Merge remote branch 'qatar/master'

* qatar/master: (30 commits)
  AVOptions: make default_val a union, as proposed in AVOption2.
  arm/h264pred: add missing argument type.
  h264dsp_mmx: place bracket outside #if/#endif block.
  lavf/utils: fix ff_interleave_compare_dts corner case.
  fate: add 10-bit H264 tests.
  h264: do not print "too many references" warning for intra-only.
  Enable decoding of high bit depth h264.
  Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 decoder.
  Add support for higher QP values in h264.
  Add the notion of pixel size in h264 related functions.
  Make the h264 loop filter bit depth aware.
  Template dsputil_template.c with respect to pixel size, etc.
  Template h264idct_template.c with respect to pixel size, etc.
  Preparatory patch for high bit depth h264 decoding support.
  Move some functions in dsputil.c into a new file dsputil_template.c.
  Move the functions in h264idct into a new file h264idct_template.c.
  Move the functions in h264pred.c into a new file h264pred_template.c.
  Preparatory patch for high bit depth h264 decoding support.
  Add pixel formats for 9- and 10-bit yuv420p.
  Choose h264 chroma dc dequant function dynamically.
  ...

Conflicts:
	doc/APIchanges
	ffmpeg.c
	ffplay.c
	libavcodec/alpha/dsputil_alpha.c
	libavcodec/arm/dsputil_init_arm.c
	libavcodec/arm/dsputil_init_armv6.c
	libavcodec/arm/dsputil_init_neon.c
	libavcodec/arm/dsputil_iwmmxt.c
	libavcodec/arm/h264pred_init_arm.c
	libavcodec/bfin/dsputil_bfin.c
	libavcodec/dsputil.c
	libavcodec/h264.c
	libavcodec/h264.h
	libavcodec/h264_cabac.c
	libavcodec/h264_cavlc.c
	libavcodec/h264_loopfilter.c
	libavcodec/h264_ps.c
	libavcodec/h264_refs.c
	libavcodec/h264dsp.c
	libavcodec/h264idct.c
	libavcodec/h264pred.c
	libavcodec/mlib/dsputil_mlib.c
	libavcodec/options.c
	libavcodec/ppc/dsputil_altivec.c
	libavcodec/ppc/dsputil_ppc.c
	libavcodec/ppc/h264_altivec.c
	libavcodec/ps2/dsputil_mmi.c
	libavcodec/sh4/dsputil_align.c
	libavcodec/sh4/dsputil_sh4.c
	libavcodec/sparc/dsputil_vis.c
	libavcodec/utils.c
	libavcodec/version.h
	libavcodec/x86/dsputil_mmx.c
	libavformat/options.c
	libavformat/utils.c
	libavutil/pixfmt.h
	libswscale/swscale.c
	libswscale/swscale_internal.h
	libswscale/swscale_template.c
	tests/ref/seek/lavf_avi

Merged-by: Michael Niedermayer <michaelni@gmx.at>

1 files changed, 343 insertions, 21 deletions

diff --git a/libavcodec/h264pred.c b/libavcodec/h264pred.c
index 8d2c6f0355..f6533cf9ba 100644
--- a/libavcodec/h264pred.c
+++ b/libavcodec/h264pred.c
@@ -28,17 +28,338 @@
 #include "h264pred.h"
 
 #define BIT_DEPTH 8
-#include "h264pred_internal.h"
+#include "h264pred_template.c"
 #undef BIT_DEPTH
 
 #define BIT_DEPTH 9
-#include "h264pred_internal.h"
+#include "h264pred_template.c"
 #undef BIT_DEPTH
 
 #define BIT_DEPTH 10
-#include "h264pred_internal.h"
+#include "h264pred_template.c"
