Snow mmx + sse2 part 2

Patch by Robert Edele,  yartrebo <<at>> earthlink <<dot>> net

Originally committed as revision 5184 to svn://svn.ffmpeg.org/ffmpeg/trunk

1 files changed, 81 insertions, 65 deletions

diff --git a/libavcodec/snow.c b/libavcodec/snow.c
index 8fdc956c2b..084a298625 100644
--- a/libavcodec/snow.c
+++ b/libavcodec/snow.c
@@ -230,57 +230,57 @@ static const uint8_t obmc16[256]={
 };
 #elif 1 // 64*linear
 static const uint8_t obmc32[1024]={
- 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0,
- 0, 1, 1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 5, 5, 5, 4, 4, 4, 3, 3, 2, 2, 2, 1, 1, 1, 0,
- 0, 1, 2, 2, 3, 3, 4, 5, 5, 6, 7, 7, 8, 8, 9,10,10, 9, 8, 8, 7, 7, 6, 5, 5, 4, 3, 3, 2, 2, 1, 0,
- 0, 1, 2, 3, 4, 5, 6, 7, 7, 8, 9,10,11,12,13,14,14,13,12,11,10, 9, 8, 7, 7, 6, 5, 4, 3, 2, 1, 0,
- 1, 2, 3, 4, 5, 6, 7, 8,10,11,12,13,14,15,16,17,17,16,15,14,13,12,11,10, 8, 7, 6, 5, 4, 3, 2, 1,
- 1, 2, 3, 5, 6, 8, 9,10,12,13,14,16,17,19,20,21,21,20,19,17,16,14,13,12,10, 9, 8, 6, 5, 3, 2, 1,
- 1, 2, 4, 6, 7, 9,11,12,14,15,17,19,20,22,24,25,25,24,22,20,19,17,15,14,12,11, 9, 7, 6, 4, 2, 1,
- 1, 3, 5, 7, 8,10,12,14,16,18,20,22,23,25,27,29,29,27,25,23,22,20,18,16,14,12,10, 8, 7, 5, 3, 1,
- 1, 3, 5, 7,10,12,14,16,18,20,22,24,27,29,31,33,33,31,29,27,24,22,20,18,16,14,12,10, 7, 5, 3, 1,
- 1, 4, 6, 8,11,13,15,18,20,23,25,27,30,32,34,37,37,34,32,30,27,25,23,20,18,15,13,11, 8, 6, 4, 1,
- 1, 4, 7, 9,12,14,17,20,22,25,28,30,33,35,38,41,41,38,35,33,30,28,25,22,20,17,14,12, 9, 7, 4, 1,
- 1, 4, 7,10,13,16,19,22,24,27,30,33,36,39,42,45,45,42,39,36,33,30,27,24,22,19,16,13,10, 7, 4, 1,
- 2, 5, 8,11,14,17,20,23,27,30,33,36,39,42,45,48,48,45,42,39,36,33,30,27,23,20,17,14,11, 8, 5, 2,
- 2, 5, 8,12,15,19,22,25,29,32,35,39,42,46,49,52,52,49,46,42,39,35,32,29,25,22,19,15,12, 8, 5, 2,
- 2, 5, 9,13,16,20,24,27,31,34,38,42,45,49,53,56,56,53,49,45,42,38,34,31,27,24,20,16,13, 9, 5, 2,
- 2, 6,10,14,17,21,25,29,33,37,41,45,48,52,56,60,60,56,52,48,45,41,37,33,29,25,21,17,14,10, 6, 2,
- 2, 6,10,14,17,21,25,29,33,37,41,45,48,52,56,60,60,56,52,48,45,41,37,33,29,25,21,17,14,10, 6, 2,
- 2, 5, 9,13,16,20,24,27,31,34,38,42,45,49,53,56,56,53,49,45,42,38,34,31,27,24,20,16,13, 9, 5, 2,
- 2, 5, 8,12,15,19,22,25,29,32,35,39,42,46,49,52,52,49,46,42,39,35,32,29,25,22,19,15,12, 8, 5, 2,
- 2, 5, 8,11,14,17,20,23,27,30,33,36,39,42,45,48,48,45,42,39,36,33,30,27,23,20,17,14,11, 8, 5, 2,
