Merge remote-tracking branch 'qatar/master'

* qatar/master: (22 commits)
  rv40dsp x86: use only one register, for both increment and loop counter
  rv40dsp: implement prescaled versions for biweight.
  avconv: use default channel layouts when they are unknown
  avconv: parse channel layout string
  nutdec: K&R formatting cosmetics
  vda: Signal 4 byte NAL headers to the decoder regardless of what's in the extradata
  mem: Consistently return NULL for av_malloc(0)
  vf_overlay: implement poll_frame()
  vf_scale: support named constants for sws flags.
  lavc doxy: add all installed headers to doxy groups.
  lavc doxy: add avfft to the main lavc group.
  lavc doxy: add remaining avcodec.h functions to a misc doxygen group.
  lavc doxy: add AVPicture functions to a doxy group.
  lavc doxy: add resampling functions to a doxy group.
  lavc doxy: replace \ with /
  lavc doxy: add encoding functions to a doxy group.
  lavc doxy: add decoding functions to a doxy group.
  lavc doxy: fix formatting of AV_PKT_DATA_{PARAM_CHANGE,H263_MB_INFO}
  lavc doxy: add AVPacket-related stuff to a separate doxy group.
  lavc doxy: add core functions/definitions to a doxy group.
  ...

Conflicts:
	ffmpeg.c
	libavcodec/avcodec.h
	libavcodec/vda.c
	libavcodec/x86/rv40dsp.asm
	libavfilter/vf_scale.c
	libavformat/nutdec.c
	libavutil/mem.c
	tests/ref/acodec/pcm_s24daud

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

1 files changed, 17 insertions, 3 deletions

diff --git a/libavcodec/rv40dsp.c b/libavcodec/rv40dsp.c
index fbe59ef7b3..8ba10beac8 100644
--- a/libavcodec/rv40dsp.c
+++ b/libavcodec/rv40dsp.c
@@ -278,7 +278,7 @@ RV40_CHROMA_MC(put_, op_put)
 RV40_CHROMA_MC(avg_, op_avg)
 
 #define RV40_WEIGHT_FUNC(size) \
-static void rv40_weight_func_ ## size (uint8_t *dst, uint8_t *src1, uint8_t *src2, int w1, int w2, ptrdiff_t stride)\
+static void rv40_weight_func_rnd_ ## size (uint8_t *dst, uint8_t *src1, uint8_t *src2, int w1, int w2, ptrdiff_t stride)\
 {\
     int i, j;\
 \
@@ -289,6 +289,18 @@ static void rv40_weight_func_ ## size (uint8_t *dst, uint8_t *src1, uint8_t *src
         src2 += stride;\
         dst  += stride;\
     }\
+}\
+static void rv40_weight_func_nornd_ ## size (uint8_t *dst, uint8_t *src1, uint8_t *src2, int w1, int w2, ptrdiff_t stride)\
+{\
+    int i, j;\
+\
+    for (j = 0; j < size; j++) {\
+        for (i = 0; i < size; i++)\
+            dst[i] = (w2 * src1[i] + w1 * src2[i] + 0x10) >> 5;\
+        src1 += stride;\
+        src2 += stride;\
+        dst  += stride;\
+    }\
 }
 
 RV40_WEIGHT_FUNC(16)
@@ -578,8 +590,10 @@ av_cold void ff_rv40dsp_init(RV34DSPContext *c, DSPContext* dsp) {
     c->avg_chroma_pixels_tab[0] = avg_rv40_chroma_mc8_c;
     c->avg_chroma_pixels_tab[1] = avg_rv40_chroma_mc4_c;
 
-    c->rv40_weight_pixels_tab[0] = rv40_weight_func_16;
-    c->rv40_weight_pixels_tab[1] = rv40_weight_func_8;
+    c->rv40_weight_pixels_tab[0][0] = rv40_weight_func_rnd_16;
+    c->rv40_weight_pixels_tab[0][1] = rv40_weight_func_rnd_8;
+    c->rv40_weight_pixels_tab[1][0] = rv40_weight_func_nornd_16;
+    c->rv40_weight_pixels_tab[1][1] = rv40_weight_func_nornd_8;
 
     c->rv40_weak_loop_filter[0]     = rv40_h_weak_loop_filter;
     c->rv40_weak_loop_filter[1]     = rv40_v_weak_loop_filter;