 #undef BIT_DEPTH
 
+static void pred4x4_vertical_vp8_c(uint8_t *src, const uint8_t *topright, int stride){
+    const int lt= src[-1-1*stride];
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+    uint32_t v = PACK_4U8((lt + 2*t0 + t1 + 2) >> 2,
+                          (t0 + 2*t1 + t2 + 2) >> 2,
+                          (t1 + 2*t2 + t3 + 2) >> 2,
+                          (t2 + 2*t3 + t4 + 2) >> 2);
+
+    AV_WN32A(src+0*stride, v);
+    AV_WN32A(src+1*stride, v);
+    AV_WN32A(src+2*stride, v);
+    AV_WN32A(src+3*stride, v);
+}
+
+static void pred4x4_horizontal_vp8_c(uint8_t *src, const uint8_t *topright, int stride){
+    const int lt= src[-1-1*stride];
+    LOAD_LEFT_EDGE
+
+    AV_WN32A(src+0*stride, ((lt + 2*l0 + l1 + 2) >> 2)*0x01010101);
+    AV_WN32A(src+1*stride, ((l0 + 2*l1 + l2 + 2) >> 2)*0x01010101);
+    AV_WN32A(src+2*stride, ((l1 + 2*l2 + l3 + 2) >> 2)*0x01010101);
+    AV_WN32A(src+3*stride, ((l2 + 2*l3 + l3 + 2) >> 2)*0x01010101);
+}
+
+static void pred4x4_down_left_svq3_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_TOP_EDGE
+    LOAD_LEFT_EDGE
+    const av_unused int unu0= t0;
+    const av_unused int unu1= l0;
+
+    src[0+0*stride]=(l1 + t1)>>1;
+    src[1+0*stride]=
+    src[0+1*stride]=(l2 + t2)>>1;
+    src[2+0*stride]=
+    src[1+1*stride]=
+    src[0+2*stride]=
+    src[3+0*stride]=
+    src[2+1*stride]=
+    src[1+2*stride]=
+    src[0+3*stride]=
+    src[3+1*stride]=
+    src[2+2*stride]=
+    src[1+3*stride]=
+    src[3+2*stride]=
+    src[2+3*stride]=
+    src[3+3*stride]=(l3 + t3)>>1;
+}
+
+static void pred4x4_down_left_rv40_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+    LOAD_LEFT_EDGE
+    LOAD_DOWN_LEFT_EDGE
+
+    src[0+0*stride]=(t0 + t2 + 2*t1 + 2 + l0 + l2 + 2*l1 + 2)>>3;
+    src[1+0*stride]=
+    src[0+1*stride]=(t1 + t3 + 2*t2 + 2 + l1 + l3 + 2*l2 + 2)>>3;
+    src[2+0*stride]=
+    src[1+1*stride]=
+    src[0+2*stride]=(t2 + t4 + 2*t3 + 2 + l2 + l4 + 2*l3 + 2)>>3;
+    src[3+0*stride]=
+    src[2+1*stride]=
+    src[1+2*stride]=
+    src[0+3*stride]=(t3 + t5 + 2*t4 + 2 + l3 + l5 + 2*l4 + 2)>>3;
+    src[3+1*stride]=
+    src[2+2*stride]=
+    src[1+3*stride]=(t4 + t6 + 2*t5 + 2 + l4 + l6 + 2*l5 + 2)>>3;
+    src[3+2*stride]=
+    src[2+3*stride]=(t5 + t7 + 2*t6 + 2 + l5 + l7 + 2*l6 + 2)>>3;
+    src[3+3*stride]=(t6 + t7 + 1 + l6 + l7 + 1)>>2;
+}
+
+static void pred4x4_down_left_rv40_nodown_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+    LOAD_LEFT_EDGE
+
+    src[0+0*stride]=(t0 + t2 + 2*t1 + 2 + l0 + l2 + 2*l1 + 2)>>3;
+    src[1+0*stride]=
+    src[0+1*stride]=(t1 + t3 + 2*t2 + 2 + l1 + l3 + 2*l2 + 2)>>3;
+    src[2+0*stride]=
+    src[1+1*stride]=
+    src[0+2*stride]=(t2 + t4 + 2*t3 + 2 + l2 + 3*l3 + 2)>>3;
+    src[3+0*stride]=
+    src[2+1*stride]=
+    src[1+2*stride]=
+    src[0+3*stride]=(t3 + t5 + 2*t4 + 2 + l3*4 + 2)>>3;
