1dnl HP-PA 2.0 32-bit mpn_sub_n -- Subtract two limb vectors of the same 2dnl length > 0 and store difference in a third limb vector. 3 4dnl Copyright 1997, 1998, 2000-2002 Free Software Foundation, Inc. 5 6dnl This file is part of the GNU MP Library. 7dnl 8dnl The GNU MP Library is free software; you can redistribute it and/or modify 9dnl it under the terms of either: 10dnl 11dnl * the GNU Lesser General Public License as published by the Free 12dnl Software Foundation; either version 3 of the License, or (at your 13dnl option) any later version. 14dnl 15dnl or 16dnl 17dnl * the GNU General Public License as published by the Free Software 18dnl Foundation; either version 2 of the License, or (at your option) any 19dnl later version. 20dnl 21dnl or both in parallel, as here. 22dnl 23dnl The GNU MP Library is distributed in the hope that it will be useful, but 24dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY 25dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 26dnl for more details. 27dnl 28dnl You should have received copies of the GNU General Public License and the 29dnl GNU Lesser General Public License along with the GNU MP Library. If not, 30dnl see https://www.gnu.org/licenses/. 31 32include(`../config.m4') 33 34C INPUT PARAMETERS 35C res_ptr gr26 36C s1_ptr gr25 37C s2_ptr gr24 38C size gr23 39 40C This runs at 2 cycles/limb on PA8000. 41 42ASM_START() 43PROLOGUE(mpn_sub_n) 44 sub %r0,%r23,%r22 45 zdep %r22,30,3,%r28 C r28 = 2 * (-n & 7) 46 zdep %r22,29,3,%r22 C r22 = 4 * (-n & 7) 47 sub %r25,%r22,%r25 C offset s1_ptr 48 sub %r24,%r22,%r24 C offset s2_ptr 49 blr %r28,%r0 C branch into loop 50 sub %r26,%r22,%r26 C offset res_ptr and set carry 51 52LDEF(loop) 53 ldw 0(%r25),%r20 54 ldw 0(%r24),%r31 55 subb %r20,%r31,%r20 56 stw %r20,0(%r26) 57 58LDEF(7) 59 ldw 4(%r25),%r21 60 ldw 4(%r24),%r19 61 subb %r21,%r19,%r21 62 stw %r21,4(%r26) 63 64LDEF(6) 65 ldw 8(%r25),%r20 66 ldw 8(%r24),%r31 67 subb %r20,%r31,%r20 68 stw %r20,8(%r26) 69 70LDEF(5) 71 ldw 12(%r25),%r21 72 ldw 12(%r24),%r19 73 subb %r21,%r19,%r21 74 stw %r21,12(%r26) 75 76LDEF(4) 77 ldw 16(%r25),%r20 78 ldw 16(%r24),%r31 79 subb %r20,%r31,%r20 80 stw %r20,16(%r26) 81 82LDEF(3) 83 ldw 20(%r25),%r21 84 ldw 20(%r24),%r19 85 subb %r21,%r19,%r21 86 stw %r21,20(%r26) 87 88LDEF(2) 89 ldw 24(%r25),%r20 90 ldw 24(%r24),%r31 91 subb %r20,%r31,%r20 92 stw %r20,24(%r26) 93 94LDEF(1) 95 ldw 28(%r25),%r21 96 ldo 32(%r25),%r25 97 ldw 28(%r24),%r19 98 subb %r21,%r19,%r21 99 stw %r21,28(%r26) 100 ldo 32(%r24),%r24 101 addib,> -8,%r23,L(loop) 102 ldo 32(%r26),%r26 103 104 addc %r0,%r0,%r28 105 bv (%r2) 106 subi 1,%r28,%r28 107EPILOGUE() 108