On Thu, Jul 31, 2008 at 09:46:52AM -0500, keith preston wrote: > > Marvell Xscale processor family provides some SSE-like instructions, and > > others ARM vendor may have different solution on SIMD and vector. > > If you look at > http://developer.garmin.com/linux/nuvi-8xx-series/ > They actually use the marvell processor and a specific resampler and > mixer written for the process. Nice! I will try it definitely. > > > I think > > a generic ARM implementation is better for open source, as Nick said. On > > the other hand, it is great to have some plugin interfaces for users to > > insert their own resampler and mixing functions. The ARM vendor > > usually provides some optimized functions based on their architecture. > > So I like the resampler implementation very well, and I could insert my > > routines to replace the one in PA. > > > > The resampler is already pluggable, I just think that the mixer should > also be pluggable. I expect the feature too. One more optimization (this probably not a good idea) is to do resampling and mixing in a loop, but PA seperates resampler and mixer into sink input and sink. -- Stanley Cai Gtalk: stanley.w.cai at gmail.com GnuPG: 0x86A5B367
