[theora-dev] Proposal for replacing asm code with intrinsics

[Nils Pipenbrinck]

After checking my old emails I have to correct myself:


Nils Pipenbrinck wrote (back, in february):
> For completes sake: The intrinsics compile on linux as well. I made the 
> same benchmarks as before, but this time with GCC 4.2.4 on Linux (ubuntu)
>
> All functions with inline-asm:           100%     
> inter_mmx replaced by C-function:    	 92%
> no mmx at all:                           54%
> all oc_frag functions intrinsic based:   99%
>   

We're not talking about 10 to 15% but just a percent or two. Hardly
worth a performance based regression.

Guess I've had the C vs. ASM numbers in mind.. :-)

Cheers,
  Nils