From: Andrew B. <an...@ca...> - 2012-11-28 11:07:20
|
Hi Sylvain, On 28 November 2012 09:56, Sylvain Munaut <24...@gm...> wrote: >> Could anyone tell me which code/algorithms would benefit from being >> targeted to a parallel (single precision) floating point architecture? >> With this information I can see if there is interest in providing >> support. > > All the SDR stuff ... > > You have resampling & filtering (and channelizing in multi ARFCN > setup) which is expensive. > The other thing would be burst demodulation. > > Above that it's not really floating point anymore. > > Since the parellala can do int as well, you could directly take the > result of the demod and apply the inverse channel coding,, but from an > architecture point of view this is not going to be easy because in > OpenBTS those two steps don't even happen in the same unix process ... Is it possible to point to particular code in SVN, or would there be a reasonable amount of work in just identifying this? I guess if just one or two of the most compute intensive parts could be identified that would be a start. Cheers, Andrew -- Andrew Back http://carrierdetect.com |