private void jpeg_idct_16x8(int component_index, short[] coef_block, int output_row, int output_col)
{
/* buffers data between passes */
int[] workspace = new int[8 * 8];
/* Pass 1: process columns from input, store into work array. */
/* Note results are scaled up by sqrt(8) compared to a true IDCT; */
/* furthermore, we scale the results by 2**SLOW_INTEGER_PASS1_BITS. */
/* 8 - point IDCT kernel, cK represents sqrt(2) * cos(K * pi / 16). */
int coefBlockIndex = 0;
int[] quantTable = m_dctTables[component_index].int_array;
int quantTableIndex = 0;
int workspaceIndex = 0;
for (int ctr = JpegConstants.DCTSIZE; ctr > 0; ctr--)
{
/* Due to quantization, we will usually find that many of the input
* coefficients are zero, especially the AC terms. We can exploit this
* by short-circuiting the IDCT calculation for any column in which all
* the AC terms are zero. In that case each output is equal to the
* DC coefficient (with scale factor as needed).
* With typical images and quantization tables, half or more of the
* column DCT calculations can be simplified this way.
*/
if (coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 1] == 0 &&
coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 2] == 0 &&
coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 3] == 0 &&
coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 4] == 0 &&
coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 5] == 0 &&
coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 6] == 0 &&
coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 7] == 0)
{
/* AC terms all zero */
int dcval = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 0],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 0]) << SLOW_INTEGER_PASS1_BITS;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 0] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 1] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 2] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 3] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 4] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 5] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 6] = dcval;
workspace[workspaceIndex + JpegConstants.DCTSIZE * 7] = dcval;
/* advance pointers to next column */
coefBlockIndex++;
quantTableIndex++;
workspaceIndex++;
continue;
}
/* Even part: reverse the even part of the forward DCT. */
/* The rotator is c(-6). */
int z2 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 2],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 2]);
int z3 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 6],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 6]);
int z1 = (z2 + z3) * SLOW_INTEGER_FIX_0_541196100;
int tmp2 = z1 + z2 * SLOW_INTEGER_FIX_0_765366865;
int tmp3 = z1 - z3 * SLOW_INTEGER_FIX_1_847759065;
z2 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 0],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 0]);
z3 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 4],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 4]);
z2 <<= SLOW_INTEGER_CONST_BITS;
z3 <<= SLOW_INTEGER_CONST_BITS;
/* Add fudge factor here for final descale. */
z2 += 1 << (SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS - 1);
int tmp0 = z2 + z3;
int tmp1 = z2 - z3;
int tmp10 = tmp0 + tmp2;
int tmp13 = tmp0 - tmp2;
int tmp11 = tmp1 + tmp3;
int tmp12 = tmp1 - tmp3;
/* Odd part per figure 8; the matrix is unitary and hence its
* transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively.
