xf.li | bdd93d5 | 2023-05-12 07:10:14 -0700 | [diff] [blame^] | 1 | /* mpn_divrem -- Divide natural numbers, producing both remainder and |
| 2 | quotient. |
| 3 | |
| 4 | Copyright (C) 1993-2016 Free Software Foundation, Inc. |
| 5 | |
| 6 | This file is part of the GNU MP Library. |
| 7 | |
| 8 | The GNU MP Library is free software; you can redistribute it and/or modify |
| 9 | it under the terms of the GNU Lesser General Public License as published by |
| 10 | the Free Software Foundation; either version 2.1 of the License, or (at your |
| 11 | option) any later version. |
| 12 | |
| 13 | The GNU MP Library is distributed in the hope that it will be useful, but |
| 14 | WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY |
| 15 | or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public |
| 16 | License for more details. |
| 17 | |
| 18 | You should have received a copy of the GNU Lesser General Public License |
| 19 | along with the GNU MP Library; see the file COPYING.LIB. If not, see |
| 20 | <http://www.gnu.org/licenses/>. */ |
| 21 | |
| 22 | #include <gmp.h> |
| 23 | #include "gmp-impl.h" |
| 24 | #include "longlong.h" |
| 25 | |
| 26 | /* Divide num (NP/NSIZE) by den (DP/DSIZE) and write |
| 27 | the NSIZE-DSIZE least significant quotient limbs at QP |
| 28 | and the DSIZE long remainder at NP. If QEXTRA_LIMBS is |
| 29 | non-zero, generate that many fraction bits and append them after the |
| 30 | other quotient limbs. |
| 31 | Return the most significant limb of the quotient, this is always 0 or 1. |
| 32 | |
| 33 | Preconditions: |
| 34 | 0. NSIZE >= DSIZE. |
| 35 | 1. The most significant bit of the divisor must be set. |
| 36 | 2. QP must either not overlap with the input operands at all, or |
| 37 | QP + DSIZE >= NP must hold true. (This means that it's |
| 38 | possible to put the quotient in the high part of NUM, right after the |
| 39 | remainder in NUM. |
| 40 | 3. NSIZE >= DSIZE, even if QEXTRA_LIMBS is non-zero. */ |
| 41 | |
| 42 | mp_limb_t |
| 43 | mpn_divrem (mp_ptr qp, mp_size_t qextra_limbs, |
| 44 | mp_ptr np, mp_size_t nsize, |
| 45 | mp_srcptr dp, mp_size_t dsize) |
| 46 | { |
| 47 | mp_limb_t most_significant_q_limb = 0; |
| 48 | |
| 49 | switch (dsize) |
| 50 | { |
| 51 | case 0: |
| 52 | /* We are asked to divide by zero, so go ahead and do it! (To make |
| 53 | the compiler not remove this statement, return the value.) */ |
| 54 | return 1 / dsize; |
| 55 | |
| 56 | case 1: |
| 57 | { |
| 58 | mp_size_t i; |
| 59 | mp_limb_t n1; |
| 60 | mp_limb_t d; |
| 61 | |
| 62 | d = dp[0]; |
| 63 | n1 = np[nsize - 1]; |
| 64 | |
| 65 | if (n1 >= d) |
| 66 | { |
| 67 | n1 -= d; |
| 68 | most_significant_q_limb = 1; |
| 69 | } |
| 70 | |
| 71 | qp += qextra_limbs; |
| 72 | for (i = nsize - 2; i >= 0; i--) |
| 73 | udiv_qrnnd (qp[i], n1, n1, np[i], d); |
| 74 | qp -= qextra_limbs; |
| 75 | |
| 76 | for (i = qextra_limbs - 1; i >= 0; i--) |
| 77 | udiv_qrnnd (qp[i], n1, n1, 0, d); |
| 78 | |
| 79 | np[0] = n1; |
| 80 | } |
| 81 | break; |
| 82 | |
| 83 | case 2: |
| 84 | { |
| 85 | mp_size_t i; |
| 86 | mp_limb_t n1, n0, n2; |
| 87 | mp_limb_t d1, d0; |
| 88 | |
| 89 | np += nsize - 2; |
| 90 | d1 = dp[1]; |
| 91 | d0 = dp[0]; |
| 92 | n1 = np[1]; |
| 93 | n0 = np[0]; |
| 94 | |
| 95 | if (n1 >= d1 && (n1 > d1 || n0 >= d0)) |
| 96 | { |
| 97 | sub_ddmmss (n1, n0, n1, n0, d1, d0); |
| 98 | most_significant_q_limb = 1; |
