1dnl PowerPC-64 mpn_modexact_1_odd -- mpn by limb exact remainder. 2 3dnl Copyright 2006 Free Software Foundation, Inc. 4 5dnl This file is part of the GNU MP Library. 6dnl 7dnl The GNU MP Library is free software; you can redistribute it and/or modify 8dnl it under the terms of either: 9dnl 10dnl * the GNU Lesser General Public License as published by the Free 11dnl Software Foundation; either version 3 of the License, or (at your 12dnl option) any later version. 13dnl 14dnl or 15dnl 16dnl * the GNU General Public License as published by the Free Software 17dnl Foundation; either version 2 of the License, or (at your option) any 18dnl later version. 19dnl 20dnl or both in parallel, as here. 21dnl 22dnl The GNU MP Library is distributed in the hope that it will be useful, but 23dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 24dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 25dnl for more details. 26dnl 27dnl You should have received copies of the GNU General Public License and the 28dnl GNU Lesser General Public License along with the GNU MP Library. If not, 29dnl see https://www.gnu.org/licenses/. 30 31include(`../config.m4') 32 33C cycles/limb 34C POWER3/PPC630 13-19 35C POWER4/PPC970 16 36C POWER5 16 37C POWER6 ? 38C POWER7 12 39 40C TODO 41C * Check if n=1 code is really an improvement. It probably isn't. 42C * Make more similar to dive_1.asm. 43 44C INPUT PARAMETERS 45define(`up', `r3') 46define(`n', `r4') 47define(`d', `r5') 48define(`cy', `r6') 49 50 51ASM_START() 52 53EXTERN(binvert_limb_table) 54 55PROLOGUE(mpn_modexact_1c_odd,toc) 56 addic. n, n, -1 C set carry as side effect 57 ld r8, 0(up) 58 bne cr0, L(2) 59 cmpld cr7, r6, r8 60 bge cr7, L(4) 61 subf r8, r6, r8 62 divdu r3, r8, d 63 mulld r3, r3, d 64 subf. r3, r3, r8 65 beqlr cr0 66 subf r3, r3, d 67 blr 68 69L(4): subf r3, r8, r6 70 divdu r8, r3, d 71 mulld r8, r8, d 72 subf r3, r8, r3 73 blr 74 75L(2): LEA( r7, binvert_limb_table) 76 rldicl r9, d, 63, 57 77 mtctr n 78 lbzx r0, r7, r9 79 mulld r7, r0, r0 80 sldi r0, r0, 1 81 mulld r7, d, r7 82 subf r0, r7, r0 83 mulld r9, r0, r0 84 sldi r0, r0, 1 85 mulld r9, d, r9 86 subf r0, r9, r0 87 mulld r7, r0, r0 88 sldi r0, r0, 1 89 mulld r7, d, r7 90 subf r9, r7, r0 91 92 ALIGN(16) 93L(loop): 94 subfe r0, r6, r8 95 ld r8, 8(up) 96 addi up, up, 8 97 mulld r0, r9, r0 98 mulhdu r6, r0, d 99 bdnz L(loop) 100 101 cmpld cr7, d, r8 102 blt cr7, L(10) 103 104 subfe r0, r0, r0 105 subf r6, r0, r6 106 cmpld cr7, r6, r8 107 subf r3, r8, r6 108 bgelr cr7 109 add r3, d, r3 110 blr 111 112L(10): subfe r0, r6, r8 113 mulld r0, r9, r0 114 mulhdu r3, r0, d 115 blr 116EPILOGUE() 117ASM_END() 118