> >
> > /*
> > + * Maximum numa importance can be 1998 (2*999);
> > + * SMALLIMP @ 30 would be close to 1998/64.
> > + * Used to deter task migration.
> > + */
> > +#define SMALLIMP 30
> > +
> > +/*
> >
> > /*
> > +* If the numa importance is less than SMALLIMP,
> > +* task
> >
> > /*
> > + * Maximum numa importance can be 1998 (2*999);
> > + * SMALLIMP @ 30 would be close to 1998/64.
> > + * Used to deter task migration.
> > + */
> > +#define SMALLIMP 30
> > +
> > +/*
> >
> > /*
> > +* If the numa importance is less than SMALLIMP,
> > +* task
* Srikar Dronamraju wrote:
> If numa improvement from the task migration is going to be very
> minimal, then avoid task migration.
>
> specjbb2005 / bops/JVM / higher bops are better
> on 2 Socket/2 Node Intel
> JVMS PrevCurrent %Change
> 4 200892 210118 4.59252
> 1 325766
* Srikar Dronamraju wrote:
> If numa improvement from the task migration is going to be very
> minimal, then avoid task migration.
>
> specjbb2005 / bops/JVM / higher bops are better
> on 2 Socket/2 Node Intel
> JVMS PrevCurrent %Change
> 4 200892 210118 4.59252
> 1 325766
If numa improvement from the task migration is going to be very
minimal, then avoid task migration.
specjbb2005 / bops/JVM / higher bops are better
on 2 Socket/2 Node Intel
JVMS PrevCurrent %Change
4 200892 210118 4.59252
1 325766 313171 -3.86627
on 2 Socket/4 Node Power8
If numa improvement from the task migration is going to be very
minimal, then avoid task migration.
specjbb2005 / bops/JVM / higher bops are better
on 2 Socket/2 Node Intel
JVMS PrevCurrent %Change
4 200892 210118 4.59252
1 325766 313171 -3.86627
on 2 Socket/4 Node Power8
6 matches
Mail list logo
