Hello, > Can you give a status update: what remains to be done before these > patches can be merged? I am glad you asked; I am working on a v3 these days to address the following issues: - performance degradation on Cortex-A9 / pandaboard for remap: NEON is fast on Cortex-A8 but slow on A9; need to distinguish - reimplement using gcc inline assemlby instead of intrinsics (similar to the SBC neon code) - fix issues in test code remap and sconv is complete, working on svolume now; you'll see something really-soon-now (early next week probably) I do not plan to work on the configuration system now: an open issue is runtime configuration, i.e. compile with NEON support and decide at runtime if NEON is available or not -- I hope this can be addressed later-on regards, p. > On Thu, 2012-03-15 at 14:21 +0100, Peter Meerwald wrote: > > Hello Arun, > > > > > FWIW, you can get a Gentoo rootfs (stage3) snapshot at -- > > > http://gentoo.osuosl.org/releases/arm/autobuilds/ > > > > ah, this is useful > > I have produced a hardfp rootfs using buildroot, but it is good to have > > the same environment > > > > > Given that this is a complicated change, I'd like to push merging this > > > to after 2.0. Unfortunately I've not had enough free time to look at > > > your patches for a while, and I'm sorry about the delay. Hopefully we > > > can iron out the kinks and get this merged early in the 3.0 cycle. > > > > I also have other priorities ATM; one option would be to drop the remap > > patch for now and just keep sconv and svolume; I think sconv is most > > useful for the moment as the default resampler is speex in float mode, > > float->s16 conversion is likely to happen -- but that's up to you > > > > I will do more testing early April > > > > regards, p. > > > > -- Peter Meerwald +43-664-2444418 (mobile)
