avfilter/vf_nlmeans: refactor line processing in preparation for x86 SIMD assembly

libavfilter/vf_nlmeans.c

@@ -38,11 +38,6 @@
 #include "vf_nlmeans.h"
 #include "video.h"
 
-struct weighted_avg {
-    float total_weight;
-    float sum;
-};
-
 typedef struct NLMeansContext {
     const AVClass *class;
     int nb_planes;
@@ -329,28 +324,17 @@ struct thread_data {
     int p;
 };
 
-static int nlmeans_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
+static void compute_weights_line_c(const uint32_t *const iia,
+                                   const uint32_t *const iib,
+                                   const uint32_t *const iid,
+                                   const uint32_t *const iie,
+                                   const uint8_t *const src,
+                                   struct weighted_avg *wa,
+                                   const float *const weight_lut,
+                                   int max_meaningful_diff,
+                                   int startx, int endx)
 {
-    NLMeansContext *s = ctx->priv;
+    for (int x = startx; x < endx; x++) {
-    const uint32_t max_meaningful_diff = s->max_meaningful_diff;
-    const struct thread_data *td = arg;
-    const ptrdiff_t src_linesize = td->src_linesize;
-    const int process_h = td->endy - td->starty;
-    const int slice_start = (process_h *  jobnr   ) / nb_jobs;
-    const int slice_end   = (process_h * (jobnr+1)) / nb_jobs;
-    const int starty = td->starty + slice_start;
-    const int endy   = td->starty + slice_end;
-    const int p = td->p;
-    const uint32_t *ii = td->ii_start + (starty - p - 1) * s->ii_lz_32 - p - 1;
-    const int dist_b = 2*p + 1;
-    const int dist_d = dist_b * s->ii_lz_32;
-    const int dist_e = dist_d + dist_b;
-    const float *const weight_lut = s->weight_lut;
-
-    for (int y = starty; y < endy; y++) {
-        const uint8_t *src = td->src + y*src_linesize;
-        struct weighted_avg *wa = s->wa + y*s->wa_linesize;
-        for (int x = td->startx; x < td->endx; x++) {
         /*
          * M is a discrete map where every entry contains the sum of all the entries
          * in the rectangle from the top-left origin of M to its coordinate. In the
@@ -380,16 +364,48 @@ static int nlmeans_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs
          * contains the sum of the squared difference of every corresponding pixels of
          * two input planes of the same size as M.
          */
-            const uint32_t a = ii[x];
+        const uint32_t a = iia[x];
-            const uint32_t b = ii[x + dist_b];
+        const uint32_t b = iib[x];
-            const uint32_t d = ii[x + dist_d];
+        const uint32_t d = iid[x];
-            const uint32_t e = ii[x + dist_e];
+        const uint32_t e = iie[x];
         const uint32_t patch_diff_sq = FFMIN(e - d - b + a, max_meaningful_diff);
         const float weight = weight_lut[patch_diff_sq]; // exp(-patch_diff_sq * s->pdiff_scale)
 
         wa[x].total_weight += weight;
         wa[x].sum += weight * src[x];
     }
+}
+
+static int nlmeans_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
+{
+    NLMeansContext *s = ctx->priv;
+    const uint32_t max_meaningful_diff = s->max_meaningful_diff;
+    const struct thread_data *td = arg;
+    const ptrdiff_t src_linesize = td->src_linesize;
+    const int process_h = td->endy - td->starty;
+    const int slice_start = (process_h *  jobnr   ) / nb_jobs;
+    const int slice_end   = (process_h * (jobnr+1)) / nb_jobs;
+    const int starty = td->starty + slice_start;
+    const int endy   = td->starty + slice_end;
+    const int p = td->p;
+    const uint32_t *ii = td->ii_start + (starty - p - 1) * s->ii_lz_32 - p - 1;
+    const int dist_b = 2*p + 1;
+    const int dist_d = dist_b * s->ii_lz_32;
+    const int dist_e = dist_d + dist_b;
+    const float *const weight_lut = s->weight_lut;
+    NLMeansDSPContext *dsp = &s->dsp;
+
+    for (int y = starty; y < endy; y++) {
+        const uint8_t *const src = td->src + y*src_linesize;
+        struct weighted_avg *wa = s->wa + y*s->wa_linesize;
+        const uint32_t *const iia = ii;
+        const uint32_t *const iib = ii + dist_b;
+        const uint32_t *const iid = ii + dist_d;
+        const uint32_t *const iie = ii + dist_e;
+
+        dsp->compute_weights_line(iia, iib, iid, iie, src, wa,
+                                  weight_lut, max_meaningful_diff,
+                                  td->startx, td->endx);
         ii += s->ii_lz_32;
     }
     return 0;
@@ -493,6 +509,7 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *in)
 void ff_nlmeans_init(NLMeansDSPContext *dsp)
 {
     dsp->compute_safe_ssd_integral_image = compute_safe_ssd_integral_image_c;
+    dsp->compute_weights_line = compute_weights_line_c;
 
     if (ARCH_AARCH64)
         ff_nlmeans_init_aarch64(dsp);

libavfilter/vf_nlmeans.h

@@ -22,11 +22,25 @@
 #include <stddef.h>
 #include <stdint.h>
 
+struct weighted_avg {
+    float total_weight;
+    float sum;
+};
+
 typedef struct NLMeansDSPContext {
     void (*compute_safe_ssd_integral_image)(uint32_t *dst, ptrdiff_t dst_linesize_32,
                                             const uint8_t *s1, ptrdiff_t linesize1,
                                             const uint8_t *s2, ptrdiff_t linesize2,
                                             int w, int h);
+    void (*compute_weights_line)(const uint32_t *const iia,
+                                 const uint32_t *const iib,
+                                 const uint32_t *const iid,
+                                 const uint32_t *const iie,
+                                 const uint8_t *const src,
+                                 struct weighted_avg *wa,
+                                 const float *const weight_lut,
+                                 int max_meaningful_diff,
+                                 int startx, int endx);
 } NLMeansDSPContext;
 
 void ff_nlmeans_init(NLMeansDSPContext *dsp);