X-Git-Url: https://oss.titaniummirror.com/gitweb?a=blobdiff_plain;f=gmp%2Fmpn%2Fmips32%2Fsubmul_1.asm;fp=gmp%2Fmpn%2Fmips32%2Fsubmul_1.asm;h=4e43654e0a025ec95819bfd529dab86832e4c379;hb=6fed43773c9b0ce596dca5686f37ac3fc0fa11c0;hp=0000000000000000000000000000000000000000;hpb=27b11d56b743098deb193d510b337ba22dc52e5c;p=msp430-gcc.git diff --git a/gmp/mpn/mips32/submul_1.asm b/gmp/mpn/mips32/submul_1.asm new file mode 100644 index 00000000..4e43654e --- /dev/null +++ b/gmp/mpn/mips32/submul_1.asm @@ -0,0 +1,90 @@ +dnl MIPS32 mpn_submul_1 -- Multiply a limb vector with a single limb and +dnl subtract the product from a second limb vector. + +dnl Copyright 1992, 1994, 1996, 2000, 2002 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. + +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of the GNU Lesser General Public License as published +dnl by the Free Software Foundation; either version 3 of the License, or (at +dnl your option) any later version. + +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public +dnl License for more details. + +dnl You should have received a copy of the GNU Lesser General Public License +dnl along with the GNU MP Library. If not, see http://www.gnu.org/licenses/. + +include(`../config.m4') + +C INPUT PARAMETERS +C res_ptr $4 +C s1_ptr $5 +C size $6 +C s2_limb $7 + +ASM_START() +PROLOGUE(mpn_submul_1) + +C feed-in phase 0 + lw $8,0($5) + +C feed-in phase 1 + addiu $5,$5,4 + multu $8,$7 + + addiu $6,$6,-1 + beq $6,$0,$LC0 + move $2,$0 C zero cy2 + + addiu $6,$6,-1 + beq $6,$0,$LC1 + lw $8,0($5) C load new s1 limb as early as possible + +Loop: lw $10,0($4) + mflo $3 + mfhi $9 + addiu $5,$5,4 + addu $3,$3,$2 C add old carry limb to low product limb + multu $8,$7 + lw $8,0($5) C load new s1 limb as early as possible + addiu $6,$6,-1 C decrement loop counter + sltu $2,$3,$2 C carry from previous addition -> $2 + subu $3,$10,$3 + sgtu $10,$3,$10 + addu $2,$2,$10 + sw $3,0($4) + addiu $4,$4,4 + bne $6,$0,Loop + addu $2,$9,$2 C add high product limb and carry from addition + +C wind-down phase 1 +$LC1: lw $10,0($4) + mflo $3 + mfhi $9 + addu $3,$3,$2 + sltu $2,$3,$2 + multu $8,$7 + subu $3,$10,$3 + sgtu $10,$3,$10 + addu $2,$2,$10 + sw $3,0($4) + addiu $4,$4,4 + addu $2,$9,$2 C add high product limb and carry from addition + +C wind-down phase 0 +$LC0: lw $10,0($4) + mflo $3 + mfhi $9 + addu $3,$3,$2 + sltu $2,$3,$2 + subu $3,$10,$3 + sgtu $10,$3,$10 + addu $2,$2,$10 + sw $3,0($4) + j $31 + addu $2,$9,$2 C add high product limb and carry from addition +EPILOGUE(mpn_submul_1)