Merge remote-tracking branch 'qatar/master' into master

* qatar/master: (27 commits)
  ac3enc: fix LOCAL_ALIGNED usage in count_mantissa_bits()
  ac3dsp: do not use the ff_* prefix when referencing ff_ac3_bap_bits.
  ac3dsp: fix loop condition in ac3_update_bap_counts_c()
  ARM: unbreak build
  ac3enc: modify mantissa bit counting to keep bap counts for all values of bap instead of just 0 to 4.
  ac3enc: split mantissa bit counting into a separate function.
  ac3enc: store per-block/channel bap pointers by reference block in a 2D array rather than in the AC3Block struct.
  get_bits: add av_unused tag to cache variable
  sws: replace all long with int.
  ARM: aacdec: fix constraints on inline asm
  ARM: remove unnecessary volatile from inline asm
  ARM: add "cc" clobbers to inline asm where needed
  ARM: improve FASTDIV asm
  ac3enc: use LOCAL_ALIGNED macro
  APIchanges: fill in git hash for av_get_pix_fmt_name (0420bd7).
  lavu: add av_get_pix_fmt_name() convenience function
  cmdutils: remove OPT_FUNC2
  swscale: fix crash in bilinear scaling.
  vpxenc: add VP8E_SET_STATIC_THRESHOLD mapping
  webm: support stereo videos in matroska/webm muxer
  ...

Conflicts:
	Changelog
	cmdutils.c
	cmdutils.h
	doc/APIchanges
	doc/muxers.texi
	ffmpeg.c
	ffplay.c
	libavcodec/ac3enc.c
	libavcodec/ac3enc_float.c
	libavcodec/avcodec.h
	libavcodec/get_bits.h
	libavcodec/libvpxenc.c
	libavcodec/version.h
	libavdevice/libdc1394.c
	libavformat/matroskaenc.c
	libavutil/avutil.h
	libswscale/rgb2rgb.c
	libswscale/swscale.c
	libswscale/swscale_template.c
	libswscale/x86/swscale_template.c

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

1 files changed, 53 insertions, 0 deletions

diff --git a/libavcodec/x86/ac3dsp.asm b/libavcodec/x86/ac3dsp.asm
index b67f893f22..99c5df340e 100644
--- a/libavcodec/x86/ac3dsp.asm
+++ b/libavcodec/x86/ac3dsp.asm
@@ -27,6 +27,11 @@ SECTION_RODATA
 ; 16777216.0f - used in ff_float_to_fixed24()
 pf_1_24: times 4 dd 0x4B800000
 
+; used in ff_ac3_compute_mantissa_size()
+cextern ac3_bap_bits
+pw_bap_mul1: dw 21846, 21846, 0, 32768, 21846, 21846, 0, 32768
+pw_bap_mul2: dw 5, 7, 0, 7, 5, 7, 0, 7
+
 SECTION .text
 
 ;-----------------------------------------------------------------------------
@@ -293,3 +298,51 @@ cglobal float_to_fixed24_sse2, 3,3,9, dst, src, len
 %endif
     ja .loop
     REP_RET
+
+;------------------------------------------------------------------------------
+; int ff_ac3_compute_mantissa_size(uint16_t mant_cnt[6][16])
+;------------------------------------------------------------------------------
+
+%macro PHADDD4 2 ; xmm src, xmm tmp
+    movhlps  %2, %1
+    paddd    %1, %2
+    pshufd   %2, %1, 0x1
+    paddd    %1, %2
+%endmacro
+
+INIT_XMM
+cglobal ac3_compute_mantissa_size_sse2, 1,2,4, mant_cnt, sum
+    movdqa      m0, [mant_cntq      ]
+    movdqa      m1, [mant_cntq+ 1*16]
+    paddw       m0, [mant_cntq+ 2*16]
+    paddw       m1, [mant_cntq+ 3*16]
+    paddw       m0, [mant_cntq+ 4*16]
+    paddw       m1, [mant_cntq+ 5*16]
+    paddw       m0, [mant_cntq+ 6*16]
+    paddw       m1, [mant_cntq+ 7*16]
+    paddw       m0, [mant_cntq+ 8*16]
+    paddw       m1, [mant_cntq+ 9*16]
+    paddw       m0, [mant_cntq+10*16]
+    paddw       m1, [mant_cntq+11*16]
+    pmaddwd     m0, [ac3_bap_bits   ]
+    pmaddwd     m1, [ac3_bap_bits+16]
+    paddd       m0, m1
+    PHADDD4     m0, m1
+    movd      sumd, m0
+    movdqa      m3, [pw_bap_mul1]
+    movhpd      m0, [mant_cntq     +2]
+    movlpd      m0, [mant_cntq+1*32+2]
+    movhpd      m1, [mant_cntq+2*32+2]
+    movlpd      m1, [mant_cntq+3*32+2]
+    movhpd      m2, [mant_cntq+4*32+2]
+    movlpd      m2, [mant_cntq+5*32+2]
+    pmulhuw     m0, m3
+    pmulhuw     m1, m3
+    pmulhuw     m2, m3
+    paddusw     m0, m1
+    paddusw     m0, m2
+    pmaddwd     m0, [pw_bap_mul2]
+    PHADDD4     m0, m1
+    movd       eax, m0
+    add        eax, sumd
+    RET