- 1, 4, 7,10,13,16,19,22,24,27,30,33,36,39,42,45,45,42,39,36,33,30,27,24,22,19,16,13,10, 7, 4, 1,
- 1, 4, 7, 9,12,14,17,20,22,25,28,30,33,35,38,41,41,38,35,33,30,28,25,22,20,17,14,12, 9, 7, 4, 1,
- 1, 4, 6, 8,11,13,15,18,20,23,25,27,30,32,34,37,37,34,32,30,27,25,23,20,18,15,13,11, 8, 6, 4, 1,
- 1, 3, 5, 7,10,12,14,16,18,20,22,24,27,29,31,33,33,31,29,27,24,22,20,18,16,14,12,10, 7, 5, 3, 1,
- 1, 3, 5, 7, 8,10,12,14,16,18,20,22,23,25,27,29,29,27,25,23,22,20,18,16,14,12,10, 8, 7, 5, 3, 1,
- 1, 2, 4, 6, 7, 9,11,12,14,15,17,19,20,22,24,25,25,24,22,20,19,17,15,14,12,11, 9, 7, 6, 4, 2, 1,
- 1, 2, 3, 5, 6, 8, 9,10,12,13,14,16,17,19,20,21,21,20,19,17,16,14,13,12,10, 9, 8, 6, 5, 3, 2, 1,
- 1, 2, 3, 4, 5, 6, 7, 8,10,11,12,13,14,15,16,17,17,16,15,14,13,12,11,10, 8, 7, 6, 5, 4, 3, 2, 1,
- 0, 1, 2, 3, 4, 5, 6, 7, 7, 8, 9,10,11,12,13,14,14,13,12,11,10, 9, 8, 7, 7, 6, 5, 4, 3, 2, 1, 0,
- 0, 1, 2, 2, 3, 3, 4, 5, 5, 6, 7, 7, 8, 8, 9,10,10, 9, 8, 8, 7, 7, 6, 5, 5, 4, 3, 3, 2, 2, 1, 0,
- 0, 1, 1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 5, 5, 5, 4, 4, 4, 3, 3, 2, 2, 2, 1, 1, 1, 0,
- 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0,
+  0,  0,  0,  0,  4,  4,  4,  4,  4,  4,  4,  4,  8,  8,  8,  8,  8,  8,  8,  8,  4,  4,  4,  4,  4,  4,  4,  4,  0,  0,  0,  0,
+  0,  4,  4,  4,  8,  8,  8, 12, 12, 16, 16, 16, 20, 20, 20, 24, 24, 20, 20, 20, 16, 16, 16, 12, 12,  8,  8,  8,  4,  4,  4,  0,
+  0,  4,  8,  8, 12, 12, 16, 20, 20, 24, 28, 28, 32, 32, 36, 40, 40, 36, 32, 32, 28, 28, 24, 20, 20, 16, 12, 12,  8,  8,  4,  0,
+  0,  4,  8, 12, 16, 20, 24, 28, 28, 32, 36, 40, 44, 48, 52, 56, 56, 52, 48, 44, 40, 36, 32, 28, 28, 24, 20, 16, 12,  8,  4,  0,
+  4,  8, 12, 16, 20, 24, 28, 32, 40, 44, 48, 52, 56, 60, 64, 68, 68, 64, 60, 56, 52, 48, 44, 40, 32, 28, 24, 20, 16, 12,  8,  4,
+  4,  8, 12, 20, 24, 32, 36, 40, 48, 52, 56, 64, 68, 76, 80, 84, 84, 80, 76, 68, 64, 56, 52, 48, 40, 36, 32, 24, 20, 12,  8,  4,
+  4,  8, 16, 24, 28, 36, 44, 48, 56, 60, 68, 76, 80, 88, 96,100,100, 96, 88, 80, 76, 68, 60, 56, 48, 44, 36, 28, 24, 16,  8,  4,
+  4, 12, 20, 28, 32, 40, 48, 56, 64, 72, 80, 88, 92,100,108,116,116,108,100, 92, 88, 80, 72, 64, 56, 48, 40, 32, 28, 20, 12,  4,
+  4, 12, 20, 28, 40, 48, 56, 64, 72, 80, 88, 96,108,116,124,132,132,124,116,108, 96, 88, 80, 72, 64, 56, 48, 40, 28, 20, 12,  4,
+  4, 16, 24, 32, 44, 52, 60, 72, 80, 92,100,108,120,128,136,148,148,136,128,120,108,100, 92, 80, 72, 60, 52, 44, 32, 24, 16,  4,
