| Message ID | 20170311005652.10041-1-mfcc64@gmail.com |
|---|---|
| State | Accepted |
| Commit | 0bab78f7e729a76ea7a8cbec7f1de033c52494e8 |
| Headers | show |
On Sat, 11 Mar 2017 07:56:52 +0700 Muhammad Faiz <mfcc64@gmail.com> wrote: > slightly improved speed > > Signed-off-by: Muhammad Faiz <mfcc64@gmail.com> > --- > libavfilter/af_firequalizer.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/libavfilter/af_firequalizer.c b/libavfilter/af_firequalizer.c > index 5c6fd54..4243d66 100644 > --- a/libavfilter/af_firequalizer.c > +++ b/libavfilter/af_firequalizer.c > @@ -197,8 +197,8 @@ static int query_formats(AVFilterContext *ctx) > return ff_set_common_samplerates(ctx, formats); > } > > -static void fast_convolute(FIREqualizerContext *s, const float *kernel_buf, float *conv_buf, > - OverlapIndex *idx, float *data, int nsamples) > +static void fast_convolute(FIREqualizerContext *av_restrict s, const float *av_restrict kernel_buf, float *av_restrict conv_buf, > + OverlapIndex *av_restrict idx, float *av_restrict data, int nsamples) > { > if (nsamples <= s->nsamples_max) { > float *buf = conv_buf + idx->buf_idx * s->rdft_len; > @@ -235,8 +235,8 @@ static void fast_convolute(FIREqualizerContext *s, const float *kernel_buf, floa > } > } > > -static void fast_convolute2(FIREqualizerContext *s, const float *kernel_buf, FFTComplex *conv_buf, > - OverlapIndex *idx, float *data0, float *data1, int nsamples) > +static void fast_convolute2(FIREqualizerContext *av_restrict s, const float *av_restrict kernel_buf, FFTComplex *av_restrict conv_buf, > + OverlapIndex *av_restrict idx, float *av_restrict data0, float *av_restrict data1, int nsamples) > { > if (nsamples <= s->nsamples_max) { > FFTComplex *buf = conv_buf + idx->buf_idx * s->rdft_len; Seems ok. How much improved?
On Sat, Mar 11, 2017 at 8:05 PM, wm4 <nfxjfg@googlemail.com> wrote: > On Sat, 11 Mar 2017 07:56:52 +0700 > Muhammad Faiz <mfcc64@gmail.com> wrote: > >> slightly improved speed >> >> Signed-off-by: Muhammad Faiz <mfcc64@gmail.com> >> --- >> libavfilter/af_firequalizer.c | 8 ++++---- >> 1 file changed, 4 insertions(+), 4 deletions(-) >> >> diff --git a/libavfilter/af_firequalizer.c b/libavfilter/af_firequalizer.c >> index 5c6fd54..4243d66 100644 >> --- a/libavfilter/af_firequalizer.c >> +++ b/libavfilter/af_firequalizer.c >> @@ -197,8 +197,8 @@ static int query_formats(AVFilterContext *ctx) >> return ff_set_common_samplerates(ctx, formats); >> } >> >> -static void fast_convolute(FIREqualizerContext *s, const float *kernel_buf, float *conv_buf, >> - OverlapIndex *idx, float *data, int nsamples) >> +static void fast_convolute(FIREqualizerContext *av_restrict s, const float *av_restrict kernel_buf, float *av_restrict conv_buf, >> + OverlapIndex *av_restrict idx, float *av_restrict data, int nsamples) >> { >> if (nsamples <= s->nsamples_max) { >> float *buf = conv_buf + idx->buf_idx * s->rdft_len; >> @@ -235,8 +235,8 @@ static void fast_convolute(FIREqualizerContext *s, const float *kernel_buf, floa >> } >> } >> >> -static void fast_convolute2(FIREqualizerContext *s, const float *kernel_buf, FFTComplex *conv_buf, >> - OverlapIndex *idx, float *data0, float *data1, int nsamples) >> +static void fast_convolute2(FIREqualizerContext *av_restrict s, const float *av_restrict kernel_buf, FFTComplex *av_restrict conv_buf, >> + OverlapIndex *av_restrict idx, float *av_restrict data0, float *av_restrict data1, int nsamples) >> { >> if (nsamples <= s->nsamples_max) { >> FFTComplex *buf = conv_buf + idx->buf_idx * s->rdft_len; > > Seems ok. How much improved? fast_convolute(): old: 791277 decicycles in fast_convolute(), 65536 runs, 0 skips new: 775519 decicycles in fast_convolute(), 65536 runs, 0 skips fast_convolute2(): old: 532707 decicycles in fast_convolute2(), 65535 runs, 1 skips new: 518874 decicycles in fast_convolute2(), 65536 runs, 0 skips Applied. Thank's
diff --git a/libavfilter/af_firequalizer.c b/libavfilter/af_firequalizer.c index 5c6fd54..4243d66 100644 --- a/libavfilter/af_firequalizer.c +++ b/libavfilter/af_firequalizer.c @@ -197,8 +197,8 @@ static int query_formats(AVFilterContext *ctx) return ff_set_common_samplerates(ctx, formats); } -static void fast_convolute(FIREqualizerContext *s, const float *kernel_buf, float *conv_buf, - OverlapIndex *idx, float *data, int nsamples) +static void fast_convolute(FIREqualizerContext *av_restrict s, const float *av_restrict kernel_buf, float *av_restrict conv_buf, + OverlapIndex *av_restrict idx, float *av_restrict data, int nsamples) { if (nsamples <= s->nsamples_max) { float *buf = conv_buf + idx->buf_idx * s->rdft_len; @@ -235,8 +235,8 @@ static void fast_convolute(FIREqualizerContext *s, const float *kernel_buf, floa } } -static void fast_convolute2(FIREqualizerContext *s, const float *kernel_buf, FFTComplex *conv_buf, - OverlapIndex *idx, float *data0, float *data1, int nsamples) +static void fast_convolute2(FIREqualizerContext *av_restrict s, const float *av_restrict kernel_buf, FFTComplex *av_restrict conv_buf, + OverlapIndex *av_restrict idx, float *av_restrict data0, float *av_restrict data1, int nsamples) { if (nsamples <= s->nsamples_max) { FFTComplex *buf = conv_buf + idx->buf_idx * s->rdft_len;
slightly improved speed Signed-off-by: Muhammad Faiz <mfcc64@gmail.com> --- libavfilter/af_firequalizer.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)