![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to addmul_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 / v8|
Return to addmul_1.asm CVS log | Up to [local] / OpenXM_contrib / gmp / mpn / sparc32 / v8 |
1.1 maekawa 1: dnl SPARC v8 mpn_addmul_1 -- Multiply a limb vector with a limb and
2: dnl add the result to a second limb vector.
3:
4: dnl Copyright (C) 1992, 1993, 1994, 1995, 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_addmul_1)
34: orcc %g0,%g0,%g2
35: ld [%o1+0],%o4 C 1
36:
37: sll %o2,4,%g1
38: and %g1,(4-1)<<4,%g1
39: ifdef(`PIC',
40: ` mov %o7,%g4 C Save return address register
41: 0: call 1f
42: add %o7,L(1)-0b,%g3
43: 1: mov %g4,%o7 C Restore return address register
44: ',
45: ` sethi %hi(L(1)),%g3
46: or %g3,%lo(L(1)),%g3
47: ')
48: jmp %g3+%g1
49: nop
50: L(1):
51: L(L00): add %o0,-4,%o0
52: b L(loop00) C 4, 8, 12, ...
53: add %o1,-4,%o1
54: nop
55: L(L01): b L(loop01) C 1, 5, 9, ...
56: nop
57: nop
58: nop
59: L(L10): add %o0,-12,%o0 C 2, 6, 10, ...
60: b L(loop10)
61: add %o1,4,%o1
62: nop
63: L(L11): add %o0,-8,%o0 C 3, 7, 11, ...
64: b L(loop11)
65: add %o1,-8,%o1
66: nop
67:
68: L(loop):
69: addcc %g3,%g2,%g3 C 1
70: ld [%o1+4],%o4 C 2
71: rd %y,%g2 C 1
72: addx %g0,%g2,%g2
73: ld [%o0+0],%g1 C 2
74: addcc %g1,%g3,%g3
75: st %g3,[%o0+0] C 1
76: L(loop00):
77: umul %o4,%o3,%g3 C 2
78: ld [%o0+4],%g1 C 2
79: addxcc %g3,%g2,%g3 C 2
80: ld [%o1+8],%o4 C 3
81: rd %y,%g2 C 2
82: addx %g0,%g2,%g2
83: nop
84: addcc %g1,%g3,%g3
85: st %g3,[%o0+4] C 2
86: L(loop11):
87: umul %o4,%o3,%g3 C 3
88: addxcc %g3,%g2,%g3 C 3
89: ld [%o1+12],%o4 C 4
90: rd %y,%g2 C 3
91: add %o1,16,%o1
92: addx %g0,%g2,%g2
93: ld [%o0+8],%g1 C 2
94: addcc %g1,%g3,%g3
95: st %g3,[%o0+8] C 3
96: L(loop10):
97: umul %o4,%o3,%g3 C 4
98: addxcc %g3,%g2,%g3 C 4
99: ld [%o1+0],%o4 C 1
100: rd %y,%g2 C 4
101: addx %g0,%g2,%g2
102: ld [%o0+12],%g1 C 2
103: addcc %g1,%g3,%g3
104: st %g3,[%o0+12] C 4
105: add %o0,16,%o0
106: addx %g0,%g2,%g2
107: L(loop01):
108: addcc %o2,-4,%o2
109: bg L(loop)
110: umul %o4,%o3,%g3 C 1
111:
112: addcc %g3,%g2,%g3 C 4
113: rd %y,%g2 C 4
114: addx %g0,%g2,%g2
115: ld [%o0+0],%g1 C 2
116: addcc %g1,%g3,%g3
117: st %g3,[%o0+0] C 4
118: addx %g0,%g2,%o0
119:
120: retl
121: nop
122: EPILOGUE(mpn_addmul_1)