avfilter/vf_lut3d: add x86-optimized tetrahedral interpolation

I spotted an interesting pattern that I didn't see before that leads to the implementation being faster.
The bit shifting table I was using before is no longer needed, and was able to remove quite a few lines. 
I also add use of FMA on the AVX2 version.

f32 1920x1080 1 thread with prelut
c impl
1434012700 UNITS in lut3d->interp,       1 runs,      0 skips
1434035335 UNITS in lut3d->interp,       2 runs,      0 skips
1423615347 UNITS in lut3d->interp,       4 runs,      0 skips
1426268863 UNITS in lut3d->interp,       8 runs,      0 skips

sse2
905484420 UNITS in lut3d->interp,       1 runs,      0 skips
905659010 UNITS in lut3d->interp,       2 runs,      0 skips
915167140 UNITS in lut3d->interp,       4 runs,      0 skips
915834222 UNITS in lut3d->interp,       8 runs,      0 skips

avx
574794860 UNITS in lut3d->interp,       1 runs,      0 skips
581035090 UNITS in lut3d->interp,       2 runs,      0 skips
584116720 UNITS in lut3d->interp,       4 runs,      0 skips
581460290 UNITS in lut3d->interp,       8 runs,      0 skips

avx2
301698880 UNITS in lut3d->interp,       1 runs,      0 skips
301982880 UNITS in lut3d->interp,       2 runs,      0 skips
306962430 UNITS in lut3d->interp,       4 runs,      0 skips
305472025 UNITS in lut3d->interp,       8 runs,      0 skips

gbrap16 1920x1080 1 thread with prelut
c impl
1480894840 UNITS in lut3d->interp,       1 runs,      0 skips
1502922990 UNITS in lut3d->interp,       2 runs,      0 skips
1496114307 UNITS in lut3d->interp,       4 runs,      0 skips
1492554551 UNITS in lut3d->interp,       8 runs,      0 skips

sse2
980777180 UNITS in lut3d->interp,       1 runs,      0 skips
986121520 UNITS in lut3d->interp,       2 runs,      0 skips
986489840 UNITS in lut3d->interp,       4 runs,      0 skips
998832248 UNITS in lut3d->interp,       8 runs,      0 skips

avx
622212360 UNITS in lut3d->interp,       1 runs,      0 skips
622981160 UNITS in lut3d->interp,       2 runs,      0 skips
645396315 UNITS in lut3d->interp,       4 runs,      0 skips
641057075 UNITS in lut3d->interp,       8 runs,      0 skips

avx2
321336400 UNITS in lut3d->interp,       1 runs,      0 skips
321268920 UNITS in lut3d->interp,       2 runs,      0 skips
323459895 UNITS in lut3d->interp,       4 runs,      0 skips
324949967 UNITS in lut3d->interp,       8 runs,      0 skips

1 files changed, 5 insertions, 56 deletions

diff --git a/libavfilter/vf_lut3d.c b/libavfilter/vf_lut3d.c
index 8ec07f8ab0..7ef96906fc 100644
--- a/libavfilter/vf_lut3d.c
+++ b/libavfilter/vf_lut3d.c
@@ -31,73 +31,18 @@
 #include "libavutil/intreadwrite.h"
 #include "libavutil/intfloat.h"
 #include "libavutil/avassert.h"
-#include "libavutil/pixdesc.h"
 #include "libavutil/avstring.h"
-#include "avfilter.h"
 #include "drawutils.h"
 #include "formats.h"
-#include "framesync.h"
 #include "internal.h"
 #include "video.h"
+#include "lut3d.h"
 
 #define R 0
 #define G 1
 #define B 2
 #define A 3
 
-enum interp_mode {
-    INTERPOLATE_NEAREST,
-    INTERPOLATE_TRILINEAR,
-    INTERPOLATE_TETRAHEDRAL,
-    INTERPOLATE_PYRAMID,
-    INTERPOLATE_PRISM,
-    NB_INTERP_MODE
-};
-
-struct rgbvec {
-    float r, g, b;
-};
-
-/* 3D LUT don't often go up to level 32, but it is common to have a Hald CLUT
- * of 512x512 (64x64x64) */
-#define MAX_LEVEL 256
-#define PRELUT_SIZE 65536
-
-typedef struct Lut3DPreLut {
-    int size;
-    float min[3];
-    float max[3];
-    float scale[3];
-    float* lut[3];
-} Lut3DPreLut;
-
-typedef struct LUT3DContext {
-    const AVClass *class;
-    int interpolation;          ///<interp_mode
-    char *file;
-    uint8_t rgba_map[4];
-    int step;
-    avfilter_action_func *interp;
-    struct rgbvec scale;
-    struct rgbvec *lut;
-    int lutsize;
-    int lutsize2;
-    Lut3DPreLut prelut;
-#if CONFIG_HALDCLUT_FILTER
-    uint8_t clut_rgba_map[4];
-    int clut_step;
-    int clut_bits;
-    int clut_planar;
-    int clut_float;
-    int clut_width;
-    FFFrameSync fs;
-#endif
-} LUT3DContext;
-
-typedef struct ThreadData {
-    AVFrame *in, *out;
-} ThreadData;
-
 #define OFFSET(x) offsetof(LUT3DContext, x)
 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM
 #define TFLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_RUNTIME_PARAM
@@ -1203,6 +1148,10 @@ static int config_input(AVFilterLink *inlink)
         av_assert0(0);
     }
 
+    if (ARCH_X86) {
+        ff_lut3d_init_x86(lut3d, desc);
+    }
+
     return 0;
 }