[FFmpeg-devel] [PATCH v2 13/13] avfilter/x86/f_ebur128: implement AVX true peak calculation

[Niklas Haas]

From: Niklas Haas <git at haasn.dev>

Stereo only, for simplicity. Slightly faster than the C code.
---
 libavfilter/f_ebur128.c          |  8 +++-----
 libavfilter/f_ebur128.h          |  2 +-
 libavfilter/x86/f_ebur128.asm    | 25 +++++++++++++++++++++++++
 libavfilter/x86/f_ebur128_init.c |  9 +++++++--
 4 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/libavfilter/f_ebur128.c b/libavfilter/f_ebur128.c
index 0adc89c823..c64f6ed032 100644
--- a/libavfilter/f_ebur128.c
+++ b/libavfilter/f_ebur128.c
@@ -502,6 +502,9 @@ static int config_audio_output(AVFilterLink *outlink)
             return AVERROR(ENOMEM);
     }
 
+#if ARCH_X86
+    ff_ebur128_init_x86(&ebur128->dsp, nb_channels);
+#endif
     return 0;
 }
 
@@ -581,11 +584,6 @@ static av_cold int init(AVFilterContext *ctx)
 
     ebur128->dsp.filter_channels = ff_ebur128_filter_channels_c;
     ebur128->dsp.true_peak = ff_ebur128_true_peak_c;
-
-#if ARCH_X86
-    ff_ebur128_init_x86(&ebur128->dsp);
-#endif
-
     return 0;
 }
 
diff --git a/libavfilter/f_ebur128.h b/libavfilter/f_ebur128.h
index 78238e4bef..9d167a3d4a 100644
--- a/libavfilter/f_ebur128.h
+++ b/libavfilter/f_ebur128.h
@@ -50,7 +50,7 @@ static_assert(offsetof(EBUR128DSPContext, pre) == 0,                   "struct l
 static_assert(offsetof(EBUR128DSPContext, rlb) == 5  * sizeof(double), "struct layout mismatch");
 static_assert(offsetof(EBUR128DSPContext, y)   == 10 * sizeof(double), "struct layout mismatch");
 
-void ff_ebur128_init_x86(EBUR128DSPContext *dsp);
+void ff_ebur128_init_x86(EBUR128DSPContext *dsp, int nb_channels);
 
 void ff_ebur128_filter_channels_c(const EBUR128DSPContext *, const double *,
                                   double *, double *, double *, double *, int);
diff --git a/libavfilter/x86/f_ebur128.asm b/libavfilter/x86/f_ebur128.asm
index 28add77f70..99502ebe9d 100644
--- a/libavfilter/x86/f_ebur128.asm
+++ b/libavfilter/x86/f_ebur128.asm
@@ -40,6 +40,10 @@ struc DSP
     .z resq 1
 endstruc
 
+SECTION_RODATA
+
+abs_mask: dq 0x7FFFFFFFFFFFFFFF
+
 SECTION .text
 
 %macro MOVNQ 3 ; num, dst, src
@@ -140,3 +144,24 @@ cglobal ebur128_filter_channels, 7, 9, 14, dsp, samples, cache400, cache3000, su
     test channelsd, channelsd
     jnz .loop
     RET
+
+cglobal ebur128_true_peak_stereo, 5, 6, 4, tp, tppf, channels, samples, nb_samples
+    vpbroadcastq m4, [abs_mask]
+    pxor m0, m0      ; maxpeak
+    movupd m1, [tpq] ; tp
+    pxor m2, m2      ; tppf
+.inner:
+    movupd m3, [samplesq]
+    add samplesq, 16
+    pand m3, m4
+    maxpd m1, m3
+    maxpd m2, m3
+    dec nb_samplesd
+    jg .inner
+    movupd [tpq],  m1
+    movupd [tppfq], m2
+    maxpd m0, m1
+    shufpd m1, m0, m0, 1
+    maxpd m0, m1
+    movq rax, m0
+    RET
diff --git a/libavfilter/x86/f_ebur128_init.c b/libavfilter/x86/f_ebur128_init.c
index c5edfde03a..324faf7c31 100644
--- a/libavfilter/x86/f_ebur128_init.c
+++ b/libavfilter/x86/f_ebur128_init.c
@@ -26,10 +26,15 @@
 void ff_ebur128_filter_channels_avx(const EBUR128DSPContext *, const double *,
                                     double *, double *, double *, double *, int);
 
-av_cold void ff_ebur128_init_x86(EBUR128DSPContext *dsp)
+double ff_ebur128_true_peak_stereo_avx(double *, double *, int, const double *, int);
+
+av_cold void ff_ebur128_init_x86(EBUR128DSPContext *dsp, int nb_channels)
 {
     int cpu_flags = av_get_cpu_flags();
 
-    if (EXTERNAL_AVX(cpu_flags))
+    if (EXTERNAL_AVX(cpu_flags)) {
         dsp->filter_channels = ff_ebur128_filter_channels_avx;
+        if (nb_channels == 2)
+            dsp->true_peak = ff_ebur128_true_peak_stereo_avx;
+    }
 }
-- 
2.49.0