Merge remote-tracking branch 'qatar/master'

* qatar/master:
  x86: vc1: call ff_vc1dsp_init_x86() under if (ARCH_X86)
  x86: cavs: call ff_cavsdsp_init_x86() under if (ARCH_X86)
  x86: call most of the x86 dsp init functions under if (ARCH_X86)
  doc: support the new website layout
  doc: remove a warning from filters.texi
  doc: initial nut documentation
  segment: drop global headers setting
  lavu: fix typo in Makefile

Conflicts:
	doc/Makefile
	doc/filters.texi
	doc/t2h.init
	libavcodec/fmtconvert.c
	libavcodec/proresdsp.c
	libavcodec/x86/Makefile
	libavcodec/x86/vc1dsp_mmx.c

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

8 files changed, 207 insertions, 135 deletions

diff --git a/libavcodec/x86/Makefile b/libavcodec/x86/Makefile
index 39d27271ec..4ddd06d678 100644
--- a/libavcodec/x86/Makefile
+++ b/libavcodec/x86/Makefile
@@ -1,42 +1,43 @@
+OBJS                                   += x86/fmtconvert_init.o
+
+OBJS-$(CONFIG_AAC_DECODER)             += x86/sbrdsp_init.o
+OBJS-$(CONFIG_AC3DSP)                  += x86/ac3dsp_init.o
+OBJS-$(CONFIG_CAVS_DECODER)            += x86/cavsdsp.o
 OBJS-$(CONFIG_DNXHD_ENCODER)           += x86/dnxhdenc.o
+OBJS-$(CONFIG_FFT)                     += x86/fft_init.o
+OBJS-$(CONFIG_GPL)                     += x86/idct_mmx.o
+OBJS-$(CONFIG_H264DSP)                 += x86/h264dsp_init.o
+OBJS-$(CONFIG_H264PRED)                += x86/h264_intrapred_init.o
+OBJS-$(CONFIG_LPC)                     += x86/lpc.o
 OBJS-$(CONFIG_MLP_DECODER)             += x86/mlpdsp.o
+OBJS-$(CONFIG_MPEGAUDIODSP)            += x86/mpegaudiodec.o
 OBJS-$(CONFIG_MPEGVIDEO)               += x86/mpegvideo.o
 OBJS-$(CONFIG_MPEGVIDEOENC)            += x86/mpegvideoenc.o
+OBJS-$(CONFIG_PNG_DECODER)             += x86/pngdsp_init.o
+OBJS-$(CONFIG_PRORES_LGPL_DECODER)     += x86/proresdsp_init.o
+OBJS-$(CONFIG_RV30_DECODER)            += x86/rv34dsp_init.o
+OBJS-$(CONFIG_RV40_DECODER)            += x86/rv34dsp_init.o            \
+                                          x86/rv40dsp_init.o
+OBJS-$(CONFIG_V210_DECODER)            += x86/v210-init.o
 OBJS-$(CONFIG_TRUEHD_DECODER)          += x86/mlpdsp.o
+OBJS-$(CONFIG_VC1_DECODER)             += x86/vc1dsp_init.o
 OBJS-$(CONFIG_VP3DSP)                  += x86/vp3dsp_init.o
+OBJS-$(CONFIG_VP5_DECODER)             += x86/vp56dsp_init.o
+OBJS-$(CONFIG_VP6_DECODER)             += x86/vp56dsp_init.o
+OBJS-$(CONFIG_VP8_DECODER)             += x86/vp8dsp_init.o
 OBJS-$(CONFIG_XMM_CLOBBER_TEST)        += x86/w64xmmtest.o
 
 MMX-OBJS                               += x86/dsputil_mmx.o             \
                                           x86/fdct.o                    \
-                                          x86/fmtconvert_init.o         \
                                           x86/idct_mmx_xvid.o           \
                                           x86/idct_sse2_xvid.o          \
                                           x86/simple_idct.o             \
 
