![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to submul_1.asm CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [local] / OpenXM_contrib / gmp / mpn / sparc32|
Return to submul_1.asm CVS log | Up to [local] / OpenXM_contrib / gmp / mpn / sparc32 |
1.1 maekawa 1: dnl SPARC mpn_submul_1 -- Multiply a limb vector with a limb and subtract
2: dnl the result from a second limb vector.
3:
4: dnl Copyright (C) 1992, 1993, 1994, 2000 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:
24: include(`../config.m4')
25:
26: C INPUT PARAMETERS
27: C res_ptr o0
28: C s1_ptr o1
29: C size o2
30: C s2_limb o3
31:
32: ASM_START()
33: PROLOGUE(mpn_submul_1)
34: C Make S1_PTR and RES_PTR point at the end of their blocks
35: C and put (- 4 x SIZE) in index/loop counter.
36: sll %o2,2,%o2
37: add %o0,%o2,%o4 C RES_PTR in o4 since o0 is retval
38: add %o1,%o2,%o1
39: sub %g0,%o2,%o2
40:
41: cmp %o3,0xfff
42: bgu L(large)
43: nop
44:
45: ld [%o1+%o2],%o5
46: mov 0,%o0
47: b L(0)
48: add %o4,-4,%o4
49: L(loop0):
50: subcc %o5,%g1,%g1
51: ld [%o1+%o2],%o5
52: addx %o0,%g0,%o0
53: st %g1,[%o4+%o2]
54: L(0): wr %g0,%o3,%y
55: sra %o5,31,%g2
56: and %o3,%g2,%g2
57: andcc %g1,0,%g1
58: mulscc %g1,%o5,%g1
59: mulscc %g1,%o5,%g1
60: mulscc %g1,%o5,%g1
61: mulscc %g1,%o5,%g1
62: mulscc %g1,%o5,%g1
63: mulscc %g1,%o5,%g1
64: mulscc %g1,%o5,%g1
65: mulscc %g1,%o5,%g1
66: mulscc %g1,%o5,%g1
67: mulscc %g1,%o5,%g1
68: mulscc %g1,%o5,%g1
69: mulscc %g1,%o5,%g1
70: mulscc %g1,0,%g1
71: sra %g1,20,%g4
72: sll %g1,12,%g1
73: rd %y,%g3
74: srl %g3,20,%g3
75: or %g1,%g3,%g1
76:
77: addcc %g1,%o0,%g1
78: addx %g2,%g4,%o0 C add sign-compensation and cy to hi limb
79: addcc %o2,4,%o2 C loop counter
80: bne L(loop0)
81: ld [%o4+%o2],%o5
82:
83: subcc %o5,%g1,%g1
84: addx %o0,%g0,%o0
85: retl
86: st %g1,[%o4+%o2]
87:
88: L(large):
89: ld [%o1+%o2],%o5
90: mov 0,%o0
91: sra %o3,31,%g4 C g4 = mask of ones iff S2_LIMB < 0
92: b L(1)
93: add %o4,-4,%o4
94: L(loop):
95: subcc %o5,%g3,%g3
96: ld [%o1+%o2],%o5
97: addx %o0,%g0,%o0
98: st %g3,[%o4+%o2]
99: L(1): wr %g0,%o5,%y
100: and %o5,%g4,%g2
101: andcc %g0,%g0,%g1
102: mulscc %g1,%o3,%g1
103: mulscc %g1,%o3,%g1
104: mulscc %g1,%o3,%g1
105: mulscc %g1,%o3,%g1
106: mulscc %g1,%o3,%g1
107: mulscc %g1,%o3,%g1
108: mulscc %g1,%o3,%g1
109: mulscc %g1,%o3,%g1
110: mulscc %g1,%o3,%g1
111: mulscc %g1,%o3,%g1
112: mulscc %g1,%o3,%g1
113: mulscc %g1,%o3,%g1
114: mulscc %g1,%o3,%g1
115: mulscc %g1,%o3,%g1
116: mulscc %g1,%o3,%g1
117: mulscc %g1,%o3,%g1
118: mulscc %g1,%o3,%g1
119: mulscc %g1,%o3,%g1
120: mulscc %g1,%o3,%g1
121: mulscc %g1,%o3,%g1
122: mulscc %g1,%o3,%g1
123: mulscc %g1,%o3,%g1
124: mulscc %g1,%o3,%g1
125: mulscc %g1,%o3,%g1
126: mulscc %g1,%o3,%g1
127: mulscc %g1,%o3,%g1
128: mulscc %g1,%o3,%g1
129: mulscc %g1,%o3,%g1
130: mulscc %g1,%o3,%g1
131: mulscc %g1,%o3,%g1
132: mulscc %g1,%o3,%g1
133: mulscc %g1,%o3,%g1
134: mulscc %g1,%g0,%g1
135: rd %y,%g3
136: addcc %g3,%o0,%g3
137: addx %g2,%g1,%o0
138: addcc %o2,4,%o2
139: bne L(loop)
140: ld [%o4+%o2],%o5
141:
142: subcc %o5,%g3,%g3
143: addx %o0,%g0,%o0
144: retl
145: st %g3,[%o4+%o2]
146: EPILOGUE(mpn_submul_1)