*/
tmp0 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 7],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 7]);
tmp1 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 5],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 5]);
tmp2 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 3],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 3]);
tmp3 = SLOW_INTEGER_DEQUANTIZE(coef_block[coefBlockIndex + JpegConstants.DCTSIZE * 1],
quantTable[quantTableIndex + JpegConstants.DCTSIZE * 1]);
z2 = tmp0 + tmp2;
z3 = tmp1 + tmp3;
z1 = (z2 + z3) * SLOW_INTEGER_FIX_1_175875602; /* c3 */
z2 = z2 * (-SLOW_INTEGER_FIX_1_961570560); /* -c3-c5 */
z3 = z3 * (-SLOW_INTEGER_FIX_0_390180644); /* -c3+c5 */
z2 += z1;
z3 += z1;
z1 = (tmp0 + tmp3) * (-SLOW_INTEGER_FIX_0_899976223); /* -c3+c7 */
tmp0 = tmp0 * SLOW_INTEGER_FIX_0_298631336; /* -c1+c3+c5-c7 */
tmp3 = tmp3 * SLOW_INTEGER_FIX_1_501321110; /* c1+c3-c5-c7 */
tmp0 += z1 + z2;
tmp3 += z1 + z3;
z1 = (tmp1 + tmp2) * (-SLOW_INTEGER_FIX_2_562915447); /* -c1-c3 */
tmp1 = tmp1 * SLOW_INTEGER_FIX_2_053119869; /* c1+c3-c5+c7 */
tmp2 = tmp2 * SLOW_INTEGER_FIX_3_072711026; /* c1+c3+c5-c7 */
tmp1 += z1 + z3;
tmp2 += z1 + z2;
/* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
workspace[workspaceIndex + JpegConstants.DCTSIZE * 0] = JpegUtils.RIGHT_SHIFT(tmp10 + tmp3, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 7] = JpegUtils.RIGHT_SHIFT(tmp10 - tmp3, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 1] = JpegUtils.RIGHT_SHIFT(tmp11 + tmp2, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 6] = JpegUtils.RIGHT_SHIFT(tmp11 - tmp2, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 2] = JpegUtils.RIGHT_SHIFT(tmp12 + tmp1, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 5] = JpegUtils.RIGHT_SHIFT(tmp12 - tmp1, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 3] = JpegUtils.RIGHT_SHIFT(tmp13 + tmp0, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
workspace[workspaceIndex + JpegConstants.DCTSIZE * 4] = JpegUtils.RIGHT_SHIFT(tmp13 - tmp0, SLOW_INTEGER_CONST_BITS - SLOW_INTEGER_PASS1_BITS);
/* advance pointers to next column */
coefBlockIndex++;
quantTableIndex++;
workspaceIndex++;
}
/* Pass 2: process 8 rows from work array, store into output array.
* 16-point IDCT kernel, cK represents sqrt(2) * cos(K*pi/32).
*/
workspaceIndex = 0;
byte[] limit = m_cinfo.m_sample_range_limit;
int limitOffset = m_cinfo.m_sampleRangeLimitOffset - RANGE_SUBSET;
for (int ctr = 0; ctr < 8; ctr++)
{
/* Even part */
/* Add range center and fudge factor for final descale and range-limit. */
int tmp0 = workspace[workspaceIndex + 0] +
(RANGE_CENTER << (SLOW_INTEGER_PASS1_BITS + 3)) +
(1 << (SLOW_INTEGER_PASS1_BITS + 2));
tmp0 <<= SLOW_INTEGER_CONST_BITS;
int z1 = workspace[workspaceIndex + 4];
int tmp1 = z1 * SLOW_INTEGER_FIX(1.306562965); /* c4[16] = c2[8] */
int tmp2 = z1 * SLOW_INTEGER_FIX_0_541196100; /* c12[16] = c6[8] */
int tmp10 = tmp0 + tmp1;
int tmp11 = tmp0 - tmp1;
int tmp12 = tmp0 + tmp2;
int tmp13 = tmp0 - tmp2;
z1 = workspace[workspaceIndex + 2];
int z2 = workspace[workspaceIndex + 6];
int z3 = z1 - z2;
int z4 = z3 * SLOW_INTEGER_FIX(0.275899379); /* c14[16] = c7[8] */
z3 = z3 * SLOW_INTEGER_FIX(1.387039845); /* c2[16] = c1[8] */
tmp0 = z3 + z2 * SLOW_INTEGER_FIX_2_562915447; /* (c6+c2)[16] = (c3+c1)[8] */
tmp1 = z4 + z1 * SLOW_INTEGER_FIX_0_899976223; /* (c6-c14)[16] = (c3-c7)[8] */
tmp2 = z3 - z1 * SLOW_INTEGER_FIX(0.601344887); /* (c2-c10)[16] = (c1-c5)[8] */
int tmp3 = z4 - z2 * SLOW_INTEGER_FIX(0.509795579); /* (c10-c14)[16] = (c5-c7)[8] */
int tmp20 = tmp10 + tmp0;
int tmp27 = tmp10 - tmp0;
int tmp21 = tmp12 + tmp1;
int tmp26 = tmp12 - tmp1;
int tmp22 = tmp13 + tmp2;
int tmp25 = tmp13 - tmp2;
int tmp23 = tmp11 + tmp3;
