void jsimd_idct_islow_altivec()

in simd/powerpc/jidctint-altivec.c [207:357]

• 122 lines of code
• 2 McCabe index (conditional complexity)

void jsimd_idct_islow_altivec(void *dct_table_, JCOEFPTR coef_block,
                              JSAMPARRAY output_buf, JDIMENSION output_col)
{
  short *dct_table = (short *)dct_table_;
  int *outptr;

  __vector short row0, row1, row2, row3, row4, row5, row6, row7,
    col0, col1, col2, col3, col4, col5, col6, col7,
    quant0, quant1, quant2, quant3, quant4, quant5, quant6, quant7,
    tmp0, tmp1, tmp2, tmp3, z3, z4,
    z34l, z34h, col71l, col71h, col26l, col26h, col53l, col53h,
    row71l, row71h, row26l, row26h, row53l, row53h,
    out0, out1, out2, out3, out4, out5, out6, out7;
  __vector int tmp0l, tmp0h, tmp1l, tmp1h, tmp2l, tmp2h, tmp3l, tmp3h,
    tmp10l, tmp10h, tmp11l, tmp11h, tmp12l, tmp12h, tmp13l, tmp13h,
    z3l, z3h, z4l, z4h,
    out0l, out0h, out1l, out1h, out2l, out2h, out3l, out3h, out4l, out4h,
    out5l, out5h, out6l, out6h, out7l, out7h;
  __vector signed char outb;

  /* Constants */
  __vector short pw_zero = { __8X(0) },
    pw_f130_f054 = { __4X2(F_0_541 + F_0_765, F_0_541) },
    pw_f054_mf130 = { __4X2(F_0_541, F_0_541 - F_1_847) },
    pw_mf078_f117 = { __4X2(F_1_175 - F_1_961, F_1_175) },
    pw_f117_f078 = { __4X2(F_1_175, F_1_175 - F_0_390) },
    pw_mf060_mf089 = { __4X2(F_0_298 - F_0_899, -F_0_899) },
    pw_mf089_f060 = { __4X2(-F_0_899, F_1_501 - F_0_899) },
    pw_mf050_mf256 = { __4X2(F_2_053 - F_2_562, -F_2_562) },
    pw_mf256_f050 = { __4X2(-F_2_562, F_3_072 - F_2_562) };
  __vector unsigned short pass1_bits = { __8X(PASS1_BITS) };
  __vector int pd_zero = { __4X(0) },
    pd_descale_p1 = { __4X(1 << (DESCALE_P1 - 1)) },
    pd_descale_p2 = { __4X(1 << (DESCALE_P2 - 1)) };
  __vector unsigned int descale_p1 = { __4X(DESCALE_P1) },
    descale_p2 = { __4X(DESCALE_P2) },
    const_bits = { __4X(CONST_BITS) };
  __vector signed char pb_centerjsamp = { __16X((signed char)CENTERJSAMPLE) };

  /* Pass 1: process columns */

  col0 = vec_ld(0, coef_block);
  col1 = vec_ld(16, coef_block);
  col2 = vec_ld(32, coef_block);
  col3 = vec_ld(48, coef_block);
  col4 = vec_ld(64, coef_block);
  col5 = vec_ld(80, coef_block);
  col6 = vec_ld(96, coef_block);
  col7 = vec_ld(112, coef_block);

  tmp1 = vec_or(col1, col2);
  tmp2 = vec_or(col3, col4);
  tmp1 = vec_or(tmp1, tmp2);
  tmp3 = vec_or(col5, col6);
  tmp3 = vec_or(tmp3, col7);
  tmp1 = vec_or(tmp1, tmp3);

  quant0 = vec_ld(0, dct_table);
  col0 = vec_mladd(col0, quant0, pw_zero);

  if (vec_all_eq(tmp1, pw_zero)) {
    /* AC terms all zero */

    col0 = vec_sl(col0, pass1_bits);

    row0 = vec_splat(col0, 0);
    row1 = vec_splat(col0, 1);
    row2 = vec_splat(col0, 2);
    row3 = vec_splat(col0, 3);
    row4 = vec_splat(col0, 4);
    row5 = vec_splat(col0, 5);
    row6 = vec_splat(col0, 6);
    row7 = vec_splat(col0, 7);

  } else {

    quant1 = vec_ld(16, dct_table);
    quant2 = vec_ld(32, dct_table);
    quant3 = vec_ld(48, dct_table);
    quant4 = vec_ld(64, dct_table);
    quant5 = vec_ld(80, dct_table);
    quant6 = vec_ld(96, dct_table);
    quant7 = vec_ld(112, dct_table);

    col1 = vec_mladd(col1, quant1, pw_zero);
    col2 = vec_mladd(col2, quant2, pw_zero);
    col3 = vec_mladd(col3, quant3, pw_zero);
    col4 = vec_mladd(col4, quant4, pw_zero);
    col5 = vec_mladd(col5, quant5, pw_zero);
    col6 = vec_mladd(col6, quant6, pw_zero);
    col7 = vec_mladd(col7, quant7, pw_zero);

    DO_IDCT(col, 1);

    TRANSPOSE(out, row);
  }

  /* Pass 2: process rows */

  DO_IDCT(row, 2);

  TRANSPOSE(out, col);

  outb = vec_packs(col0, col0);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[0] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col1, col1);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[1] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col2, col2);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[2] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col3, col3);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[3] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col4, col4);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[4] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col5, col5);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[5] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col6, col6);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[6] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);

  outb = vec_packs(col7, col7);
  outb = vec_add(outb, pb_centerjsamp);
  outptr = (int *)(output_buf[7] + output_col);
  vec_ste((__vector int)outb, 0, outptr);
  vec_ste((__vector int)outb, 4, outptr);
}