On Tue, Sep 6, 2016 at 11:39 AM, Anton Khirnov <[email protected]> wrote:
>> Use 3-arg maxps instead of mova.
>
> Isn't that AVX-only?

It is, x86inc will simply convert it to mova+minps when assembling it
as non-AVX code but it reduces the line count. It's certainly not
worth to go into bikeshedding territory about it however, so if you
prefer to use plain mova:s just keep them.

>> Otherwise LGTM, you could make an AVX version using ymm registers
>> as well in a separate patch if you want to, just need to make sure
>> the buffers are aligned.
>
> This function is only used in two rather obscure places, so probably
> not worth it

Fair enough.
_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel

Reply via email to