![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to add_n.asm CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [local] / OpenXM_contrib / gmp / mpn / ia64|
Return to add_n.asm CVS log | Up to [local] / OpenXM_contrib / gmp / mpn / ia64 |
1.1 ohara 1: dnl IA-64 mpn_add_n -- Add two limb vectors of the same length > 0 and store
2: dnl sum in a third limb vector.
3:
4: dnl Copyright 2000, 2001, 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 rp = r32
27: C up = r33
28: C vp = r34
29: C n = r35
30:
31: C cycles/limb
32: C Itanium: 6
33: C Itanium 2: ?
34:
35:
36: ASM_START()
37: PROLOGUE(mpn_add_n)
38: .prologue
39: ifdef(`HAVE_ABI_32',
40: ` addp4 r32 = 0, r32
41: addp4 r33 = 0, r33
42: addp4 r34 = 0, r34
43: sxt4 r35 = r35
44: ;;
45: ')
46: { .mib; cmp.eq p6, p7 = 1, r35
47: add r35 = -2, r35
48: nop.b 0
49: } { .mib; cmp.ne p8, p9 = r0, r0
50: .save ar.lc, r2
51: mov r2 = ar.lc
52: .body
53: nop.b 0 ;;
54: } { .mib; ld8 r16 = [r33], 8
55: mov ar.lc = r35
56: nop.b 0
57: } { .mib; ld8 r17 = [r34], 8
58: nop.i 0
59: (p6) br.dptk .Lend ;;
60: }
61: .align 32
62: .Loop:
63: .pred.rel "mutex",p8,p9
64: { .mii; mov r20 = r16
65: (p8) add r19 = r16, r17, 1
66: (p9) add r19 = r16, r17 ;;
67: } { .mfi; ld8 r16 = [r33], 8
68: nop.f 0
69: (p8) cmp.leu p6, p7 = r19, r20
70: } { .mfi; ld8 r17 = [r34], 8
71: nop.f 0
72: (p9) cmp.ltu p6, p7 = r19, r20
73: } { .mbb; st8 [r32] = r19, 8
74: nop.b 0
75: br.cloop.dptk .Loopm ;;
76: }
77: .pred.rel "mutex",p6,p7
78: { .mfi; (p6) add r19 = r16, r17, 1
79: nop.f 0
80: (p7) add r19 = r16, r17 ;;
81: } { .mii; st8 [r32] = r19
82: (p6) cmp.leu p8, p9 = r19, r16
83: (p7) cmp.ltu p8, p9 = r19, r16 ;;
84: }
85: .pred.rel "mutex",p8,p9
86: { .mfi; (p8) mov r8 = 1
87: nop.f 0
88: (p9) mov r8 = 0
89: }
90: mov ar.lc = r2
91: br.ret.sptk.many b0
92: .Loopm:
93: .pred.rel "mutex",p6,p7
94: { .mii; mov r20 = r16
95: (p6) add r19 = r16, r17, 1
96: (p7) add r19 = r16, r17 ;;
97: } { .mfi; ld8 r16 = [r33], 8
98: nop.f 0
99: (p6) cmp.leu p8, p9 = r19, r20
100: } { .mfi; ld8 r17 = [r34], 8
101: nop.f 0
102: (p7) cmp.ltu p8, p9 = r19, r20
103: } { .mbb; st8 [r32] = r19, 8
104: nop.b 0
105: br.cloop.dptk .Loop ;;
106: }
107: .Lend:
108: .pred.rel "mutex",p8,p9
109: { .mfi; (p8) add r19 = r16, r17, 1
110: nop.f 0
111: (p9) add r19 = r16, r17 ;;
112: } { .mii; st8 [r32] = r19
113: (p8) cmp.leu p6, p7 = r19, r16
114: (p9) cmp.ltu p6, p7 = r19, r16 ;;
115: }
116: .pred.rel "mutex",p6,p7
117: { .mfi; (p6) mov r8 = 1
118: nop.f 0
119: (p7) mov r8 = 0
120: }
121: mov ar.lc = r2
122: br.ret.sptk.many b0
123: EPILOGUE(mpn_add_n)
124: ASM_END()