[FFmpeg-devel] [PATCH] Altivec vector_fmul_scalar

Guillaume POIRIER poirierg
Wed Jan 7 00:05:48 CET 2009


Hello,

On Tue, Jan 6, 2009 at 5:31 PM, David Conrad <lessen42 at gmail.com> wrote:
> On Jan 6, 2009, at 8:19 AM, Guillaume Poirier wrote:

>> I somehow thought that this code
>>
>>> +        t0 = vec_madd(s0, wj, vadd_bias);
>>> +        t1 = vec_madd(s1, wi, zero);
>>> +        t0 = vec_sub(t0, t1);
>>
>> could be reduced to 2 instructions using vec_nmsub(), but I guess
>> not.... right?
>
> Forgot about vec_nmsub. It works perfectly here.

Good, glad that I could help. tiny_psnr tells me that the new output
is extremely close, so patch applied.

Guillaume
-- 
Only a very small fraction of our DNA does anything; the rest is all
comments and ifdefs.

Everett Dirksen  - "A billion here, a billion there, and pretty soon
you're talking about real money."




More information about the ffmpeg-devel mailing list