Merge remote-tracking branch 'qatar/master'

* qatar/master:
  swscale: make yuv2yuv1 use named registers.
  h264: mark h264_idct_add8_10 with number of XMM registers.
  swscale: fix V plane memory location in bilinear/unscaled RGB/YUYV case.
  vp8: always update next_framep[] before returning from decode_frame().
  avconv: estimate next_dts from framerate if it is set.
  avconv: better next_dts usage.
  avconv: rename InputStream.pts to last_dts.
  avconv: reduce overloading for InputStream.pts.
  avconv: rename InputStream.next_pts to next_dts.
  avconv: rework -t handling for encoding.
  avconv: set encoder timebase for subtitles.
  pva-demux test: add -vn
  swscale: K&R formatting cosmetics for SPARC code
  apedec: allow the user to set the maximum number of output samples per call
  apedec: do not unnecessarily zero output samples for mono frames
  apedec: allocate a single flat buffer for decoded samples
  apedec: use sizeof(field) instead of sizeof(type)
  swscale: split C output functions into separate file.
  swscale: Split C input functions into separate file.
  bytestream: Add bytestream2 writing API.

The avconv changes are due to massive regressions and bugs not merged yet.

Conflicts:
	ffmpeg.c
	libavcodec/vp8.c
	libswscale/swscale.c
	libswscale/x86/swscale_template.c
	tests/fate/demux.mak
	tests/ref/lavf/asf
	tests/ref/lavf/avi
	tests/ref/lavf/mkv
	tests/ref/lavf/mpg
	tests/ref/lavf/nut
	tests/ref/lavf/ogg
	tests/ref/lavf/rm
	tests/ref/lavf/ts
	tests/ref/seek/lavf_avi
	tests/ref/seek/lavf_mkv
	tests/ref/seek/lavf_rm

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

2 files changed, 37 insertions, 37 deletions

diff --git a/libswscale/x86/output.asm b/libswscale/x86/output.asm
index 70a2c16bcf..4b2f5c89eb 100644
--- a/libswscale/x86/output.asm
+++ b/libswscale/x86/output.asm
@@ -275,17 +275,17 @@ yuv2planeX_fn 10,  7, 5
 %macro yuv2plane1_mainloop 2
 .loop_%2:
 %if %1 == 8
-    paddsw          m0, m2, [r0+r2*2+mmsize*0]
-    paddsw          m1, m3, [r0+r2*2+mmsize*1]
+    paddsw          m0, m2, [srcq+dstwq*2+mmsize*0]
+    paddsw          m1, m3, [srcq+dstwq*2+mmsize*1]
     psraw           m0, 7
     psraw           m1, 7
     packuswb        m0, m1
     mov%2      [r1+r2], m0
 %elif %1 == 16
-    paddd           m0, m4, [r0+r2*4+mmsize*0]
-    paddd           m1, m4, [r0+r2*4+mmsize*1]
-    paddd           m2, m4, [r0+r2*4+mmsize*2]
-    paddd           m3, m4, [r0+r2*4+mmsize*3]
+    paddd           m0, m4, [srcq+dstwq*4+mmsize*0]
+    paddd           m1, m4, [srcq+dstwq*4+mmsize*1]
+    paddd           m2, m4, [srcq+dstwq*4+mmsize*2]
+    paddd           m3, m4, [srcq+dstwq*4+mmsize*3]
     psrad           m0, 3
     psrad           m1, 3
     psrad           m2, 3
@@ -299,46 +299,46 @@ yuv2planeX_fn 10,  7, 5
     paddw           m0, m5
     paddw           m2, m5
 %endif ; mmx/sse2/sse4/avx
-    mov%2    [r1+r2*2], m0
-    mov%2    [r1+r2*2+mmsize], m2
-%else
-    paddsw          m0, m2, [r0+r2*2+mmsize*0]
-    paddsw          m1, m2, [r0+r2*2+mmsize*1]
+    mov%2    [dstq+dstwq*2+mmsize*0], m0
+    mov%2    [dstq+dstwq*2+mmsize*1], m2
+%else ; %1 == 9/10
+    paddsw          m0, m2, [srcq+dstwq*2+mmsize*0]
+    paddsw          m1, m2, [srcq+dstwq*2+mmsize*1]
     psraw           m0, 15 - %1
     psraw           m1, 15 - %1
     pmaxsw          m0, m4
     pmaxsw          m1, m4
     pminsw          m0, m3
     pminsw          m1, m3
-    mov%2    [r1+r2*2], m0
-    mov%2    [r1+r2*2+mmsize], m1
+    mov%2    [dstq+dstwq*2+mmsize*0], m0
+    mov%2    [dstq+dstwq*2+mmsize*1], m1
 %endif
-    add             r2, mmsize
+    add          dstwq, mmsize
     jl .loop_%2
 %endmacro
 
