comparison dsputil.c @ 2979:bfabfdf9ce55 libavcodec

COSMETICS: tabs --> spaces, some prettyprinting

2978:403183bbb505

  17318417,   17248865,   17179870,   17111424,   17043522,   16976156,   16909321,   16843010,
};

/* Input permutation for the simple_idct_mmx */
static const uint8_t simple_mmx_permutation[64]={
	0x00, 0x08, 0x04, 0x09, 0x01, 0x0C, 0x05, 0x0D,
	0x10, 0x18, 0x14, 0x19, 0x11, 0x1C, 0x15, 0x1D,
	0x20, 0x28, 0x24, 0x29, 0x21, 0x2C, 0x25, 0x2D,
	0x12, 0x1A, 0x16, 0x1B, 0x13, 0x1E, 0x17, 0x1F,
	0x02, 0x0A, 0x06, 0x0B, 0x03, 0x0E, 0x07, 0x0F,
	0x30, 0x38, 0x34, 0x39, 0x31, 0x3C, 0x35, 0x3D,
	0x22, 0x2A, 0x26, 0x2B, 0x23, 0x2E, 0x27, 0x2F,
	0x32, 0x3A, 0x36, 0x3B, 0x33, 0x3E, 0x37, 0x3F,
};

static int pix_sum_c(uint8_t * pix, int line_size)
{
    int s, i, j;

    s = 0;
    for (i = 0; i < 16; i++) {
	for (j = 0; j < 16; j += 8) {
	    s += pix[0];
	    s += pix[1];
	    s += pix[2];
	    s += pix[3];
	    s += pix[4];
	    s += pix[5];
	    s += pix[6];
	    s += pix[7];
	    pix += 8;
	}
	pix += line_size - 16;
    }
    return s;
}

static int pix_norm1_c(uint8_t * pix, int line_size)

    int s, i, j;
    uint32_t *sq = squareTbl + 256;

    s = 0;
    for (i = 0; i < 16; i++) {
	for (j = 0; j < 16; j += 8) {
#if 0
	    s += sq[pix[0]];
	    s += sq[pix[1]];
	    s += sq[pix[2]];
	    s += sq[pix[3]];
	    s += sq[pix[4]];
	    s += sq[pix[5]];
	    s += sq[pix[6]];
	    s += sq[pix[7]];
#else
#if LONG_MAX > 2147483647
	    register uint64_t x=*(uint64_t*)pix;
	    s += sq[x&0xff];
	    s += sq[(x>>8)&0xff];
	    s += sq[(x>>16)&0xff];
	    s += sq[(x>>24)&0xff];
            s += sq[(x>>32)&0xff];
            s += sq[(x>>40)&0xff];
            s += sq[(x>>48)&0xff];
            s += sq[(x>>56)&0xff];
#else
	    register uint32_t x=*(uint32_t*)pix;
	    s += sq[x&0xff];
	    s += sq[(x>>8)&0xff];
	    s += sq[(x>>16)&0xff];
	    s += sq[(x>>24)&0xff];
            x=*(uint32_t*)(pix+4);
            s += sq[x&0xff];
            s += sq[(x>>8)&0xff];
            s += sq[(x>>16)&0xff];
            s += sq[(x>>24)&0xff];
#endif
#endif
	    pix += 8;
	}
	pix += line_size - 16;
    }
    return s;
}

static void bswap_buf(uint32_t *dst, uint32_t *src, int w){

        block += 8;
    }
}

static void diff_pixels_c(DCTELEM *restrict block, const uint8_t *s1,
			  const uint8_t *s2, int stride){
    int i;

    /* read the pixels */
    for(i=0;i<8;i++) {
        block[0] = s1[0] - s2[0];

