Annotation of OpenXM_contrib/gmp/mpn/a29k/lshift.s, Revision 1.1.1.3
1.1.1.2 maekawa 1: ; 29000 __gmpn_lshift --
1.1 maekawa 2:
1.1.1.3 ! ohara 3: ; Copyright 1992, 1994, 2000 Free Software Foundation, Inc.
1.1 maekawa 4:
5: ; This file is part of the GNU MP Library.
6:
7: ; The GNU MP Library is free software; you can redistribute it and/or modify
1.1.1.2 maekawa 8: ; it under the terms of the GNU Lesser General Public License as published by
9: ; the Free Software Foundation; either version 2.1 of the License, or (at your
1.1 maekawa 10: ; option) any later version.
11:
12: ; The GNU MP Library is distributed in the hope that it will be useful, but
13: ; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
1.1.1.2 maekawa 14: ; or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
1.1 maekawa 15: ; License for more details.
16:
1.1.1.2 maekawa 17: ; You should have received a copy of the GNU Lesser General Public License
1.1 maekawa 18: ; along with the GNU MP Library; see the file COPYING.LIB. If not, write to
19: ; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
20: ; MA 02111-1307, USA.
21:
22:
23: ; INPUT PARAMETERS
24: ; res_ptr lr2
25: ; s1_ptr lr3
26: ; s2_ptr lr4
27: ; size lr5
28:
29: ; We use the loadm/storem instructions and operate on chunks of 8
30: ; limbs/per iteration, until less than 8 limbs remain.
31:
32: .sect .lit,lit
33: .text
34: .align 4
1.1.1.2 maekawa 35: .global ___gmpn_lshift
1.1 maekawa 36: .word 0x60000
1.1.1.2 maekawa 37: ___gmpn_lshift:
1.1 maekawa 38: sll gr116,lr4,2
39: add lr3,gr116,lr3
40: add lr2,gr116,lr2
41: sub lr3,lr3,4
42: load 0,0,gr119,lr3
43:
44: subr gr116,lr5,32
45: srl gr96,gr119,gr116 ; return value
46: sub lr4,lr4,1 ; actual loop count is SIZE - 1
47:
48: srl gr117,lr4,3 ; chuck count = (actual count) / 8
49: cpeq gr118,gr117,0
50: jmpt gr118,Ltail
51: mtsr fc,lr5
52:
53: sub gr117,gr117,2 ; count for jmpfdec
54:
55: ; Main loop working 8 limbs/iteration.
56: Loop: sub lr3,lr3,32
57: mtsrim cr,(8-1)
58: loadm 0,0,gr100,lr3
59:
60: extract gr109,gr119,gr107
61: extract gr108,gr107,gr106
62: extract gr107,gr106,gr105
63: extract gr106,gr105,gr104
64: extract gr105,gr104,gr103
65: extract gr104,gr103,gr102
66: extract gr103,gr102,gr101
67: extract gr102,gr101,gr100
68:
69: sub lr2,lr2,32
70: mtsrim cr,(8-1)
71: storem 0,0,gr102,lr2
72: jmpfdec gr117,Loop
73: or gr119,gr100,0
74:
75: ; Code for the last up-to-7 limbs.
76:
77: and lr4,lr4,(8-1)
78: Ltail: cpeq gr118,lr4,0
79: jmpt gr118,Lend
80: sub lr4,lr4,2 ; count for jmpfdec
81:
82: Loop2: sub lr3,lr3,4
83: load 0,0,gr116,lr3
84: extract gr117,gr119,gr116
85: sub lr2,lr2,4
86: store 0,0,gr117,lr2
87: jmpfdec lr4,Loop2
88: or gr119,gr116,0
89:
90: Lend: extract gr117,gr119,0
91: sub lr2,lr2,4
92: jmpi lr0
93: store 0,0,gr117,lr2
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>