[pulseaudio-discuss] [PATCH 1/6 v3] core: Initialize ARM NEON code if available

Arun Raghavan arun.raghavan at collabora.co.uk
Mon Oct 15 22:19:34 PDT 2012


On Tue, 2012-07-24 at 10:20 +0200, Peter Meerwald wrote:
> From: Peter Meerwald <p.meerwald at bct-electronic.com>
> 
> Signed-off-by: Peter Meerwald <p.meerwald at bct-electronic.com>
> ---

Surprise! I'm reviewing this now. :p

Some general general questions:

1. v3 drops intrinsics in favour of inline asm -- is that for
performance reasons?

2. In the mono->stereo float case, the Cortex A9 code is actually
slower. I recall that in a previous thread, we had this sort of
situation on one of Panda/Beagleboard. Do we need some way to pick and
choose implementations?

3. How shall we go about enabling this code? Have a configure time check
for some instructions that are needed, build it in if available, and
then run-time detection should pick the right code path?

I'll take a closer look at things, run some tests, and start pushing
this work. I'll also be moving all the test code to src/tests/cpu-test.c
where the x86 tests have been consolidated, so running tests on
different boards should become a lot less painful.

Thank you very much for your patience!

Cheers,
Arun



More information about the pulseaudio-discuss mailing list