+    src[3+1*stride]=
+    src[2+2*stride]=
+    src[1+3*stride]=(t4 + t6 + 2*t5 + 2 + l3*4 + 2)>>3;
+    src[3+2*stride]=
+    src[2+3*stride]=(t5 + t7 + 2*t6 + 2 + l3*4 + 2)>>3;
+    src[3+3*stride]=(t6 + t7 + 1 + 2*l3 + 1)>>2;
+}
+
+static void pred4x4_vertical_left_rv40(uint8_t *src, const uint8_t *topright, int stride,
+                                       const int l0, const int l1, const int l2, const int l3, const int l4){
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+
+    src[0+0*stride]=(2*t0 + 2*t1 + l1 + 2*l2 + l3 + 4)>>3;
+    src[1+0*stride]=
+    src[0+2*stride]=(t1 + t2 + 1)>>1;
+    src[2+0*stride]=
+    src[1+2*stride]=(t2 + t3 + 1)>>1;
+    src[3+0*stride]=
+    src[2+2*stride]=(t3 + t4+ 1)>>1;
+    src[3+2*stride]=(t4 + t5+ 1)>>1;
+    src[0+1*stride]=(t0 + 2*t1 + t2 + l2 + 2*l3 + l4 + 4)>>3;
+    src[1+1*stride]=
+    src[0+3*stride]=(t1 + 2*t2 + t3 + 2)>>2;
+    src[2+1*stride]=
+    src[1+3*stride]=(t2 + 2*t3 + t4 + 2)>>2;
+    src[3+1*stride]=
+    src[2+3*stride]=(t3 + 2*t4 + t5 + 2)>>2;
+    src[3+3*stride]=(t4 + 2*t5 + t6 + 2)>>2;
+}
+
+static void pred4x4_vertical_left_rv40_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_LEFT_EDGE
+    LOAD_DOWN_LEFT_EDGE
+
+    pred4x4_vertical_left_rv40(src, topright, stride, l0, l1, l2, l3, l4);
+}
+
+static void pred4x4_vertical_left_rv40_nodown_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_LEFT_EDGE
+
+    pred4x4_vertical_left_rv40(src, topright, stride, l0, l1, l2, l3, l3);
+}
+
+static void pred4x4_vertical_left_vp8_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+
+    src[0+0*stride]=(t0 + t1 + 1)>>1;
+    src[1+0*stride]=
+    src[0+2*stride]=(t1 + t2 + 1)>>1;
+    src[2+0*stride]=
+    src[1+2*stride]=(t2 + t3 + 1)>>1;
+    src[3+0*stride]=
+    src[2+2*stride]=(t3 + t4 + 1)>>1;
+    src[0+1*stride]=(t0 + 2*t1 + t2 + 2)>>2;
+    src[1+1*stride]=
+    src[0+3*stride]=(t1 + 2*t2 + t3 + 2)>>2;
+    src[2+1*stride]=
+    src[1+3*stride]=(t2 + 2*t3 + t4 + 2)>>2;
+    src[3+1*stride]=
+    src[2+3*stride]=(t3 + 2*t4 + t5 + 2)>>2;
+    src[3+2*stride]=(t4 + 2*t5 + t6 + 2)>>2;
+    src[3+3*stride]=(t5 + 2*t6 + t7 + 2)>>2;
+}
+
+static void pred4x4_horizontal_up_rv40_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_LEFT_EDGE
+    LOAD_DOWN_LEFT_EDGE
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+
+    src[0+0*stride]=(t1 + 2*t2 + t3 + 2*l0 + 2*l1 + 4)>>3;
+    src[1+0*stride]=(t2 + 2*t3 + t4 + l0 + 2*l1 + l2 + 4)>>3;
+    src[2+0*stride]=
+    src[0+1*stride]=(t3 + 2*t4 + t5 + 2*l1 + 2*l2 + 4)>>3;
+    src[3+0*stride]=
+    src[1+1*stride]=(t4 + 2*t5 + t6 + l1 + 2*l2 + l3 + 4)>>3;
+    src[2+1*stride]=
+    src[0+2*stride]=(t5 + 2*t6 + t7 + 2*l2 + 2*l3 + 4)>>3;
+    src[3+1*stride]=
+    src[1+2*stride]=(t6 + 3*t7 + l2 + 3*l3 + 4)>>3;
+    src[3+2*stride]=
