avcodec/mpeg12dec: Optimize mpeg1_decode_block_intra()

sandybridge i7 274->260 cycles
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

libavcodec/mpeg12dec.c

@@ -142,29 +142,30 @@ static inline int mpeg1_decode_block_intra(MpegEncContext *s, int16_t *block, in
     i = 0;
     {
         OPEN_READER(re, &s->gb);
+        UPDATE_CACHE(re, &s->gb);
+        if (((int32_t)GET_CACHE(re, &s->gb)) <= (int32_t)0xBFFFFFFF)
+            goto end;
+
         /* now quantify & encode AC coefficients */
         for (;;) {
-            UPDATE_CACHE(re, &s->gb);
             GET_RL_VLC(level, run, re, &s->gb, rl->rl_vlc[0], TEX_VLC_BITS, 2, 0);
 
-            if (level == 127) {
-                break;
-            } else if (level != 0) {
+            if (level != 0) {
                 i += run;
                 j = scantable[i];
                 level = (level * qscale * quant_matrix[j]) >> 4;
                 level = (level - 1) | 1;
                 level = (level ^ SHOW_SBITS(re, &s->gb, 1)) - SHOW_SBITS(re, &s->gb, 1);
-                LAST_SKIP_BITS(re, &s->gb, 1);
+                SKIP_BITS(re, &s->gb, 1);
             } else {
                 /* escape */
                 run = SHOW_UBITS(re, &s->gb, 6) + 1; LAST_SKIP_BITS(re, &s->gb, 6);
                 UPDATE_CACHE(re, &s->gb);
                 level = SHOW_SBITS(re, &s->gb, 8); SKIP_BITS(re, &s->gb, 8);
                 if (level == -128) {
-                    level = SHOW_UBITS(re, &s->gb, 8) - 256; LAST_SKIP_BITS(re, &s->gb, 8);
+                    level = SHOW_UBITS(re, &s->gb, 8) - 256; SKIP_BITS(re, &s->gb, 8);
                 } else if (level == 0) {
-                    level = SHOW_UBITS(re, &s->gb, 8)      ; LAST_SKIP_BITS(re, &s->gb, 8);
+                    level = SHOW_UBITS(re, &s->gb, 8)      ; SKIP_BITS(re, &s->gb, 8);
                 }
                 i += run;
                 j = scantable[i];
@@ -184,7 +185,13 @@ static inline int mpeg1_decode_block_intra(MpegEncContext *s, int16_t *block, in
             }
 
             block[j] = level;
+            if (((int32_t)GET_CACHE(re, &s->gb)) <= (int32_t)0xBFFFFFFF)
+               break;
+
+            UPDATE_CACHE(re, &s->gb);
         }
+end:
+        LAST_SKIP_BITS(re, &s->gb, 2);
         CLOSE_READER(re, &s->gb);
     }
     s->block_last_index[n] = i;