beta-0.89.2
[luatex.git] / source / libs / gmp / gmp-src / mpn / x86_64 / k10 / hamdist.asm
blob44b67b5e4e6619556ec3954ab5557bdb99a5b440
1 dnl AMD64 mpn_hamdist -- hamming distance.
3 dnl Copyright 2008, 2010-2012 Free Software Foundation, Inc.
5 dnl This file is part of the GNU MP Library.
6 dnl
7 dnl The GNU MP Library is free software; you can redistribute it and/or modify
8 dnl it under the terms of either:
9 dnl
10 dnl * the GNU Lesser General Public License as published by the Free
11 dnl Software Foundation; either version 3 of the License, or (at your
12 dnl option) any later version.
13 dnl
14 dnl or
15 dnl
16 dnl * the GNU General Public License as published by the Free Software
17 dnl Foundation; either version 2 of the License, or (at your option) any
18 dnl later version.
19 dnl
20 dnl or both in parallel, as here.
21 dnl
22 dnl The GNU MP Library is distributed in the hope that it will be useful, but
23 dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
24 dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
25 dnl for more details.
26 dnl
27 dnl You should have received copies of the GNU General Public License and the
28 dnl GNU Lesser General Public License along with the GNU MP Library. If not,
29 dnl see https://www.gnu.org/licenses/.
31 include(`../config.m4')
33 C cycles/limb
34 C AMD K8,K9 n/a
35 C AMD K10 2
36 C Intel P4 n/a
37 C Intel core2 n/a
38 C Intel corei 2.05
39 C Intel atom n/a
40 C VIA nano n/a
42 C This is very straightforward 2-way unrolled code.
44 C TODO
45 C * Write something less basic. It should not be hard to reach 1.5 c/l with
46 C 4-way unrolling.
48 define(`ap', `%rdi')
49 define(`bp', `%rsi')
50 define(`n', `%rdx')
52 ABI_SUPPORT(DOS64)
53 ABI_SUPPORT(STD64)
55 ASM_START()
56 TEXT
57 ALIGN(32)
58 PROLOGUE(mpn_hamdist)
59 FUNC_ENTRY(3)
60 mov (ap), %r8
61 xor (bp), %r8
63 lea (ap,n,8), ap C point at A operand end
64 lea (bp,n,8), bp C point at B operand end
65 neg n
67 bt $0, R32(n)
68 jnc L(2)
70 L(1): .byte 0xf3,0x49,0x0f,0xb8,0xc0 C popcnt %r8, %rax
71 xor R32(%r10), R32(%r10)
72 add $1, n
73 js L(top)
74 FUNC_EXIT()
75 ret
77 ALIGN(16)
78 L(2): mov 8(ap,n,8), %r9
79 .byte 0xf3,0x49,0x0f,0xb8,0xc0 C popcnt %r8, %rax
80 xor 8(bp,n,8), %r9
81 .byte 0xf3,0x4d,0x0f,0xb8,0xd1 C popcnt %r9, %r10
82 add $2, n
83 js L(top)
84 lea (%r10, %rax), %rax
85 FUNC_EXIT()
86 ret
88 ALIGN(16)
89 L(top): mov (ap,n,8), %r8
90 lea (%r10, %rax), %rax
91 mov 8(ap,n,8), %r9
92 xor (bp,n,8), %r8
93 xor 8(bp,n,8), %r9
94 .byte 0xf3,0x49,0x0f,0xb8,0xc8 C popcnt %r8, %rcx
95 lea (%rcx, %rax), %rax
96 .byte 0xf3,0x4d,0x0f,0xb8,0xd1 C popcnt %r9, %r10
97 add $2, n
98 js L(top)
100 lea (%r10, %rax), %rax
101 FUNC_EXIT()
103 EPILOGUE()