 %macro yuv2plane1_fn 3
-cglobal yuv2plane1_%1, %3, %3, %2
-    add             r2, mmsize - 1
-    and             r2, ~(mmsize - 1)
+cglobal yuv2plane1_%1, %3, %3, %2, src, dst, dstw, dither, offset
+    add          dstwq, mmsize - 1
+    and          dstwq, ~(mmsize - 1)
 %if %1 == 8
-    add             r1, r2
+    add           dstq, dstwq
 %else ; %1 != 8
-    lea             r1, [r1+r2*2]
+    lea           dstq, [dstq+dstwq*2]
 %endif ; %1 == 8
 %if %1 == 16
-    lea             r0, [r0+r2*4]
+    lea           srcq, [srcq+dstwq*4]
 %else ; %1 != 16
-    lea             r0, [r0+r2*2]
+    lea           srcq, [srcq+dstwq*2]
 %endif ; %1 == 16
-    neg             r2
+    neg          dstwq
 
 %if %1 == 8
     pxor            m4, m4               ; zero
 
     ; create registers holding dither
-    movq            m3, [r3]             ; dither
-    test           r4d, r4d
+    movq            m3, [ditherq]        ; dither
+    test       offsetd, offsetd
     jz              .no_rot
 %if mmsize == 16
     punpcklqdq      m3, m3
@@ -374,7 +374,7 @@ cglobal yuv2plane1_%1, %3, %3, %2
 %if mmsize == 8
     yuv2plane1_mainloop %1, a
 %else ; mmsize == 16
-    test            r1, 15
+    test          dstq, 15
     jnz .unaligned
     yuv2plane1_mainloop %1, a
     REP_RET
diff --git a/libswscale/x86/swscale_template.c b/libswscale/x86/swscale_template.c
index 8a98c7b924..d9e5cbbf44 100644
--- a/libswscale/x86/swscale_template.c
+++ b/libswscale/x86/swscale_template.c
@@ -762,10 +762,10 @@ static void RENAME(yuv2yuyv422_X)(SwsContext *c, const int16_t *lumFilter,
     "1:                                 \n\t"\
     "movq     (%2, "#index"), %%mm2     \n\t" /* uvbuf0[eax]*/\
     "movq     (%3, "#index"), %%mm3     \n\t" /* uvbuf1[eax]*/\
-    "add           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "add "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "movq     (%2, "#index"), %%mm5     \n\t" /* uvbuf0[eax+2048]*/\
     "movq     (%3, "#index"), %%mm4     \n\t" /* uvbuf1[eax+2048]*/\
-    "sub           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "sub "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "psubw             %%mm3, %%mm2     \n\t" /* uvbuf0[eax] - uvbuf1[eax]*/\
     "psubw             %%mm4, %%mm5     \n\t" /* uvbuf0[eax+2048] - uvbuf1[eax+2048]*/\
     "movq "CHR_MMX_FILTER_OFFSET"+8("#c"), %%mm0    \n\t"\
@@ -993,10 +993,10 @@ static void RENAME(yuv2rgb565_2)(SwsContext *c, const int16_t *buf[2],
     "1:                                 \n\t"\
     "movq     (%2, "#index"), %%mm2     \n\t" /* uvbuf0[eax]*/\
     "movq     (%3, "#index"), %%mm3     \n\t" /* uvbuf1[eax]*/\
-    "add           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "add "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "movq     (%2, "#index"), %%mm5     \n\t" /* uvbuf0[eax+2048]*/\
     "movq     (%3, "#index"), %%mm4     \n\t" /* uvbuf1[eax+2048]*/\
-    "sub           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "sub "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "psubw             %%mm3, %%mm2     \n\t" /* uvbuf0[eax] - uvbuf1[eax]*/\
     "psubw             %%mm4, %%mm5     \n\t" /* uvbuf0[eax+2048] - uvbuf1[eax+2048]*/\
     "movq "CHR_MMX_FILTER_OFFSET"+8("#c"), %%mm0    \n\t"\
