X-Git-Url: https://oss.titaniummirror.com/gitweb?a=blobdiff_plain;f=gmp%2Fmpn%2Fsparc32%2Fmul_1.asm;fp=gmp%2Fmpn%2Fsparc32%2Fmul_1.asm;h=147db11157f265499a1bda0955267c61f6ea06b3;hb=6fed43773c9b0ce596dca5686f37ac3fc0fa11c0;hp=0000000000000000000000000000000000000000;hpb=27b11d56b743098deb193d510b337ba22dc52e5c;p=msp430-gcc.git diff --git a/gmp/mpn/sparc32/mul_1.asm b/gmp/mpn/sparc32/mul_1.asm new file mode 100644 index 00000000..147db111 --- /dev/null +++ b/gmp/mpn/sparc32/mul_1.asm @@ -0,0 +1,135 @@ +dnl SPARC mpn_mul_1 -- Multiply a limb vector with a limb and store +dnl the result in a second limb vector. + +dnl Copyright 1992, 1993, 1994, 2000 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 o0 +C s1_ptr o1 +C size o2 +C s2_limb o3 + +ASM_START() +PROLOGUE(mpn_mul_1) + C Make S1_PTR and RES_PTR point at the end of their blocks + C and put (- 4 x SIZE) in index/loop counter. + sll %o2,2,%o2 + add %o0,%o2,%o4 C RES_PTR in o4 since o0 is retval + add %o1,%o2,%o1 + sub %g0,%o2,%o2 + + cmp %o3,0xfff + bgu L(large) + nop + + ld [%o1+%o2],%o5 + mov 0,%o0 + b L(0) + add %o4,-4,%o4 +L(loop0): + st %g1,[%o4+%o2] +L(0): wr %g0,%o3,%y + sra %o5,31,%g2 + and %o3,%g2,%g2 + andcc %g1,0,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,%o5,%g1 + mulscc %g1,0,%g1 + sra %g1,20,%g4 + sll %g1,12,%g1 + rd %y,%g3 + srl %g3,20,%g3 + or %g1,%g3,%g1 + + addcc %g1,%o0,%g1 + addx %g2,%g4,%o0 C add sign-compensation and cy to hi limb + addcc %o2,4,%o2 C loop counter + bne,a L(loop0) + ld [%o1+%o2],%o5 + + retl + st %g1,[%o4+%o2] + + +L(large): + ld [%o1+%o2],%o5 + mov 0,%o0 + sra %o3,31,%g4 C g4 = mask of ones iff S2_LIMB < 0 + b L(1) + add %o4,-4,%o4 +L(loop): + st %g3,[%o4+%o2] +L(1): wr %g0,%o5,%y + and %o5,%g4,%g2 C g2 = S1_LIMB iff S2_LIMB < 0, else 0 + andcc %g0,%g0,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%o3,%g1 + mulscc %g1,%g0,%g1 + rd %y,%g3 + addcc %g3,%o0,%g3 + addx %g2,%g1,%o0 C add sign-compensation and cy to hi limb + addcc %o2,4,%o2 C loop counter + bne,a L(loop) + ld [%o1+%o2],%o5 + + retl + st %g3,[%o4+%o2] +EPILOGUE(mpn_mul_1)