[cpp-threads] modes

[Alexander Terekhov]

On 5/7/05, Peter Dimov <pdimov at mmltd.net> wrote:
> Doug Lea wrote:
> 
> > One question is whether distinguishing CAS.none buys you anything vs
> > CAS.rel wrt performance on current or plausible future platforms.
> > Which I think is mainly another empirical question about PPC-smps. (I
> > don't have one around to check either.)
> 
> I think that the answer here is almost certainly "yes" (maybe even with
> capital letters), because PPC CAS.rel is CAS.none prefixed with (lw)sync,

Likewise, under (hypothetical) Sparc RMO, CAS.rel is CAS.none 
prefixed with LoadStore + StoreStore (or LoadLoad + StoreLoad (or 
LoadStore + StoreLoad (or LoadLoad + StoreStore))). I mean that 
"gcc/gas" for Sparc RMO can safely spare that membar prefix 
instruction in the case of CAS.none for (hypothetical) Sparc RMO.

regards,
alexander.