Reworked context conversion between 8x8 and 4x4

The commit rationized and simplified the entropy context conversion
betwen MB using 8x8 transform and MB using 4x4 transform. The old version
had a number of weirdness in how 4x4 transform MB's context is used for
8x8 blocks other than the first 8x8 within a MB.

Test showed the change has a gain ~.1% for avg psnr, glb psnr and ssim on
the limited HD set.

Change-Id: I774536c416baa6845aa741f956d8a69fa40e5d47

7 files changed, 84 insertions, 309 deletions

diff --git a/vp8/common/blockd.c b/vp8/common/blockd.c
index 1fc3cd0ca..661a77fe5 100644
--- a/vp8/common/blockd.c
+++ b/vp8/common/blockd.c
@@ -12,6 +12,7 @@
 #include "blockd.h"
 #include "vpx_mem/vpx_mem.h"
 
+
 const unsigned char vp8_block2left[25] =
 {
     0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8
@@ -20,3 +21,16 @@ const unsigned char vp8_block2above[25] =
 {
     0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 4, 5, 4, 5, 6, 7, 6, 7, 8
 };
+
+
+const unsigned char vp8_block2left_8x8[25] =
+{
+    0, 0, 0, 0, 0, 0, 0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 6, 6, 6, 6, 8
+};
+const unsigned char vp8_block2above_8x8[25] =
+{
+    0, 0, 0, 0, 2, 2, 2, 2, 0, 0, 0, 0, 2, 2, 2, 2, 4, 4, 4, 4, 6, 6, 6, 6, 8
+};
+
+
+
diff --git a/vp8/common/blockd.h b/vp8/common/blockd.h
index cadc44229..7850fb065 100644
--- a/vp8/common/blockd.h
+++ b/vp8/common/blockd.h
@@ -65,6 +65,9 @@ typedef struct
 
 extern const unsigned char vp8_block2left[25];
 extern const unsigned char vp8_block2above[25];
+extern const unsigned char vp8_block2left_8x8[25];
+extern const unsigned char vp8_block2above_8x8[25];
+
 
 #define VP8_COMBINEENTROPYCONTEXTS( Dest, A, B) \
     Dest = ((A)!=0) + ((B)!=0);
diff --git a/vp8/decoder/detokenize.c b/vp8/decoder/detokenize.c
index 905c29ec4..d7dc143c7 100644
--- a/vp8/decoder/detokenize.c
+++ b/vp8/decoder/detokenize.c
@@ -321,20 +321,9 @@ int vp8_decode_mb_tokens_8x8(VP8D_COMP *dx, MACROBLOCKD *x)
     coef_probs = oc->fc.coef_probs_8x8 [type] [ 0 ] [0];
 
 BLOCK_LOOP_8x8:
-    a = A + vp8_block2above[i];
-    l = L + vp8_block2left[i];
-
-    if(i < 16)
-    {
-       a1 = A + vp8_block2above[i+1];
-       l1 = L + vp8_block2left[i+4];
-    }
-    else if(i<24)
-    {
-      a1 = A + vp8_block2above[i+1];
-      l1 = L + vp8_block2left[i+2];
+    a = A + vp8_block2above_8x8[i];
+    l = L + vp8_block2left_8x8[i];
 
-    }
     c = (INT16)(!type);
 
 //    Dest = ((A)!=0) + ((B)!=0);
@@ -350,7 +339,7 @@ BLOCK_LOOP_8x8:
     }
     else
     {
-      VP8_COMBINEENTROPYCONTEXTS_8x8(v, *a, *l, *a1, *l1);
+      VP8_COMBINEENTROPYCONTEXTS(v, *a, *l);
       if ( segfeature_active( x, segment_id, SEG_LVL_EOB ) )
       {
           seg_eob = get_segdata( x, segment_id, SEG_LVL_EOB );
@@ -549,45 +538,10 @@ ONE_CONTEXT_NODE_0_8x8_:
 
