[FFmpeg-devel] [PATCH 7/9] lavfi/nlmeans: switch from double to float

Clément Bœsch u at pkh.me
Sun May 6 14:40:58 EEST 2018


Overall speed appears to be 1.1x faster with no noticeable quality impact.
---
 libavfilter/vf_nlmeans.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/libavfilter/vf_nlmeans.c b/libavfilter/vf_nlmeans.c
index f37f1183f7..201e4feb41 100644
--- a/libavfilter/vf_nlmeans.c
+++ b/libavfilter/vf_nlmeans.c
@@ -40,8 +40,8 @@
 #include "video.h"
 
 struct weighted_avg {
-    double total_weight;
-    double sum;
+    float total_weight;
+    float sum;
 };
 
 #define WEIGHT_LUT_NBITS 9
@@ -63,8 +63,8 @@ typedef struct NLMeansContext {
     ptrdiff_t ii_lz_32;                         // linesize in 32-bit units of the integral image
     struct weighted_avg *wa;                    // weighted average of every pixel
     ptrdiff_t wa_linesize;                      // linesize for wa in struct size unit
-    double weight_lut[WEIGHT_LUT_SIZE];         // lookup table mapping (scaled) patch differences to their associated weights
-    double pdiff_lut_scale;                     // scale factor for patch differences before looking into the LUT
+    float weight_lut[WEIGHT_LUT_SIZE];          // lookup table mapping (scaled) patch differences to their associated weights
+    float pdiff_lut_scale;                      // scale factor for patch differences before looking into the LUT
     int max_meaningful_diff;                    // maximum difference considered (if the patch difference is too high we ignore the pixel)
     NLMeansDSPContext dsp;
 } NLMeansContext;
@@ -206,7 +206,7 @@ static void compute_safe_ssd_integral_image_c(uint32_t *dst, ptrdiff_t dst_lines
  * @param w                 width to compute
  * @param h                 height to compute
  */
-static inline void compute_unsafe_ssd_integral_image(uint32_t *dst, ptrdiff_t dst_linesize_32,
+static void compute_unsafe_ssd_integral_image(uint32_t *dst, ptrdiff_t dst_linesize_32,
                                                      int startx, int starty,
                                                      const uint8_t *src, ptrdiff_t linesize,
                                                      int offx, int offy, int r, int sw, int sh,
@@ -402,7 +402,7 @@ static int nlmeans_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs
             const int patch_diff_sq = get_integral_patch_value(td->ii_start, s->ii_lz_32, x, y, td->p);
             if (patch_diff_sq < s->max_meaningful_diff) {
                 const int weight_lut_idx = patch_diff_sq * s->pdiff_lut_scale;
-                const double weight = s->weight_lut[weight_lut_idx]; // exp(-patch_diff_sq * s->pdiff_scale)
+                const float weight = s->weight_lut[weight_lut_idx]; // exp(-patch_diff_sq * s->pdiff_scale)
                 wa[x].total_weight += weight;
                 wa[x].sum += weight * src[x];
             }
-- 
2.17.0



More information about the ffmpeg-devel mailing list