juanrga (nospam.delete@this.juanrga.com) on August 12, 2014 11:19 am wrote:
> Klimax (danklima.delete@this.gmail.com) on August 12, 2014 6:29 am wrote:
> > juanrga (nospam.delete@this.juanrga.com) on August 12, 2014 2:21 am wrote:
> > > Klimax (danklima.delete@this.gmail.com) on August 11, 2014 10:06 pm wrote:
> > > > juanrga (nospam.delete@this.juanrga.com) on August 11, 2014 7:00 pm wrote:
> > > > > David Kanter (dkanter.delete@this.realworldtech.com) on August 10, 2014 9:12 pm wrote:
> > > > > > > 20--30% sounds as the right efficiency numbers at that level. Precisely 90W
> > > > > > > ARM SoCs are providing around 80--90% of performance of 140W Haswell Xeons.
> > > > > >
> > > > > > Seriously dude. What 90W ARM server chip is providing performance to customers?
> > > > > >
> > > > > > Let me remind you that server chips must be implemented in
> > > > > > silicon, not power point to provide value to customers.
> > > > > >
> > > > > > And I'm quite willing to bet that no ARM server design in
> > > > > > the next 2-3 years will provide 80% of the performance
> > > > > > of the highest bin Xeon. If they are lucky, they might get to the low-end territory. They probably also
> > > > > > won't have as much memory capacity and generally be inferior across a number of dimensions.
> > > > > >
> > > > > > DK
> > > > >
> > > > > First, you pretended that you didn't hear of any high-performance
> > > > > ARM design, despite many being announced in many places.
> > > > >
> > > > > Then you ignored the specs given to you for one of those designs.
> > > > >
> > > > > Now you ignore any announcement made about "memory capacity": native support for DDR4-2400MHz, "about
> > > > > the same memory bandwidth as a Sandy Bridge Xeon E5", a maximum of 64 GB of memory for SoC...
> > > > >
> > > > > Stop pretending this is low-end territory, it is not:
> > > > >
> > > > > http://www.techweekeurope.co.uk/news/cavium-arm-server-146626
> > > > >
> > > > > http://blogs.nvidia.com/blog/2014/06/24/nvidia-gpu-arm-hpc/
> > > > >
> > > > > http://www.electronicsweekly.com/news/components/microprocessors-and-dsps/applied-micros-x-gene-challenges-server-processor-market-2014-08/
> > > > >
> > > > >
> > > > No data and not shipping yet. So far there is nothing. There were number of claims,
> > > > nothing survived. Get back when it will ship and evidence will exist.
> > > >
> > > > For now it is as good as vaporware.
> > >
> > > Several products and demos were shown during last supercomputer conference, and some are already shipping.
> > >
> > > Seriously guys stop this anti-ARM charade.
> >
> > Where is evidence that they are shipping. Where is evidence of their performance and consumption! WHERE?
> >
> > Demos are useless. They are not indicative of anything. There are not evidence for shipping hardware.
> > Or we could look outright at Broadwell and Airmont or various other things in development in Intel.
> >
> > There is no anti-ARM anything. Just your imagination.
>
> There is an evident anti-ARM crow here: the same people who brings Skylake to the discussion don't want discuss
> ARM cores scheduled for the same year, the same people who uses Intel slides to get an idea about the performance
> of Xeon Phi, reject slides from competence; data and information given are systematically ignored...

Take complaint about use of Skylake to appropriate subthread, it is not relevant to this one. And slides are slideware and as useful. (Not at all) Scheduled = not shipping. Unknown and definitely unproven.