1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00

lavc/opusdsp: RISC-V V (512-bit) postfilter

This adds a variant of the postfilter for use with 512-bit vectors.
Half a vector is enough to perform the scalar product. Normally a whole
vector would be used anyhow. Indeed fractional multiplers are no faster
than the unit multipler.

But in this particular function, a full vector makes up 16 samples,
which would be loaded at each iteration of the outer loop. The minimum
guaranteed CELT postfilter period is only 15. Accounting for the edges,
we can only safely preload up to 13 samples.

The fractional multipler is thus used to cap the selected vector length
to a safe value of 8 elements or 256 bits.

Likewise, we have the 1024-bit variant with the quarter multipler. In
theory, a 2048-bit one would be possible with the eigth multipler, but
that length is not even defined in the specifications as of yet, nor is
it supported by any emulator - forget actual hardware.
This commit is contained in:
Rémi Denis-Courmont 2022-10-05 19:12:56 +03:00 committed by Lynne
parent 97d34befea
commit bfc69297c5
2 changed files with 18 additions and 0 deletions

View File

@ -27,6 +27,8 @@
void ff_opus_postfilter_rvv_128(float *data, int period, float *g, int len);
void ff_opus_postfilter_rvv_256(float *data, int period, float *g, int len);
void ff_opus_postfilter_rvv_512(float *data, int period, float *g, int len);
void ff_opus_postfilter_rvv_1024(float *data, int period, float *g, int len);
av_cold void ff_opus_dsp_init_riscv(OpusDSP *d)
{
@ -41,6 +43,12 @@ av_cold void ff_opus_dsp_init_riscv(OpusDSP *d)
case 32:
d->postfilter = ff_opus_postfilter_rvv_256;
break;
case 64:
d->postfilter = ff_opus_postfilter_rvv_512;
break;
case 128:
d->postfilter = ff_opus_postfilter_rvv_512;
break;
}
#endif
}

View File

@ -25,6 +25,16 @@ func ff_opus_postfilter_rvv_128, zve32f
j 1f
endfunc
func ff_opus_postfilter_rvv_512, zve32f
lvtypei a5, e32, mf2, ta, ma
j 1f
endfunc
func ff_opus_postfilter_rvv_1024, zve32f
lvtypei a5, e32, mf4, ta, ma
j 1f
endfunc
func ff_opus_postfilter_rvv_256, zve32f
lvtypei a5, e32, m1, ta, ma
1: