[Arm-netbook] [review] SoC proposal

[Vladimir Pantelic]

lkcl luke wrote:
> On Thu, Feb 9, 2012 at 4:54 PM, Vladimir Pantelic<vladoman at gmail.com>  wrote:
>
>>>     tensilica wouldn't have sold over 1.5 billion licenses for their RISC
>>>  cores if it didn't do a decent job, eh?
>>
>>  And these 1.5 billion cores are doing what?
>
>   take a look at the list of licensees for tensilica technology.  it
> includes qualcomm (atheros), amd, wolfson micro to name just 3.  they
> also have a Base-band DSP so their RISC cores have ended up in mobile
> phones as well as Base-Stations.  the base stations are where they
> probably make one hell of a lot of money, putting in oh i dunno 200+
> cores into a single device?  the VLIW stuff is where they save these
> companies vast amounts of money on power because they can do the same
> job as a faster CPU, at 1/3 of the clock rate, doing 3x the
> instructions.

right, so none of these ended up in a consumer facing device as an
application processor - which is what you are proposing and and for which
you want to port/adapt all the existing (linux) software. I am quite sure
that a mobile phone basestation has tremendous benefit from 200 cores,
but what about OpenOffice or Firefox?