1 dnl ARM64 mpn_mod_34lsub1 -- remainder modulo 2^48-1. 2 3 dnl Copyright 2012-2014 Free Software Foundation, Inc. 4 5 dnl This file is part of the GNU MP Library. 6 dnl 7 dnl The GNU MP Library is free software; you can redistribute it and/or modify 8 dnl it under the terms of either: 9 dnl 10 dnl * the GNU Lesser General Public License as published by the Free 11 dnl Software Foundation; either version 3 of the License, or (at your 12 dnl option) any later version. 13 dnl 14 dnl or 15 dnl 16 dnl * the GNU General Public License as published by the Free Software 17 dnl Foundation; either version 2 of the License, or (at your option) any 18 dnl later version. 19 dnl 20 dnl or both in parallel, as here. 21 dnl 22 dnl The GNU MP Library is distributed in the hope that it will be useful, but 23 dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 24 dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 25 dnl for more details. 26 dnl 27 dnl You should have received copies of the GNU General Public License and the 28 dnl GNU Lesser General Public License along with the GNU MP Library. If not, 29 dnl see https://www.gnu.org/licenses/. 30 31 include(`../config.m4') 32 33 C cycles/limb 34 C Cortex-A53 2 35 C Cortex-A57 1 36 C X-Gene 1.45 37 38 define(`ap', x0) 39 define(`n', x1) 40 41 changecom(blah) 42 43 C mp_limb_t mpn_mod_34lsub1 (mp_srcptr up, mp_size_t n) 44 45 C TODO 46 C * An alternative inner loop which could run at 0.722 c/l on A57: 47 C adds x8, x8, x2 48 C adcs x9, x9, x3 49 C ldp x2, x3, [ap, #-32] 50 C adcs x10, x10, x4 51 C adc x12, x12, xzr 52 C adds x8, x8, x5 53 C ldp x4, x5, [ap, #-16] 54 C sub n, n, #6 55 C adcs x9, x9, x6 56 C adcs x10, x10, x7 57 C ldp x6, x7, [ap], #48 58 C adc x12, x12, xzr 59 C tbz n, #63, L(top) 60 61 ASM_START() 62 TEXT 63 ALIGN(32) 64 PROLOGUE(mpn_mod_34lsub1) 65 subs n, n, #3 66 mov x8, #0 67 b.lt L(le2) C n <= 2 68 69 ldp x2, x3, [ap, #0] 70 ldr x4, [ap, #16] 71 add ap, ap, #24 72 subs n, n, #3 73 b.lt L(sum) C n <= 5 74 cmn x0, #0 C clear carry 75 76 L(top): ldp x5, x6, [ap, #0] 77 ldr x7, [ap, #16] 78 add ap, ap, #24 79 sub n, n, #3 80 adcs x2, x2, x5 81 adcs x3, x3, x6 82 adcs x4, x4, x7 83 tbz n, #63, L(top) 84 85 adc x8, xzr, xzr C x8 <= 1 86 87 L(sum): cmn n, #2 88 mov x5, #0 89 b.lo 1f 90 ldr x5, [ap], #8 91 1: mov x6, #0 92 b.ls 1f 93 ldr x6, [ap], #8 94 1: adds x2, x2, x5 95 adcs x3, x3, x6 96 adcs x4, x4, xzr 97 adc x8, x8, xzr C x8 <= 2 98 99 L(sum2): 100 and x0, x2, #0xffffffffffff 101 add x0, x0, x2, lsr #48 102 add x0, x0, x8 103 104 lsl x8, x3, #16 105 and x1, x8, #0xffffffffffff 106 add x0, x0, x1 107 add x0, x0, x3, lsr #32 108 109 lsl x8, x4, #32 110 and x1, x8, #0xffffffffffff 111 add x0, x0, x1 112 add x0, x0, x4, lsr #16 113 ret 114 115 L(le2): cmn n, #1 116 b.ne L(1) 117 ldp x2, x3, [ap] 118 mov x4, #0 119 b L(sum2) 120 L(1): ldr x2, [ap] 121 and x0, x2, #0xffffffffffff 122 add x0, x0, x2, lsr #48 123 ret 124 EPILOGUE() 125
Indexes created Thu May 07 00:24:58 UTC 2026