[Arm-netbook] Rpi vs cortexA8

[Gordan Bobic]

On 06/03/2012 01:02 PM, lkcl luke wrote:
> On Sun, Jun 3, 2012 at 12:25 PM, Gordan Bobic<gordan at bobich.net>  wrote:
>> On 06/03/2012 12:21 PM, Tsvetan Usunov, OLIMEX LTD wrote:
>>>> the Cortex A8 however was *not* designed by ARM.  it was designed
>>>> based around a streamlined pipeline architecture (Harvard
>>>> Architecture) right from the word go, by a VC-funded team in Austin,
>>>> Texas, that ran out of money.  when they ran out of money they
>>>> approached ARM and asked them if they'd like to buy the company, which
>>>> they did, because ARM's own design was so shit.
>>>
>>> then who made A9?
>>> our developers say A9 is significant faster than A8 at same clocks
>>
>> IIRC A9 is essentially an A8 with out-of-order execution added. That
>> might gain you maybe another 15-20%, depending on how good your compiler is.
>
>   linaro added gcc optimisations ooo.. last year?  they reordered
> instructions to suit the pipeline of a Cortex A8, getting i heard a
> 30% speed increase by doing so.

Actually, the better the compiler the LESS difference OoOE will make.

Gordan