 BLOCK_FINISHED_8x8:
     *a = *l = ((eobs[i] = c) != !type);   // any nonzero data?
-    /*if (i!=24) {
-      *(A + vp8_block2above[i+1]) = *(A + vp8_block2above[i+2]) = *(A + vp8_block2above[i+3]) = *a;
-      *(L + vp8_block2left[i+1]) = *(L + vp8_block2left[i+2]) = *(L + vp8_block2left[i+3]) = *l;
-    }*/
-
     if (i!=24)
     {
-      if(i==0)
-      {
-        *(A + vp8_block2above[1]) = *(A + vp8_block2above[4]) = *(A + vp8_block2above[5]) = *a;
-        *(L + vp8_block2left[1]) = *(L + vp8_block2left[4]) = *(L + vp8_block2left[5]) = *l;
-      }
-      else if(i==4)
-      {
-        *(A + vp8_block2above[2]) = *(A + vp8_block2above[3]) = *(A + vp8_block2above[6]) = *(A + vp8_block2above[7]) = *a;
-        *(L + vp8_block2left[2]) = *(L + vp8_block2left[3]) = *(L + vp8_block2left[6]) = *(L + vp8_block2left[7]) = *l;
-        *(A + vp8_block2above[4]) = *(A + vp8_block2above[1]);
-        *(L + vp8_block2left[4]) = *(L + vp8_block2left[1]);
-      }
-      else if(i==8)
-      {
-        *(A + vp8_block2above[9]) = *(A + vp8_block2above[12]) = *(A + vp8_block2above[13]) = *a;
-        *(L + vp8_block2left[9]) = *(L + vp8_block2left[12]) = *(L + vp8_block2left[13]) = *l;
-
-      }
-      else if(i==12)
-      {
-        *(A + vp8_block2above[10]) = *(A + vp8_block2above[11]) = *(A + vp8_block2above[14]) = *(A + vp8_block2above[15]) = *a;
-        *(L + vp8_block2left[10]) = *(L + vp8_block2left[11]) = *(L + vp8_block2left[14]) = *(L + vp8_block2left[15]) = *l;
-        *(A + vp8_block2above[12]) = *(A + vp8_block2above[8]);
-        *(L + vp8_block2left[12]) = *(L + vp8_block2left[8]);
-
-      }
-      else
-      {
-        *(A + vp8_block2above[i+1]) = *(A + vp8_block2above[i+2]) = *(A + vp8_block2above[i+3]) = *a;
-        *(L + vp8_block2left[i+1]) = *(L + vp8_block2left[i+2]) = *(L + vp8_block2left[i+3]) = *l;
-
-      }
+        *(a + 1)    =  *a;
+        *(l + 1)    = *l;
     }
 
     eobtotal += c;
diff --git a/vp8/encoder/bitstream.c b/vp8/encoder/bitstream.c
index 078a29791..c2613bfbd 100644
--- a/vp8/encoder/bitstream.c
+++ b/vp8/encoder/bitstream.c
@@ -2429,6 +2429,7 @@ static void update_coef_probs(VP8_COMP *cpi)
                             ((vp8_cost_one(upd) - vp8_cost_zero(upd)) >> 8);
                         const int s = old_b - new_b - update_b;
                         const int u = s > 0 ? 1 : 0;
+
 #ifdef ENTROPY_STATS
                         ++ tree_update_hist_8x8 [i][j][k][t] [u];
 #endif
diff --git a/vp8/encoder/encodemb.c b/vp8/encoder/encodemb.c
index b8f92c970..22bf92b07 100644
--- a/vp8/encoder/encodemb.c
+++ b/vp8/encoder/encodemb.c
@@ -656,7 +656,6 @@ static void check_reset_8x8_2nd_coeffs(MACROBLOCKD *x, int type,
                                    ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l)
 {
     int sum=0;
-    int i;
     BLOCKD *bd = &x->block[24];
     int coef;
 
@@ -802,7 +801,6 @@ void vp8_optimize_mbuv(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
 #if CONFIG_T8X8
 void optimize_b_8x8(MACROBLOCK *mb, int i, int type,
                     ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l,
-                    ENTROPY_CONTEXT *a1, ENTROPY_CONTEXT *l1,
                     const VP8_ENCODER_RTCD *rtcd)
 {
     BLOCK *b;
@@ -1010,7 +1008,7 @@ void optimize_b_8x8(MACROBLOCK *mb, int i, int type,
 
     /* Now pick the best path through the whole trellis. */
     band = vp8_coef_bands_8x8[i + 1];
-    VP8_COMBINEENTROPYCONTEXTS_8x8(pt, *a, *l, *a1, *l1);
+    VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);
     rate0 = tokens[next][0].rate;
     rate1 = tokens[next][1].rate;
     error0 = tokens[next][0].error;
@@ -1051,7 +1049,6 @@ void optimize_mb_8x8(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
 {
     int b;
     int type;
-    int has_2nd_order;
     ENTROPY_CONTEXT_PLANES t_above, t_left;
     ENTROPY_CONTEXT *ta;
     ENTROPY_CONTEXT *tl;
@@ -1062,79 +1059,28 @@ void optimize_mb_8x8(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
     ta = (ENTROPY_CONTEXT *)&t_above;
     tl = (ENTROPY_CONTEXT *)&t_left;
 
