Re: [PATCH] WorkStruct: Implement generic UP cmpxchg() where an arch doesn't support it

[Russell King <rmk+lkml@arm.linux.org.uk>]

On Fri, Dec 08, 2006 at 09:06:00AM -0800, Christoph Lameter wrote:
> On Fri, 8 Dec 2006, David Howells wrote:
> 
> > > It is the most universal atomic instruction that I know of.
> > 
> > I think TAS-type things and XCHG-type things are more common.
> 
> Huh? The most popular architectures are i386 x86_64 sparc ia64 etc which 
> all have one or the other form of cmpxchg (some issues with early sparc 
> and i386).

According to the latest figures, 621 million ARM processors were
shipped in Q3, which equates to about 78 processors per second.
(taken from http://www.arm.com/news/15300.html).

I'd like to know the figures for these other so-called "popular
architectures".

But in any case that's an utterly irrelevant point to the argument
at hand.

> > In fact I think more things have LL/SC than have CMPXCHG.
> 
> LL/SC can be easily used to come up with a cmpxchg equivalent.

As proven previously the reverse is also true.  And as shown previously
the cheaper out of the two for all platforms is the LL/SC based
implementation, where the architecture specific implementation can
be _either_ LL/SC based or cmpxchg based depending on what is
supported in their hardware.

I'm going to keep saying this until people get it.

-- 
Russell King
 Linux kernel    2.6 ARM Linux   - http://www.arm.linux.org.uk/
 maintainer of:
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/