jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { FAST_FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7; FAST_FLOAT tmp10, tmp11, tmp12, tmp13; FAST_FLOAT z5, z10, z11, z12, z13; JCOEFPTR inptr; FLOAT_MULT_TYPE * quantptr; FAST_FLOAT * wsptr; JSAMPROW outptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); int ctr; FAST_FLOAT workspace[DCTSIZE2]; /* buffers data between passes */ SHIFT_TEMPS /* Pass 1: process columns from input, store into work array. */ inptr = coef_block; quantptr = (FLOAT_MULT_TYPE *) compptr->dct_table; wsptr = workspace; for (ctr = 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 (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 && inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 && inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 && inptr[DCTSIZE*7] == 0) { /* AC terms all zero */ FAST_FLOAT dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); wsptr[DCTSIZE*0] = dcval; wsptr[DCTSIZE*1] = dcval; wsptr[DCTSIZE*2] = dcval; wsptr[DCTSIZE*3] = dcval; wsptr[DCTSIZE*4] = dcval; wsptr[DCTSIZE*5] = dcval; wsptr[DCTSIZE*6] = dcval; wsptr[DCTSIZE*7] = dcval; inptr++; /* advance pointers to next column */ quantptr++; wsptr++; continue; } /* Even part */ tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]); tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); tmp10 = tmp0 + tmp2; /* phase 3 */ tmp11 = tmp0 - tmp2; tmp13 = tmp1 + tmp3; /* phases 5-3 */ tmp12 = (tmp1 - tmp3) * ((FAST_FLOAT) 1.414213562) - tmp13; /* 2*c4 */ tmp0 = tmp10 + tmp13; /* phase 2 */ tmp3 = tmp10 - tmp13; tmp1 = tmp11 + tmp12; tmp2 = tmp11 - tmp12; /* Odd part */ tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]); z13 = tmp6 + tmp5; /* phase 6 */ z10 = tmp6 - tmp5; z11 = tmp4 + tmp7; z12 = tmp4 - tmp7; tmp7 = z11 + z13; /* phase 5 */ tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562); /* 2*c4 */ z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */ tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */ tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */ tmp6 = tmp12 - tmp7; /* phase 2 */ tmp5 = tmp11 - tmp6; tmp4 = tmp10 + tmp5; wsptr[DCTSIZE*0] = tmp0 + tmp7; wsptr[DCTSIZE*7] = tmp0 - tmp7; wsptr[DCTSIZE*1] = tmp1 + tmp6; wsptr[DCTSIZE*6] = tmp1 - tmp6; wsptr[DCTSIZE*2] = tmp2 + tmp5; wsptr[DCTSIZE*5] = tmp2 - tmp5; wsptr[DCTSIZE*4] = tmp3 + tmp4; wsptr[DCTSIZE*3] = tmp3 - tmp4; inptr++; /* advance pointers to next column */ quantptr++; wsptr++; } /* Pass 2: process rows from work array, store into output array. */ /* Note that we must descale the results by a factor of 8 == 2**3. */ wsptr = workspace; for (ctr = 0; ctr < DCTSIZE; ctr++) { outptr = output_buf[ctr] + output_col; /* Rows of zeroes can be exploited in the same way as we did with columns. * However, the column calculation has created many nonzero AC terms, so * the simplification applies less often (typically 5% to 10% of the time). * And testing floats for zero is relatively expensive, so we don't bother. */ /* Even part */ tmp10 = wsptr[0] + wsptr[4]; tmp11 = wsptr[0] - wsptr[4]; tmp13 = wsptr[2] + wsptr[6]; tmp12 = (wsptr[2] - wsptr[6]) * ((FAST_FLOAT) 1.414213562) - tmp13; tmp0 = tmp10 + tmp13; tmp3 = tmp10 - tmp13; tmp1 = tmp11 + tmp12; tmp2 = tmp11 - tmp12; /* Odd part */ z13 = wsptr[5] + wsptr[3]; z10 = wsptr[5] - wsptr[3]; z11 = wsptr[1] + wsptr[7]; z12 = wsptr[1] - wsptr[7]; tmp7 = z11 + z13; tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562); z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */ tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */ tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */ tmp6 = tmp12 - tmp7; tmp5 = tmp11 - tmp6; tmp4 = tmp10 + tmp5; /* Final output stage: scale down by a factor of 8 and range-limit */ outptr[0] = range_limit[(int) DESCALE((INT32) (tmp0 + tmp7), 3) & RANGE_MASK]; outptr[7] = range_limit[(int) DESCALE((INT32) (tmp0 - tmp7), 3) & RANGE_MASK]; outptr[1] = range_limit[(int) DESCALE((INT32) (tmp1 + tmp6), 3) & RANGE_MASK]; outptr[6] = range_limit[(int) DESCALE((INT32) (tmp1 - tmp6), 3) & RANGE_MASK]; outptr[2] = range_limit[(int) DESCALE((INT32) (tmp2 + tmp5), 3) & RANGE_MASK]; outptr[5] = range_limit[(int) DESCALE((INT32) (tmp2 - tmp5), 3) & RANGE_MASK]; outptr[4] = range_limit[(int) DESCALE((INT32) (tmp3 + tmp4), 3) & RANGE_MASK]; outptr[3] = range_limit[(int) DESCALE((INT32) (tmp3 - tmp4), 3) & RANGE_MASK]; wsptr += DCTSIZE; /* advance pointer to next row */ } }
jpeg_idct_islow (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { IJG_INT32 tmp0, tmp1, tmp2, tmp3; IJG_INT32 tmp10, tmp11, tmp12, tmp13; IJG_INT32 z1, z2, z3, z4, z5; JCOEFPTR inptr; ISLOW_MULT_TYPE * quantptr; int * wsptr; JSAMPROW outptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); int ctr; int workspace[DCTSIZE2]; /* buffers data between passes */ SHIFT_TEMPS /* 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**PASS1_BITS. */ inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; for (ctr = 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 (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 && inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 && inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 && inptr[DCTSIZE*7] == 0) { /* AC terms all zero */ int dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]) << PASS1_BITS; wsptr[DCTSIZE*0] = dcval; wsptr[DCTSIZE*1] = dcval; wsptr[DCTSIZE*2] = dcval; wsptr[DCTSIZE*3] = dcval; wsptr[DCTSIZE*4] = dcval; wsptr[DCTSIZE*5] = dcval; wsptr[DCTSIZE*6] = dcval; wsptr[DCTSIZE*7] = dcval; inptr++; /* advance pointers to next column */ quantptr++; wsptr++; continue; } /* Even part: reverse the even part of the forward DCT. */ /* The rotator is sqrt(2)*c(-6). */ z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); z1 = MULTIPLY(z2 + z3, FIX_0_541196100); tmp2 = z1 + MULTIPLY(z3, - FIX_1_847759065); tmp3 = z1 + MULTIPLY(z2, FIX_0_765366865); z2 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); z3 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]); tmp0 = (z2 + z3) << CONST_BITS; tmp1 = (z2 - z3) << CONST_BITS; tmp10 = tmp0 + tmp3; tmp13 = tmp0 - tmp3; tmp11 = tmp1 + tmp2; tmp12 = tmp1 - tmp2; /* 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 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]); tmp1 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); tmp2 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); tmp3 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); z1 = tmp0 + tmp3; z2 = tmp1 + tmp2; z3 = tmp0 + tmp2; z4 = tmp1 + tmp3; z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */ tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ z3 += z5; z4 += z5; tmp0 += z1 + z3; tmp1 += z2 + z4; tmp2 += z2 + z3; tmp3 += z1 + z4; /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */ wsptr[DCTSIZE*0] = (int) DESCALE(tmp10 + tmp3, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*7] = (int) DESCALE(tmp10 - tmp3, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*1] = (int) DESCALE(tmp11 + tmp2, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*6] = (int) DESCALE(tmp11 - tmp2, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*2] = (int) DESCALE(tmp12 + tmp1, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*5] = (int) DESCALE(tmp12 - tmp1, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*3] = (int) DESCALE(tmp13 + tmp0, CONST_BITS-PASS1_BITS); wsptr[DCTSIZE*4] = (int) DESCALE(tmp13 - tmp0, CONST_BITS-PASS1_BITS); inptr++; /* advance pointers to next column */ quantptr++; wsptr++; } /* Pass 2: process rows from work array, store into output array. */ /* Note that we must descale the results by a factor of 8 == 2**3, */ /* and also undo the PASS1_BITS scaling. */ wsptr = workspace; for (ctr = 0; ctr < DCTSIZE; ctr++) { outptr = output_buf[ctr] + output_col; /* Rows of zeroes can be exploited in the same way as we did with columns. * However, the column calculation has created many nonzero AC terms, so * the simplification applies less often (typically 5% to 10% of the time). * On machines with very fast multiplication, it's possible that the * test takes more time than it's worth. In that case this section * may be commented out. */ #ifndef NO_ZERO_ROW_TEST if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[4] == 0 && wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) { /* AC terms all zero */ JSAMPLE dcval = range_limit[(int) DESCALE((IJG_INT32) wsptr[0], PASS1_BITS+3) & RANGE_MASK]; outptr[0] = dcval; outptr[1] = dcval; outptr[2] = dcval; outptr[3] = dcval; outptr[4] = dcval; outptr[5] = dcval; outptr[6] = dcval; outptr[7] = dcval; wsptr += DCTSIZE; /* advance pointer to next row */ continue; } #endif /* Even part: reverse the even part of the forward DCT. */ /* The rotator is sqrt(2)*c(-6). */ z2 = (IJG_INT32) wsptr[2]; z3 = (IJG_INT32) wsptr[6]; z1 = MULTIPLY(z2 + z3, FIX_0_541196100); tmp2 = z1 + MULTIPLY(z3, - FIX_1_847759065); tmp3 = z1 + MULTIPLY(z2, FIX_0_765366865); tmp0 = ((IJG_INT32) wsptr[0] + (IJG_INT32) wsptr[4]) << CONST_BITS; tmp1 = ((IJG_INT32) wsptr[0] - (IJG_INT32) wsptr[4]) << CONST_BITS; tmp10 = tmp0 + tmp3; tmp13 = tmp0 - tmp3; tmp11 = tmp1 + tmp2; tmp12 = tmp1 - tmp2; /* 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 = (IJG_INT32) wsptr[7]; tmp1 = (IJG_INT32) wsptr[5]; tmp2 = (IJG_INT32) wsptr[3]; tmp3 = (IJG_INT32) wsptr[1]; z1 = tmp0 + tmp3; z2 = tmp1 + tmp2; z3 = tmp0 + tmp2; z4 = tmp1 + tmp3; z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */ tmp0 = MULTIPLY(tmp0, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ tmp1 = MULTIPLY(tmp1, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ tmp2 = MULTIPLY(tmp2, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ tmp3 = MULTIPLY(tmp3, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */ z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */ z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */ z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */ z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */ z3 += z5; z4 += z5; tmp0 += z1 + z3; tmp1 += z2 + z4; tmp2 += z2 + z3; tmp3 += z1 + z4; /* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */ outptr[0] = range_limit[(int) DESCALE(tmp10 + tmp3, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[7] = range_limit[(int) DESCALE(tmp10 - tmp3, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[1] = range_limit[(int) DESCALE(tmp11 + tmp2, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[6] = range_limit[(int) DESCALE(tmp11 - tmp2, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[2] = range_limit[(int) DESCALE(tmp12 + tmp1, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[5] = range_limit[(int) DESCALE(tmp12 - tmp1, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[3] = range_limit[(int) DESCALE(tmp13 + tmp0, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; outptr[4] = range_limit[(int) DESCALE(tmp13 - tmp0, CONST_BITS+PASS1_BITS+3) & RANGE_MASK]; wsptr += DCTSIZE; /* advance pointer to next row */ } }
openexif_jpeg_idct_4x4 (oe_j_decompress_ptr cinfo, openexif_jpeg_component_info * compptr, OE_JCOEFPTR coef_block, OE_JSAMPARRAY output_buf, OE_JDIMENSION output_col) { INT32 tmp0, tmp2, tmp10, tmp12; INT32 z1, z2, z3, z4; OE_JCOEFPTR inptr; ISLOW_MULT_TYPE * quantptr; int * wsptr; OE_JSAMPROW outptr; OE_JSAMPLE *range_limit = IDCT_range_limit(cinfo); int ctr; int workspace[DCTSIZE*4]; /* buffers data between passes */ SHIFT_TEMPS /* Pass 1: process columns from input, store into work array. */ inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; for (ctr = DCTSIZE; ctr > 0; inptr++, quantptr++, wsptr++, ctr--) { /* Don't bother to process column 4, because second pass won't use it */ if (ctr == DCTSIZE-4) continue; if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 && inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 && inptr[DCTSIZE*7] == 0) { /* AC terms all zero; we need not examine term 4 for 4x4 output */ int dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]) << PASS1_BITS; wsptr[DCTSIZE*0] = dcval; wsptr[DCTSIZE*1] = dcval; wsptr[DCTSIZE*2] = dcval; wsptr[DCTSIZE*3] = dcval; continue; } /* Even part */ tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); tmp0 <<= (CONST_BITS+1); z2 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); z3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); tmp2 = MULTIPLY(z2, FIX_1_847759065) + MULTIPLY(z3, - FIX_0_765366865); tmp10 = tmp0 + tmp2; tmp12 = tmp0 - tmp2; /* Odd part */ z1 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]); z2 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); z3 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); z4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); tmp0 = MULTIPLY(z1, - FIX_0_211164243) /* sqrt(2) * (c3-c1) */ + MULTIPLY(z2, FIX_1_451774981) /* sqrt(2) * (c3+c7) */ + MULTIPLY(z3, - FIX_2_172734803) /* sqrt(2) * (-c1-c5) */ + MULTIPLY(z4, FIX_1_061594337); /* sqrt(2) * (c5+c7) */ tmp2 = MULTIPLY(z1, - FIX_0_509795579) /* sqrt(2) * (c7-c5) */ + MULTIPLY(z2, - FIX_0_601344887) /* sqrt(2) * (c5-c1) */ + MULTIPLY(z3, FIX_0_899976223) /* sqrt(2) * (c3-c7) */ + MULTIPLY(z4, FIX_2_562915447); /* sqrt(2) * (c1+c3) */ /* Final output stage */ wsptr[DCTSIZE*0] = (int) DESCALE(tmp10 + tmp2, CONST_BITS-PASS1_BITS+1); wsptr[DCTSIZE*3] = (int) DESCALE(tmp10 - tmp2, CONST_BITS-PASS1_BITS+1); wsptr[DCTSIZE*1] = (int) DESCALE(tmp12 + tmp0, CONST_BITS-PASS1_BITS+1); wsptr[DCTSIZE*2] = (int) DESCALE(tmp12 - tmp0, CONST_BITS-PASS1_BITS+1); } /* Pass 2: process 4 rows from work array, store into output array. */ wsptr = workspace; for (ctr = 0; ctr < 4; ctr++) { outptr = output_buf[ctr] + output_col; /* It's not clear whether a zero row test is worthwhile here ... */ #ifndef