-MMX-OBJS-$(CONFIG_AAC_DECODER)         += x86/sbrdsp_init.o
-MMX-OBJS-$(CONFIG_AC3DSP)              += x86/ac3dsp_init.o
-MMX-OBJS-$(CONFIG_CAVS_DECODER)        += x86/cavsdsp.o
 MMX-OBJS-$(CONFIG_DWT)                 += x86/snowdsp.o \
                                           x86/dwt.o
 MMX-OBJS-$(CONFIG_ENCODERS)            += x86/dsputilenc_mmx.o          \
                                           x86/motion_est.o
-MMX-OBJS-$(CONFIG_FFT)                 += x86/fft_init.o
-MMX-OBJS-$(CONFIG_GPL)                 += x86/idct_mmx.o
-MMX-OBJS-$(CONFIG_H264DSP)             += x86/h264dsp_init.o
-MMX-OBJS-$(CONFIG_H264PRED)            += x86/h264_intrapred_init.o
-MMX-OBJS-$(CONFIG_LPC)                 += x86/lpc.o
-MMX-OBJS-$(CONFIG_MPEGAUDIODSP)        += x86/mpegaudiodec.o
-MMX-OBJS-$(CONFIG_PNG_DECODER)         += x86/pngdsp_init.o
-MMX-OBJS-$(CONFIG_PRORES_DECODER)      += x86/proresdsp_init.o
-MMX-OBJS-$(CONFIG_PRORES_LGPL_DECODER) += x86/proresdsp_init.o
-MMX-OBJS-$(CONFIG_RV30_DECODER)        += x86/rv34dsp_init.o
-MMX-OBJS-$(CONFIG_RV40_DECODER)        += x86/rv34dsp_init.o            \
-                                          x86/rv40dsp_init.o
-MMX-OBJS-$(CONFIG_V210_DECODER)        += x86/v210-init.o
 MMX-OBJS-$(CONFIG_VC1_DECODER)         += x86/vc1dsp_mmx.o
-MMX-OBJS-$(CONFIG_VP5_DECODER)         += x86/vp56dsp_init.o
-MMX-OBJS-$(CONFIG_VP6_DECODER)         += x86/vp56dsp_init.o
-MMX-OBJS-$(CONFIG_VP8_DECODER)         += x86/vp8dsp_init.o
 
 YASM-OBJS-$(CONFIG_AAC_DECODER)        += x86/sbrdsp.o
 YASM-OBJS-$(CONFIG_AC3DSP)             += x86/ac3dsp.o
diff --git a/libavcodec/x86/cavsdsp.c b/libavcodec/x86/cavsdsp.c
index 03a8b87ec3..9643b81af3 100644
--- a/libavcodec/x86/cavsdsp.c
+++ b/libavcodec/x86/cavsdsp.c
@@ -25,11 +25,13 @@
 #include "libavutil/common.h"
 #include "libavutil/cpu.h"
 #include "libavutil/x86/asm.h"
+#include "libavutil/x86/cpu.h"
 #include "libavcodec/dsputil.h"
 #include "libavcodec/cavsdsp.h"
 #include "dsputil_mmx.h"
+#include "config.h"
 
-#if HAVE_INLINE_ASM
+#if (HAVE_MMXEXT_INLINE || HAVE_AMD3DNOW_INLINE)
 
 /* in/out: mma=mma+mmb, mmb=mmb-mma */
 #define SUMSUB_BA( a, b ) \
@@ -433,15 +435,12 @@ static void ff_ ## OPNAME ## cavs_qpel ## SIZE ## _mc03_ ## MMX(uint8_t *dst, ui
 "pavgb " #temp ", " #a "          \n\t"\
 "mov" #size " " #a ", " #b "      \n\t"
 
-QPEL_CAVS(put_,       PUT_OP, 3dnow)
-QPEL_CAVS(avg_, AVG_3DNOW_OP, 3dnow)
+#endif /* (HAVE_MMXEXT_INLINE || HAVE_AMD3DNOW_INLINE) */
+
+#if HAVE_MMXEXT_INLINE
 QPEL_CAVS(put_,       PUT_OP, mmx2)
 QPEL_CAVS(avg_,  AVG_MMX2_OP, mmx2)
 
-CAVS_MC(put_, 8, 3dnow)
-CAVS_MC(put_, 16,3dnow)
-CAVS_MC(avg_, 8, 3dnow)
-CAVS_MC(avg_, 16,3dnow)
 CAVS_MC(put_, 8, mmx2)
 CAVS_MC(put_, 16,mmx2)
 CAVS_MC(avg_, 8, mmx2)
@@ -463,6 +462,16 @@ static void ff_cavsdsp_init_mmx2(CAVSDSPContext* c, AVCodecContext *avctx) {
     c->cavs_idct8_add = cavs_idct8_add_mmx;
     c->idct_perm = FF_TRANSPOSE_IDCT_PERM;
 }
+#endif /* HAVE_MMXEXT_INLINE */
+
+#if HAVE_AMD3DNOW_INLINE
+QPEL_CAVS(put_,       PUT_OP, 3dnow)
+QPEL_CAVS(avg_, AVG_3DNOW_OP, 3dnow)
+
+CAVS_MC(put_, 8, 3dnow)
+CAVS_MC(put_, 16,3dnow)
+CAVS_MC(avg_, 8, 3dnow)
+CAVS_MC(avg_, 16,3dnow)
 
