Subj : Re: What is the real costs of LOCK on x86 multiprocesor machine?
To   : comp.programming.threads
From : Mirek Fidler
Date : Fri Jul 29 2005 07:36 pm

>>Measuring the same on my uniprocesor AMD64 machine, LOCKed instructin
>>seem to be 3 times slower than regular one, but I guess that has only a
>>little relevance on real MP machine.
> 
> 
> Surprisingly, on Intel Pentium processors the overhead of
> a locked instruction is about the same for a single processor
> as for one in a multiple processor configuration.

Hm, can you give me some numbers? Is it closer to my measurement (3 
times slower than non-atomic) or to 100 cycles I have seen somewhere?

> 
> The way Microsoft (for example) avoid the performance hit is
> to replace the LOCK prefixes in uniprocessor builds of their
> operating system binaries with NOP instructions.

I stepped through InterlockedIncrement and there definitely IS lock.

Mirek

.