+    src[1+3*stride]=(l3 + 2*l4 + l5 + 2)>>2;
+    src[0+3*stride]=
+    src[2+2*stride]=(t6 + t7 + l3 + l4 + 2)>>2;
+    src[2+3*stride]=(l4 + l5 + 1)>>1;
+    src[3+3*stride]=(l4 + 2*l5 + l6 + 2)>>2;
+}
+
+static void pred4x4_horizontal_up_rv40_nodown_c(uint8_t *src, const uint8_t *topright, int stride){
+    LOAD_LEFT_EDGE
+    LOAD_TOP_EDGE
+    LOAD_TOP_RIGHT_EDGE
+
+    src[0+0*stride]=(t1 + 2*t2 + t3 + 2*l0 + 2*l1 + 4)>>3;
+    src[1+0*stride]=(t2 + 2*t3 + t4 + l0 + 2*l1 + l2 + 4)>>3;
+    src[2+0*stride]=
+    src[0+1*stride]=(t3 + 2*t4 + t5 + 2*l1 + 2*l2 + 4)>>3;
+    src[3+0*stride]=
+    src[1+1*stride]=(t4 + 2*t5 + t6 + l1 + 2*l2 + l3 + 4)>>3;
+    src[2+1*stride]=
+    src[0+2*stride]=(t5 + 2*t6 + t7 + 2*l2 + 2*l3 + 4)>>3;
+    src[3+1*stride]=
+    src[1+2*stride]=(t6 + 3*t7 + l2 + 3*l3 + 4)>>3;
+    src[3+2*stride]=
+    src[1+3*stride]=l3;
+    src[0+3*stride]=
+    src[2+2*stride]=(t6 + t7 + 2*l3 + 2)>>2;
+    src[2+3*stride]=
+    src[3+3*stride]=l3;
+}
+
+static void pred4x4_tm_vp8_c(uint8_t *src, const uint8_t *topright, int stride){
+    uint8_t *cm = ff_cropTbl + MAX_NEG_CROP - src[-1-stride];
+    uint8_t *top = src-stride;
+    int y;
+
+    for (y = 0; y < 4; y++) {
+        uint8_t *cm_in = cm + src[-1];
+        src[0] = cm_in[top[0]];
+        src[1] = cm_in[top[1]];
+        src[2] = cm_in[top[2]];
+        src[3] = cm_in[top[3]];
+        src += stride;
+    }
+}
+
+static void pred16x16_plane_svq3_c(uint8_t *src, int stride){
+    pred16x16_plane_compat_8_c(src, stride, 1, 0);
+}
+
+static void pred16x16_plane_rv40_c(uint8_t *src, int stride){
+    pred16x16_plane_compat_8_c(src, stride, 0, 1);
+}
+
+static void pred16x16_tm_vp8_c(uint8_t *src, int stride){
+    uint8_t *cm = ff_cropTbl + MAX_NEG_CROP - src[-1-stride];
+    uint8_t *top = src-stride;
+    int y;
+
+    for (y = 0; y < 16; y++) {
+        uint8_t *cm_in = cm + src[-1];
+        src[0]  = cm_in[top[0]];
+        src[1]  = cm_in[top[1]];
+        src[2]  = cm_in[top[2]];
+        src[3]  = cm_in[top[3]];
+        src[4]  = cm_in[top[4]];
+        src[5]  = cm_in[top[5]];
+        src[6]  = cm_in[top[6]];
+        src[7]  = cm_in[top[7]];
+        src[8]  = cm_in[top[8]];
+        src[9]  = cm_in[top[9]];
+        src[10] = cm_in[top[10]];
+        src[11] = cm_in[top[11]];
+        src[12] = cm_in[top[12]];
+        src[13] = cm_in[top[13]];
+        src[14] = cm_in[top[14]];
+        src[15] = cm_in[top[15]];
+        src += stride;
+    }
+}
+
+static void pred8x8_left_dc_rv40_c(uint8_t *src, int stride){
+    int i;
+    int dc0;
+
+    dc0=0;
+    for(i=0;i<8; i++)
+        dc0+= src[-1+i*stride];
+    dc0= 0x01010101*((dc0 + 4)>>3);
+
+    for(i=0; i<8; i++){
+        ((uint32_t*)(src+i*stride))[0]=
+        ((uint32_t*)(src+i*stride))[1]= dc0;
+    }
+}
+
+static void pred8x8_top_dc_rv40_c(uint8_t *src, int stride){