 static void ff_cavsdsp_init_3dnow(CAVSDSPContext* c, AVCodecContext *avctx) {
 #define dspfunc(PFX, IDX, NUM) \
@@ -480,15 +489,16 @@ static void ff_cavsdsp_init_3dnow(CAVSDSPContext* c, AVCodecContext *avctx) {
     c->cavs_idct8_add = cavs_idct8_add_mmx;
     c->idct_perm = FF_TRANSPOSE_IDCT_PERM;
 }
+#endif /* HAVE_AMD3DNOW_INLINE */
 
-#endif /* HAVE_INLINE_ASM */
-
-void ff_cavsdsp_init_mmx(CAVSDSPContext *c, AVCodecContext *avctx)
+av_cold void ff_cavsdsp_init_x86(CAVSDSPContext *c, AVCodecContext *avctx)
 {
     int mm_flags = av_get_cpu_flags();
 
-#if HAVE_INLINE_ASM
+#if HAVE_MMXEXT_INLINE
     if (mm_flags & AV_CPU_FLAG_MMXEXT) ff_cavsdsp_init_mmx2(c, avctx);
+#endif /* HAVE_MMXEXT_INLINE */
+#if HAVE_AMD3DNOW_INLINE
     if (mm_flags & AV_CPU_FLAG_3DNOW) ff_cavsdsp_init_3dnow(c, avctx);
-#endif /* HAVE_INLINE_ASM */
+#endif /* HAVE_AMD3DNOW_INLINE */
 }
diff --git a/libavcodec/x86/fft_init.c b/libavcodec/x86/fft_init.c
index d7a31d4efa..a9d95799ba 100644
--- a/libavcodec/x86/fft_init.c
+++ b/libavcodec/x86/fft_init.c
@@ -22,7 +22,7 @@
 #include "libavcodec/dct.h"
 #include "fft.h"
 
-av_cold void ff_fft_init_mmx(FFTContext *s)
+av_cold void ff_fft_init_x86(FFTContext *s)
 {
     int has_vectors = av_get_cpu_flags();
 #if ARCH_X86_32
@@ -56,7 +56,7 @@ av_cold void ff_fft_init_mmx(FFTContext *s)
 }
 
 #if CONFIG_DCT
-av_cold void ff_dct_init_mmx(DCTContext *s)
+av_cold void ff_dct_init_x86(DCTContext *s)
 {
     int has_vectors = av_get_cpu_flags();
     if (EXTERNAL_SSE(has_vectors))
diff --git a/libavcodec/x86/mpegaudiodec.c b/libavcodec/x86/mpegaudiodec.c
index a8b55aedf0..44cbf9a428 100644
--- a/libavcodec/x86/mpegaudiodec.c
+++ b/libavcodec/x86/mpegaudiodec.c
@@ -232,7 +232,7 @@ DECL_IMDCT_BLOCKS(avx,avx)
 #endif
 #endif /* HAVE_YASM */
 
-void ff_mpadsp_init_mmx(MPADSPContext *s)
+void ff_mpadsp_init_x86(MPADSPContext *s)
 {
     int mm_flags = av_get_cpu_flags();
 
