lavc/nellymoserenc: avoid wasteful pow

exp2 suffices here. Some trivial speedup is done in addition here by
reusing results.

This retains accuracy, and in particular results in identical values
with GNU libm + gcc/clang.

sample benchmark (Haswell, GNU/Linux):
proposed : 424160 decicycles in pow_table,     512 runs,      0 skips
exp2 only: 1262093 decicycles in pow_table,     512 runs,      0 skips
old      : 2849085 decicycles in pow_table,     512 runs,      0 skips

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>

diff --git a/libavcodec/nellymoserenc.c b/libavcodec/nellymoserenc.c
index d998dbafee9ed41cb6b127dc094615a90351f928..9d22ac8cca20eb387547f4f2e53cd4f79e19124d 100644 (file)
--- a/libavcodec/nellymoserenc.c
+++ b/libavcodec/nellymoserenc.c
@@ -179,8 +179,18 @@ static av_cold int encode_init(AVCodecContext *avctx)
 
     /* Generate overlap window */
     ff_init_ff_sine_windows(7);
+    /* faster way of doing
     for (i = 0; i < POW_TABLE_SIZE; i++)
-        pow_table[i] = pow(2, -i / 2048.0 - 3.0 + POW_TABLE_OFFSET);
+       pow_table[i] = 2^(-i / 2048.0 - 3.0 + POW_TABLE_OFFSET); */
+    pow_table[0] = 1;
+    pow_table[1024] = M_SQRT1_2;
+    for (i = 1; i < 513; i++) {
+        double tmp = exp2(-i / 2048.0);
+        pow_table[i] = tmp;
+        pow_table[1024-i] = M_SQRT1_2 / tmp;
+        pow_table[1024+i] = tmp * M_SQRT1_2;
+        pow_table[2048-i] = 0.5 / tmp;
+    }
 
     if (s->avctx->trellis) {
         s->opt  = av_malloc(NELLY_BANDS * OPT_SIZE * sizeof(float  ));