-    has_2nd_order = (x->e_mbd.mode_info_context->mbmi.mode != B_PRED
-        &&x->e_mbd.mode_info_context->mbmi.mode != I8X8_PRED
-        && x->e_mbd.mode_info_context->mbmi.mode != SPLITMV);
-    type = has_2nd_order ? 0 : 3;
-
+    type = 0;
     for (b = 0; b < 16; b+=4)
     {
         optimize_b_8x8(x, b, type,
-            ta + vp8_block2above[b], tl + vp8_block2left[b],
-            ta + vp8_block2above[b+1], tl + vp8_block2left[b+4],
-            rtcd);
-
-        if(b==0)
-        {
-          *(ta + vp8_block2above[1]) = *(ta + vp8_block2above[4]) = *(ta + vp8_block2above[5]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[1]) = *(tl + vp8_block2left[4]) = *(tl + vp8_block2left[5]) = *(tl + vp8_block2left[b]);
-        }
-        else if(b==4)
-        {
-          *(ta + vp8_block2above[2]) = *(ta + vp8_block2above[3]) = *(ta + vp8_block2above[6]) = *(ta + vp8_block2above[7]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[2]) = *(tl + vp8_block2left[3]) = *(tl + vp8_block2left[6]) = *(tl + vp8_block2left[7]) = *(tl + vp8_block2left[b]);
-          *(ta + vp8_block2above[4]) = *(ta + vp8_block2above[1]);
-          *(tl + vp8_block2left[4]) = *(tl + vp8_block2left[1]);
-        }
-        else if(b==8)
-        {
-          *(ta + vp8_block2above[9]) = *(ta + vp8_block2above[12]) = *(ta + vp8_block2above[13]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[9]) = *(tl + vp8_block2left[12]) = *(tl + vp8_block2left[13]) = *(tl + vp8_block2left[b]);
-
-        }
-        else if(b==12)
-        {
-          *(ta + vp8_block2above[10]) = *(ta + vp8_block2above[11]) = *(ta + vp8_block2above[14]) = *(ta + vp8_block2above[15]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[10]) = *(tl + vp8_block2left[11]) = *(tl + vp8_block2left[14]) = *(tl + vp8_block2left[15]) = *(tl + vp8_block2left[b]);
-          *(ta + vp8_block2above[12]) = *(ta + vp8_block2above[8]);
-          *(tl + vp8_block2left[12]) = *(tl + vp8_block2left[8]);
-
-        }
-
-
-
-    }
-
-    for (b = 16; b < 20; b+=4)
-    {
-        optimize_b_8x8(x, b, PLANE_TYPE_UV, //vp8_block2type[b],
-            ta + vp8_block2above[b], tl + vp8_block2left[b],
-            ta + vp8_block2above[b+1], tl + vp8_block2left[b+2],
+            ta + vp8_block2above_8x8[b], tl + vp8_block2left_8x8[b],
             rtcd);
-        *(ta + vp8_block2above[b+1]) = *(ta + vp8_block2above[b+2]) = *(ta + vp8_block2above[b+3]) =
-            *(ta + vp8_block2above[b]);
-        *(tl + vp8_block2left[b+1]) = *(tl + vp8_block2left[b+2]) = *(tl + vp8_block2left[b+3]) =
-            *(tl + vp8_block2left[b]);
-
+        *(ta + vp8_block2above_8x8[b] + 1) = *(ta + vp8_block2above_8x8[b]);
+        *(tl + vp8_block2left_8x8[b] + 1)  = *(tl + vp8_block2left_8x8[b] );
     }
 