| 99 | } |
| 100 | |
| 101 | for (i = qextra_limbs + nsize - 2 - 1; i >= 0; i--) |
| 102 | { |
| 103 | mp_limb_t q; |
| 104 | mp_limb_t r; |
| 105 | |
| 106 | if (i >= qextra_limbs) |
| 107 | np--; |
| 108 | else |
| 109 | np[0] = 0; |
| 110 | |
| 111 | if (n1 == d1) |
| 112 | { |
| 113 | /* Q should be either 111..111 or 111..110. Need special |
| 114 | treatment of this rare case as normal division would |
| 115 | give overflow. */ |
| 116 | q = ~(mp_limb_t) 0; |
| 117 | |
| 118 | r = n0 + d1; |
| 119 | if (r < d1) /* Carry in the addition? */ |
| 120 | { |
| 121 | add_ssaaaa (n1, n0, r - d0, np[0], 0, d0); |
| 122 | qp[i] = q; |
| 123 | continue; |
| 124 | } |
| 125 | n1 = d0 - (d0 != 0); |
| 126 | n0 = -d0; |
| 127 | } |
| 128 | else |
| 129 | { |
| 130 | udiv_qrnnd (q, r, n1, n0, d1); |
| 131 | umul_ppmm (n1, n0, d0, q); |
| 132 | } |
| 133 | |
| 134 | n2 = np[0]; |
| 135 | q_test: |
| 136 | if (n1 > r || (n1 == r && n0 > n2)) |
| 137 | { |
| 138 | /* The estimated Q was too large. */ |
| 139 | q--; |
| 140 | |
| 141 | sub_ddmmss (n1, n0, n1, n0, 0, d0); |
| 142 | r += d1; |
| 143 | if (r >= d1) /* If not carry, test Q again. */ |
| 144 | goto q_test; |
| 145 | } |
| 146 | |
| 147 | qp[i] = q; |
| 148 | sub_ddmmss (n1, n0, r, n2, n1, n0); |
| 149 | } |
| 150 | np[1] = n1; |
| 151 | np[0] = n0; |
| 152 | } |
| 153 | break; |
| 154 | |
| 155 | default: |
| 156 | { |
| 157 | mp_size_t i; |
| 158 | mp_limb_t dX, d1, n0; |
| 159 | |
| 160 | np += nsize - dsize; |
| 161 | dX = dp[dsize - 1]; |
| 162 | d1 = dp[dsize - 2]; |
| 163 | n0 = np[dsize - 1]; |
| 164 | |
| 165 | if (n0 >= dX) |
| 166 | { |
| 167 | if (n0 > dX || mpn_cmp (np, dp, dsize - 1) >= 0) |
| 168 | { |
| 169 | mpn_sub_n (np, np, dp, dsize); |
| 170 | n0 = np[dsize - 1]; |
| 171 | most_significant_q_limb = 1; |
| 172 | } |
| 173 | } |
| 174 | |
| 175 | for (i = qextra_limbs + nsize - dsize - 1; i >= 0; i--) |
| 176 | { |
| 177 | mp_limb_t q; |
| 178 | mp_limb_t n1, n2; |
| 179 | mp_limb_t cy_limb; |
| 180 | |
| 181 | if (i >= qextra_limbs) |
| 182 | { |
| 183 | np--; |
| 184 | n2 = np[dsize]; |
| 185 | } |
| 186 | else |
| 187 | { |
| 188 | n2 = np[dsize - 1]; |
| 189 | MPN_COPY_DECR (np + 1, np, dsize); |
| 190 | np[0] = 0; |
| 191 | } |
| 192 | |
| 193 | if (n0 == dX) |
| 194 | /* This might over-estimate q, but it's probably not worth |
| 195 | the extra code here to find out. */ |
| 196 | q = ~(mp_limb_t) 0; |
| 197 | else |
| 198 | { |
| 199 | mp_limb_t r; |
| 200 | |
| 201 | udiv_qrnnd (q, r, n0, np[dsize - 1], dX); |
| 202 | umul_ppmm (n1, n0, d1, q); |
| 203 | |
| 204 | while (n1 > r || (n1 == r && n0 > np[dsize - 2])) |
| 205 | { |
| 206 | q--; |
| 207 | r += dX; |
| 208 | if (r < dX) /* I.e. "carry in previous addition?" */ |
| 209 | break; |
| 210 | n1 -= n0 < d1; |
| 211 | n0 -= d1; |
| 212 | } |
| 213 | } |
| 214 | |
| 215 | /* Possible optimization: We already have (q * n0) and (1 * n1) |
| 216 | after the calculation of q. Taking advantage of that, we |
| 217 | could make this loop make two iterations less. */ |
| 218 | |
| 219 | cy_limb = mpn_submul_1 (np, dp, dsize, q); |
| 220 | |
| 221 | if (n2 != cy_limb) |
| 222 | { |
| 223 | mpn_add_n (np, np, dp, dsize); |
| 224 | q--; |
| 225 | } |
| 226 | |
| 227 | qp[i] = q; |
| 228 | n0 = np[dsize - 1]; |
| 229 | } |
| 230 | } |
| 231 | } |
| 232 | |
| 233 | return most_significant_q_limb; |
| 234 | } |