1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
|
dnl AMD64 mpn_rshift -- mpn right shift, optimised for Atom.
dnl Contributed to the GNU project by Torbjorn Granlund.
dnl Copyright 2011, 2012 Free Software Foundation, Inc.
dnl This file is part of the GNU MP Library.
dnl
dnl The GNU MP Library is free software; you can redistribute it and/or modify
dnl it under the terms of either:
dnl
dnl * the GNU Lesser General Public License as published by the Free
dnl Software Foundation; either version 3 of the License, or (at your
dnl option) any later version.
dnl
dnl or
dnl
dnl * the GNU General Public License as published by the Free Software
dnl Foundation; either version 2 of the License, or (at your option) any
dnl later version.
dnl
dnl or both in parallel, as here.
dnl
dnl The GNU MP Library is distributed in the hope that it will be useful, but
dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
dnl for more details.
dnl
dnl You should have received copies of the GNU General Public License and the
dnl GNU Lesser General Public License along with the GNU MP Library. If not,
dnl see https://www.gnu.org/licenses/.
include(`../config.m4')
C cycles/limb
C AMD K8,K9 ?
C AMD K10 ?
C Intel P4 ?
C Intel core2 ?
C Intel NHM ?
C Intel SBR ?
C Intel atom 4.5
C VIA nano ?
C TODO
C * Consider using 4-way unrolling. We reach 4 c/l, but the code is 2.5 times
C larger.
C INPUT PARAMETERS
define(`rp', `%rdi')
define(`up', `%rsi')
define(`n', `%rdx')
define(`cnt', `%rcx')
ABI_SUPPORT(DOS64)
ABI_SUPPORT(STD64)
ASM_START()
TEXT
ALIGN(16)
PROLOGUE(mpn_rshift)
FUNC_ENTRY(4)
shr R32(n)
mov (up), %rax
jnc L(evn)
mov %rax, %r11
shr R8(cnt), %r11
neg R8(cnt)
shl R8(cnt), %rax
test n, n
jnz L(gt1)
mov %r11, (rp)
FUNC_EXIT()
ret
L(gt1): mov 8(up), %r8
mov %r8, %r10
shl R8(cnt), %r8
jmp L(lo1)
L(evn): mov %rax, %r10
neg R8(cnt)
shl R8(cnt), %rax
mov 8(up), %r9
mov %r9, %r11
shl R8(cnt), %r9
neg R8(cnt)
dec n
lea -8(rp), rp
lea 8(up), up
jz L(end)
ALIGN(8)
L(top): shr R8(cnt), %r10
or %r10, %r9
shr R8(cnt), %r11
neg R8(cnt)
mov 8(up), %r8
mov %r8, %r10
mov %r9, 8(rp)
shl R8(cnt), %r8
lea 16(rp), rp
L(lo1): mov 16(up), %r9
or %r11, %r8
mov %r9, %r11
shl R8(cnt), %r9
lea 16(up), up
neg R8(cnt)
mov %r8, (rp)
dec n
jg L(top)
L(end): shr R8(cnt), %r10
or %r10, %r9
shr R8(cnt), %r11
mov %r9, 8(rp)
mov %r11, 16(rp)
FUNC_EXIT()
ret
EPILOGUE()
|
