|Using extra outputs of an instruction email@example.com (Dobes Vandermeer) (2002-03-09)|
|Re: Using extra outputs of an instruction firstname.lastname@example.org (2002-03-11)|
|Re: Using extra outputs of an instruction email@example.com (2002-03-17)|
|Re: Using extra outputs of an instruction firstname.lastname@example.org (Michael Meissner) (2002-03-21)|
|Re: Using extra outputs of an instruction email@example.com (David Chase) (2002-03-22)|
|Re: Using extra outputs of an instruction firstname.lastname@example.org (Bo Persson) (2002-03-24)|
|From:||"Bo Persson" <email@example.com>|
|Date:||24 Mar 2002 00:17:24 -0500|
|References:||02-03-017 02-03-133 02-03-152|
|Posted-Date:||24 Mar 2002 00:17:24 EST|
"David Chase" <firstname.lastname@example.org> skrev i meddelandet
>> [The XCHG instruction only locks the bus if it has a LOCK prefix,
>> but it's slow anyway. -John]
> Careful -- some architectures, the exchange-with-memory operation (not
> sure how it is spelled, since it is an assembler mnemnonic anyway)
> does implicitly lock the bus. Pentium is one example of this.
> CMPXCHG (Pentium-speak for Compare-and-swap) does not, and does
> require a prefix.
It's even worse than that!
Pre-Pentium implementations of the same architecture indeed required a
LOCK prefix to lock the bus. Intel "fixed" that with an automatic lock
for XCHG and then had to invent a new instruction for those who really
didn't want the lock.
Nice and smooth. :-)
Return to the
Search the comp.compilers archives again.