ffmpeg source update for sep 09

source/patched-ffmpeg-mt/libavcodec/x86/dsputil_mmx.h

 /*
  * MMX optimized DSP utils
  * Copyright (c) 2007  Aurelien Jacobs <aurel@gnuage.org>
  *
  * 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.
@@ skipping 39 matching lines @@
 extern const uint64_t ff_pw_96;
 extern const uint64_t ff_pw_128;
 extern const uint64_t ff_pw_255;
 
 extern const xmm_reg  ff_pb_1;
 extern const xmm_reg  ff_pb_3;
 extern const uint64_t ff_pb_7;
 extern const uint64_t ff_pb_1F;
 extern const uint64_t ff_pb_3F;
 extern const uint64_t ff_pb_81;
-extern const uint64_t ff_pb_A1;
+extern const xmm_reg  ff_pb_A1;
 extern const xmm_reg  ff_pb_F8;
 extern const uint64_t ff_pb_FC;
 extern const xmm_reg  ff_pb_FE;
 
 extern const double ff_pd_1[2];
 extern const double ff_pd_2[2];
 
 #define LOAD4(stride,in,a,b,c,d)\
     "movq 0*"#stride"+"#in", "#a"\n\t"\
     "movq 1*"#stride"+"#in", "#b"\n\t"\
@@ skipping 16 matching lines @@
     "mov" #m " " #a ", " #t "         \n\t" /* abcd */\
     "punpckl" #n " " #b ", " #a "     \n\t" /* aebf */\
     "punpckh" #n " " #b ", " #t "     \n\t" /* cgdh */\
 
 #define TRANSPOSE4(a,b,c,d,t)\
     SBUTTERFLY(a,b,t,wd,q) /* a=aebf t=cgdh */\
     SBUTTERFLY(c,d,b,wd,q) /* c=imjn b=kolp */\
     SBUTTERFLY(a,c,d,dq,q) /* a=aeim d=bfjn */\
     SBUTTERFLY(t,b,c,dq,q) /* t=cgko c=dhlp */
 
+static inline void transpose4x4(uint8_t *dst, uint8_t *src, int dst_stride, int src_stride){
+    __asm__ volatile( //FIXME could save 1 instruction if done as 8x4 ...
+        "movd  %4, %%mm0                \n\t"
+        "movd  %5, %%mm1                \n\t"
+        "movd  %6, %%mm2                \n\t"
+        "movd  %7, %%mm3                \n\t"
+        "punpcklbw %%mm1, %%mm0         \n\t"
+        "punpcklbw %%mm3, %%mm2         \n\t"
+        "movq %%mm0, %%mm1              \n\t"
+        "punpcklwd %%mm2, %%mm0         \n\t"
+        "punpckhwd %%mm2, %%mm1         \n\t"
+        "movd  %%mm0, %0                \n\t"
+        "punpckhdq %%mm0, %%mm0         \n\t"
+        "movd  %%mm0, %1                \n\t"
+        "movd  %%mm1, %2                \n\t"
+        "punpckhdq %%mm1, %%mm1         \n\t"
+        "movd  %%mm1, %3                \n\t"
+
+        : "=m" (*(uint32_t*)(dst + 0*dst_stride)),
+          "=m" (*(uint32_t*)(dst + 1*dst_stride)),
+          "=m" (*(uint32_t*)(dst + 2*dst_stride)),
+          "=m" (*(uint32_t*)(dst + 3*dst_stride))
+        :  "m" (*(uint32_t*)(src + 0*src_stride)),
+           "m" (*(uint32_t*)(src + 1*src_stride)),
+           "m" (*(uint32_t*)(src + 2*src_stride)),
+           "m" (*(uint32_t*)(src + 3*src_stride))
+    );
+}
+
 // e,f,g,h can be memory
 // out: a,d,t,c
 #define TRANSPOSE8x4(a,b,c,d,e,f,g,h,t)\
     "punpcklbw " #e ", " #a " \n\t" /* a0 e0 a1 e1 a2 e2 a3 e3 */\
     "punpcklbw " #f ", " #b " \n\t" /* b0 f0 b1 f1 b2 f2 b3 f3 */\
     "punpcklbw " #g ", " #c " \n\t" /* c0 g0 c1 g1 c2 g2 d3 g3 */\
     "punpcklbw " #h ", " #d " \n\t" /* d0 h0 d1 h1 d2 h2 d3 h3 */\
     SBUTTERFLY(a, b, t, bw, q)   /* a= a0 b0 e0 f0 a1 b1 e1 f1 */\
                                  /* t= a2 b2 e2 f2 a3 b3 e3 f3 */\
     SBUTTERFLY(c, d, b, bw, q)   /* c= c0 d0 g0 h0 c1 d1 g1 h1 */\
@@ skipping 44 matching lines @@
 #endif
 
 #define MOVQ_WONE(regd) \
     __asm__ volatile ( \
     "pcmpeqd %%" #regd ", %%" #regd " \n\t" \
     "psrlw $15, %%" #regd ::)
 
 void dsputilenc_init_mmx(DSPContext* c, AVCodecContext *avctx);
 void dsputil_init_pix_mmx(DSPContext* c, AVCodecContext *avctx);
 
-void add_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
-void put_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
-void put_signed_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
+void ff_add_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
+void ff_put_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
+void ff_put_signed_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
 
 void ff_put_cavs_qpel8_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
 void ff_avg_cavs_qpel8_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
 void ff_put_cavs_qpel16_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
 void ff_avg_cavs_qpel16_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
 
 void ff_vc1dsp_init_mmx(DSPContext* dsp, AVCodecContext *avctx);
 void ff_put_vc1_mspel_mc00_mmx(uint8_t *dst, const uint8_t *src, int stride, int rnd);
 void ff_avg_vc1_mspel_mc00_mmx2(uint8_t *dst, const uint8_t *src, int stride, int rnd);
 
@@ skipping 10 matching lines @@
                              const uint8_t *lum,
                              int size);
 
 void ff_deinterlace_line_inplace_mmx(const uint8_t *lum_m4,
                                      const uint8_t *lum_m3,
                                      const uint8_t *lum_m2,
                                      const uint8_t *lum_m1,
                                      const uint8_t *lum, int size);
 
 #endif /* AVCODEC_X86_DSPUTIL_MMX_H */