+    int i;
+    int dc0;
+
+    dc0=0;
+    for(i=0;i<8; i++)
+        dc0+= src[i-stride];
+    dc0= 0x01010101*((dc0 + 4)>>3);
+
+    for(i=0; i<8; i++){
+        ((uint32_t*)(src+i*stride))[0]=
+        ((uint32_t*)(src+i*stride))[1]= dc0;
+    }
+}
+
+static void pred8x8_dc_rv40_c(uint8_t *src, int stride){
+    int i;
+    int dc0=0;
+
+    for(i=0;i<4; i++){
+        dc0+= src[-1+i*stride] + src[i-stride];
+        dc0+= src[4+i-stride];
+        dc0+= src[-1+(i+4)*stride];
+    }
+    dc0= 0x01010101*((dc0 + 8)>>4);
+
+    for(i=0; i<4; i++){
+        ((uint32_t*)(src+i*stride))[0]= dc0;
+        ((uint32_t*)(src+i*stride))[1]= dc0;
+    }
+    for(i=4; i<8; i++){
+        ((uint32_t*)(src+i*stride))[0]= dc0;
+        ((uint32_t*)(src+i*stride))[1]= dc0;
+    }
+}
+
+static void pred8x8_tm_vp8_c(uint8_t *src, int stride){
+    uint8_t *cm = ff_cropTbl + MAX_NEG_CROP - src[-1-stride];
+    uint8_t *top = src-stride;
+    int y;
+
+    for (y = 0; y < 8; y++) {
+        uint8_t *cm_in = cm + src[-1];
+        src[0] = cm_in[top[0]];
+        src[1] = cm_in[top[1]];
+        src[2] = cm_in[top[2]];
+        src[3] = cm_in[top[3]];
+        src[4] = cm_in[top[4]];
+        src[5] = cm_in[top[5]];
+        src[6] = cm_in[top[6]];
+        src[7] = cm_in[top[7]];
+        src += stride;
+    }
+}
+
 /**
  * Set the intra prediction function pointers.
  */
@@ -49,26 +370,27 @@ void ff_h264_pred_init(H264PredContext *h, int codec_id, const int bit_depth){
 #undef FUNCC
 #define FUNC(a, depth) a ## _ ## depth
 #define FUNCC(a, depth) a ## _ ## depth ## _c
+#define FUNCD(a) a ## _c
 
 #define H264_PRED(depth) \
     if(codec_id != CODEC_ID_RV40){\
         if(codec_id == CODEC_ID_VP8) {\
-            h->pred4x4[VERT_PRED       ]= FUNCC(pred4x4_vertical_vp8      , depth);\
-            h->pred4x4[HOR_PRED        ]= FUNCC(pred4x4_horizontal_vp8    , depth);\
+            h->pred4x4[VERT_PRED       ]= FUNCD(pred4x4_vertical_vp8);\
+            h->pred4x4[HOR_PRED        ]= FUNCD(pred4x4_horizontal_vp8);\
         } else {\
             h->pred4x4[VERT_PRED       ]= FUNCC(pred4x4_vertical          , depth);\
             h->pred4x4[HOR_PRED        ]= FUNCC(pred4x4_horizontal        , depth);\
         }\
         h->pred4x4[DC_PRED             ]= FUNCC(pred4x4_dc                , depth);\
         if(codec_id == CODEC_ID_SVQ3)\
-            h->pred4x4[DIAG_DOWN_LEFT_PRED ]= FUNCC(pred4x4_down_left_svq3, depth);\
+            h->pred4x4[DIAG_DOWN_LEFT_PRED ]= FUNCD(pred4x4_down_left_svq3);\
         else\
             h->pred4x4[DIAG_DOWN_LEFT_PRED ]= FUNCC(pred4x4_down_left     , depth);\
         h->pred4x4[DIAG_DOWN_RIGHT_PRED]= FUNCC(pred4x4_down_right        , depth);\
         h->pred4x4[VERT_RIGHT_PRED     ]= FUNCC(pred4x4_vertical_right    , depth);\
         h->pred4x4[HOR_DOWN_PRED       ]= FUNCC(pred4x4_horizontal_down   , depth);\