+  4, 16, 28, 36, 48, 56, 68, 80, 88,100,112,120,132,140,152,164,164,152,140,132,120,112,100, 88, 80, 68, 56, 48, 36, 28, 16,  4,
+  4, 16, 28, 40, 52, 64, 76, 88, 96,108,120,132,144,156,168,180,180,168,156,144,132,120,108, 96, 88, 76, 64, 52, 40, 28, 16,  4,
+  8, 20, 32, 44, 56, 68, 80, 92,108,120,132,144,156,168,180,192,192,180,168,156,144,132,120,108, 92, 80, 68, 56, 44, 32, 20,  8,
+  8, 20, 32, 48, 60, 76, 88,100,116,128,140,156,168,184,196,208,208,196,184,168,156,140,128,116,100, 88, 76, 60, 48, 32, 20,  8,
+  8, 20, 36, 52, 64, 80, 96,108,124,136,152,168,180,196,212,224,224,212,196,180,168,152,136,124,108, 96, 80, 64, 52, 36, 20,  8,
+  8, 24, 40, 56, 68, 84,100,116,132,148,164,180,192,208,224,240,240,224,208,192,180,164,148,132,116,100, 84, 68, 56, 40, 24,  8,
+  8, 24, 40, 56, 68, 84,100,116,132,148,164,180,192,208,224,240,240,224,208,192,180,164,148,132,116,100, 84, 68, 56, 40, 24,  8,
+  8, 20, 36, 52, 64, 80, 96,108,124,136,152,168,180,196,212,224,224,212,196,180,168,152,136,124,108, 96, 80, 64, 52, 36, 20,  8,
+  8, 20, 32, 48, 60, 76, 88,100,116,128,140,156,168,184,196,208,208,196,184,168,156,140,128,116,100, 88, 76, 60, 48, 32, 20,  8,
+  8, 20, 32, 44, 56, 68, 80, 92,108,120,132,144,156,168,180,192,192,180,168,156,144,132,120,108, 92, 80, 68, 56, 44, 32, 20,  8,
+  4, 16, 28, 40, 52, 64, 76, 88, 96,108,120,132,144,156,168,180,180,168,156,144,132,120,108, 96, 88, 76, 64, 52, 40, 28, 16,  4,
+  4, 16, 28, 36, 48, 56, 68, 80, 88,100,112,120,132,140,152,164,164,152,140,132,120,112,100, 88, 80, 68, 56, 48, 36, 28, 16,  4,
+  4, 16, 24, 32, 44, 52, 60, 72, 80, 92,100,108,120,128,136,148,148,136,128,120,108,100, 92, 80, 72, 60, 52, 44, 32, 24, 16,  4,
+  4, 12, 20, 28, 40, 48, 56, 64, 72, 80, 88, 96,108,116,124,132,132,124,116,108, 96, 88, 80, 72, 64, 56, 48, 40, 28, 20, 12,  4,
+  4, 12, 20, 28, 32, 40, 48, 56, 64, 72, 80, 88, 92,100,108,116,116,108,100, 92, 88, 80, 72, 64, 56, 48, 40, 32, 28, 20, 12,  4,
+  4,  8, 16, 24, 28, 36, 44, 48, 56, 60, 68, 76, 80, 88, 96,100,100, 96, 88, 80, 76, 68, 60, 56, 48, 44, 36, 28, 24, 16,  8,  4,
+  4,  8, 12, 20, 24, 32, 36, 40, 48, 52, 56, 64, 68, 76, 80, 84, 84, 80, 76, 68, 64, 56, 52, 48, 40, 36, 32, 24, 20, 12,  8,  4,
+  4,  8, 12, 16, 20, 24, 28, 32, 40, 44, 48, 52, 56, 60, 64, 68, 68, 64, 60, 56, 52, 48, 44, 40, 32, 28, 24, 20, 16, 12,  8,  4,
+  0,  4,  8, 12, 16, 20, 24, 28, 28, 32, 36, 40, 44, 48, 52, 56, 56, 52, 48, 44, 40, 36, 32, 28, 28, 24, 20, 16, 12,  8,  4,  0,
