By: bakaneko (nyan.delete@this.hyan.wan), May 22, 2013 3:42 am
Room: Moderated Discussions
anon (anon.delete@this.anon.com) on May 21, 2013 4:54 pm wrote:
> David Kanter (dkanter.delete@this.realworldtech.com) on May 21, 2013 1:54 pm wrote:
> > > The thing is that Intel already knows how to do good, performant, power efficient cores.
> > > There is two decades of experience there, you don't *need* to go back to Pentium core.
> > >
> > > They could have started with a pentium-m ish core, and probably had a much easier ability to take improved
> > > structures from later cores and even share their own improvements back to the high performance line.
> >
> > I don't think that's true. The fundamental structures for
> > memory and instruction reordering in the P6-derivatives
> > and Silvermont are VERY different.]
>
> No, I'm talking about the first Atom microarchitecture. If the requirement was a quick turnaround time
> with a small team, it would seem better to start with a Yonah core than to start with a P54 core.
That doesn't matter. Quick turnaround is
about only playing the realistic cards
however bad the outcome.
It is bad if you can't produce the chip
without interrupting production. And it
is bad if you don't have people available
with the right knowledge and experience
to tweak an existing core for the new
targets.
> David Kanter (dkanter.delete@this.realworldtech.com) on May 21, 2013 1:54 pm wrote:
> > > The thing is that Intel already knows how to do good, performant, power efficient cores.
> > > There is two decades of experience there, you don't *need* to go back to Pentium core.
> > >
> > > They could have started with a pentium-m ish core, and probably had a much easier ability to take improved
> > > structures from later cores and even share their own improvements back to the high performance line.
> >
> > I don't think that's true. The fundamental structures for
> > memory and instruction reordering in the P6-derivatives
> > and Silvermont are VERY different.]
>
> No, I'm talking about the first Atom microarchitecture. If the requirement was a quick turnaround time
> with a small team, it would seem better to start with a Yonah core than to start with a P54 core.
That doesn't matter. Quick turnaround is
about only playing the realistic cards
however bad the outcome.
It is bad if you can't produce the chip
without interrupting production. And it
is bad if you don't have people available
with the right knowledge and experience
to tweak an existing core for the new
targets.