@@ -1048,9 +1048,9 @@ static void RENAME(yuv2yuyv422_2)(SwsContext *c, const int16_t *buf[2],
     ".p2align              4            \n\t"\
     "1:                                 \n\t"\
     "movq     (%2, "#index"), %%mm3     \n\t" /* uvbuf0[eax]*/\
-    "add           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "add "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "movq     (%2, "#index"), %%mm4     \n\t" /* uvbuf0[eax+2048]*/\
-    "sub           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "sub "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "psraw                $4, %%mm3     \n\t" /* uvbuf0[eax] - uvbuf1[eax] >>4*/\
     "psraw                $4, %%mm4     \n\t" /* uvbuf0[eax+2048] - uvbuf1[eax+2048] >>4*/\
     "psubw  "U_OFFSET"("#c"), %%mm3     \n\t" /* (U-128)8*/\
@@ -1101,10 +1101,10 @@ static void RENAME(yuv2yuyv422_2)(SwsContext *c, const int16_t *buf[2],
     "1:                                 \n\t"\
     "movq     (%2, "#index"), %%mm2     \n\t" /* uvbuf0[eax]*/\
     "movq     (%3, "#index"), %%mm3     \n\t" /* uvbuf1[eax]*/\
-    "add           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "add "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "movq     (%2, "#index"), %%mm5     \n\t" /* uvbuf0[eax+2048]*/\
     "movq     (%3, "#index"), %%mm4     \n\t" /* uvbuf1[eax+2048]*/\
-    "sub           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "sub "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "paddw             %%mm2, %%mm3     \n\t" /* uvbuf0[eax] + uvbuf1[eax]*/\
     "paddw             %%mm5, %%mm4     \n\t" /* uvbuf0[eax+2048] + uvbuf1[eax+2048]*/\
     "psrlw                $5, %%mm3     \n\t" /*FIXME might overflow*/\
@@ -1368,9 +1368,9 @@ static void RENAME(yuv2rgb565_1)(SwsContext *c, const int16_t *buf0,
     ".p2align              4            \n\t"\
     "1:                                 \n\t"\
     "movq     (%2, "#index"), %%mm3     \n\t" /* uvbuf0[eax]*/\
-    "add           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "add "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "movq     (%2, "#index"), %%mm4     \n\t" /* uvbuf0[eax+2048]*/\
-    "sub           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "sub "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "psraw                $7, %%mm3     \n\t" \
     "psraw                $7, %%mm4     \n\t" \
     "movq  (%0, "#index", 2), %%mm1     \n\t" /*buf0[eax]*/\
@@ -1386,10 +1386,10 @@ static void RENAME(yuv2rgb565_1)(SwsContext *c, const int16_t *buf0,
     "1:                                 \n\t"\
     "movq     (%2, "#index"), %%mm2     \n\t" /* uvbuf0[eax]*/\
     "movq     (%3, "#index"), %%mm3     \n\t" /* uvbuf1[eax]*/\
-    "add           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "add "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "movq     (%2, "#index"), %%mm5     \n\t" /* uvbuf0[eax+2048]*/\
     "movq     (%3, "#index"), %%mm4     \n\t" /* uvbuf1[eax+2048]*/\
-    "sub           "UV_OFFx2"("#c"), "#index"  \n\t" \
+    "sub "UV_OFF_BYTE"("#c"), "#index"  \n\t" \
     "paddw             %%mm2, %%mm3     \n\t" /* uvbuf0[eax] + uvbuf1[eax]*/\
     "paddw             %%mm5, %%mm4     \n\t" /* uvbuf0[eax+2048] + uvbuf1[eax+2048]*/\
     "psrlw                $8, %%mm3     \n\t" \