Well I’ve finally finished the write-up for my Altivec vs SSE testing. Believe it or not its quite an interesting read (Even if I do say so myself) and if you’ve ever wondered about what exactly SIMD is then its not a bad place to start.
The report is available here
michael says:
Nice one brother!! Are you planning on publishing this? It’d make a really informative paper at a conference etc.
Kurt Christensen says:
This is a nice informative paper. It is worthwhile noting that the algorithm chosen employs a divide instruction that Altivec does not provide. As a companion to this experiment, I would like to see a similar comparison in either image processing, cellular atomata or neural networks, resting heavily on multiplies instead of divides.
No more pink walls » Blog Archive » SIMD Part 2 says:
[…] [Update]: The final results from this work can be found at http://noisymime.org/blog/?p=20Â […]