Michael S (already5chosen@yahoo.com) on 9/28/09 wrote:
---------------------------
>someone (someone@somewhere.com) on 9/27/09 wrote:
>---------------------------
>>Wilco (Wilco.Dijkstra@ntlworld.com) on 9/27/09 wrote:
>>---------------------------
>>>The A9 pulled so much ahead of Atom that there is now a significant overlap
>>>between high-end ARM and low-end x86.
>>
>>Put down your crack pipe for a second and look at the
>>facts. The current Atom has been shipping commercially
>>for a year and a half while the A9 has yet to even reach
>>silicon.
>>
>>Pulled ahead? There is now a significant overlap?
>>
>>The only thing being pulled here is your male appendage
>>by your own hand. Stop mislabelling your fanatasies of
>>the near future as current fact. It may come to pass IF 1)
>>A9 meets marketing claims AND 2) Intel choses not to
>>release second generation Atom products that have been
>>sampling since about mid year.
>>
>>While 1) is not implausible 2) is.
>
>There is another possible scenario too.
>Specifically, in good old Andy.G. tradition Intel took Cortex-A9 threat very seriously
>or at least much more seriously than you.

someone's points need to be taken seriously. he has
very extensive knowledge of uarchs, and seemingly
unlimited access to obscure intel literatures.

cortex-a9 is doing some *non-trivial* tricks to reduce
power consumption, while at the same time have to
deal with crazy stuff like handling interrupt efficiently
to support drm features like Trustzone. if arm
decided to go after the pc market, they would be facing
an expensive validation effort, and have to document
the uarch and memory model. that's very different
from the market they've been serving.

besides, when a9 silicon is out, people are going to
subject it to some *real* bechmarks. guess we have to
wait and see if a9 pans out.