    }
}


static void put_pixels_clamped_c(const DCTELEM *block, uint8_t *restrict pixels,
				 int line_size)
{
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    /* read the pixels */

        block += 8;
    }
}

static void put_pixels_clamped4_c(const DCTELEM *block, uint8_t *restrict pixels,
				 int line_size)
{
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    /* read the pixels */

        block += 8;
    }
}

static void put_pixels_clamped2_c(const DCTELEM *block, uint8_t *restrict pixels,
				 int line_size)
{
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    /* read the pixels */

static inline void put_tpel_pixels_mc10_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (683*(2*src[j] + src[j+1] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc20_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (683*(src[j] + 2*src[j+1] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc01_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (683*(2*src[j] + src[j+stride] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc11_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (2731*(4*src[j] + 3*src[j+1] + 3*src[j+stride] + 2*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc12_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (2731*(3*src[j] + 2*src[j+1] + 4*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc02_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (683*(src[j] + 2*src[j+stride] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc21_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (2731*(3*src[j] + 4*src[j+1] + 2*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc22_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (2731*(2*src[j] + 3*src[j+1] + 3*src[j+stride] + 4*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc10_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((683*(2*src[j] + src[j+1] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc20_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((683*(src[j] + 2*src[j+1] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc01_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((683*(2*src[j] + src[j+stride] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc11_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((2731*(4*src[j] + 3*src[j+1] + 3*src[j+stride] + 2*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc12_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((2731*(3*src[j] + 2*src[j+1] + 4*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc02_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((683*(src[j] + 2*src[j+stride] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc21_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((2731*(3*src[j] + 4*src[j+1] + 2*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc22_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
	dst[j] = (dst[j] + ((2731*(2*src[j] + 3*src[j+1] + 3*src[j+stride] + 4*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

    int i;

#ifdef CONFIG_ENCODERS
    if(avctx->dct_algo==FF_DCT_FASTINT) {
        c->fdct = fdct_ifast;
	c->fdct248 = fdct_ifast248;
    }
    else if(avctx->dct_algo==FF_DCT_FAAN) {
        c->fdct = ff_faandct;
	c->fdct248 = ff_faandct248;
    }
    else {
        c->fdct = ff_jpeg_fdct_islow; //slow/accurate/default
	c->fdct248 = ff_fdct248_islow;
    }
#endif //CONFIG_ENCODERS

    if(avctx->lowres==1){
        if(avctx->idct_algo==FF_IDCT_INT || avctx->idct_algo==FF_IDCT_AUTO){

2979:bfabfdf9ce55

  17318417,   17248865,   17179870,   17111424,   17043522,   16976156,   16909321,   16843010,
};

/* Input permutation for the simple_idct_mmx */
static const uint8_t simple_mmx_permutation[64]={
        0x00, 0x08, 0x04, 0x09, 0x01, 0x0C, 0x05, 0x0D,
        0x10, 0x18, 0x14, 0x19, 0x11, 0x1C, 0x15, 0x1D,
        0x20, 0x28, 0x24, 0x29, 0x21, 0x2C, 0x25, 0x2D,
        0x12, 0x1A, 0x16, 0x1B, 0x13, 0x1E, 0x17, 0x1F,
        0x02, 0x0A, 0x06, 0x0B, 0x03, 0x0E, 0x07, 0x0F,
        0x30, 0x38, 0x34, 0x39, 0x31, 0x3C, 0x35, 0x3D,
        0x22, 0x2A, 0x26, 0x2B, 0x23, 0x2E, 0x27, 0x2F,
        0x32, 0x3A, 0x36, 0x3B, 0x33, 0x3E, 0x37, 0x3F,
};

static int pix_sum_c(uint8_t * pix, int line_size)
{
    int s, i, j;

    s = 0;
    for (i = 0; i < 16; i++) {
        for (j = 0; j < 16; j += 8) {
            s += pix[0];
            s += pix[1];
            s += pix[2];
            s += pix[3];
            s += pix[4];
            s += pix[5];
            s += pix[6];
            s += pix[7];
            pix += 8;
        }
        pix += line_size - 16;
    }
    return s;
}

static int pix_norm1_c(uint8_t * pix, int line_size)

    int s, i, j;
    uint32_t *sq = squareTbl + 256;

