comparison x86/dsputil_mmx.h @ 12450:3941687b4fa9 libavcodec

Split h264dsp_mmx.c (which was #included in dsputil_mmx.c) in h264_qpel_mmx.c, still #included in dsputil_mmx.c and is part of DSPContext, and h264dsp_mmx.c, which represents H264DSPContext and is now compiled on its own.

12449:3bca212d6f51

#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 */

// 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 */\

12450:3941687b4fa9

#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 */\