         if (codec_id == CODEC_ID_VP8) {\
-            h->pred4x4[VERT_LEFT_PRED  ]= FUNCC(pred4x4_vertical_left_vp8 , depth);\
+            h->pred4x4[VERT_LEFT_PRED  ]= FUNCD(pred4x4_vertical_left_vp8);\
         } else\
             h->pred4x4[VERT_LEFT_PRED  ]= FUNCC(pred4x4_vertical_left     , depth);\
         h->pred4x4[HOR_UP_PRED         ]= FUNCC(pred4x4_horizontal_up     , depth);\
@@ -77,7 +399,7 @@ void ff_h264_pred_init(H264PredContext *h, int codec_id, const int bit_depth){
             h->pred4x4[TOP_DC_PRED     ]= FUNCC(pred4x4_top_dc            , depth);\
             h->pred4x4[DC_128_PRED     ]= FUNCC(pred4x4_128_dc            , depth);\
         } else {\
-            h->pred4x4[TM_VP8_PRED     ]= FUNCC(pred4x4_tm_vp8            , depth);\
+            h->pred4x4[TM_VP8_PRED     ]= FUNCD(pred4x4_tm_vp8);\
             h->pred4x4[DC_127_PRED     ]= FUNCC(pred4x4_127_dc            , depth);\
             h->pred4x4[DC_129_PRED     ]= FUNCC(pred4x4_129_dc            , depth);\
             h->pred4x4[VERT_VP8_PRED   ]= FUNCC(pred4x4_vertical          , depth);\
@@ -87,18 +409,18 @@ void ff_h264_pred_init(H264PredContext *h, int codec_id, const int bit_depth){
         h->pred4x4[VERT_PRED           ]= FUNCC(pred4x4_vertical          , depth);\
         h->pred4x4[HOR_PRED            ]= FUNCC(pred4x4_horizontal        , depth);\
         h->pred4x4[DC_PRED             ]= FUNCC(pred4x4_dc                , depth);\
-        h->pred4x4[DIAG_DOWN_LEFT_PRED ]= FUNCC(pred4x4_down_left_rv40    , depth);\
+        h->pred4x4[DIAG_DOWN_LEFT_PRED ]= FUNCD(pred4x4_down_left_rv40);\
         h->pred4x4[DIAG_DOWN_RIGHT_PRED]= FUNCC(pred4x4_down_right        , depth);\
         h->pred4x4[VERT_RIGHT_PRED     ]= FUNCC(pred4x4_vertical_right    , depth);\
         h->pred4x4[HOR_DOWN_PRED       ]= FUNCC(pred4x4_horizontal_down   , depth);\
-        h->pred4x4[VERT_LEFT_PRED      ]= FUNCC(pred4x4_vertical_left_rv40, depth);\
-        h->pred4x4[HOR_UP_PRED         ]= FUNCC(pred4x4_horizontal_up_rv40, depth);\
+        h->pred4x4[VERT_LEFT_PRED      ]= FUNCD(pred4x4_vertical_left_rv40);\
+        h->pred4x4[HOR_UP_PRED         ]= FUNCD(pred4x4_horizontal_up_rv40);\
         h->pred4x4[LEFT_DC_PRED        ]= FUNCC(pred4x4_left_dc           , depth);\
         h->pred4x4[TOP_DC_PRED         ]= FUNCC(pred4x4_top_dc            , depth);\
         h->pred4x4[DC_128_PRED         ]= FUNCC(pred4x4_128_dc            , depth);\
-        h->pred4x4[DIAG_DOWN_LEFT_PRED_RV40_NODOWN]= FUNCC(pred4x4_down_left_rv40_nodown, depth);\
-        h->pred4x4[HOR_UP_PRED_RV40_NODOWN]= FUNCC(pred4x4_horizontal_up_rv40_nodown    , depth);\
-        h->pred4x4[VERT_LEFT_PRED_RV40_NODOWN]= FUNCC(pred4x4_vertical_left_rv40_nodown , depth);\
+        h->pred4x4[DIAG_DOWN_LEFT_PRED_RV40_NODOWN]= FUNCD(pred4x4_down_left_rv40_nodown);\
