Merge remote-tracking branch 'qatar/master'

* qatar/master: (24 commits)
  flvdec: remove incomplete, disabled seeking code
  mem: add support for _aligned_malloc() as found on Windows
  lavc: Extend the documentation for avcodec_init_packet
  flvdec: remove incomplete, disabled seeking code
  http: replace atoll() with strtoll()
  mpegts: remove unused/incomplete/broken seeking code
  af_amix: allow float planar sample format as input
  af_amix: use AVFloatDSPContext.vector_fmac_scalar()
  float_dsp: add x86-optimized functions for vector_fmac_scalar()
  float_dsp: Move vector_fmac_scalar() from libavcodec to libavutil
  lavr: Add x86-optimized function for flt to s32 conversion
  lavr: Add x86-optimized function for flt to s16 conversion
  lavr: Add x86-optimized functions for s32 to flt conversion
  lavr: Add x86-optimized functions for s32 to s16 conversion
  lavr: Add x86-optimized functions for s16 to flt conversion
  lavr: Add x86-optimized function for s16 to s32 conversion
  rtpenc: Support packetizing iLBC
  rtpdec: Add a depacketizer for iLBC
  Implement the iLBC storage file format
  mov: Support muxing/demuxing iLBC
  ...

Conflicts:
	Changelog
	configure
	libavcodec/avcodec.h
	libavcodec/dsputil.c
	libavcodec/version.h
	libavformat/movenc.c
	libavformat/mpegts.c
	libavformat/version.h
	libavutil/mem.c

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

2 files changed, 54 insertions, 0 deletions

diff --git a/libavutil/x86/float_dsp.asm b/libavutil/x86/float_dsp.asm
index 6ed716c026..f68e0bfe2d 100644
--- a/libavutil/x86/float_dsp.asm
+++ b/libavutil/x86/float_dsp.asm
@@ -21,6 +21,7 @@
 ;******************************************************************************
 
 %include "x86inc.asm"
+%include "x86util.asm"
 
 SECTION .text
 
@@ -55,3 +56,49 @@ VECTOR_FMUL
 INIT_YMM avx
 VECTOR_FMUL
 %endif
+
+;------------------------------------------------------------------------------
+; void ff_vector_fmac_scalar(float *dst, const float *src, float mul, int len)
+;------------------------------------------------------------------------------
+
+%macro VECTOR_FMAC_SCALAR 0
+%if UNIX64
+cglobal vector_fmac_scalar, 3,3,3, dst, src, len
+%else
+cglobal vector_fmac_scalar, 4,4,3, dst, src, mul, len
+%endif
+%if WIN64
+    SWAP 0, 2
+%endif
+%if ARCH_X86_32
+    VBROADCASTSS m0, mulm
+%else
+    shufps     xmm0, xmm0, 0
+%if cpuflag(avx)
+    vinsertf128  m0, m0, xmm0, 1
+%endif
+%endif
+    lea    lenq, [lend*4-2*mmsize]
+.loop
+    mulps    m1, m0, [srcq+lenq       ]
+    mulps    m2, m0, [srcq+lenq+mmsize]
+    addps    m1, m1, [dstq+lenq       ]
+    addps    m2, m2, [dstq+lenq+mmsize]
+    mova  [dstq+lenq       ], m1
+    mova  [dstq+lenq+mmsize], m2
+    sub    lenq, 2*mmsize
+    jge .loop
+%if mmsize == 32
+    vzeroupper
+    RET
+%else
+    REP_RET
+%endif
+%endmacro
+
+INIT_XMM sse
+VECTOR_FMAC_SCALAR
+%if HAVE_AVX
+INIT_YMM avx
+VECTOR_FMAC_SCALAR
+%endif
diff --git a/libavutil/x86/float_dsp_init.c b/libavutil/x86/float_dsp_init.c
index 8f6980cbc2..3e05b9d4ca 100644
--- a/libavutil/x86/float_dsp_init.c
+++ b/libavutil/x86/float_dsp_init.c
@@ -26,6 +26,11 @@ extern void ff_vector_fmul_sse(float *dst, const float *src0, const float *src1,
 extern void ff_vector_fmul_avx(float *dst, const float *src0, const float *src1,
                                int len);
 
+extern void ff_vector_fmac_scalar_sse(float *dst, const float *src, float mul,
+                                      int len);
+extern void ff_vector_fmac_scalar_avx(float *dst, const float *src, float mul,
+                                      int len);
+
 void ff_float_dsp_init_x86(AVFloatDSPContext *fdsp)
 {
 #if HAVE_YASM
@@ -33,9 +38,11 @@ void ff_float_dsp_init_x86(AVFloatDSPContext *fdsp)
 
     if (mm_flags & AV_CPU_FLAG_SSE && HAVE_SSE) {
         fdsp->vector_fmul = ff_vector_fmul_sse;
+        fdsp->vector_fmac_scalar = ff_vector_fmac_scalar_sse;
     }
     if (mm_flags & AV_CPU_FLAG_AVX && HAVE_AVX) {
         fdsp->vector_fmul = ff_vector_fmul_avx;
+        fdsp->vector_fmac_scalar = ff_vector_fmac_scalar_avx;
     }
 #endif
 }