diff --git a/libavcodec/x86/rv40dsp_init.c b/libavcodec/x86/rv40dsp_init.c
index 966e3f22f5..902ae19075 100644
--- a/libavcodec/x86/rv40dsp_init.c
+++ b/libavcodec/x86/rv40dsp_init.c
@@ -195,12 +195,12 @@ void ff_rv40dsp_init_x86(RV34DSPContext *c, DSPContext *dsp)
     if (EXTERNAL_MMX(mm_flags)) {
         c->put_chroma_pixels_tab[0] = ff_put_rv40_chroma_mc8_mmx;
         c->put_chroma_pixels_tab[1] = ff_put_rv40_chroma_mc4_mmx;
-#if HAVE_INLINE_ASM
+#if HAVE_MMX_INLINE
         c->put_pixels_tab[0][15] = ff_put_rv40_qpel16_mc33_mmx;
         c->put_pixels_tab[1][15] = ff_put_rv40_qpel8_mc33_mmx;
         c->avg_pixels_tab[0][15] = ff_avg_rv40_qpel16_mc33_mmx;
         c->avg_pixels_tab[1][15] = ff_avg_rv40_qpel8_mc33_mmx;
-#endif /* HAVE_INLINE_ASM */
+#endif /* HAVE_MMX_INLINE */
 #if ARCH_X86_32
         QPEL_MC_SET(put_, _mmx)
 #endif
diff --git a/libavcodec/x86/vc1dsp.h b/libavcodec/x86/vc1dsp.h
new file mode 100644
index 0000000000..fdd4de1813
--- /dev/null
+++ b/libavcodec/x86/vc1dsp.h
@@ -0,0 +1,29 @@
+/*
+ * VC-1 and WMV3 decoder - X86 DSP init functions
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifndef AVCODEC_X86_VC1DSP_H
+#define AVCODEC_X86_VC1DSP_H
+
+#include "libavcodec/vc1dsp.h"
+
+void ff_vc1dsp_init_mmx(VC1DSPContext *dsp);
+void ff_vc1dsp_init_mmxext(VC1DSPContext *dsp);
+
+#endif /* AVCODEC_X86_VC1DSP_H */
diff --git a/libavcodec/x86/vc1dsp_init.c b/libavcodec/x86/vc1dsp_init.c
new file mode 100644
index 0000000000..d2548fc348
--- /dev/null
+++ b/libavcodec/x86/vc1dsp_init.c
@@ -0,0 +1,123 @@
+/*
+ * VC-1 and WMV3 - DSP functions MMX-optimized
+ * Copyright (c) 2007 Christophe GISQUET <christophe.gisquet@free.fr>
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "libavutil/cpu.h"
+#include "libavutil/x86/cpu.h"
+#include "libavcodec/vc1dsp.h"
+#include "vc1dsp.h"
+#include "config.h"
+
+#define LOOP_FILTER(EXT) \
+void ff_vc1_v_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \
+void ff_vc1_h_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \
+void ff_vc1_v_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \
+void ff_vc1_h_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \
+\
+static void vc1_v_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \
+{ \
+    ff_vc1_v_loop_filter8_ ## EXT(src,   stride, pq); \
+    ff_vc1_v_loop_filter8_ ## EXT(src+8, stride, pq); \
+} \
+\
+static void vc1_h_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \
+{ \
+    ff_vc1_h_loop_filter8_ ## EXT(src,          stride, pq); \
+    ff_vc1_h_loop_filter8_ ## EXT(src+8*stride, stride, pq); \
+}
+
+#if HAVE_YASM
+LOOP_FILTER(mmx2)
+LOOP_FILTER(sse2)
+LOOP_FILTER(ssse3)
+
+void ff_vc1_h_loop_filter8_sse4(uint8_t *src, int stride, int pq);
+
+static void vc1_h_loop_filter16_sse4(uint8_t *src, int stride, int pq)
+{
+    ff_vc1_h_loop_filter8_sse4(src,          stride, pq);
+    ff_vc1_h_loop_filter8_sse4(src+8*stride, stride, pq);
+}
+#endif /* HAVE_YASM */
+
+void ff_put_vc1_chroma_mc8_mmx_nornd  (uint8_t *dst, uint8_t *src,
+                                       int stride, int h, int x, int y);
+void ff_avg_vc1_chroma_mc8_mmx2_nornd (uint8_t *dst, uint8_t *src,
+                                       int stride, int h, int x, int y);
+void ff_avg_vc1_chroma_mc8_3dnow_nornd(uint8_t *dst, uint8_t *src,
+                                       int stride, int h, int x, int y);
+void ff_put_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src,
+                                       int stride, int h, int x, int y);
+void ff_avg_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src,
+                                       int stride, int h, int x, int y);
+
+
+av_cold void ff_vc1dsp_init_x86(VC1DSPContext *dsp)
+{
+    int mm_flags = av_get_cpu_flags();
+
+    if (INLINE_MMX(mm_flags))
+        ff_vc1dsp_init_mmx(dsp);
+
+    if (INLINE_MMXEXT(mm_flags))
+        ff_vc1dsp_init_mmxext(dsp);
+
+#define ASSIGN_LF(EXT) \
+        dsp->vc1_v_loop_filter4  = ff_vc1_v_loop_filter4_ ## EXT; \
+        dsp->vc1_h_loop_filter4  = ff_vc1_h_loop_filter4_ ## EXT; \
+        dsp->vc1_v_loop_filter8  = ff_vc1_v_loop_filter8_ ## EXT; \
+        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_ ## EXT; \
+        dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_ ## EXT; \
+        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_ ## EXT
+
+#if HAVE_YASM
+    if (mm_flags & AV_CPU_FLAG_MMX) {
+        dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_mmx_nornd;
+    }
+
+    if (mm_flags & AV_CPU_FLAG_MMXEXT) {
+        ASSIGN_LF(mmx2);
+        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_mmx2_nornd;
+    } else if (mm_flags & AV_CPU_FLAG_3DNOW) {
+        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_3dnow_nornd;
+    }
+
+    if (mm_flags & AV_CPU_FLAG_SSE2) {
+        dsp->vc1_v_loop_filter8  = ff_vc1_v_loop_filter8_sse2;
+        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_sse2;
+        dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_sse2;
+        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse2;
+    }
+    if (mm_flags & AV_CPU_FLAG_SSSE3) {
+        ASSIGN_LF(ssse3);
+        dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_ssse3_nornd;
+        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_ssse3_nornd;
+    }
+    if (mm_flags & AV_CPU_FLAG_SSE4) {
+        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_sse4;
+        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse4;
+    }
+#endif /* HAVE_YASM */
+}
diff --git a/libavcodec/x86/vc1dsp_mmx.c b/libavcodec/x86/vc1dsp_mmx.c
index 66251d0b15..adf89b2f0c 100644
--- a/libavcodec/x86/vc1dsp_mmx.c
+++ b/libavcodec/x86/vc1dsp_mmx.c
@@ -27,9 +27,11 @@
 #include "libavutil/cpu.h"
 #include "libavutil/mem.h"
 #include "libavutil/x86/asm.h"
+#include "libavutil/x86/cpu.h"
 #include "libavcodec/dsputil.h"
 #include "dsputil_mmx.h"
 #include "libavcodec/vc1dsp.h"
+#include "vc1dsp.h"
 
