Merge remote-tracking branch 'qatar/master'

* qatar/master: (27 commits)
  cmdutils: use new avcodec_is_decoder/encoder() functions.
  lavc: make codec_is_decoder/encoder() public.
  lavc: deprecate AVCodecContext.sub_id.
  libcdio: add a forgotten AVClass to the private context.
  swscale: remove "cpu flags" from -sws_flags description.
  proresenc: give user a possibility to alter some encoding parameters
  vorbisenc: add output buffer overwrite protection
  libopencore-amrnbenc: fix end-of-stream handling
  ra144enc: fix end-of-stream handling
  nellymoserenc: zero any leftover packet bytes
  nellymoserenc: use proper MDCT overlap delay
  qpeg: Use bytestream2 functions to prevent buffer overreads.
  swscale: make %rep unconditional.
  vp8: convert simple loopfilter x86 assembly to use named arguments.
  vp8: convert idct x86 assembly to use named arguments.
  vp8: convert mc x86 assembly to use named arguments.
  vp8: convert loopfilter x86 assembly to use cpuflags().
  vp8: convert idct/mc x86 assembly to use cpuflags().
  swscale: remove now unnecessary hack.
  x86inc: don't "bake" stack_offset in named arguments.
  ...

Conflicts:
	cmdutils.c
	doc/APIchanges
	libavcodec/mpeg12.c
	libavcodec/options.c
	libavcodec/qpeg.c
	libavcodec/utils.c
	libavcodec/version.h
	libavdevice/libcdio.c
	tests/lavf-regression.sh

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

2 files changed, 9 insertions, 6 deletions

diff --git a/libswscale/options.c b/libswscale/options.c
index f8fa13a726..ade9888d35 100644
--- a/libswscale/options.c
+++ b/libswscale/options.c
@@ -34,7 +34,7 @@ static const char *sws_context_to_name(void *ptr)
 #define VE AV_OPT_FLAG_VIDEO_PARAM | AV_OPT_FLAG_ENCODING_PARAM
 
 static const AVOption options[] = {
-    { "sws_flags",       "scaler/cpu flags",              OFFSET(flags),     AV_OPT_TYPE_FLAGS,  { .dbl = DEFAULT            }, 0,       UINT_MAX,       VE, "sws_flags" },
+    { "sws_flags",       "scaler flags",                  OFFSET(flags),     AV_OPT_TYPE_FLAGS,  { .dbl = DEFAULT            }, 0,       UINT_MAX,       VE, "sws_flags" },
     { "fast_bilinear",   "fast bilinear",                 0,                 AV_OPT_TYPE_CONST,  { .dbl = SWS_FAST_BILINEAR  }, INT_MIN, INT_MAX,        VE, "sws_flags" },
     { "bilinear",        "bilinear",                      0,                 AV_OPT_TYPE_CONST,  { .dbl = SWS_BILINEAR       }, INT_MIN, INT_MAX,        VE, "sws_flags" },
     { "bicubic",         "bicubic",                       0,                 AV_OPT_TYPE_CONST,  { .dbl = SWS_BICUBIC        }, INT_MIN, INT_MAX,        VE, "sws_flags" },
diff --git a/libswscale/x86/output.asm b/libswscale/x86/output.asm
index 11e89a4269..874fac21af 100644
--- a/libswscale/x86/output.asm
+++ b/libswscale/x86/output.asm
@@ -131,8 +131,12 @@ cglobal yuv2planeX_%1, %3, 7, %2, filter, fltsize, src, dst, w, dither, offset
     ; pixels per iteration. In order to not have to keep track of where
     ; we are w.r.t. dithering, we unroll the mmx/8bit loop x2.
 %if %1 == 8
-%rep 16/mmsize
-%endif ; %1 == 8
+%assign %%repcnt 16/mmsize
+%else
+%assign %%repcnt 1
+%endif
+
+%rep %%repcnt
 
 %if %1 == 8
 %if ARCH_X86_32
@@ -146,7 +150,7 @@ cglobal yuv2planeX_%1, %3, 7, %2, filter, fltsize, src, dst, w, dither, offset
     mova            m1, [yuv2yuvX_%1_start]
     mova            m2,  m1
 %endif ; %1 == 8/9/10/16
-    movsx     cntr_reg,  r1m ; FIXME should be fltsizem, but the assembler does the wrong thing b/c of SUB above
+    movsx     cntr_reg,  fltsizem
 .filterloop_ %+ %%i:
     ; input pixels
     mov             r6, [srcq+gprsize*cntr_reg-2*gprsize]
@@ -226,10 +230,9 @@ cglobal yuv2planeX_%1, %3, 7, %2, filter, fltsize, src, dst, w, dither, offset
 
     add             r5,  mmsize/2
     sub             wd,  mmsize/2
-%if %1 == 8
+
 %assign %%i %%i+2
 %endrep
-%endif ; %1 == 8
     jg .pixelloop
 
 %if %1 == 8