[FFmpeg-devel] [PATCH 1/2] lavc/pcm_tablegen: slight speedup of table generation

[Ganesh Ajjanagadde]

This gets rid of some branches to speed up table generation slightly
(impact higher on mulaw than alaw). Tables are identical to before,
tested with FATE.

Sample benchmark (Haswell, GNU/Linux+gcc):
old:
 313494 decicycles in build_alaw_table,    4094 runs,      2 skips
 315959 decicycles in build_alaw_table,    8190 runs,      2 skips

 323599 decicycles in build_ulaw_table,    4095 runs,      1 skips
 318849 decicycles in build_ulaw_table,    8188 runs,      4 skips

new:
 261902 decicycles in build_alaw_table,    4096 runs,      0 skips
 266519 decicycles in build_alaw_table,    8192 runs,      0 skips

 209657 decicycles in build_ulaw_table,    4096 runs,      0 skips
 232656 decicycles in build_ulaw_table,    8192 runs,      0 skips

Signed-off-by: Ganesh Ajjanagadde <gajjanagadde at gmail.com>
---
 libavcodec/pcm_tablegen.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/libavcodec/pcm_tablegen.h b/libavcodec/pcm_tablegen.h
index 1387210..7269977 100644
--- a/libavcodec/pcm_tablegen.h
+++ b/libavcodec/pcm_tablegen.h
@@ -87,21 +87,21 @@ static av_cold void build_xlaw_table(uint8_t *linear_to_xlaw,
 {
     int i, j, v, v1, v2;
 
-    j = 0;
-    for(i=0;i<128;i++) {
-        if (i != 127) {
-            v1 = xlaw2linear(i ^ mask);
-            v2 = xlaw2linear((i + 1) ^ mask);
-            v = (v1 + v2 + 4) >> 3;
-        } else {
-            v = 8192;
-        }
-        for(;j<v;j++) {
+    j = 1;
+    linear_to_xlaw[8192] = mask;
+    for(i=0;i<127;i++) {
+        v1 = xlaw2linear(i ^ mask);
+        v2 = xlaw2linear((i + 1) ^ mask);
+        v = (v1 + v2 + 4) >> 3;
+        for(;j<v;j+=1) {
+            linear_to_xlaw[8192 - j] = (i ^ (mask ^ 0x80));
             linear_to_xlaw[8192 + j] = (i ^ mask);
-            if (j > 0)
-                linear_to_xlaw[8192 - j] = (i ^ (mask ^ 0x80));
         }
     }
+    for(;j<8192;j++) {
+        linear_to_xlaw[8192 - j] = (127 ^ (mask ^ 0x80));
+        linear_to_xlaw[8192 + j] = (127 ^ mask);
+    }
     linear_to_xlaw[0] = linear_to_xlaw[1];
 }
 
-- 
2.6.4