-    for (b = 20; b < 24; b+=4)
+    for (b = 16; b < 24; b+=4)
     {
-        optimize_b_8x8(x, b, PLANE_TYPE_UV, //vp8_block2type[b],
-            ta + vp8_block2above[b], tl + vp8_block2left[b],
-            ta + vp8_block2above[b+1], tl + vp8_block2left[b+2],
+        optimize_b_8x8(x, b, PLANE_TYPE_UV,
+            ta + vp8_block2above_8x8[b], tl + vp8_block2left_8x8[b],
             rtcd);
-        *(ta + vp8_block2above[b+1]) = *(ta + vp8_block2above[b+2]) = *(ta + vp8_block2above[b+3]) =
-            *(ta + vp8_block2above[b]);
-        *(tl + vp8_block2left[b+1]) = *(tl + vp8_block2left[b+2]) = *(tl + vp8_block2left[b+3]) =
-            *(tl + vp8_block2left[b]);
-
+        *(ta + vp8_block2above_8x8[b]+1) = *(ta + vp8_block2above_8x8[b]);
+        *(tl + vp8_block2left_8x8[b]+1 ) = *(tl + vp8_block2left_8x8[b]);
     }
 
     //8x8 always have 2nd roder haar block
     check_reset_8x8_2nd_coeffs(&x->e_mbd, PLANE_TYPE_Y2,
-            ta + vp8_block2above[24], tl + vp8_block2left[24]);
-
+            ta + vp8_block2above_8x8[24], tl + vp8_block2left_8x8[24]);
 
 }
 
@@ -1160,50 +1106,18 @@ void vp8_optimize_mby_8x8(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
 
     ta = (ENTROPY_CONTEXT *)&t_above;
     tl = (ENTROPY_CONTEXT *)&t_left;
-
-    has_2nd_order = (x->e_mbd.mode_info_context->mbmi.mode != B_PRED
-        && x->e_mbd.mode_info_context->mbmi.mode != I8X8_PRED
-        && x->e_mbd.mode_info_context->mbmi.mode != SPLITMV);
-    type = has_2nd_order ? 0 : 3;
-
+    type = 0;
     for (b = 0; b < 16; b+=4)
     {
         optimize_b_8x8(x, b, type,
         ta + vp8_block2above[b], tl + vp8_block2left[b],
-        ta + vp8_block2above[b+1], tl + vp8_block2left[b+4],
         rtcd);
-        if(b==0)
-        {
-          *(ta + vp8_block2above[1]) = *(ta + vp8_block2above[4]) = *(ta + vp8_block2above[5]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[1]) = *(tl + vp8_block2left[4]) = *(tl + vp8_block2left[5]) = *(tl + vp8_block2left[b]);
-        }
-        else if(b==4)
-        {
-          *(ta + vp8_block2above[2]) = *(ta + vp8_block2above[3]) = *(ta + vp8_block2above[6]) = *(ta + vp8_block2above[7]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[2]) = *(tl + vp8_block2left[3]) = *(tl + vp8_block2left[6]) = *(tl + vp8_block2left[7]) = *(tl + vp8_block2left[b]);
-          *(ta + vp8_block2above[4]) = *(ta + vp8_block2above[1]);
-          *(tl + vp8_block2left[4]) = *(tl + vp8_block2left[1]);
-        }
-        else if(b==8)
-        {
-          *(ta + vp8_block2above[9]) = *(ta + vp8_block2above[12]) = *(ta + vp8_block2above[13]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[9]) = *(tl + vp8_block2left[12]) = *(tl + vp8_block2left[13]) = *(tl + vp8_block2left[b]);
-
-        }
-        else if(b==12)
-        {
-          *(ta + vp8_block2above[10]) = *(ta + vp8_block2above[11]) = *(ta + vp8_block2above[14]) = *(ta + vp8_block2above[15]) = *(ta + vp8_block2above[b]);
-          *(tl + vp8_block2left[10]) = *(tl + vp8_block2left[11]) = *(tl + vp8_block2left[14]) = *(tl + vp8_block2left[15]) = *(tl + vp8_block2left[b]);
-          *(ta + vp8_block2above[12]) = *(ta + vp8_block2above[8]);
-          *(tl + vp8_block2left[12]) = *(tl + vp8_block2left[8]);
-
-        }
-
-
+        *(ta + vp8_block2above_8x8[b] + 1) = *(ta + vp8_block2above_8x8[b]);
+        *(tl + vp8_block2left_8x8[b] + 1)  = *(tl + vp8_block2left_8x8[b] );
     }
     //8x8 always have 2nd roder haar block
     check_reset_8x8_2nd_coeffs(&x->e_mbd, PLANE_TYPE_Y2,
-            ta + vp8_block2above[24], tl + vp8_block2left[24]);
+            ta + vp8_block2above_8x8[24], tl + vp8_block2left_8x8[24]);
 