+  0,  4,  8,  8, 12, 12, 16, 20, 20, 24, 28, 28, 32, 32, 36, 40, 40, 36, 32, 32, 28, 28, 24, 20, 20, 16, 12, 12,  8,  8,  4,  0,
+  0,  4,  4,  4,  8,  8,  8, 12, 12, 16, 16, 16, 20, 20, 20, 24, 24, 20, 20, 20, 16, 16, 16, 12, 12,  8,  8,  8,  4,  4,  4,  0,
+  0,  0,  0,  0,  4,  4,  4,  4,  4,  4,  4,  4,  8,  8,  8,  8,  8,  8,  8,  8,  4,  4,  4,  4,  4,  4,  4,  4,  0,  0,  0,  0,
  //error:0.000020
 };
 static const uint8_t obmc16[256]={
- 0, 1, 1, 2, 2, 3, 3, 4, 4, 3, 3, 2, 2, 1, 1, 0,
- 1, 2, 4, 5, 7, 8,10,11,11,10, 8, 7, 5, 4, 2, 1,
- 1, 4, 6, 9,11,14,16,19,19,16,14,11, 9, 6, 4, 1,
- 2, 5, 9,12,16,19,23,26,26,23,19,16,12, 9, 5, 2,
- 2, 7,11,16,20,25,29,34,34,29,25,20,16,11, 7, 2,
- 3, 8,14,19,25,30,36,41,41,36,30,25,19,14, 8, 3,
- 3,10,16,23,29,36,42,49,49,42,36,29,23,16,10, 3,
- 4,11,19,26,34,41,49,56,56,49,41,34,26,19,11, 4,
- 4,11,19,26,34,41,49,56,56,49,41,34,26,19,11, 4,
- 3,10,16,23,29,36,42,49,49,42,36,29,23,16,10, 3,
- 3, 8,14,19,25,30,36,41,41,36,30,25,19,14, 8, 3,
- 2, 7,11,16,20,25,29,34,34,29,25,20,16,11, 7, 2,
- 2, 5, 9,12,16,19,23,26,26,23,19,16,12, 9, 5, 2,
- 1, 4, 6, 9,11,14,16,19,19,16,14,11, 9, 6, 4, 1,
- 1, 2, 4, 5, 7, 8,10,11,11,10, 8, 7, 5, 4, 2, 1,
- 0, 1, 1, 2, 2, 3, 3, 4, 4, 3, 3, 2, 2, 1, 1, 0,
+  0,  4,  4,  8,  8, 12, 12, 16, 16, 12, 12,  8,  8,  4,  4,  0,
+  4,  8, 16, 20, 28, 32, 40, 44, 44, 40, 32, 28, 20, 16,  8,  4,
+  4, 16, 24, 36, 44, 56, 64, 76, 76, 64, 56, 44, 36, 24, 16,  4,
+  8, 20, 36, 48, 64, 76, 92,104,104, 92, 76, 64, 48, 36, 20,  8,
+  8, 28, 44, 64, 80,100,116,136,136,116,100, 80, 64, 44, 28,  8,
+ 12, 32, 56, 76,100,120,144,164,164,144,120,100, 76, 56, 32, 12,
+ 12, 40, 64, 92,116,144,168,196,196,168,144,116, 92, 64, 40, 12,
+ 16, 44, 76,104,136,164,196,224,224,196,164,136,104, 76, 44, 16,
+ 16, 44, 76,104,136,164,196,224,224,196,164,136,104, 76, 44, 16,
+ 12, 40, 64, 92,116,144,168,196,196,168,144,116, 92, 64, 40, 12,
+ 12, 32, 56, 76,100,120,144,164,164,144,120,100, 76, 56, 32, 12,
+  8, 28, 44, 64, 80,100,116,136,136,116,100, 80, 64, 44, 28,  8,
+  8, 20, 36, 48, 64, 76, 92,104,104, 92, 76, 64, 48, 36, 20,  8,
+  4, 16, 24, 36, 44, 56, 64, 76, 76, 64, 56, 44, 36, 24, 16,  4,
+  4,  8, 16, 20, 28, 32, 40, 44, 44, 40, 32, 28, 20, 16,  8,  4,
+  0,  4,  4,  8,  8, 12, 12, 16, 16, 12, 12,  8,  8,  4,  4,  0,
 //error:0.000015
 };
 #else //64*cos
@@ -342,23 +342,23 @@ static const uint8_t obmc16[256]={
 
