1dnl MIPS32 mpn_submul_1 -- Multiply a limb vector with a single limb and 2dnl subtract the product from a second limb vector. 3 4dnl Copyright 1992, 1994, 1996, 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 $4 36C s1_ptr $5 37C size $6 38C s2_limb $7 39 40ASM_START() 41PROLOGUE(mpn_submul_1) 42 43C feed-in phase 0 44 lw $8,0($5) 45 46C feed-in phase 1 47 addiu $5,$5,4 48 multu $8,$7 49 50 addiu $6,$6,-1 51 beq $6,$0,$LC0 52 move $2,$0 C zero cy2 53 54 addiu $6,$6,-1 55 beq $6,$0,$LC1 56 lw $8,0($5) C load new s1 limb as early as possible 57 58Loop: lw $10,0($4) 59 mflo $3 60 mfhi $9 61 addiu $5,$5,4 62 addu $3,$3,$2 C add old carry limb to low product limb 63 multu $8,$7 64 lw $8,0($5) C load new s1 limb as early as possible 65 addiu $6,$6,-1 C decrement loop counter 66 sltu $2,$3,$2 C carry from previous addition -> $2 67 subu $3,$10,$3 68 sgtu $10,$3,$10 69 addu $2,$2,$10 70 sw $3,0($4) 71 addiu $4,$4,4 72 bne $6,$0,Loop 73 addu $2,$9,$2 C add high product limb and carry from addition 74 75C wind-down phase 1 76$LC1: lw $10,0($4) 77 mflo $3 78 mfhi $9 79 addu $3,$3,$2 80 sltu $2,$3,$2 81 multu $8,$7 82 subu $3,$10,$3 83 sgtu $10,$3,$10 84 addu $2,$2,$10 85 sw $3,0($4) 86 addiu $4,$4,4 87 addu $2,$9,$2 C add high product limb and carry from addition 88 89C wind-down phase 0 90$LC0: lw $10,0($4) 91 mflo $3 92 mfhi $9 93 addu $3,$3,$2 94 sltu $2,$3,$2 95 subu $3,$10,$3 96 sgtu $10,$3,$10 97 addu $2,$2,$10 98 sw $3,0($4) 99 j $31 100 addu $2,$9,$2 C add high product limb and carry from addition 101EPILOGUE(mpn_submul_1) 102