mod_34lsub1.asm revision 1.1.1.2
1 1.1 mrg dnl ARM64 mpn_mod_34lsub1 -- remainder modulo 2^48-1. 2 1.1 mrg 3 1.1 mrg dnl Copyright 2012-2014 Free Software Foundation, Inc. 4 1.1 mrg 5 1.1 mrg dnl This file is part of the GNU MP Library. 6 1.1 mrg dnl 7 1.1 mrg dnl The GNU MP Library is free software; you can redistribute it and/or modify 8 1.1 mrg dnl it under the terms of either: 9 1.1 mrg dnl 10 1.1 mrg dnl * the GNU Lesser General Public License as published by the Free 11 1.1 mrg dnl Software Foundation; either version 3 of the License, or (at your 12 1.1 mrg dnl option) any later version. 13 1.1 mrg dnl 14 1.1 mrg dnl or 15 1.1 mrg dnl 16 1.1 mrg dnl * the GNU General Public License as published by the Free Software 17 1.1 mrg dnl Foundation; either version 2 of the License, or (at your option) any 18 1.1 mrg dnl later version. 19 1.1 mrg dnl 20 1.1 mrg dnl or both in parallel, as here. 21 1.1 mrg dnl 22 1.1 mrg dnl The GNU MP Library is distributed in the hope that it will be useful, but 23 1.1 mrg dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 24 1.1 mrg dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 25 1.1 mrg dnl for more details. 26 1.1 mrg dnl 27 1.1 mrg dnl You should have received copies of the GNU General Public License and the 28 1.1 mrg dnl GNU Lesser General Public License along with the GNU MP Library. If not, 29 1.1 mrg dnl see https://www.gnu.org/licenses/. 30 1.1 mrg 31 1.1 mrg include(`../config.m4') 32 1.1 mrg 33 1.1 mrg C cycles/limb 34 1.1.1.2 mrg C Cortex-A53 2 35 1.1.1.2 mrg C Cortex-A57 1 36 1.1.1.2 mrg C X-Gene 1.45 37 1.1 mrg 38 1.1 mrg define(`ap', x0) 39 1.1 mrg define(`n', x1) 40 1.1 mrg 41 1.1.1.2 mrg changecom(blah) 42 1.1 mrg 43 1.1 mrg C mp_limb_t mpn_mod_34lsub1 (mp_srcptr up, mp_size_t n) 44 1.1 mrg 45 1.1 mrg C TODO 46 1.1.1.2 mrg C * An alternative inner loop which could run at 0.722 c/l on A57: 47 1.1 mrg C adds x8, x8, x2 48 1.1 mrg C adcs x9, x9, x3 49 1.1 mrg C ldp x2, x3, [ap, #-32] 50 1.1 mrg C adcs x10, x10, x4 51 1.1 mrg C adc x12, x12, xzr 52 1.1 mrg C adds x8, x8, x5 53 1.1 mrg C ldp x4, x5, [ap, #-16] 54 1.1 mrg C sub n, n, #6 55 1.1 mrg C adcs x9, x9, x6 56 1.1 mrg C adcs x10, x10, x7 57 1.1 mrg C ldp x6, x7, [ap], #48 58 1.1 mrg C adc x12, x12, xzr 59 1.1 mrg C tbz n, #63, L(top) 60 1.1 mrg 61 1.1 mrg ASM_START() 62 1.1 mrg TEXT 63 1.1 mrg ALIGN(32) 64 1.1 mrg PROLOGUE(mpn_mod_34lsub1) 65 1.1 mrg subs n, n, #3 66 1.1 mrg mov x8, #0 67 1.1 mrg b.lt L(le2) C n <= 2 68 1.1 mrg 69 1.1 mrg ldp x2, x3, [ap, #0] 70 1.1 mrg ldr x4, [ap, #16] 71 1.1 mrg add ap, ap, #24 72 1.1 mrg subs n, n, #3 73 1.1 mrg b.lt L(sum) C n <= 5 74 1.1 mrg cmn x0, #0 C clear carry 75 1.1 mrg 76 1.1 mrg L(top): ldp x5, x6, [ap, #0] 77 1.1 mrg ldr x7, [ap, #16] 78 1.1 mrg add ap, ap, #24 79 1.1 mrg sub n, n, #3 80 1.1 mrg adcs x2, x2, x5 81 1.1 mrg adcs x3, x3, x6 82 1.1 mrg adcs x4, x4, x7 83 1.1 mrg tbz n, #63, L(top) 84 1.1 mrg 85 1.1 mrg adc x8, xzr, xzr C x8 <= 1 86 1.1 mrg 87 1.1 mrg L(sum): cmn n, #2 88 1.1 mrg mov x5, #0 89 1.1 mrg b.lo 1f 90 1.1 mrg ldr x5, [ap], #8 91 1.1 mrg 1: mov x6, #0 92 1.1 mrg b.ls 1f 93 1.1 mrg ldr x6, [ap], #8 94 1.1 mrg 1: adds x2, x2, x5 95 1.1 mrg adcs x3, x3, x6 96 1.1 mrg adcs x4, x4, xzr 97 1.1 mrg adc x8, x8, xzr C x8 <= 2 98 1.1 mrg 99 1.1 mrg L(sum2): 100 1.1 mrg and x0, x2, #0xffffffffffff 101 1.1 mrg add x0, x0, x2, lsr #48 102 1.1 mrg add x0, x0, x8 103 1.1 mrg 104 1.1 mrg lsl x8, x3, #16 105 1.1 mrg and x1, x8, #0xffffffffffff 106 1.1 mrg add x0, x0, x1 107 1.1 mrg add x0, x0, x3, lsr #32 108 1.1 mrg 109 1.1 mrg lsl x8, x4, #32 110 1.1 mrg and x1, x8, #0xffffffffffff 111 1.1 mrg add x0, x0, x1 112 1.1 mrg add x0, x0, x4, lsr #16 113 1.1 mrg ret 114 1.1 mrg 115 1.1 mrg L(le2): cmn n, #1 116 1.1 mrg b.ne L(1) 117 1.1 mrg ldp x2, x3, [ap] 118 1.1 mrg mov x4, #0 119 1.1 mrg b L(sum2) 120 1.1 mrg L(1): ldr x2, [ap] 121 1.1 mrg and x0, x2, #0xffffffffffff 122 1.1 mrg add x0, x0, x2, lsr #48 123 1.1 mrg ret 124 1.1 mrg EPILOGUE() 125
Indexes created Sun Jun 28 00:24:58 UTC 2026