gcd_22.asm revision 1.1
1 1.1 mrg dnl ARM v8a mpn_gcd_22. 2 1.1 mrg 3 1.1 mrg dnl Copyright 2019 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 changecom(blah) 34 1.1 mrg 35 1.1 mrg C cycles/bit (approx) 36 1.1 mrg C Cortex-A35 ? 37 1.1 mrg C Cortex-A53 7.26 38 1.1 mrg C Cortex-A55 ? 39 1.1 mrg C Cortex-A57 ? 40 1.1 mrg C Cortex-A72 5.72 41 1.1 mrg C Cortex-A73 6.43 42 1.1 mrg C Cortex-A75 ? 43 1.1 mrg C Cortex-A76 ? 44 1.1 mrg C Cortex-A77 ? 45 1.1 mrg 46 1.1 mrg 47 1.1 mrg define(`u1', `x0') 48 1.1 mrg define(`u0', `x1') 49 1.1 mrg define(`v1', `x2') 50 1.1 mrg define(`v0', `x3') 51 1.1 mrg 52 1.1 mrg define(`t0', `x5') 53 1.1 mrg define(`t1', `x6') 54 1.1 mrg define(`cnt', `x7') 55 1.1 mrg define(`tnc', `x8') 56 1.1 mrg 57 1.1 mrg ASM_START() 58 1.1 mrg PROLOGUE(mpn_gcd_22) 59 1.1 mrg 60 1.1 mrg ALIGN(16) 61 1.1 mrg L(top): subs t0, u0, v0 C 0 6 62 1.1 mrg cbz t0, L(lowz) 63 1.1 mrg sbcs t1, u1, v1 C 1 7 64 1.1 mrg 65 1.1 mrg rbit cnt, t0 C 1 66 1.1 mrg 67 1.1 mrg cneg t0, t0, cc C 2 68 1.1 mrg cinv t1, t1, cc C 2 u = |u - v| 69 1.1 mrg L(bck): csel v0, v0, u0, cs C 2 70 1.1 mrg csel v1, v1, u1, cs C 2 v = min(u,v) 71 1.1 mrg 72 1.1 mrg clz cnt, cnt C 2 73 1.1 mrg sub tnc, xzr, cnt C 3 74 1.1 mrg 75 1.1 mrg lsr u0, t0, cnt C 3 76 1.1 mrg lsl x14, t1, tnc C 4 77 1.1 mrg lsr u1, t1, cnt C 3 78 1.1 mrg orr u0, u0, x14 C 5 79 1.1 mrg 80 1.1 mrg orr x11, u1, v1 81 1.1 mrg cbnz x11, L(top) 82 1.1 mrg 83 1.1 mrg 84 1.1 mrg subs x4, u0, v0 C 0 85 1.1 mrg b.eq L(end1) C 86 1.1 mrg 87 1.1 mrg ALIGN(16) 88 1.1 mrg L(top1):rbit x12, x4 C 1,5 89 1.1 mrg clz x12, x12 C 2 90 1.1 mrg csneg x4, x4, x4, cs C v = abs(u-v), even 1 91 1.1 mrg csel u0, v0, u0, cs C u = min(u,v) 1 92 1.1 mrg lsr v0, x4, x12 C 3 93 1.1 mrg subs x4, u0, v0 C 4 94 1.1 mrg b.ne L(top1) C 95 1.1 mrg L(end1):mov x0, u0 96 1.1 mrg mov x1, #0 97 1.1 mrg ret 98 1.1 mrg 99 1.1 mrg L(lowz):C We come here when v0 - u0 = 0 100 1.1 mrg C 1. If v1 - u1 = 0, then gcd is u = v. 101 1.1 mrg C 2. Else compute gcd_21({v1,v0}, |u1-v1|) 102 1.1 mrg subs t0, u1, v1 103 1.1 mrg b.eq L(end) 104 1.1 mrg mov t1, #0 105 1.1 mrg rbit cnt, t0 C 1 106 1.1 mrg cneg t0, t0, cc C 2 107 1.1 mrg b L(bck) C FIXME: make conditional 108 1.1 mrg 109 1.1 mrg L(end): mov x0, v0 110 1.1 mrg mov x1, v1 111 1.1 mrg ret 112 1.1 mrg EPILOGUE() 113
Indexes created Mon Oct 26 00:26:21 UTC 2026