Annotation of OpenXM_contrib/gmp/mpn/mips32/submul_1.asm, Revision 1.1.1.1
1.1 ohara 1: dnl MIPS32 mpn_submul_1 -- Multiply a limb vector with a single limb and
2: dnl subtract the product from a second limb vector.
3:
4: dnl Copyright 1992, 1994, 1996, 2000, 2002 Free Software Foundation, Inc.
5:
6: dnl This file is part of the GNU MP Library.
7:
8: dnl The GNU MP Library is free software; you can redistribute it and/or modify
9: dnl it under the terms of the GNU Lesser General Public License as published
10: dnl by the Free Software Foundation; either version 2.1 of the License, or (at
11: dnl your option) any later version.
12:
13: dnl The GNU MP Library is distributed in the hope that it will be useful, but
14: dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
15: dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
16: dnl License for more details.
17:
18: dnl You should have received a copy of the GNU Lesser General Public License
19: dnl along with the GNU MP Library; see the file COPYING.LIB. If not, write to
20: dnl the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
21: dnl MA 02111-1307, USA.
22:
23: include(`../config.m4')
24:
25: C INPUT PARAMETERS
26: C res_ptr $4
27: C s1_ptr $5
28: C size $6
29: C s2_limb $7
30:
31: ASM_START()
32: PROLOGUE(mpn_submul_1)
33:
34: C feed-in phase 0
35: lw $8,0($5)
36:
37: C feed-in phase 1
38: addiu $5,$5,4
39: multu $8,$7
40:
41: addiu $6,$6,-1
42: beq $6,$0,$LC0
43: move $2,$0 C zero cy2
44:
45: addiu $6,$6,-1
46: beq $6,$0,$LC1
47: lw $8,0($5) C load new s1 limb as early as possible
48:
49: Loop: lw $10,0($4)
50: mflo $3
51: mfhi $9
52: addiu $5,$5,4
53: addu $3,$3,$2 C add old carry limb to low product limb
54: multu $8,$7
55: lw $8,0($5) C load new s1 limb as early as possible
56: addiu $6,$6,-1 C decrement loop counter
57: sltu $2,$3,$2 C carry from previous addition -> $2
58: subu $3,$10,$3
59: sgtu $10,$3,$10
60: addu $2,$2,$10
61: sw $3,0($4)
62: addiu $4,$4,4
63: bne $6,$0,Loop
64: addu $2,$9,$2 C add high product limb and carry from addition
65:
66: C wind-down phase 1
67: $LC1: lw $10,0($4)
68: mflo $3
69: mfhi $9
70: addu $3,$3,$2
71: sltu $2,$3,$2
72: multu $8,$7
73: subu $3,$10,$3
74: sgtu $10,$3,$10
75: addu $2,$2,$10
76: sw $3,0($4)
77: addiu $4,$4,4
78: addu $2,$9,$2 C add high product limb and carry from addition
79:
80: C wind-down phase 0
81: $LC0: lw $10,0($4)
82: mflo $3
83: mfhi $9
84: addu $3,$3,$2
85: sltu $2,$3,$2
86: subu $3,$10,$3
87: sgtu $10,$3,$10
88: addu $2,$2,$10
89: sw $3,0($4)
90: j $31
91: addu $2,$9,$2 C add high product limb and carry from addition
92: EPILOGUE(mpn_submul_1)
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>