libSIMD

Last updated 4th April 2005
Copyright (C) 2001-2005 by Iain Nicholson

No ePatents!Fight software patents in Europe!

Software patents may make Free and Open Source software impossible to produce legally. They also may slow software developemt, and therefore the technological progress of society in general, to a crawl. Small and medium-sized companies, hobbiests and those who believe in Free Software will no longer be able to participate in an already highly-biased market.

Abstract

Mathematical library utilising SIMD features of common processors to accelerate many commonly-used algorithms where compilers fear to tread.

Kindly hosted by SourceForge.net Logo

Status

After a long haitus, libSIMD development has restarted. Initially, the project had lofty goals to become a comprehensive mathematical library implementing as many useful functions as possible, in C for portability, and in various SIMD instruction sets (using the gcc inline assembler) for optimum performance on a wide range of processors.

Due to professional commitments and possible legal issues, there has been little development recently, however circumstances have changed allowing development to resume.

Just now, efforts are being targetted on cleaning up the source and fixing bugs. SSE and SSE2 implementations of basic functions are in development.

Get the Source

Go here to browse the CVS archive. Alternatively, you can download a source tarball by following the links here. Note that the CVS tree will probably be more up-to-date, but the source tarball should compile and run the test out of the box.

Contact

Email me (Iain Nicholson) as ijnicholson at users dot sourceforge dot net. I would be pleased to recieve constructive feedback, especially ideas for extra functions to implement, or what you would (or have) found useful.

Acknowledgements

3DNow!, SSE, SSE2, AltiVec, Velocity Engine and VIS are all registered trademarks.

Developed on Slackware Linux using anjuta.