Michael S (already5chosen.delete@this.yahoo.com) on February 21, 2019 2:25 am wrote:
> juanrga (noemail.delete@this.juanrga.com) on February 21, 2019 1:28 am wrote:
> > nobody in particular (nobody.delete@this.nowhe.re) on February 20, 2019 7:35 am wrote:
> > > Write-up at Anandtech
> > >
> > > The stated SPECint numbers are superb. I'm looking forward
> > > to spec2017, but this is a very, very promising start.
> >
> > 64C Neoverse with similar performance to 64C Rome but on half the power, and the platform scales up to 128C
> >
> > https://community.arm.com/processors/b/blog/posts/arm-neoverse-n1-platform-accelerating-the-transformation-to-a-scalable-cloud-to-edge-infrastructure?_ga=2.136797808.1352467979.1550509544-2036853662.1547133064
> >
> > Where are now all those that said that ARM couldn't scale up
> > or that if it did, it would lose all efficiency advantage?
>
> Your biggest problem, as RWT poster, always was lack of understanding
> of the differences between paper and silicon.
>

I think that’s unfair. The real difference, it seems to me, is between the people who can (reasonably accurately) extrapolate what’s coming (based on the literature and on what *trustworthy* companies have announced) and those who insist that nothing different is ever possible until the day after it ships...