avcodec/ffv1enc: replace the remaining log2() by magic

big secret, reading a float as the corresponding integer is a good
approximation of log2() for numbers not too close to 1.0. At the same
time it maintains strict monotonicity

this reduces run time from 19sec to 17sec for the slowest of my testcases
(with default remap_optimizer 3)

Compression is about the same:

-rw-r----- 1 michael michael  497603370 Mar 30 15:23 float-303503-fixed-40-optim-3-1log2F.nut
-rw-r----- 1 michael michael  497603374 Mar 28 11:27 float-303503-fixed-40-optim-3b.nut
-rw-r----- 1 michael michael  549938852 Mar 28 11:27 float-303503-float16-40-optim-3b.nut
-rw-r----- 1 michael michael  549938857 Mar 30 15:23 float-303503-float16-40-optim-3-1log2F.nut
-rw-r----- 1 michael michael 1150827841 Mar 28 11:28 float-303503-float-40-optim-3b.nut
-rw-r----- 1 michael michael 1150832913 Mar 30 15:22 float-303503-float-40-optim-3ref-log2F2.nut

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

1 files changed, 8 insertions, 2 deletions

diff --git a/libavcodec/ffv1enc.c b/libavcodec/ffv1enc.c
index 2a188ade77..a09ab30038 100644
--- a/libavcodec/ffv1enc.c
+++ b/libavcodec/ffv1enc.c
@@ -1375,6 +1375,7 @@ static void encode_float32_remap(FFV1Context *f, FFV1SliceContext *sc,
     const int log2_mul_step       = ((int[]){  1,  8,  1,  1,  1,   1})[f->remap_optimizer];
     const int bruteforce_count    = ((int[]){  0,  0,  0,  1,  1,   1})[f->remap_optimizer];
     const int stair_mode          = ((int[]){  0,  0,  0,  1,  0,   0})[f->remap_optimizer];
+    const int magic_log2          = ((int[]){  1,  1,  1,  1,  0,   0})[f->remap_optimizer];
 
     av_assert0 (pixel_num <= 65536);
 
@@ -1390,7 +1391,9 @@ static void encode_float32_remap(FFV1Context *f, FFV1SliceContext *sc,
             int last_mul_index = -1;
             int mul_count = 1 << log2_mul_count;
 
-            score_sum[log2_mul_count] += log2_mul_count * log2_mul_count;
+            score_sum[log2_mul_count] = 2 * log2_mul_count;
+            if (magic_log2)
+                score_sum[log2_mul_count] = av_float2int((float)mul_count * mul_count);
             for (int i= 0; i<pixel_num; i++) {
                 int64_t val = sc->unit[p][i].val;
                 int mul_index = (val + 1LL)*mul_count >> 32;
@@ -1424,7 +1427,10 @@ static void encode_float32_remap(FFV1Context *f, FFV1SliceContext *sc,
                         score *= score;
                         if (mul_index != last_mul_index)
                             score *= mul;
-                        score_tab[si] += log2f(score);
+                        if (magic_log2) {
+                            score_tab[si] += av_float2int(score);
+                        } else
+                            score_tab[si] += log2f(score);
                     }
                 }
                 last_val = val;