[FFmpeg-devel] [PATCH] Faster CABAC H.264 residual decoding

[Siarhei Siamashka]

On Monday 28 April 2008, Ian Caulfield wrote:
> On Sun, Apr 27, 2008 at 12:38 PM, Siarhei Siamashka
>
> <siarhei.siamashka at gmail.com> wrote:
> >  Yes, I'm well aware of it. And I'm sorry for nitpicking, but you
> > probably wanted to say ARM11? As there may be other microarchitectures
> > compatible with ARMv6 ISA (Cortex cores are coming). I used words "some"
> > and "may" on purpose just because interlock behaviour is different for
> > different cores.
>
> Cortex cores are all ARMv7 (except the -M0, but that's v6M anyway...)

ARMv6 is a subset of ARMv7.

The general idea was that ARMv6, ARMv7, ARMv5TE are all just instruction 
sets and such things as cycle counts, latencies or interlocks are not 
directly applicable to them (this stuff is related to some specific
implementations in silicon such as ARM7, ARM9, ARM11, XScale, Cortex-A8,
Cortex-A9, ...)

Anyway, it is great getting more ARM experts around ;) So we can hope that
with more people around, more ARM specific performance optimizations can get
added to FFmpeg. And also new stuff like this faster CABAC patch will get
benchmarked in addition to having nice theoretical discussions, am I right?

Who is up to run some benchmark for this patch on ARM?

-- 
Best regards,
Siarhei Siamashka