Merge remote-tracking branch 'qatar/master'

* qatar/master: (40 commits)
  H.264: template left MB handling
  H.264: faster fill_decode_caches
  H.264: faster write_back_*
  H.264: faster fill_filter_caches
  H.264: make filter_mb_fast support the case of unavailable top mb
  Do not include log.h in avutil.h
  Do not include pixfmt.h in avutil.h
  Do not include rational.h in avutil.h
  Do not include mathematics.h in avutil.h
  Do not include intfloat_readwrite.h in avutil.h
  Remove return statements following infinite loops without break
  RTSP: Doxygen comment cleanup
  doxygen: Escape '\' in Doxygen documentation.
  md5: cosmetics
  md5: use AV_WL32 to write result
  md5: add fate test
  md5: include correct headers
  md5: fix test program
  doxygen: Drop array size declarations from Doxygen parameter names.
  doxygen: Fix parameter names to match the function prototypes.
  ...

Conflicts:
	libavcodec/x86/dsputil_mmx.c
	libavformat/flvenc.c
	libavformat/oggenc.c
	libavformat/wtv.c

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

1 files changed, 98 insertions, 0 deletions

diff --git a/libavcodec/x86/h264_qpel_mmx.c b/libavcodec/x86/h264_qpel_mmx.c
index f5af44e82f..4dac05cfa3 100644
--- a/libavcodec/x86/h264_qpel_mmx.c
+++ b/libavcodec/x86/h264_qpel_mmx.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2004-2005 Michael Niedermayer, Loren Merritt
+ * Copyright (c) 2011 Daniel Kang
  *
  * This file is part of FFmpeg.
  *
@@ -1199,3 +1200,100 @@ H264_MC_816(H264_MC_HV, sse2)
 H264_MC_816(H264_MC_H, ssse3)
 H264_MC_816(H264_MC_HV, ssse3)
 #endif
+
+
+
+//10bit
+#define LUMA_MC_OP(OP, NUM, DEPTH, TYPE, OPT) \
+void ff_ ## OP ## _h264_qpel ## NUM ## _ ## TYPE ## _ ## DEPTH ## _ ## OPT \
+    (uint8_t *dst, uint8_t *src, int stride);
+
+#define LUMA_MC_ALL(DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(put,  4, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(avg,  4, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(put,  8, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(avg,  8, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(put, 16, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(avg, 16, DEPTH, TYPE, OPT)
+
+#define LUMA_MC_816(DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(put,  8, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(avg,  8, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(put, 16, DEPTH, TYPE, OPT) \
+    LUMA_MC_OP(avg, 16, DEPTH, TYPE, OPT)
+
+LUMA_MC_ALL(10, mc00, mmxext)
+LUMA_MC_ALL(10, mc10, mmxext)
+LUMA_MC_ALL(10, mc20, mmxext)
+LUMA_MC_ALL(10, mc30, mmxext)
+LUMA_MC_ALL(10, mc01, mmxext)
+LUMA_MC_ALL(10, mc11, mmxext)
+LUMA_MC_ALL(10, mc21, mmxext)
+LUMA_MC_ALL(10, mc31, mmxext)
+LUMA_MC_ALL(10, mc02, mmxext)
+LUMA_MC_ALL(10, mc12, mmxext)
+LUMA_MC_ALL(10, mc22, mmxext)
+LUMA_MC_ALL(10, mc32, mmxext)
+LUMA_MC_ALL(10, mc03, mmxext)
+LUMA_MC_ALL(10, mc13, mmxext)
+LUMA_MC_ALL(10, mc23, mmxext)
+LUMA_MC_ALL(10, mc33, mmxext)
+
+LUMA_MC_816(10, mc00, sse2)
+LUMA_MC_816(10, mc10, sse2)
+LUMA_MC_816(10, mc10, sse2_cache64)
+LUMA_MC_816(10, mc10, ssse3_cache64)
+LUMA_MC_816(10, mc20, sse2)
+LUMA_MC_816(10, mc20, sse2_cache64)
+LUMA_MC_816(10, mc20, ssse3_cache64)
+LUMA_MC_816(10, mc30, sse2)
+LUMA_MC_816(10, mc30, sse2_cache64)
+LUMA_MC_816(10, mc30, ssse3_cache64)
+LUMA_MC_816(10, mc01, sse2)
+LUMA_MC_816(10, mc11, sse2)
+LUMA_MC_816(10, mc21, sse2)
+LUMA_MC_816(10, mc31, sse2)
+LUMA_MC_816(10, mc02, sse2)
+LUMA_MC_816(10, mc12, sse2)
+LUMA_MC_816(10, mc22, sse2)
+LUMA_MC_816(10, mc32, sse2)
+LUMA_MC_816(10, mc03, sse2)
+LUMA_MC_816(10, mc13, sse2)
+LUMA_MC_816(10, mc23, sse2)
+LUMA_MC_816(10, mc33, sse2)
+
+#define QPEL16_OPMC(OP, MC, MMX)\
+void ff_ ## OP ## _h264_qpel16_ ## MC ## _10_ ## MMX(uint8_t *dst, uint8_t *src, int stride){\
+    ff_ ## OP ## _h264_qpel8_ ## MC ## _10_ ## MMX(dst   , src   , stride);\
+    ff_ ## OP ## _h264_qpel8_ ## MC ## _10_ ## MMX(dst+16, src+16, stride);\
+    src += 8*stride;\
+    dst += 8*stride;\
+    ff_ ## OP ## _h264_qpel8_ ## MC ## _10_ ## MMX(dst   , src   , stride);\
+    ff_ ## OP ## _h264_qpel8_ ## MC ## _10_ ## MMX(dst+16, src+16, stride);\
+}
+
+#define QPEL16_OP(MC, MMX)\
+QPEL16_OPMC(put, MC, MMX)\
+QPEL16_OPMC(avg, MC, MMX)
+
+#define QPEL16(MMX)\
+QPEL16_OP(mc00, MMX)\
+QPEL16_OP(mc01, MMX)\
+QPEL16_OP(mc02, MMX)\
+QPEL16_OP(mc03, MMX)\
+QPEL16_OP(mc10, MMX)\
+QPEL16_OP(mc11, MMX)\
+QPEL16_OP(mc12, MMX)\
+QPEL16_OP(mc13, MMX)\
+QPEL16_OP(mc20, MMX)\
+QPEL16_OP(mc21, MMX)\
+QPEL16_OP(mc22, MMX)\
+QPEL16_OP(mc23, MMX)\
+QPEL16_OP(mc30, MMX)\
+QPEL16_OP(mc31, MMX)\
+QPEL16_OP(mc32, MMX)\
+QPEL16_OP(mc33, MMX)
+
+#if ARCH_X86_32 // ARCH_X86_64 implies sse2+
+QPEL16(mmxext)
+#endif