1dnl x86 mpn_sec_tabselect. 2 3dnl Copyright 2011 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 33 34C cycles/limb 35C P5 ? 36C P6 model 0-8,10-12 ? 37C P6 model 9 (Banias) ? 38C P6 model 13 (Dothan) ? 39C P4 model 0 (Willamette) ? 40C P4 model 1 (?) ? 41C P4 model 2 (Northwood) 4.5 42C P4 model 3 (Prescott) ? 43C P4 model 4 (Nocona) ? 44C Intel Atom ? 45C AMD K6 ? 46C AMD K7 3.4 47C AMD K8 ? 48C AMD K10 ? 49 50C NOTES 51C * This has not been tuned for any specific processor. Its speed should not 52C be too bad, though. 53C * Using SSE2 could result in many-fold speedup. 54 55C mpn_sec_tabselect (mp_limb_t *rp, mp_limb_t *tp, mp_size_t n, mp_size_t nents, mp_size_t which) 56define(`rp', `%edi') 57define(`tp', `%esi') 58define(`n', `%ebx') 59define(`nents', `%ecx') 60define(`which', `36(%esp)') 61 62define(`i', `%ebp') 63define(`maskp', `20(%esp)') 64define(`maskn', `32(%esp)') 65 66ASM_START() 67 TEXT 68 ALIGN(16) 69PROLOGUE(mpn_sec_tabselect) 70 push %edi 71 push %esi 72 push %ebx 73 push %ebp 74 mov 20(%esp), rp 75 mov 24(%esp), tp 76 mov 28(%esp), n 77 mov 32(%esp), nents 78 79 lea (rp,n,4), rp 80 lea (tp,n,4), tp 81 sub nents, which 82L(outer): 83 mov which, %eax 84 add nents, %eax 85 neg %eax C set CF iff 'which' != k 86 sbb %eax, %eax 87 mov %eax, maskn 88 not %eax 89 mov %eax, maskp 90 91 mov n, i 92 neg i 93 94 ALIGN(16) 95L(top): mov (tp,i,4), %eax 96 and maskp, %eax 97 mov (rp,i,4), %edx 98 and maskn, %edx 99 or %edx, %eax 100 mov %eax, (rp,i,4) 101 inc i 102 js L(top) 103 104L(end): mov n, %eax 105 lea (tp,%eax,4), tp 106 dec nents 107 jne L(outer) 108 109L(outer_end): 110 pop %ebp 111 pop %ebx 112 pop %esi 113 pop %edi 114 ret 115EPILOGUE() 116