NO_ZERO_ROW_TEST if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) { /* AC terms all zero */ OE_JSAMPLE dcval = range_limit[(int) DESCALE((INT32) wsptr[0], PASS1_BITS+3) & RANGE_MASK]; outptr[0] = dcval; outptr[1] = dcval; outptr[2] = dcval; outptr[3] = dcval; wsptr += DCTSIZE; /* advance pointer to next row */ continue; } #endif /* Even part */ tmp0 = ((INT32) wsptr[0]) << (CONST_BITS+1); tmp2 = MULTIPLY((INT32) wsptr[2], FIX_1_847759065) + MULTIPLY((INT32) wsptr[6], - FIX_0_765366865); tmp10 = tmp0 + tmp2; tmp12 = tmp0 - tmp2; /* Odd part */ z1 = (INT32) wsptr[7]; z2 = (INT32) wsptr[5]; z3 = (INT32) wsptr[3]; z4 = (INT32) wsptr[1]; tmp0 = MULTIPLY(z1, - FIX_0_211164243) /* sqrt(2) * (c3-c1) */ + MULTIPLY(z2, FIX_1_451774981) /* sqrt(2) * (c3+c7) */ + MULTIPLY(z3, - FIX_2_172734803) /* sqrt(2) * (-c1-c5) */ + MULTIPLY(z4, FIX_1_061594337); /* sqrt(2) * (c5+c7) */ tmp2 = MULTIPLY(z1, - FIX_0_509795579) /* sqrt(2) * (c7-c5) */ + MULTIPLY(z2, - FIX_0_601344887) /* sqrt(2) * (c5-c1) */ + MULTIPLY(z3, FIX_0_899976223) /* sqrt(2) * (c3-c7) */ + MULTIPLY(z4, FIX_2_562915447); /* sqrt(2) * (c1+c3) */ /* Final output stage */ outptr[0] = range_limit[(int) DESCALE(tmp10 + tmp2, CONST_BITS+PASS1_BITS+3+1) & RANGE_MASK]; outptr[3] = range_limit[(int) DESCALE(tmp10 - tmp2, CONST_BITS+PASS1_BITS+3+1) & RANGE_MASK]; outptr[1] = range_limit[(int) DESCALE(tmp12 + tmp0, CONST_BITS+PASS1_BITS+3+1) & RANGE_MASK]; outptr[2] = range_limit[(int) DESCALE(tmp12 - tmp0, CONST_BITS+PASS1_BITS+3+1) & RANGE_MASK]; wsptr += DCTSIZE; /* advance pointer to next row */ } }
openexif_jpeg_idct_2x2 (oe_j_decompress_ptr cinfo, openexif_jpeg_component_info * compptr, OE_JCOEFPTR coef_block, OE_JSAMPARRAY output_buf, OE_JDIMENSION output_col) { INT32 tmp0, tmp10, z1; OE_JCOEFPTR inptr; ISLOW_MULT_TYPE * quantptr; int * wsptr; OE_JSAMPROW outptr; OE_JSAMPLE *range_limit = IDCT_range_limit(cinfo); int ctr; int workspace[DCTSIZE*2]; /* buffers data between passes */ SHIFT_TEMPS /* Pass 1: process columns from input, store into work array. */ inptr = coef_block; quantptr = (ISLOW_MULT_TYPE *) compptr->dct_table; wsptr = workspace; for (ctr = DCTSIZE; ctr > 0; inptr++, quantptr++, wsptr++, ctr--) { /* Don't bother to process columns 2,4,6 */ if (ctr == DCTSIZE-2 || ctr == DCTSIZE-4 || ctr == DCTSIZE-6) continue; if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*7] == 0) { /* AC terms all zero; we need not examine terms 2,4,6 for 2x2 output */ int dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]) << PASS1_BITS; wsptr[DCTSIZE*0] = dcval; wsptr[DCTSIZE*1] = dcval; continue; } /* Even part */ z1 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); tmp10 = z1 << (CONST_BITS+2); /* Odd part */ z1 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]); tmp0 = MULTIPLY(z1, - FIX_0_720959822); /* sqrt(2) * (c7-c5+c3-c1) */ z1 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); tmp0 += MULTIPLY(z1, FIX_0_850430095); /* sqrt(2) * (-c1+c3+c5+c7) */ z1 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); tmp0 += MULTIPLY(z1, - FIX_1_272758580); /* sqrt(2) * (-c1+c3-c5-c7) */ z1 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); tmp0 += MULTIPLY(z1, FIX_3_624509785); /* sqrt(2) * (c1+c3+c5+c7) */ /* Final output stage */ wsptr[DCTSIZE*0] = (int) DESCALE(tmp10 + tmp0, CONST_BITS-PASS1_BITS+2); wsptr[DCTSIZE*1] = (int) DESCALE(tmp10 - tmp0, CONST_BITS-PASS1_BITS+2); } /* Pass 2: process 2 