    s = 0;
    for (i = 0; i < 16; i++) {
        for (j = 0; j < 16; j += 8) {
#if 0
            s += sq[pix[0]];
            s += sq[pix[1]];
            s += sq[pix[2]];
            s += sq[pix[3]];
            s += sq[pix[4]];
            s += sq[pix[5]];
            s += sq[pix[6]];
            s += sq[pix[7]];
#else
#if LONG_MAX > 2147483647
            register uint64_t x=*(uint64_t*)pix;
            s += sq[x&0xff];
            s += sq[(x>>8)&0xff];
            s += sq[(x>>16)&0xff];
            s += sq[(x>>24)&0xff];
            s += sq[(x>>32)&0xff];
            s += sq[(x>>40)&0xff];
            s += sq[(x>>48)&0xff];
            s += sq[(x>>56)&0xff];
#else
            register uint32_t x=*(uint32_t*)pix;
            s += sq[x&0xff];
            s += sq[(x>>8)&0xff];
            s += sq[(x>>16)&0xff];
            s += sq[(x>>24)&0xff];
            x=*(uint32_t*)(pix+4);
            s += sq[x&0xff];
            s += sq[(x>>8)&0xff];
            s += sq[(x>>16)&0xff];
            s += sq[(x>>24)&0xff];
#endif
#endif
            pix += 8;
        }
        pix += line_size - 16;
    }
    return s;
}

static void bswap_buf(uint32_t *dst, uint32_t *src, int w){

        block += 8;
    }
}

static void diff_pixels_c(DCTELEM *restrict block, const uint8_t *s1,
                          const uint8_t *s2, int stride){
    int i;

    /* read the pixels */
    for(i=0;i<8;i++) {
        block[0] = s1[0] - s2[0];

    }
}


static void put_pixels_clamped_c(const DCTELEM *block, uint8_t *restrict pixels,
                                 int line_size)
{
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    /* read the pixels */

        block += 8;
    }
}

static void put_pixels_clamped4_c(const DCTELEM *block, uint8_t *restrict pixels,
                                 int line_size)
{
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    /* read the pixels */

        block += 8;
    }
}

static void put_pixels_clamped2_c(const DCTELEM *block, uint8_t *restrict pixels,
                                 int line_size)
{
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    /* read the pixels */

static inline void put_tpel_pixels_mc10_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (683*(2*src[j] + src[j+1] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc20_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (683*(src[j] + 2*src[j+1] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc01_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (683*(2*src[j] + src[j+stride] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc11_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (2731*(4*src[j] + 3*src[j+1] + 3*src[j+stride] + 2*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc12_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (2731*(3*src[j] + 2*src[j+1] + 4*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc02_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (683*(src[j] + 2*src[j+stride] + 1)) >> 11;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc21_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (2731*(3*src[j] + 4*src[j+1] + 2*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void put_tpel_pixels_mc22_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (2731*(2*src[j] + 3*src[j+1] + 3*src[j+stride] + 4*src[j+stride+1] + 6)) >> 15;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc10_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((683*(2*src[j] + src[j+1] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc20_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((683*(src[j] + 2*src[j+1] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc01_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((683*(2*src[j] + src[j+stride] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc11_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((2731*(4*src[j] + 3*src[j+1] + 3*src[j+stride] + 2*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc12_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((2731*(3*src[j] + 2*src[j+1] + 4*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc02_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((683*(src[j] + 2*src[j+stride] + 1)) >> 11) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc21_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((2731*(3*src[j] + 4*src[j+1] + 2*src[j+stride] + 3*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

static inline void avg_tpel_pixels_mc22_c(uint8_t *dst, const uint8_t *src, int stride, int width, int height){
    int i,j;
    for (i=0; i < height; i++) {
      for (j=0; j < width; j++) {
        dst[j] = (dst[j] + ((2731*(2*src[j] + 3*src[j+1] + 3*src[j+stride] + 4*src[j+stride+1] + 6)) >> 15) + 1) >> 1;
      }
      src += stride;
      dst += stride;
    }
}

    int i;

#ifdef CONFIG_ENCODERS
    if(avctx->dct_algo==FF_DCT_FASTINT) {
        c->fdct = fdct_ifast;
        c->fdct248 = fdct_ifast248;
    }
    else if(avctx->dct_algo==FF_DCT_FAAN) {
        c->fdct = ff_faandct;
        c->fdct248 = ff_faandct248;
    }
    else {
        c->fdct = ff_jpeg_fdct_islow; //slow/accurate/default
        c->fdct248 = ff_fdct248_islow;
    }
#endif //CONFIG_ENCODERS

    if(avctx->lowres==1){
        if(avctx->idct_algo==FF_IDCT_INT || avctx->idct_algo==FF_IDCT_AUTO){