[FFmpeg-devel] [PATCH] HE-AACv1 second revision

[Måns Rullgård]

Alex Converse <alex.converse at gmail.com> writes:

>>> + ? ? ? ?for (i = 0; i < 64; i++) {
>>> + ? ? ? ? ? ?float f = z[i] + z[i + 64] + z[i + 128] + z[i + 192] + z[i + 256];
>>> + ? ? ? ? ? ?u[revtab[i]].re = f * analysis_cos_pre[i];
>>> + ? ? ? ? ? ?u[revtab[i]].im = f * analysis_sin_pre[i];
>>> + ? ? ? ?}
>>
>> SIMD should help here despite the permutation. ?It can probably be
>> combined with the z[] calculation too.
>>
>>> + ? ? ? ?ff_fft_calc(fft, u);
>>> + ? ? ? ?for (k = 0; k < 32; k++) {
>>> + ? ? ? ? ? ?W[1][k][l][0] = u[k].re * analysis_cos_post[k] - u[k].im * analysis_sin_post[k];
>>> + ? ? ? ? ? ?W[1][k][l][1] = u[k].re * analysis_sin_post[k] + u[k].im * analysis_cos_post[k];
>>> + ? ? ? ?}
>>
>> SIMD
>>
>
> We seem to be missing appropriate DSPutil functions for some of these.
> Does it really make sense to clutter up the already messy dsputil with
> a bunch of placeholder functions?

Placeholder?  It's much easier for someone to optimise them if the
dsputil hookup is already done.

-- 
M?ns Rullg?rd
mans at mansr.com