rows from work array, store into output array. */ wsptr = workspace; for (ctr = 0; ctr < 2; ctr++) { outptr = output_buf[ctr] + output_col; /* It's not clear whether a zero row test is worthwhile here ... */ #ifndef NO_ZERO_ROW_TEST if (wsptr[1] == 0 && wsptr[3] == 0 && wsptr[5] == 0 && wsptr[7] == 0) { /* AC terms all zero */ OE_JSAMPLE dcval = range_limit[(int) DESCALE((INT32) wsptr[0], PASS1_BITS+3) & RANGE_MASK]; outptr[0] = dcval; outptr[1] = dcval; wsptr += DCTSIZE; /* advance pointer to next row */ continue; } #endif /* Even part */ tmp10 = ((INT32) wsptr[0]) << (CONST_BITS+2); /* Odd part */ tmp0 = MULTIPLY((INT32) wsptr[7], - FIX_0_720959822) /* sqrt(2) * (c7-c5+c3-c1) */ + MULTIPLY((INT32) wsptr[5], FIX_0_850430095) /* sqrt(2) * (-c1+c3+c5+c7) */ + MULTIPLY((INT32) wsptr[3], - FIX_1_272758580) /* sqrt(2) * (-c1+c3-c5-c7) */ + MULTIPLY((INT32) wsptr[1], FIX_3_624509785); /* sqrt(2) * (c1+c3+c5+c7) */ /* Final output stage */ outptr[0] = range_limit[(int) DESCALE(tmp10 + tmp0, CONST_BITS+PASS1_BITS+3+2) & RANGE_MASK]; outptr[1] = range_limit[(int) DESCALE(tmp10 - tmp0, CONST_BITS+PASS1_BITS+3+2) & RANGE_MASK]; wsptr += DCTSIZE; /* advance pointer to next row */ } }
jpeg_idct_ifast (j_decompress_ptr cinfo, jpeg_component_info * compptr, JCOEFPTR coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { DCTELEM tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7; DCTELEM tmp10, tmp11, tmp12, tmp13; DCTELEM z5, z10, z11, z12, z13; JCOEFPTR inptr; IFAST_MULT_TYPE * quantptr; int * wsptr; JSAMPROW outptr; JSAMPLE *range_limit = IDCT_range_limit(cinfo); int ctr; int workspace[DCTSIZE2]; /* buffers data between passes */ SHIFT_TEMPS /* for DESCALE */ ISHIFT_TEMPS /* for IDESCALE */ /* Pass 1: process columns from input, store into work array. */ inptr = coef_block; quantptr = (IFAST_MULT_TYPE *) compptr->dct_table; wsptr = workspace; for (ctr = 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 (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 && inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 && inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 && inptr[DCTSIZE*7] == 0) { /* AC terms all zero */ int dcval = (int) DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); wsptr[DCTSIZE*0] = dcval; wsptr[DCTSIZE*1] = dcval; wsptr[DCTSIZE*2] = dcval; wsptr[DCTSIZE*3] = dcval; wsptr[DCTSIZE*4] = dcval; wsptr[DCTSIZE*5] = dcval; wsptr[DCTSIZE*6] = dcval; wsptr[DCTSIZE*7] = dcval; inptr++; /* advance pointers to next column */ quantptr++; wsptr++; continue; } /* Even part */ tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]); tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]); tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]); tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]); tmp10 = tmp0 + tmp2; /* phase 3 */ tmp11 = tmp0 - tmp2; tmp13 = tmp1 + tmp3; /* phases 5-3 */ tmp12 = MULTIPLY(tmp1 - tmp3, FIX_1_414213562) - tmp13; /* 2*c4 */ tmp0 = tmp10 + tmp13; /* phase 2 */ tmp3 = tmp10 - tmp13; tmp1 = tmp11 + tmp12; tmp2 = tmp11 - tmp12; /* Odd part */ tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]); tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]); tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]); tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]); z13 = tmp6 + tmp5; /* phase 6 */ z10 = tmp6 - tmp5; z11 = tmp4 + tmp7; z12 = tmp4 - tmp7; tmp7 = z11 + z13; /* phase 5 */ tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */ z5 = MULTIPLY(z10 + z12, FIX_1_847759065); /* 2*c2 */ tmp10 = MULTIPLY(z12, FIX_1_082392200) - z5; /* 2*(c2-c6) */ tmp12 = MULTIPLY(z10, - FIX_2_613125930) + z5; /* -2*(c2+c6) */ tmp6 = tmp12 - tmp7; /* phase 2 */ tmp5 = tmp11 - tmp6; tmp4 = tmp10 + tmp5; wsptr[DCTSIZE*0] = (int) (tmp0 + tmp7); wsptr[DCTSIZE*7] = (int) (tmp0 - tmp7); wsptr[DCTSIZE*1] = (int) (tmp1 + tmp6); wsptr[DCTSIZE*6] = (int) (tmp1 - tmp6); wsptr[DCTSIZE*2] = (int) (tmp2 + tmp5); wsptr[DCTSIZE*5] = (int) (tmp2 - tmp5); wsptr[DCTSIZE*4] = (int) (tmp3 + tmp4); wsptr[DCTSIZE*3] = (int) (tmp3 - tmp4); inptr++; /* advance pointers to next column */ quantptr++; wsptr++; } /* Pass 2: process rows from work array, store into output array. */ /* Note that we must descale the results by a factor of 8 == 2**3, */ /* and also undo the PASS1_BITS scaling. */ wsptr = workspace; for (ctr = 0; ctr < DCTSIZE; ctr++) { outptr = output_buf[ctr] + output_col; /* Rows of zeroes can be exploited in the same way as we did with columns. * However, the column calculation has created many nonzero AC terms, so * the simplification applies less often (typically 5% to 10% of the time). * On machines with very fast multiplication, it's possible that the * test takes more time than it's worth. In that case this section * may be commented out. */ #ifndef NO_ZERO_ROW_TEST if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[4] == 0 && wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) { /* AC terms all zero */ JSAMPLE dcval = range_limit[IDESCALE(wsptr[0], PASS1_BITS+3) & RANGE_MASK]; outptr[0] = dcval; outptr[1] = dcval; outptr[2] = dcval; outptr[3] = dcval; outptr[4] = dcval; outptr[5] = dcval; outptr[6] = dcval; outptr[7] = dcval; wsptr += DCTSIZE; /* advance pointer to next row */ continue; } #endif /* Even part */ tmp10 = ((DCTELEM) wsptr[0] + (DCTELEM) wsptr[4]); tmp11 = ((DCTELEM) wsptr[0] - (DCTELEM) wsptr[4]); tmp13 = ((DCTELEM) wsptr[2] + (DCTELEM) wsptr[6]); tmp12 = MULTIPLY((DCTELEM) wsptr[2] - (DCTELEM) wsptr[6], FIX_1_414213562) - tmp13; tmp0 = tmp10 + tmp13; tmp3 = tmp10 - tmp13; tmp1 = tmp11 + tmp12; tmp2 = tmp11 - tmp12; /* Odd part */ z13 = (DCTELEM) wsptr[5] + (DCTELEM) wsptr[3]; z10 = (DCTELEM) wsptr[5] - (DCTELEM) wsptr[3]; z11 = (DCTELEM) wsptr[1] + (DCTELEM) wsptr[7]; z12 = (DCTELEM) wsptr[1] - (DCTELEM) wsptr[7]; tmp7 = z11 + z13; /* phase 5 */ tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */ z5 = MULTIPLY(z10 + z12, FIX_1_847759065); /* 2*c2 */ tmp10 = MULTIPLY(z12, FIX_1_082392200) - z5; /* 2*(c2-c6) */ tmp12 = MULTIPLY(z10, - FIX_2_613125930) + z5; /* -2*(c2+c6) */ tmp6 = tmp12 - tmp7; /* phase 2 */ tmp5 = tmp11 - tmp6; tmp4 = tmp10 + tmp5; /* Final output stage: scale down by a factor of 8 and range-limit */ outptr[0] = range_limit[IDESCALE(tmp0 + tmp7, PASS1_BITS+3) & RANGE_MASK]; outptr[7] = range_limit[IDESCALE(tmp0 - tmp7, PASS1_BITS+3) & RANGE_MASK]; outptr[1] = range_limit[IDESCALE(tmp1 + tmp6, PASS1_BITS+3) & RANGE_MASK]; outptr[6] = range_limit[IDESCALE(tmp1 - tmp6, PASS1_BITS+3) & RANGE_MASK]; outptr[2] = range_limit[IDESCALE(tmp2 + tmp5, PASS1_BITS+3) & RANGE_MASK]; outptr[5] = range_limit[IDESCALE(tmp2 - tmp5, PASS1_BITS+3) & RANGE_MASK]; outptr[4] = range_limit[IDESCALE(tmp3 + tmp4, PASS1_BITS+3) & RANGE_MASK]; outptr[3] = range_limit[IDESCALE(tmp3 - tmp4, PASS1_BITS+3) & RANGE_MASK]; wsptr += DCTSIZE; /* advance pointer to next row */ } }