 }
 
@@ -1226,30 +1140,13 @@ void vp8_optimize_mbuv_8x8(MACROBLOCK *x, const VP8_ENCODER_RTCD *rtcd)
     ta = (ENTROPY_CONTEXT *)&t_above;
     tl = (ENTROPY_CONTEXT *)&t_left;
 
-    for (b = 16; b < 20; b+=4)
+    for (b = 16; b < 24; b+=4)
     {
-        optimize_b_8x8(x, b, PLANE_TYPE_UV, //vp8_block2type[b],
-            ta + vp8_block2above[b], tl + vp8_block2left[b],
-            ta + vp8_block2above[b+1], tl + vp8_block2left[b+2],
+        optimize_b_8x8(x, b, PLANE_TYPE_UV,
+            ta + vp8_block2above_8x8[b], tl + vp8_block2left_8x8[b],
             rtcd);
-        *(ta + vp8_block2above[b+1]) = *(ta + vp8_block2above[b+2]) = *(ta + vp8_block2above[b+3]) =
-            *(ta + vp8_block2above[b]);
-        *(tl + vp8_block2left[b+1]) = *(tl + vp8_block2left[b+2]) = *(tl + vp8_block2left[b+3]) =
-            *(tl + vp8_block2left[b]);
-
-    }
-
-    for (b = 20; b < 24; b+=4)
-    {
-        optimize_b_8x8(x, b, PLANE_TYPE_UV, //vp8_block2type[b],
-            ta + vp8_block2above[b], tl + vp8_block2left[b],
-            ta + vp8_block2above[b+1], tl + vp8_block2left[b+2],
-            rtcd);
-        *(ta + vp8_block2above[b+1]) = *(ta + vp8_block2above[b+2]) = *(ta + vp8_block2above[b+3]) =
-            *(ta + vp8_block2above[b]);
-        *(tl + vp8_block2left[b+1]) = *(tl + vp8_block2left[b+2]) = *(tl + vp8_block2left[b+3]) =
-            *(tl + vp8_block2left[b]);
-
+        *(ta + vp8_block2above_8x8[b]+1) = *(ta + vp8_block2above_8x8[b]);
+        *(tl + vp8_block2left_8x8[b]+1 ) = *(tl + vp8_block2left_8x8[b]);
     }
 
 }
diff --git a/vp8/encoder/rdopt.c b/vp8/encoder/rdopt.c
index 61ee7fe5c..73cd21e2a 100644
--- a/vp8/encoder/rdopt.c
+++ b/vp8/encoder/rdopt.c
@@ -690,8 +690,7 @@ static int cost_coeffs_2x2(MACROBLOCK *mb,
 
 static int cost_coeffs_8x8(MACROBLOCK *mb,
                            BLOCKD *b, int type,
-                           ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l,
-                           ENTROPY_CONTEXT *a1, ENTROPY_CONTEXT *l1)
+                           ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l)
 {
     int c = !type;              /* start at coef 0, unless Y with Y2 */
     int eob = b->eob;
@@ -699,7 +698,7 @@ static int cost_coeffs_8x8(MACROBLOCK *mb,
     int cost = 0;
     short *qcoeff_ptr = b->qcoeff;
 
-    VP8_COMBINEENTROPYCONTEXTS_8x8(pt, *a, *l, *a1, *l1);
+    VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);
 
 # define QC8X8( I)  ( qcoeff_ptr [vp8_default_zig_zag1d_8x8[I]] )
 
@@ -738,8 +737,7 @@ static int vp8_rdcost_mby_8x8(MACROBLOCK *mb)
 
     for (b = 0; b < 16; b+=4)
         cost += cost_coeffs_8x8(mb, x->block + b, PLANE_TYPE_Y_NO_DC,
-                    ta + vp8_block2above[b], tl + vp8_block2left[b],
-                    ta + vp8_block2above[b+1], tl + vp8_block2left[b+4]);
+                    ta + vp8_block2above_8x8[b], tl + vp8_block2left_8x8[b]);
 
     cost += cost_coeffs_2x2(mb, x->block + 24, PLANE_TYPE_Y2,
                 ta + vp8_block2above[24], tl + vp8_block2left[24]);
@@ -1204,10 +1202,8 @@ static int rd_cost_mbuv_8x8(MACROBLOCK *mb)
 
     for (b = 16; b < 24; b+=4)
         cost += cost_coeffs_8x8(mb, x->block + b, PLANE_TYPE_UV,
-                                ta + vp8_block2above[b],
-                                tl + vp8_block2left[b],
-                                ta + vp8_block2above[b+1],
-                                tl + vp8_block2left[b+2]);
+                                ta + vp8_block2above_8x8[b],
+                                tl + vp8_block2left_8x8[b]);
 
