summaryrefslogtreecommitdiff
path: root/libswscale/x86/swscale_template.c
diff options
context:
space:
mode:
authorMichael Niedermayer <michaelni@gmx.at>2012-02-08 02:59:09 +0100
committerMichael Niedermayer <michaelni@gmx.at>2012-02-08 05:53:35 +0100
commit18d0a16fc9d189b1d5593f9a42bb2316e9a66ca9 (patch)
treeaad3d9b1a07b9efebd7435bb27dde147cfa67913 /libswscale/x86/swscale_template.c
parent950930b461cef025152de406f816a3b2efffb540 (diff)
parentef1c785f11c168384e42d147648c8fdf5317739b (diff)
downloadffmpeg-18d0a16fc9d189b1d5593f9a42bb2316e9a66ca9.tar.gz
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>
Diffstat (limited to 'libswscale/x86/swscale_template.c')
-rw-r--r--libswscale/x86/swscale_template.c24
1 files changed, 12 insertions, 12 deletions
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" \