[patch] tuning gcc for Intel Core2

[Vladimir Makarov]

Andi Kleen wrote:

>>I tried these parameters and got better results (although I don't 
>>remeber exact numbers).  Actually I've tried all parameters.  I started 
>>the work when intel's guide was not public so I had to try all parameters.
>>
>>Even if Core2 has special hardware to decrease problem of dependencies 
>>on stack pointer, it does not mean that usage of push/pop will be better.
>>    
>>
>
>According to the guide PUSH has latency 1.5 (whatever that means) 
>and MOV 1. No extra dependencies on the stack pointer because those
>are optimized away early in the pipeline.
>  
>
1.5 is for Core, the latency for Core2 is missed in the table.

>The advantage would be smaller code.
>
>  
>
But utilization one more functional unit (although partially it will be 
improved by out-of-order execution).