 #if HAVE_INLINE_ASM
 
@@ -685,57 +687,8 @@ static void vc1_inv_trans_8x8_dc_mmx2(uint8_t *dest, int linesize, DCTELEM *bloc
     );
 }
 
-#endif /* HAVE_INLINE_ASM */
-
-#define LOOP_FILTER(EXT) \
-void ff_vc1_v_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \
-void ff_vc1_h_loop_filter4_ ## EXT(uint8_t *src, int stride, int pq); \
-void ff_vc1_v_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \
-void ff_vc1_h_loop_filter8_ ## EXT(uint8_t *src, int stride, int pq); \
-\
-static void vc1_v_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \
-{ \
-    ff_vc1_v_loop_filter8_ ## EXT(src,   stride, pq); \
-    ff_vc1_v_loop_filter8_ ## EXT(src+8, stride, pq); \
-} \
-\
-static void vc1_h_loop_filter16_ ## EXT(uint8_t *src, int stride, int pq) \
-{ \
-    ff_vc1_h_loop_filter8_ ## EXT(src,          stride, pq); \
-    ff_vc1_h_loop_filter8_ ## EXT(src+8*stride, stride, pq); \
-}
-
-#if HAVE_YASM
-LOOP_FILTER(mmx2)
-LOOP_FILTER(sse2)
-LOOP_FILTER(ssse3)
-
-void ff_vc1_h_loop_filter8_sse4(uint8_t *src, int stride, int pq);
-
-static void vc1_h_loop_filter16_sse4(uint8_t *src, int stride, int pq)
-{
-    ff_vc1_h_loop_filter8_sse4(src,          stride, pq);
-    ff_vc1_h_loop_filter8_sse4(src+8*stride, stride, pq);
-}
-#endif /* HAVE_YASM */
-
-void ff_put_vc1_chroma_mc8_mmx_nornd  (uint8_t *dst, uint8_t *src,
-                                       int stride, int h, int x, int y);
-void ff_avg_vc1_chroma_mc8_mmx2_nornd (uint8_t *dst, uint8_t *src,
-                                       int stride, int h, int x, int y);
-void ff_avg_vc1_chroma_mc8_3dnow_nornd(uint8_t *dst, uint8_t *src,
-                                       int stride, int h, int x, int y);
-void ff_put_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src,
-                                       int stride, int h, int x, int y);
-void ff_avg_vc1_chroma_mc8_ssse3_nornd(uint8_t *dst, uint8_t *src,
-                                       int stride, int h, int x, int y);
-
-void ff_vc1dsp_init_mmx(VC1DSPContext *dsp)
+av_cold void ff_vc1dsp_init_mmx(VC1DSPContext *dsp)
 {
-    int mm_flags = av_get_cpu_flags();
-
-#if HAVE_INLINE_ASM
-    if (mm_flags & AV_CPU_FLAG_MMX) {
         dsp->put_vc1_mspel_pixels_tab[ 0] = ff_put_vc1_mspel_mc00_mmx;
         dsp->put_vc1_mspel_pixels_tab[ 4] = put_vc1_mspel_mc01_mmx;
         dsp->put_vc1_mspel_pixels_tab[ 8] = put_vc1_mspel_mc02_mmx;
@@ -755,12 +708,10 @@ void ff_vc1dsp_init_mmx(VC1DSPContext *dsp)
         dsp->put_vc1_mspel_pixels_tab[ 7] = put_vc1_mspel_mc31_mmx;
         dsp->put_vc1_mspel_pixels_tab[11] = put_vc1_mspel_mc32_mmx;
         dsp->put_vc1_mspel_pixels_tab[15] = put_vc1_mspel_mc33_mmx;
+}
 
