virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-28 20:53:54 +02:00
Code Issues Releases Activity

lavu/tx: add fft_inplace_small transforms

Browse Source 
This is much faster than the loop.
This commit is contained in:
Lynne 2022-11-17 20:10:45 +01:00
parent d4e39cae2e
commit 68cabf8750
No known key found for this signature in database
GPG Key ID: A2FEA5F03F034464
1 changed files with 31 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
libavutil/tx_template.c
View File

@ -754,20 +754,34 @@ static av_cold int TX_NAME(ff_tx_fft_init)(AVTXContext *s,
return 0;
}
static av_cold int TX_NAME(ff_tx_fft_inplace_small_init)(AVTXContext *s,
const FFTXCodelet *cd,
uint64_t flags,
FFTXCodeletOptions *opts,
int len, int inv,
const void *scale)
{
if (!(s->tmp = av_malloc(len*sizeof(*s->tmp))))
return AVERROR(ENOMEM);
flags &= ~AV_TX_INPLACE;
return TX_NAME(ff_tx_fft_init)(s, cd, flags, opts, len, inv, scale);
}
static void TX_NAME(ff_tx_fft)(AVTXContext *s, void *_dst,
void *_src, ptrdiff_t stride)
{
TXComplex *src = _src;
TXComplex *dst = _dst;
TXComplex *dst1 = s->flags & AV_TX_INPLACE ? s->tmp : _dst;
TXComplex *dst2 = _dst;
int *map = s->sub[0].map;
int len = s->len;
/* Compilers can't vectorize this anyway without assuming AVX2, which they
* generally don't, at least without -march=native -mtune=native */
for (int i = 0; i < len; i++)
dst[i] = src[map[i]];
dst1[i] = src[map[i]];
s->fn[0](&s->sub[0], dst, dst, stride);
s->fn[0](&s->sub[0], dst2, dst1, stride);
}
static void TX_NAME(ff_tx_fft_inplace)(AVTXContext *s, void *_dst,
@ -807,6 +821,19 @@ static const FFTXCodelet TX_NAME(ff_tx_fft_def) = {
.prio = FF_TX_PRIO_BASE,
};
static const FFTXCodelet TX_NAME(ff_tx_fft_inplace_small_def) = {
.name = TX_NAME_STR("fft_inplace_small"),
.function = TX_NAME(ff_tx_fft),
.type = TX_TYPE(FFT),
.flags = AV_TX_UNALIGNED | FF_TX_OUT_OF_PLACE | AV_TX_INPLACE,
.factors[0] = TX_FACTOR_ANY,
.min_len = 2,
.max_len = 65536,
.init = TX_NAME(ff_tx_fft_inplace_small_init),
.cpu_flags = FF_TX_CPU_FLAGS_ALL,
.prio = FF_TX_PRIO_BASE - 256,
};
static const FFTXCodelet TX_NAME(ff_tx_fft_inplace_def) = {
.name = TX_NAME_STR("fft_inplace"),
.function = TX_NAME(ff_tx_fft_inplace),
@ -1638,6 +1665,7 @@ const FFTXCodelet * const TX_NAME(ff_tx_codelet_list)[] = {
/* Standalone transforms */
&TX_NAME(ff_tx_fft_def),
&TX_NAME(ff_tx_fft_inplace_def),
&TX_NAME(ff_tx_fft_inplace_small_def),
&TX_NAME(ff_tx_fft_pfa_3xM_def),
&TX_NAME(ff_tx_fft_pfa_5xM_def),
&TX_NAME(ff_tx_fft_pfa_7xM_def),