sysdeps/sparc/sparc32/sparcv9/mul_1.S

   1 ! SPARC v9 32-bit __mpn_mul_1 -- Multiply a limb vector with a single
   2 ! limb and store the product in a second limb vector.
   3 !
   4 ! Copyright (C) 2013-2014 Free Software Foundation, Inc.
   5 ! This file is part of the GNU C Library.
   6 ! Contributed by David S. Miller <davem@davemloft.net>
   7 !
   8 ! The GNU C Library is free software; you can redistribute it and/or
   9 ! modify it under the terms of the GNU Lesser General Public
  10 ! License as published by the Free Software Foundation; either
  11 ! version 2.1 of the License, or (at your option) any later version.
  12 !
  13 ! The GNU C Library is distributed in the hope that it will be useful,
  14 ! but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 ! MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16 ! Lesser General Public License for more details.
  17 !
  18 ! You should have received a copy of the GNU Lesser General Public
  19 ! License along with the GNU C Library; if not, see
  20 ! <http://www.gnu.org/licenses/>.
  21
  22 #include <sysdep.h>
  23
  24 #define res_ptr %o0
  25 #define s1_ptr  %o1
  26 #define sz      %o2
  27 #define s2_limb %o3
  28 #define carry   %o5
  29 #define tmp1    %g1
  30 #define tmp2    %g2
  31 #define tmp3    %g3
  32 #define tmp4    %o4
  33
  34 ENTRY(__mpn_mul_1)
  35         srl     sz, 0, sz
  36         srl     s2_limb, 0, s2_limb
  37         subcc   sz, 1, sz
  38         be,pn   %icc, .Lfinal_limb
  39          clr    carry
  40
  41 .Lloop:
  42         lduw    [s1_ptr + 0x00], tmp1
  43         lduw    [s1_ptr + 0x04], tmp2
  44         mulx    tmp1, s2_limb, tmp3
  45         add     s1_ptr, 8, s1_ptr
  46         mulx    tmp2, s2_limb, tmp4
  47         sub     sz, 2, sz
  48         add     res_ptr, 8, res_ptr
  49         add     carry, tmp3, tmp3
  50         stw     tmp3, [res_ptr - 0x08]
  51         srlx    tmp3, 32, carry
  52         add     carry, tmp4, tmp4
  53         stw     tmp4, [res_ptr - 0x04]
  54         brgz    sz, .Lloop
  55          srlx   tmp4, 32, carry
  56
  57         brlz,pt sz, .Lfinish
  58          nop
  59
  60 .Lfinal_limb:
  61         lduw    [s1_ptr + 0x00], tmp1
  62         mulx    tmp1, s2_limb, tmp3
  63         add     carry, tmp3, tmp3
  64         stw     tmp3, [res_ptr + 0x00]
  65         srlx    tmp3, 32, carry
  66
  67 .Lfinish:
  68         retl
  69          mov    carry, %o0
  70 END(__mpn_mul_1)