Subject: Re: [linux-audio-dev] lock-free ring buffer code
From: Steve Harris (S.W.Harris_AT_ecs.soton.ac.uk)
Date: Sat Apr 05 2003 - 20:08:51 EEST
On Sat, Apr 05, 2003 at 06:15:09 +0200, Ingo Oeser wrote:
> Now make that thread-safe and esp. thread-safe on an architecture
> with weak memory ordering and all the fun stuff.
Sure, it will only work on architectures where 32bit reads and writes are
atomic.
> If you have that all working and look at the assembly, then my
> solution is actually smaller, since all your pointer updates are
> required to be atomic anyway and that's what we tryed to optimize
> away here.
Smalled is not the issue, its branches that are important in inner loops.
> Yes, your solution is a perfect DSP-chip or hardware solution. It
> is even nice for ix86, if you have a not that optimizing
> compiler.
I dont think compiler will optimise away the trhread safeness, unless I've
missed something. A vectorising compiler might unroll the loops but it
will still keep the ordering, and the aligned vector operations are still
atomic AFAIK.
- Steve
This archive was generated by hypermail 2b28 : Sat Apr 05 2003 - 20:07:26 EEST