#include "dct.h" /* Private declarations for DCT subsystem */ #define DCTSIZE 8 #define DESCALE(x,shft) ((x) >> (shft)) #define MULTIPLY(var,const) ((var) * (const)) #define CONST_BITS 13 #define PASS1_BITS 1 /* lose a little precision to avoid overflow */ #define FIX_0_298631336 ((int) 2446) /* FIX(0.298631336) */ #define FIX_0_390180644 ((int) 3196) /* FIX(0.390180644) */ #define FIX_0_541196100 ((int) 4433) /* FIX(0.541196100) */ #define FIX_0_765366865 ((int) 6270) /* FIX(0.765366865) */ #define FIX_0_899976223 ((int) 7373) /* FIX(0.899976223) */ #define FIX_1_175875602 ((int) 9633) /* FIX(1.175875602) */ #define FIX_1_501321110 ((int) 12299) /* FIX(1.501321110) */ #define FIX_1_847759065 ((int) 15137) /* FIX(1.847759065) */ #define FIX_1_961570560 ((int) 16069) /* FIX(1.961570560) */ #define FIX_2_053119869 ((int) 16819) /* FIX(2.053119869) */ #define FIX_2_562915447 ((int) 20995) /* FIX(2.562915447) */ #define FIX_3_072711026 ((int) 25172) /* FIX(3.072711026) */ /* * Perform the forward DCT on one block of samples. */ void jpeg_fdct_ifast (DCTELEM * data, unsigned char * qdata) { int tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7; int tmp10, tmp11, tmp12, tmp13; int z1, z2, z3, z4, z5; DCTELEM *dataptr; int ctr; //SHIFT_TEMPS /* Pass 1: process rows. */ /* Note results are scaled up by sqrt(8) compared to a true DCT; */ /* furthermore, we scale the results by 2**PASS1_BITS. */ dataptr = data; for (ctr = DCTSIZE-1; ctr >= 0; ctr--) { dataptr[0] = dataptr[0] - 128; dataptr[1] = dataptr[1] - 128; dataptr[2] = dataptr[2] - 128; dataptr[3] = dataptr[3] - 128; dataptr[4] = dataptr[4] - 128; dataptr[5] = dataptr[5] - 128; dataptr[6] = dataptr[6] - 128; dataptr[7] = dataptr[7] - 128; tmp0 = dataptr[0] + dataptr[7]; tmp7 = dataptr[0] - dataptr[7]; tmp1 = dataptr[1] + dataptr[6]; tmp6 = dataptr[1] - dataptr[6]; tmp2 = dataptr[2] + dataptr[5]; tmp5 = dataptr[2] - dataptr[5]; tmp3 = dataptr[3] + dataptr[4]; tmp4 = dataptr[3] - dataptr[4]; /* Even part per LL&M figure 1 --- note that published figure is faulty; * rotator "sqrt(2)*c1" should be "sqrt(2)*c6". */ tmp10 = tmp0 + tmp3; tmp13 = tmp0 - tmp3; tmp11 = tmp1 + tmp2; tmp12 = tmp1 - tmp2; dataptr[0] = (DCTELEM) ((tmp10 + tmp11) << PASS1_BITS); dataptr[4] = (DCTELEM) ((tmp10 - tmp11) << PASS1_BITS); z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100); dataptr[2] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865), CONST_BITS-PASS1_BITS); dataptr[6] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065), CONST_BITS-PASS1_BITS); /* Odd part per figure 8 --- note paper omits factor of sqrt(2). * cK represents cos(K*pi/16). * i0..i3 in the paper are tmp4..tmp7 here. */ z1 = tmp4 + tmp7; z2 = tmp5 + tmp6; z3 = tmp4 + tmp6; z4 = tmp5 + tmp7; z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */ tmp4 = MULTIPLY(tmp4, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ tmp5 = MULTIPLY(tmp5, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ tmp6 = MULTIPLY(tmp6, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ tmp7 = MULTIPLY(tmp7, 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; dataptr[7] = (DCTELEM) DESCALE(tmp4 + z1 + z3, CONST_BITS-PASS1_BITS); dataptr[5] = (DCTELEM) DESCALE(tmp5 + z2 + z4, CONST_BITS-PASS1_BITS); dataptr[3] = (DCTELEM) DESCALE(tmp6 + z2 + z3, CONST_BITS-PASS1_BITS); dataptr[1] = (DCTELEM) DESCALE(tmp7 + z1 + z4, CONST_BITS-PASS1_BITS); dataptr += DCTSIZE; /* advance pointer to next row */ } /* Pass 2: process columns. * We remove the PASS1_BITS scaling, but leave the results scaled up * by an overall factor of 8. */ dataptr = data; for (ctr = DCTSIZE-1; ctr >= 0; ctr--) { tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*7]; tmp7 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*7]; tmp1 = dataptr[DCTSIZE*1] + dataptr[DCTSIZE*6]; tmp6 = dataptr[DCTSIZE*1] - dataptr[DCTSIZE*6]; tmp2 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*5]; tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*5]; tmp3 = dataptr[DCTSIZE*3] + dataptr[DCTSIZE*4]; tmp4 = dataptr[DCTSIZE*3] - dataptr[DCTSIZE*4]; /* Even part per LL&M figure 1 --- note that published figure is faulty; * rotator "sqrt(2)*c1" should be "sqrt(2)*c6". */ tmp10 = tmp0 + tmp3; tmp13 = tmp0 - tmp3; tmp11 = tmp1 + tmp2; tmp12 = tmp1 - tmp2; dataptr[DCTSIZE*0] = (DCTELEM) DESCALE(tmp10 + tmp11, PASS1_BITS); dataptr[DCTSIZE*4] = (DCTELEM) DESCALE(tmp10 - tmp11, PASS1_BITS); z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100); dataptr[DCTSIZE*2] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865), CONST_BITS+PASS1_BITS); dataptr[DCTSIZE*6] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065), CONST_BITS+PASS1_BITS); /* Odd part per figure 8 --- note paper omits factor of sqrt(2). * cK represents cos(K*pi/16). * i0..i3 in the paper are tmp4..tmp7 here. */ z1 = tmp4 + tmp7; z2 = tmp5 + tmp6; z3 = tmp4 + tmp6; z4 = tmp5 + tmp7; z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */ tmp4 = MULTIPLY(tmp4, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */ tmp5 = MULTIPLY(tmp5, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */ tmp6 = MULTIPLY(tmp6, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */ tmp7 = MULTIPLY(tmp7, 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; dataptr[DCTSIZE*7] = (DCTELEM) DESCALE(tmp4 + z1 + z3, CONST_BITS+PASS1_BITS); //dataptr[DCTSIZE*1] = (dataptr[DCTSIZE*1] / 8)/ qdata[DCTSIZE*1] dataptr[DCTSIZE*5] = (DCTELEM) DESCALE(tmp5 + z2 + z4, CONST_BITS+PASS1_BITS); dataptr[DCTSIZE*3] = (DCTELEM) DESCALE(tmp6 + z2 + z3, CONST_BITS+PASS1_BITS); dataptr[DCTSIZE*1] = (DCTELEM) DESCALE(tmp7 + z1 + z4, CONST_BITS+PASS1_BITS); dataptr[DCTSIZE*0] = (dataptr[DCTSIZE*0] / 8)/ qdata[DCTSIZE*0]; dataptr[DCTSIZE*1] = (dataptr[DCTSIZE*1] / 8)/ qdata[DCTSIZE*1]; dataptr[DCTSIZE*2] = (dataptr[DCTSIZE*2] / 8)/ qdata[DCTSIZE*2]; dataptr[DCTSIZE*3] = (dataptr[DCTSIZE*3] / 8)/ qdata[DCTSIZE*3]; dataptr[DCTSIZE*4] = (dataptr[DCTSIZE*4] / 8)/ qdata[DCTSIZE*4]; dataptr[DCTSIZE*5] = (dataptr[DCTSIZE*5] / 8)/ qdata[DCTSIZE*5]; dataptr[DCTSIZE*6] = (dataptr[DCTSIZE*6] / 8)/ qdata[DCTSIZE*6]; dataptr[DCTSIZE*7] = (dataptr[DCTSIZE*7] / 8)/ qdata[DCTSIZE*7]; dataptr++; /* advance pointer to next column */ } }