     return cost;
 }
diff --git a/vp8/encoder/tokenize.c b/vp8/encoder/tokenize.c
index aa9dd8ee8..d496bbde1 100644
--- a/vp8/encoder/tokenize.c
+++ b/vp8/encoder/tokenize.c
@@ -257,8 +257,6 @@ static void tokenize1st_order_b_8x8
     const FRAME_TYPE frametype,
     ENTROPY_CONTEXT *a,
     ENTROPY_CONTEXT *l,
-    ENTROPY_CONTEXT *a1,
-    ENTROPY_CONTEXT *l1,
     VP8_COMP *cpi
 )
 {
@@ -277,7 +275,7 @@ static void tokenize1st_order_b_8x8
         seg_eob = get_segdata( xd, segment_id, SEG_LVL_EOB );
     }
 
-    VP8_COMBINEENTROPYCONTEXTS_8x8(pt, *a, *l, *a1, *l1);
+    VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);
 
     do
     {
@@ -559,7 +557,8 @@ void vp8_tokenize_mb(VP8_COMP *cpi, MACROBLOCKD *x, TOKENEXTRA **t)
             ENTROPY_CONTEXT * L = (ENTROPY_CONTEXT *)x->left_context;
             tokenize2nd_order_b_8x8(x,
                         x->block + 24, t, 1, x->frame_type,
-                       A + vp8_block2above[24], L + vp8_block2left[24], cpi);
+                        A + vp8_block2above_8x8[24],
+                        L + vp8_block2left_8x8[24], cpi);
         }
         else
 #endif
@@ -576,56 +575,22 @@ void vp8_tokenize_mb(VP8_COMP *cpi, MACROBLOCKD *x, TOKENEXTRA **t)
         for (b = 0; b < 16; b+=4)
         {
             tokenize1st_order_b_8x8(x,
-                                x->block + b, t, plane_type, x->frame_type,
-                                A + vp8_block2above[b],
-                                L + vp8_block2left[b],
-                                A + vp8_block2above[b+1],
-                                L + vp8_block2left[b+4],
-                                cpi);
-          /* *(A + vp8_block2above[b+1]) = *(A + vp8_block2above[b+2]) = *(A + vp8_block2above[b+3]) =
-                *(A + vp8_block2above[b]);
-            *(L + vp8_block2left[b+1]) = *(L + vp8_block2left[b+2]) = *(L + vp8_block2left[b+3]) =
-                *(L + vp8_block2left[b]);*/
-            // build coeff context for 8x8 transform
-              if(b==0)
-              {
-                *(A + vp8_block2above[1]) = *(A + vp8_block2above[4]) = *(A + vp8_block2above[5]) = *(A + vp8_block2above[b]);
-                *(L + vp8_block2left[1]) = *(L + vp8_block2left[4]) = *(L + vp8_block2left[5]) = *(L + vp8_block2left[b]);
-              }
-              else if(b==4)
-              {
-                *(A + vp8_block2above[2]) = *(A + vp8_block2above[3]) = *(A + vp8_block2above[6]) = *(A + vp8_block2above[7]) = *(A + vp8_block2above[b]);
-                *(L + vp8_block2left[2]) = *(L + vp8_block2left[3]) = *(L + vp8_block2left[6]) = *(L + vp8_block2left[7]) = *(L + vp8_block2left[b]);
-                *(A + vp8_block2above[4]) = *(A + vp8_block2above[1]);
-                *(L + vp8_block2left[4]) = *(L + vp8_block2left[1]);
-              }
-              else if(b==8)
-              {
-                *(A + vp8_block2above[9]) = *(A + vp8_block2above[12]) = *(A + vp8_block2above[13]) = *(A + vp8_block2above[b]);
-                *(L + vp8_block2left[9]) = *(L + vp8_block2left[12]) = *(L + vp8_block2left[13]) = *(L + vp8_block2left[b]);
-              }
-              else if(b==12)
-              {
-                *(A + vp8_block2above[10]) = *(A + vp8_block2above[11]) = *(A + vp8_block2above[14]) = *(A + vp8_block2above[15]) = *(A + vp8_block2above[b]);