-        if (HAVE_YASM)
-            dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_mmx_nornd;
-    }
-
-    if (mm_flags & AV_CPU_FLAG_MMXEXT) {
+av_cold void ff_vc1dsp_init_mmxext(VC1DSPContext *dsp)
+{
         dsp->avg_vc1_mspel_pixels_tab[ 0] = ff_avg_vc1_mspel_mc00_mmx2;
         dsp->avg_vc1_mspel_pixels_tab[ 4] = avg_vc1_mspel_mc01_mmx2;
         dsp->avg_vc1_mspel_pixels_tab[ 8] = avg_vc1_mspel_mc02_mmx2;
@@ -785,47 +736,5 @@ void ff_vc1dsp_init_mmx(VC1DSPContext *dsp)
         dsp->vc1_inv_trans_4x8_dc = vc1_inv_trans_4x8_dc_mmx2;
         dsp->vc1_inv_trans_8x4_dc = vc1_inv_trans_8x4_dc_mmx2;
         dsp->vc1_inv_trans_4x4_dc = vc1_inv_trans_4x4_dc_mmx2;
-
-        if (HAVE_YASM)
-            dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_mmx2_nornd;
-    } else if (HAVE_YASM && mm_flags & AV_CPU_FLAG_3DNOW) {
-        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_3dnow_nornd;
-    }
-
-    if (HAVE_YASM && mm_flags & AV_CPU_FLAG_SSSE3) {
-        dsp->put_no_rnd_vc1_chroma_pixels_tab[0]= ff_put_vc1_chroma_mc8_ssse3_nornd;
-        dsp->avg_no_rnd_vc1_chroma_pixels_tab[0]= ff_avg_vc1_chroma_mc8_ssse3_nornd;
-    }
-#endif /* HAVE_INLINE_ASM */
-
-#define ASSIGN_LF(EXT) \
-        dsp->vc1_v_loop_filter4  = ff_vc1_v_loop_filter4_ ## EXT; \
-        dsp->vc1_h_loop_filter4  = ff_vc1_h_loop_filter4_ ## EXT; \
-        dsp->vc1_v_loop_filter8  = ff_vc1_v_loop_filter8_ ## EXT; \
-        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_ ## EXT; \
-        dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_ ## EXT; \
-        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_ ## EXT
-
-#if HAVE_YASM
-    if (mm_flags & AV_CPU_FLAG_MMX) {
-    }
-
-    if (mm_flags & AV_CPU_FLAG_MMXEXT) {
-        ASSIGN_LF(mmx2);
-    }
-
-    if (mm_flags & AV_CPU_FLAG_SSE2) {
-        dsp->vc1_v_loop_filter8  = ff_vc1_v_loop_filter8_sse2;
-        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_sse2;
-        dsp->vc1_v_loop_filter16 = vc1_v_loop_filter16_sse2;
-        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse2;
-    }
-    if (mm_flags & AV_CPU_FLAG_SSSE3) {
-        ASSIGN_LF(ssse3);
-    }
-    if (mm_flags & AV_CPU_FLAG_SSE4) {
-        dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_sse4;
-        dsp->vc1_h_loop_filter16 = vc1_h_loop_filter16_sse4;
-    }
-#endif /* HAVE_YASM */
 }
+#endif /* HAVE_INLINE_ASM */