Re: [RFC] Optimize swab operations on mips_r2 cpu

[Nigel Stephens <nigel@mips.com>]

Franck wrote:

>>-march=mips32r2 is to allow the compiler to generate branch-likely
>>instructions -- they're deprecated for generic mips32 code but carry no
>>penalty on the 4K core. It will also cause the compiler's "4kc" pipeline
>>description to be used for instruction scheduling, instead of the
>>default "24kc", but that should only change the order of instructions
>>    
>>
>
>Do you mean that the code can be run faster when using -march=4ksd ?
>  
>

Yes, though the difference is likely to be small. The -march=4ksd option 
also enables the SmartMIPS ASE, but you've already done that explicitly 
with -msmartmips.

>  
>
>>and shouldn't really make a significant difference to the code size.
>>
>>    
>>
>
>yes but I have :(
>  
>

Then you'll have to have a look at the resulting disassembled code and 
figure what's changed. :)

Thinking about this in more detail:

1) Using -march=4ksd reduces the cost of a multiply by 1 instruction 
(from 5 to 4 cycles), so a few more constant multiplications, previously 
expanded into a sequence of shifts, adds and subs, may now be replaced 
by a shorter sequence of "li" and "mul" instructions.

2) Enabling branch-likely may allow some instructions to be moved into a 
branch delay slot which previously couldn't be -- but usually these are 
duplicates of the code at the original branch target, so have little 
effect on overall code size.

3) Using -march=mips32r2 with -O1 and above (but not -Os) enables 64-bit 
alignment of functions and frequently-used branch targets (e.g. loop 
headers); whereas -march=4ksc will not do that. This will add some 
additional "nops" to the code.

Nigel