1dnl HP-PA 32-bit mpn_sqr_diagonal optimized for the PA8x00. 2 3dnl Copyright 2001, 2002 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 This code runs at 6 cycles/limb on the PA7100 and 2 cycles/limb on PA8x00. 34C The 2-way unrolling is actually not helping the PA7100. 35 36C INPUT PARAMETERS 37define(`rp',`%r26') 38define(`up',`%r25') 39define(`n',`%r24') 40 41ASM_START() 42PROLOGUE(mpn_sqr_diagonal) 43 44 fldws,ma 4(up),%fr4r 45 addib,= -1,n,L(end1) 46 ldo 4(rp),rp 47 48 fldws,ma 4(up),%fr6r 49 addib,= -1,n,L(end2) 50 xmpyu %fr4r,%fr4r,%fr5 51 52 fldws,ma 4(up),%fr4r 53 addib,= -1,n,L(end3) 54 xmpyu %fr6r,%fr6r,%fr7 55 56 57LDEF(loop) 58 fldws,ma 4(up),%fr6r 59 fstws %fr5r,-4(rp) 60 fstws,ma %fr5l,8(rp) 61 addib,= -1,n,L(exite) 62 xmpyu %fr4r,%fr4r,%fr5 63 fldws,ma 4(up),%fr4r 64 fstws %fr7r,-4(rp) 65 fstws,ma %fr7l,8(rp) 66 addib,<> -1,n,L(loop) 67 xmpyu %fr6r,%fr6r,%fr7 68 69LDEF(exito) 70 fstws %fr5r,-4(rp) 71 fstws %fr5l,0(rp) 72 xmpyu %fr4r,%fr4r,%fr5 73 fstws %fr7r,4(rp) 74 fstws %fr7l,8(rp) 75 fstws,mb %fr5r,12(rp) 76 bv 0(%r2) 77 fstws %fr5l,4(rp) 78 79LDEF(exite) 80 fstws %fr7r,-4(rp) 81 fstws %fr7l,0(rp) 82 xmpyu %fr6r,%fr6r,%fr7 83 fstws %fr5r,4(rp) 84 fstws %fr5l,8(rp) 85 fstws,mb %fr7r,12(rp) 86 bv 0(%r2) 87 fstws %fr7l,4(rp) 88 89LDEF(end1) 90 xmpyu %fr4r,%fr4r,%fr5 91 fstws %fr5r,-4(rp) 92 bv 0(%r2) 93 fstws,ma %fr5l,8(rp) 94 95LDEF(end2) 96 xmpyu %fr6r,%fr6r,%fr7 97 fstws %fr5r,-4(rp) 98 fstws %fr5l,0(rp) 99 fstws %fr7r,4(rp) 100 bv 0(%r2) 101 fstws %fr7l,8(rp) 102 103LDEF(end3) 104 fstws %fr5r,-4(rp) 105 fstws %fr5l,0(rp) 106 xmpyu %fr4r,%fr4r,%fr5 107 fstws %fr7r,4(rp) 108 fstws %fr7l,8(rp) 109 fstws,mb %fr5r,12(rp) 110 bv 0(%r2) 111 fstws %fr5l,4(rp) 112EPILOGUE(mpn_sqr_diagonal) 113