On quarta-feira, 23 de maio de 2012 23.44.57, Carsten Breuer wrote: > Hi Thiago, > > thanks for clearing this :-) > > >> I guess it depends a bit on if you want to yield to another thread or > >> not ;-). Of course: burning cpu time is another way to solve this ;-) > > > > According to the Intel manual, if you *don't* yield and you don't have the > > PAUSE instruction, you may make things worse. > > What do you exactly mean with a PAUSE instruction. Is this a assembler > processor command?
The PAUSE instruction on x86. I don't know of equivalent in other
architectures.
Trivia: the instruction is encoded as "REP NOP".
>
> > For one thing, if you don't yield, the processor will continue executing
> > your code, without giving a chance for other processes to run. There's no
> > guarantee even in a multiprocessor system that the other thread is
> > running. And even if it's running, if it was scheduled to another thread
> > on the same hyperthreaded core, the processor may not execute the that
> > thread because this thread still has instructions to execute.
>
> Interesting. Wouldn't it be better to change YieldCurrentThread?
> I guess, most of us are not aware of this and some of us
> learned in the 386 century that give back CPU performance to the OS is
> always a good thing. I guess it is even nowadays a good thing on single
> core machines. Isn't it?
The yieldCurrentThread call is a system call: it tells the OS to think about
scheduling another thread. The PAUSE instruction is a processor-only hint.
They have different purposes and we should benchmark.
--
Thiago Macieira - thiago.macieira (AT) intel.com
Software Architect - Intel Open Source Technology Center
Intel Sweden AB - Registration Number: 556189-6027
Knarrarnäsgatan 15, 164 40 Kista, Stockholm, Sweden
signature.asc
Description: This is a digitally signed message part.
_______________________________________________ Development mailing list Development@qt-project.org http://lists.qt-project.org/mailman/listinfo/development
