automatically tuned linear algebra software (1998)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by R. Clint Whaley , Jack J. Dongarra

Venue:	CONFERENCE ON HIGH PERFORMANCE NETWORKING AND COMPUTING
Citations:	478 - 26 self

BibTeX

@INPROCEEDINGS{Whaley98automaticallytuned,
    author = {R. Clint Whaley and Jack J. Dongarra},
    title = {Automatically tuned linear algebra software},
    booktitle = {CONFERENCE ON HIGH PERFORMANCE NETWORKING AND COMPUTING},
    year = {1998},
    pages = {1--27},
    publisher = {IEEE Computer Society}
}

OpenURL

Abstract

This paper describes an approach for the automatic generation and optimization of numerical software for processors with deep memory hierarchies and pipelined functional units. The production of such software for machines ranging from desktop workstations to embedded processors can be a tedious and time consuming process. The work described here can help in automating much of this process. We will concentrate our e orts on the widely used linear algebra kernels called the Basic Linear Algebra Subroutines (BLAS). In particular, the work presented here is for general matrix multiply, DGEMM. However much ofthe technology and approach developed here can be applied to the other Level 3 BLAS and the general strategy can have an impact on basic linear algebra operations in general and may be extended to other important kernel operations.

Keyphrases

linear algebra software deep memory hierarchy embedded processor linear algebra kernel numerical software general matrix multiply functional unit automatic generation desktop workstation important kernel operation basic linear algebra operation basic linear algebra subroutine general strategy

DMCA