someone (someone@somewhere.com) on 9/28/09 wrote:
---------------------------
>Wilco (Wilco.Dijkstra@ntlworld.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:
>>>---------------------------
>>>>none (none@none.com) on 9/27/09 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.
>>>>
>>>>Actually test chips have been around for a while, and OMAP4 chips are sampling in Q4.
>>>
>>>What is this, bait and switch?
>>>
>>>The 2 GHz, 40 nm TSMC A9 hard macro ARM is making all
>>>the big claims for isn't in silicon yet according to EET:
>>>
>>>http://www.eetimes.com/news/latest/showArticle.jhtml?articleID=220000596&pgno=2
>>>
>>>And if we take ARM's numbers and benchmark assertions at face value and conclude
>>>it has an Atom-killer we must also remember that ARM is comparing an EDA simulation
>>>of a 40-nm processor core against a 45-nm/40-nm Intel processor that is in the field.
>>>
>>>ARM's Osprey has not gone through TSMC as a system test chip yet. So by the time
>>>those Osprey processors are also in the field Intel will have, no doubt, fired its riposte.
>>
>>Sure, the 2GHz version isn't yet available in hardware. However your claim was
>>that the A9 doesn't exist at all in hardware - "while the A9 has yet to even reach silicon". That's false:
>>
>>http://www.electronicsweekly.com/Articles/2009/09/16/46955/arm-produces-hard-cortex-a9-for-high-performance.htm
>>
>
>I never said no A9 exists, the 40 nm TSMC 2 GHz A9 that
>ARM is making all the fabulous comparisons to Atom
>performance in press releases isn't in silicon yet.

The sentence "while the A9 has yet to even reach silicon" is very clear. If there is any bait and switch then it is you trying spin your own words.

>BTW, why doesn't ARM compare its *existing* A9 silicon
>to ARM instead of its simulation based wonder of tomorrow?

ARM doesn't own existing A9 silicon, it is up to ARM's partners to decide how to market their SoCs. It is hardly surprising that ARM's announcements are about IP cores with simulated performance figures. Do you really expect anything different from an IP vendor?

And before you complain about ARM marketing, Intel marketing compared a 1.6GHz Atom with a 5 year old 400MHz ARM11 when 720MHz Cortex-A8 was available.

>Like I mentioned in my previous post, you are propagating a
>bate and switch fallacy in support of ARM marketing noise.
>
>Do you work for ARM or one of its major contractors?

No, I left ARM a long time ago.

Wilco