-                *(L + vp8_block2left[10]) = *(L + vp8_block2left[11]) = *(L + vp8_block2left[14]) = *(L + vp8_block2left[15]) = *(L + vp8_block2left[b]);
-                *(A + vp8_block2above[12]) = *(A + vp8_block2above[8]);
-                *(L + vp8_block2left[12]) = *(L + vp8_block2left[8]);
-             }
-
+                x->block + b, t, plane_type, x->frame_type,
+                A + vp8_block2above_8x8[b],
+                L + vp8_block2left_8x8[b],
+                cpi);
+            *(A + vp8_block2above_8x8[b] + 1) = *(A + vp8_block2above_8x8[b]);
+            *(L + vp8_block2left_8x8[b] + 1)  = *(L + vp8_block2left_8x8[b] );
         }
-
-        for (b = 16; b < 24; b+=4) {
+        for (b = 16; b < 24; b+=4)
+        {
             tokenize1st_order_b_8x8(x,
-                                    x->block + b, t, 2, x->frame_type,
-                                    A + vp8_block2above[b],
-                                    L + vp8_block2left[b],
-                                    A + vp8_block2above[b+1],
-                                    L + vp8_block2left[b+2],
-                                    cpi);
-            *(A + vp8_block2above[b+1]) = *(A + vp8_block2above[b+2]) = *(A + vp8_block2above[b+3]) =
-                *(A + vp8_block2above[b]);
-            *(L + vp8_block2left[b+1]) = *(L + vp8_block2left[b+2]) = *(L + vp8_block2left[b+3]) =
-                *(L + vp8_block2left[b]);
+                x->block + b, t, 2, x->frame_type,
+                A + vp8_block2above_8x8[b],
+                L + vp8_block2left_8x8[b],
+                cpi);
+            *(A + vp8_block2above_8x8[b]+1) = *(A + vp8_block2above_8x8[b]);
+            *(L + vp8_block2left_8x8[b]+1 ) = *(L + vp8_block2left_8x8[b]);
         }
     }
     else
@@ -806,14 +771,12 @@ static __inline void stuff1st_order_b_8x8
     const FRAME_TYPE frametype,
     ENTROPY_CONTEXT *a,
     ENTROPY_CONTEXT *l,
-    ENTROPY_CONTEXT *a1,
-    ENTROPY_CONTEXT *l1,
     VP8_COMP *cpi
 )
 {
     int pt; /* near block/prev token context index */
     TOKENEXTRA *t = *tp;        /* store tokens starting here */
-    VP8_COMBINEENTROPYCONTEXTS_8x8(pt, *a, *l, *a1, *l1);
+    VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);
     (void) frametype;
     (void) type;
     (void) b;
@@ -840,14 +803,12 @@ void stuff1st_order_buv_8x8
     const FRAME_TYPE frametype,
     ENTROPY_CONTEXT *a,
     ENTROPY_CONTEXT *l,
-    ENTROPY_CONTEXT *a1,
-    ENTROPY_CONTEXT *l1,
     VP8_COMP *cpi
 )
 {
     int pt; /* near block/prev token context index */
     TOKENEXTRA *t = *tp;        /* store tokens starting here */
-    VP8_COMBINEENTROPYCONTEXTS_8x8(pt, *a, *l, *a1, *l1);
+    VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);
     (void) frametype;
     (void) type;
     (void) b;
@@ -872,80 +833,29 @@ void vp8_stuff_mb_8x8(VP8_COMP *cpi, MACROBLOCKD *x, TOKENEXTRA **t)
     int b;
 
     stuff2nd_order_b_8x8(x->block + 24, t, 1, x->frame_type,
-                         A + vp8_block2above[24], L + vp8_block2left[24], cpi);
+                         A + vp8_block2above_8x8[24],
+                         L + vp8_block2left_8x8[24], cpi);
     plane_type = 0;
 
