[Arm-netbook] SoC warp soldering risk?

Bill Kontos vkontogpls at gmail.com
Fri Apr 28 12:31:31 BST 2017


Where does the 40% improvement come from ? I remember watching a video from
 Berkeley student where the improvement was "only" 11%.

The kirin 960 was a complete fail on their part. They downgraded the
manufacturing node to one that has a lower frequency sweetspot but lower
cost as well... still 14nm for whatever it's worth these days. On top of
that, and especially on the gpu side they have very aggressive clock steps,
even missing the efficiency sweet spot and resulting in peak draws of up to
10 watts. All for benchmarks on reviewing websites, most reviews just run a
benchmark once and show the result but do not test overheating. Totally not
suitable for eoma, no matter how much of a sucker for high performance I
am.

On Fri, Apr 28, 2017 at 2:12 PM, Luke Kenneth Casson Leighton <lkcl at lkcl.net
> wrote:

> On Fri, Apr 28, 2017 at 10:40 AM, Bill Kontos <vkontogpls at gmail.com>
> wrote:
> > The octa core SoCs available right now are rather terrible when it comes
> to
> > heat and power management
>
> yyeah, that's no surprise.  what's really nice about RISC-V btw is
> that it's something mad like a 40% performance-watt improvement over
> ARM in the same geometry.
>
> > ( like the kirn 960) and we are rather limited by
> > the fact that everything has to run on libre software
>
>  well, there are plenty of companies that _don't_ (so it makes no
> sense to copy them or compete with them).... and the burden is
> enormous on absolutely everybody.  yet nobody's even *tried* an
> entirely libre approach *despite clearly knowing the advantages*!
>
>  http://www.h-online.com/open/news/item/Intel-and-Valve-
> collaborate-to-develop-open-source-graphics-drivers-1649632.html
>
> l.
>
> _______________________________________________
> arm-netbook mailing list arm-netbook at lists.phcomp.co.uk
> http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
> Send large attachments to arm-netbook at files.phcomp.co.uk
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.phcomp.co.uk/pipermail/arm-netbook/attachments/20170428/8fc48fac/attachment-0001.html>


More information about the arm-netbook mailing list