int tmp24 = tmp11 - tmp3;
/* Odd part */
z1 = workspace[workspaceIndex + 1];
z2 = workspace[workspaceIndex + 3];
z3 = workspace[workspaceIndex + 5];
z4 = workspace[workspaceIndex + 7];
tmp11 = z1 + z3;
tmp1 = (z1 + z2) * SLOW_INTEGER_FIX(1.353318001); /* c3 */
tmp2 = tmp11 * SLOW_INTEGER_FIX(1.247225013); /* c5 */
tmp3 = (z1 + z4) * SLOW_INTEGER_FIX(1.093201867); /* c7 */
tmp10 = (z1 - z4) * SLOW_INTEGER_FIX(0.897167586); /* c9 */
tmp11 = tmp11 * SLOW_INTEGER_FIX(0.666655658); /* c11 */
tmp12 = (z1 - z2) * SLOW_INTEGER_FIX(0.410524528); /* c13 */
tmp0 = tmp1 + tmp2 + tmp3 - z1 * SLOW_INTEGER_FIX(2.286341144); /* c7+c5+c3-c1 */
tmp13 = tmp10 + tmp11 + tmp12 - z1 * SLOW_INTEGER_FIX(1.835730603); /* c9+c11+c13-c15 */
z1 = (z2 + z3) * SLOW_INTEGER_FIX(0.138617169); /* c15 */
tmp1 += z1 + z2 * SLOW_INTEGER_FIX(0.071888074); /* c9+c11-c3-c15 */
tmp2 += z1 - z3 * SLOW_INTEGER_FIX(1.125726048); /* c5+c7+c15-c3 */
z1 = (z3 - z2) * SLOW_INTEGER_FIX(1.407403738); /* c1 */
tmp11 += z1 - z3 * SLOW_INTEGER_FIX(0.766367282); /* c1+c11-c9-c13 */
tmp12 += z1 + z2 * SLOW_INTEGER_FIX(1.971951411); /* c1+c5+c13-c7 */
z2 += z4;
z1 = z2 * (-SLOW_INTEGER_FIX(0.666655658)); /* -c11 */
tmp1 += z1;
tmp3 += z1 + z4 * SLOW_INTEGER_FIX(1.065388962); /* c3+c11+c15-c7 */
z2 = z2 * (-SLOW_INTEGER_FIX(1.247225013)); /* -c5 */
tmp10 += z2 + z4 * SLOW_INTEGER_FIX(3.141271809); /* c1+c5+c9-c13 */
tmp12 += z2;
z2 = (z3 + z4) * (-SLOW_INTEGER_FIX(1.353318001)); /* -c3 */
tmp2 += z2;
tmp3 += z2;
z2 = (z4 - z3) * SLOW_INTEGER_FIX(0.410524528); /* c13 */
tmp10 += z2;
tmp11 += z2;
/* Final output stage */
int currentOutRow = output_row + ctr;
m_componentBuffer[currentOutRow][output_col + 0] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp20 + tmp0, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 15] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp20 - tmp0, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 1] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp21 + tmp1, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 14] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp21 - tmp1, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 2] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp22 + tmp2, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 13] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp22 - tmp2, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 3] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp23 + tmp3, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 12] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp23 - tmp3, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 4] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp24 + tmp10, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 11] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp24 - tmp10, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 5] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp25 + tmp11, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 10] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp25 - tmp11, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 6] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp26 + tmp12, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 9] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp26 - tmp12, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 7] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp27 + tmp13, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
m_componentBuffer[currentOutRow][output_col + 8] = limit[limitOffset + JpegUtils.RIGHT_SHIFT(
tmp27 - tmp13, SLOW_INTEGER_CONST_BITS + SLOW_INTEGER_PASS1_BITS + 3) & RANGE_MASK];
workspaceIndex += 8; /* advance pointer to next row */
}
}