 //linear *64
 static const uint8_t obmc8[64]={
- 1, 3, 5, 7, 7, 5, 3, 1,
- 3, 9,15,21,21,15, 9, 3,
- 5,15,25,35,35,25,15, 5,
- 7,21,35,49,49,35,21, 7,
- 7,21,35,49,49,35,21, 7,
- 5,15,25,35,35,25,15, 5,
- 3, 9,15,21,21,15, 9, 3,
- 1, 3, 5, 7, 7, 5, 3, 1,
+  4, 12, 20, 28, 28, 20, 12,  4,
+ 12, 36, 60, 84, 84, 60, 36, 12,
+ 20, 60,100,140,140,100, 60, 20,
+ 28, 84,140,196,196,140, 84, 28,
+ 28, 84,140,196,196,140, 84, 28,
+ 20, 60,100,140,140,100, 60, 20,
+ 12, 36, 60, 84, 84, 60, 36, 12,
+  4, 12, 20, 28, 28, 20, 12,  4,
 //error:0.000000
 };
 
 //linear *64
 static const uint8_t obmc4[16]={
- 4,12,12, 4,
-12,36,36,12,
-12,36,36,12,
- 4,12,12, 4,
+ 16, 48, 48, 16,
+ 48,144,144, 48,
+ 48,144,144, 48,
+ 16, 48, 48, 16,
 //error:0.000000
 };
 
@@ -2962,7 +2962,7 @@ static int get_dc(SnowContext *s, int mb_x, int mb_y, int plane_index){
     }
     *b= backup;
 
-    return clip(((ab<<6) + aa/2)/aa, 0, 255); //FIXME we shouldnt need cliping
+    return clip(((ab<<LOG2_OBMC_MAX) + aa/2)/aa, 0, 255); //FIXME we shouldnt need cliping
 }
 
 static inline int get_block_bits(SnowContext *s, int x, int y, int w){
@@ -3022,10 +3022,10 @@ static int get_block_rd(SnowContext *s, int mb_x, int mb_y, int plane_index, con
     const int penalty_factor= get_penalty_factor(s->lambda, s->lambda2, s->avctx->me_cmp);
     int sx= block_w*mb_x - block_w/2;
     int sy= block_w*mb_y - block_w/2;
-    const int x0= FFMAX(0,-sx);
-    const int y0= FFMAX(0,-sy);
-    const int x1= FFMIN(block_w*2, w-sx);
-    const int y1= FFMIN(block_w*2, h-sy);
+    int x0= FFMAX(0,-sx);
+    int y0= FFMAX(0,-sy);
+    int x1= FFMIN(block_w*2, w-sx);
+    int y1= FFMIN(block_w*2, h-sy);
     int i,x,y;
 
     pred_block(s, cur, ref, tmp, ref_stride, sx, sy, block_w*2, block_w*2, &s->block[mb_x + mb_y*b_stride], plane_index, w, h);
@@ -3043,6 +3043,22 @@ static int get_block_rd(SnowContext *s, int mb_x, int mb_y, int plane_index, con
         }
     }
 
+    /* copy the regions where obmc[] = (uint8_t)256 */
+    if(LOG2_OBMC_MAX == 8
+        && (mb_x == 0 || mb_x == b_stride-1)
+        && (mb_y == 0 || mb_y == b_height-1)){
+        if(mb_x == 0)
+            x1 = block_w;
+        else
+            x0 = block_w;
+        if(mb_y == 0)
+            y1 = block_w;
+        else
+            y0 = block_w;
+        for(y=y0; y<y1; y++)
+            memcpy(dst + sx+x0 + (sy+y)*ref_stride, cur + x0 + y*ref_stride, x1-x0);
+    }
+
     //FIXME sad/ssd can be broken up, but wavelet cmp should be one 32x32 block
     if(block_w==16){
         distortion = 0;