[Arm-netbook] [review] SoC proposal

[Gordan Bobic]

Bari Ari wrote:
> On 02/09/2012 09:13 AM, Gordan Bobic wrote:
>>>   don't know.  tensilica have a proprietary "pre-processor" compiler
>>> that turns c and c++ into VLIW-capable c and c++.
>> That sounds like another one of those hare-brained solutions like the
>> JZ4760. If it's going to be mainstream, it needs to be done cleanly,
>> i.e. a proper GCC back-end - preferably one that delivers decent
>> performance unlike the current vectorization efforts.
>>
>>
> Another example of too little too late.  If only they had this out 5 
> years earlier.

5 years is a VERY long time.

> I don't think that Luke is just off on some ego trip to build an SOC.

I never meant to imply that he is. I just wanted to make sure that the 
scale of the undertaking is understood.

> It 
> really needs community input for it to work, especially from the 
> software side. The hardware and the toolchain can come together within a 
> year. Porting thousands of packages however as you have mentioned will 
> be the real work.

Indeed. And with a completely new target arch, we won't have the benefit 
of previous patches or attempts at patches to at least point in the 
right direction.

Gordan