[PATCH v4 2/2] add icswx support

Tseng-Hui (Frank) Lin thlin at linux.vnet.ibm.com
Sat Mar 5 10:07:33 EST 2011


On Sat, 2011-03-05 at 09:40 +1100, Benjamin Herrenschmidt wrote:

> > The lazy switching checks the shadow variable first before setting ACOP
> > register. This saves mtspr() only if the new value is the same as
> > current. If there are several coprocessors on the system, the ACOP
> > register may have to be changed frequently. In that case, the lazy
> > switching will not save time. In extreme case when the ACOP register
> > needs to be changed every time, it actually slows down the execution by
> > the additional shadow variable checking.
> 
> By how much ? Is it even measurable ?
> 
I don't have any measurable numbers. That's why I made it an option in
case people wants to disable it. I do agree that the kernel has so many
options that we should refrain from adding more. If the chance that the
lazy switching slows down the execution is really low, we should just
take out the option. Is there any one has an idea how much the numbers
are?

> Cheers,
> Ben.
> 
> 
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev at lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev




More information about the Linuxppc-dev mailing list