#define CONST_BITS 8 #define PASS1_BITS 2 #define FIX_1_082392200 ((INT32) 277) /* FIX(1.082392200) */ #define FIX_1_414213562 ((INT32) 362) /* FIX(1.414213562) */ #define FIX_1_847759065 ((INT32) 473) /* FIX(1.847759065) */ #define FIX_2_613125930 ((INT32) 669) /* FIX(2.613125930) */ #define DEQUANTIZE(coef,quantval) (((coef)) * (quantval)) /* * Perform dequantization and inverse DCT on one block of coefficients. */ void idct (j_decompress_ptr cinfo, jpeg_component_info * compptr, int FAR *coef_block, JSAMPARRAY output_buf, JDIMENSION output_col) { int tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7; int tmp10, tmp11, tmp12, tmp13; int z5, z10, z11, z12, z13; int inptr; int * 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). */ 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 */ } }