+        h->pred4x4[HOR_UP_PRED_RV40_NODOWN]= FUNCD(pred4x4_horizontal_up_rv40_nodown);\
+        h->pred4x4[VERT_LEFT_PRED_RV40_NODOWN]= FUNCD(pred4x4_vertical_left_rv40_nodown);\
     }\
 \
     h->pred8x8l[VERT_PRED           ]= FUNCC(pred8x8l_vertical            , depth);\
@@ -119,7 +441,7 @@ void ff_h264_pred_init(H264PredContext *h, int codec_id, const int bit_depth){
     if (codec_id != CODEC_ID_VP8) {\
         h->pred8x8[PLANE_PRED8x8]= FUNCC(pred8x8_plane                    , depth);\
     } else\
-        h->pred8x8[PLANE_PRED8x8]= FUNCC(pred8x8_tm_vp8                   , depth);\
+        h->pred8x8[PLANE_PRED8x8]= FUNCD(pred8x8_tm_vp8);\
     if(codec_id != CODEC_ID_RV40 && codec_id != CODEC_ID_VP8){\
         h->pred8x8[DC_PRED8x8     ]= FUNCC(pred8x8_dc                     , depth);\
         h->pred8x8[LEFT_DC_PRED8x8]= FUNCC(pred8x8_left_dc                , depth);\
@@ -129,9 +451,9 @@ void ff_h264_pred_init(H264PredContext *h, int codec_id, const int bit_depth){
         h->pred8x8[ALZHEIMER_DC_L00_PRED8x8 ]= FUNC(pred8x8_mad_cow_dc_l00, depth);\
         h->pred8x8[ALZHEIMER_DC_0L0_PRED8x8 ]= FUNC(pred8x8_mad_cow_dc_0l0, depth);\
     }else{\
-        h->pred8x8[DC_PRED8x8     ]= FUNCC(pred8x8_dc_rv40                , depth);\
-        h->pred8x8[LEFT_DC_PRED8x8]= FUNCC(pred8x8_left_dc_rv40           , depth);\
-        h->pred8x8[TOP_DC_PRED8x8 ]= FUNCC(pred8x8_top_dc_rv40            , depth);\
+        h->pred8x8[DC_PRED8x8     ]= FUNCD(pred8x8_dc_rv40);\
+        h->pred8x8[LEFT_DC_PRED8x8]= FUNCD(pred8x8_left_dc_rv40);\
+        h->pred8x8[TOP_DC_PRED8x8 ]= FUNCD(pred8x8_top_dc_rv40);\
         if (codec_id == CODEC_ID_VP8) {\
             h->pred8x8[DC_127_PRED8x8]= FUNCC(pred8x8_127_dc              , depth);\
             h->pred8x8[DC_129_PRED8x8]= FUNCC(pred8x8_129_dc              , depth);\
@@ -144,13 +466,13 @@ void ff_h264_pred_init(H264PredContext *h, int codec_id, const int bit_depth){
     h->pred16x16[HOR_PRED8x8    ]= FUNCC(pred16x16_horizontal             , depth);\
     switch(codec_id){\
     case CODEC_ID_SVQ3:\
-       h->pred16x16[PLANE_PRED8x8  ]= FUNCC(pred16x16_plane_svq3          , depth);\
+       h->pred16x16[PLANE_PRED8x8  ]= FUNCD(pred16x16_plane_svq3);\
        break;\
     case CODEC_ID_RV40:\
-       h->pred16x16[PLANE_PRED8x8  ]= FUNCC(pred16x16_plane_rv40          , depth);\
+       h->pred16x16[PLANE_PRED8x8  ]= FUNCD(pred16x16_plane_rv40);\
        break;\
     case CODEC_ID_VP8:\
-       h->pred16x16[PLANE_PRED8x8  ]= FUNCC(pred16x16_tm_vp8              , depth);\
+       h->pred16x16[PLANE_PRED8x8  ]= FUNCD(pred16x16_tm_vp8);\
        h->pred16x16[DC_127_PRED8x8]= FUNCC(pred16x16_127_dc               , depth);\
        h->pred16x16[DC_129_PRED8x8]= FUNCC(pred16x16_129_dc               , depth);\
        break;\