1dnl  PowerPC-64 mpn_copyd.
2
3dnl  Copyright 2004, 2005, 2013 Free Software Foundation, Inc.
4
5dnl  This file is part of the GNU MP Library.
6dnl
7dnl  The GNU MP Library is free software; you can redistribute it and/or modify
8dnl  it under the terms of either:
9dnl
10dnl    * the GNU Lesser General Public License as published by the Free
11dnl      Software Foundation; either version 3 of the License, or (at your
12dnl      option) any later version.
13dnl
14dnl  or
15dnl
16dnl    * the GNU General Public License as published by the Free Software
17dnl      Foundation; either version 2 of the License, or (at your option) any
18dnl      later version.
19dnl
20dnl  or both in parallel, as here.
21dnl
22dnl  The GNU MP Library is distributed in the hope that it will be useful, but
23dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
24dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
25dnl  for more details.
26dnl
27dnl  You should have received copies of the GNU General Public License and the
28dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
29dnl  see https://www.gnu.org/licenses/.
30
31include(`../config.m4')
32
33C                  cycles/limb
34C POWER3/PPC630          ?
35C POWER4/PPC970          ?
36C POWER5                 ?
37C POWER6                 1.25
38C POWER7                 1.09
39
40C INPUT PARAMETERS
41define(`rp',        `r3')
42define(`up',        `r4')
43define(`n',         `r5')
44
45ASM_START()
46PROLOGUE(mpn_copyd)
47
48ifdef(`HAVE_ABI_mode32',
49`         rldicl    n, n, 0,32')
50
51          sldi      r0, n, 3
52          add       up, up, r0                    C point at u[] end
53          add       rp, rp, r0                    C point at r[] end
54
55          cmpdi     cr0, n, 4
56          blt       L(sml)
57
58          addi      r10, n, 4
59          srdi      r10, r10, 3
60          mtctr     r10
61
62          andi.     r0, n, 1
63          rlwinm    r11, n, 0,30,30
64          rlwinm    r12, n, 0,29,29
65          cmpdi     cr6, r11, 0
66          cmpdi     cr7, r12, 0
67
68          beq       cr0, L(xx0)
69L(xx1):   ld        r6, -8(up)
70          addi      up, up, -8
71          std       r6, -8(rp)
72          addi      rp, rp, -8
73
74L(xx0):   bne       cr6, L(x10)
75L(x00):   ld        r6, -8(up)
76          ld        r7, -16(up)
77          bne       cr7, L(100)
78L(000):   addi      rp, rp, 32
79          b         L(lo0)
80L(100):   addi      up, up, 32
81          b         L(lo4)
82L(x10):   ld        r8, -8(up)
83          ld        r9, -16(up)
84          bne       cr7, L(110)
85L(010):   addi      up, up, -16
86          addi      rp, rp, 16
87          b         L(lo2)
88L(110):   addi      up, up, 16
89          addi      rp, rp, 48
90          b         L(lo6)
91
92L(sml):   cmpdi     cr0, n, 0
93          beqlr-    cr0
94          mtctr     n
95L(t):     ld        r6, -8(up)
96          addi      up, up, -8
97          std       r6, -8(rp)
98          addi      rp, rp, -8
99          bdnz      L(t)
100          blr
101
102          ALIGN(32)
103L(top):   std       r6, -8(rp)
104          std       r7, -16(rp)
105L(lo2):   ld        r6, -8(up)
106          ld        r7, -16(up)
107          std       r8, -24(rp)
108          std       r9, -32(rp)
109L(lo0):   ld        r8, -24(up)
110          ld        r9, -32(up)
111          std       r6, -40(rp)
112          std       r7, -48(rp)
113L(lo6):   ld        r6, -40(up)
114          ld        r7, -48(up)
115          std       r8, -56(rp)
116          std       r9, -64(rp)
117          addi      rp, rp, -64
118L(lo4):   ld        r8, -56(up)
119          ld        r9, -64(up)
120          addi      up, up, -64
121          bdnz      L(top)
122
123L(end):   std       r6, -8(rp)
124          std       r7, -16(rp)
125          std       r8, -24(rp)
126          std       r9, -32(rp)
127          blr
128EPILOGUE()
129