-    for (b = 0; b < 16; b+=4) {
-        stuff1st_order_b_8x8(x->block + b, t, plane_type, x->frame_type,
-                             A + vp8_block2above[b],
-                             L + vp8_block2left[b],
-                             A + vp8_block2above[b+1],
-                             L + vp8_block2left[b+4],
-                             cpi);
-        // build coeff context for 8x8 transform
-        if(b==0)
-        {
-          *(A + vp8_block2above[1]) = *(A + vp8_block2above[4]) = *(A + vp8_block2above[5]) = *(A + vp8_block2above[b]);
-          *(L + vp8_block2left[1]) = *(L + vp8_block2left[4]) = *(L + vp8_block2left[5]) = *(L + vp8_block2left[b]);
-        }
-        else if(b==4)
-        {
-          *(A + vp8_block2above[2]) = *(A + vp8_block2above[3]) = *(A + vp8_block2above[6]) = *(A + vp8_block2above[7]) = *(A + vp8_block2above[b]);
-          *(L + vp8_block2left[2]) = *(L + vp8_block2left[3]) = *(L + vp8_block2left[6]) = *(L + vp8_block2left[7]) = *(L + vp8_block2left[b]);
-          *(A + vp8_block2above[4]) = *(A + vp8_block2above[1]);
-          *(L + vp8_block2left[4]) = *(L + vp8_block2left[1]);
-        }
-        else if(b==8)
-        {
-          *(A + vp8_block2above[9]) = *(A + vp8_block2above[12]) = *(A + vp8_block2above[13]) = *(A + vp8_block2above[b]);
-          *(L + vp8_block2left[9]) = *(L + vp8_block2left[12]) = *(L + vp8_block2left[13]) = *(L + vp8_block2left[b]);
-
-        }
-        else if(b==12)
-        {
-          *(A + vp8_block2above[10]) = *(A + vp8_block2above[11]) = *(A + vp8_block2above[14]) = *(A + vp8_block2above[15]) = *(A + vp8_block2above[b]);
-          *(L + vp8_block2left[10]) = *(L + vp8_block2left[11]) = *(L + vp8_block2left[14]) = *(L + vp8_block2left[15]) = *(L + vp8_block2left[b]);
-          *(A + vp8_block2above[12]) = *(A + vp8_block2above[8]);
-          *(L + vp8_block2left[12]) = *(L + vp8_block2left[8]);
-
-        }
-
-    }
-    /*
-    for (b = 0; b < 16; b+=4) {
+    for (b = 0; b < 16; b+=4)
+    {
         stuff1st_order_b_8x8(x->block + b, t, plane_type, x->frame_type,
-                             A + vp8_block2above[b],
-                             L + vp8_block2left[b], cpi);
-        *(A + vp8_block2above[b+1]) = *(A + vp8_block2above[b+2]) = *(A + vp8_block2above[b+3]) =
-            *(A + vp8_block2above[b]);
-        *(L + vp8_block2left[b+1]) = *(L + vp8_block2left[b+2]) = *(L + vp8_block2left[b+3]) =
-            *(L + vp8_block2left[b]);
-    }
-    */
-
-    for (b = 16; b < 24; b+=4) {
-      stuff1st_order_buv_8x8(x->block + b, t, 2, x->frame_type,
-                             A + vp8_block2above[b],
-                             L + vp8_block2left[b],
-                             A + vp8_block2above[b+1],
-                             L + vp8_block2left[b+2],
-                             cpi);
-      *(A + vp8_block2above[b+1]) = *(A + vp8_block2above[b+2]) = *(A + vp8_block2above[b+3]) =
-          *(A + vp8_block2above[b]);
-      *(L + vp8_block2left[b+1]) = *(L + vp8_block2left[b+2]) = *(L + vp8_block2left[b+3]) =
-          *(L + vp8_block2left[b]);
+            A + vp8_block2above_8x8[b],
+            L + vp8_block2left_8x8[b],
+            cpi);
+        *(A + vp8_block2above_8x8[b] + 1) = *(A + vp8_block2above_8x8[b]);
+        *(L + vp8_block2left_8x8[b] + 1)  = *(L + vp8_block2left_8x8[b] );
     }
-    /*
-    for (b = 16; b < 24; b+=4) {
+
+    for (b = 16; b < 24; b+=4)
+    {
         stuff1st_order_buv_8x8(x->block + b, t, 2, x->frame_type,
-                               A + vp8_block2above[b],
-                               L + vp8_block2left[b], cpi);
-        *(A + vp8_block2above[b+1]) = *(A + vp8_block2above[b+2]) = *(A + vp8_block2above[b+3]) =
-            *(A + vp8_block2above[b]);
-        *(L + vp8_block2left[b+1]) = *(L + vp8_block2left[b+2]) = *(L + vp8_block2left[b+3]) =
-            *(L + vp8_block2left[b]);
+            A + vp8_block2above[b],
+            L + vp8_block2left[b],
+            cpi);
+        *(A + vp8_block2above_8x8[b]+1) = *(A + vp8_block2above_8x8[b]);
+        *(L + vp8_block2left_8x8[b]+1 ) = *(L + vp8_block2left_8x8[b]);
     }
-    */
 }
 #endif