On Fri, 2012-07-06 at 11:29 +0200, Peter Meerwald wrote: > 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: Awesome! Looking forward to this. > - performance degradation on Cortex-A9 / pandaboard for remap: NEON is > fast on Cortex-A8 but slow on A9; need to distinguish Is this some sort of known A8 vs. A9 issue? > - reimplement using gcc inline assemlby instead of intrinsics (similar to > the SBC neon code) Whichever is easies to maintain would be best. :) > - fix issues in test code Hopefully we'll be able to move this to a standalone test based on Deng's work that you might've seen. > 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 ++, makes sense. -- Arun
