1dnl  PPC64 mpn_bdiv_dbm1c.
2
3dnl  Copyright 2008, 2010 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       6-18
35C POWER4/PPC970       8.25
36C POWER5              8.5  fluctuating as function of n % 3
37C POWER6             15
38C POWER7              4.75
39
40C TODO
41C  * Nothing to do...
42
43C INPUT PARAMETERS
44define(`rp', `r3')
45define(`up', `r4')
46define(`n',  `r5')
47define(`bd', `r6')
48define(`cy', `r7')
49
50ASM_START()
51PROLOGUE(mpn_bdiv_dbm1c)
52          ld        r0, 0(r4)
53
54          rldicl.   r12, r5, 0,62
55          cmpldi    cr6, r12, 2
56          cmpldi    cr7, r5, 4
57          addi      r5, r5, 1
58          srwi      r5, r5, 2
59          mtctr     r5
60          beq       cr0, L(b00)
61          blt       cr6, L(b01)
62          beq       cr6, L(b10)
63
64          ALIGN(16)
65L(b11):   mulld     r5, r0, r6
66          mulhdu    r12, r0, r6
67          ld        r0, 8(r4)
68          addi      r4, r4, -24
69          addi      r3, r3, -24
70          b         L(3)
71
72          ALIGN(16)
73L(b00):   mulld     r9, r0, r6
74          mulhdu    r8, r0, r6
75          addi      r4, r4, -16
76          addi      r3, r3, -16
77          b         L(0)
78
79          ALIGN(16)
80L(b01):   mulld     r5, r0, r6
81          mulhdu    r12, r0, r6
82          addi      r3, r3, -8
83          ble       cr7, L(e1)
84          ld        r0, 8(r4)
85          addi      r4, r4, -8
86          b         L(1)
87
88          ALIGN(16)
89L(b10):   mulld     r9, r0, r6
90          mulhdu    r8, r0, r6
91          ble       cr7, L(e2)
92
93          ALIGN(16)
94L(top):   subfc     r11, r9, r7
95          ld        r10, 8(r4)
96          ld        r0, 16(r4)
97          subfe     r7, r8, r11
98          std       r11, 0(r3)
99          mulld     r5, r10, r6
100          mulhdu    r12, r10, r6
101L(1):     mulld     r9, r0, r6
102          mulhdu    r8, r0, r6
103          subfc     r11, r5, r7
104          subfe     r7, r12, r11
105          std       r11, 8(r3)
106L(0):     subfc     r11, r9, r7
107          ld        r10, 24(r4)
108          ld        r0, 32(r4)
109          subfe     r7, r8, r11
110          std       r11, 16(r3)
111          mulld     r5, r10, r6
112          mulhdu    r12, r10, r6
113L(3):     mulld     r9, r0, r6
114          mulhdu    r8, r0, r6
115          subfc     r11, r5, r7
116          subfe     r7, r12, r11
117          std       r11, 24(r3)
118          addi      r4, r4, 32
119          addi      r3, r3, 32
120          bdnz      L(top)
121
122L(e2):    ld        r10, 8(r4)
123          mulld     r5, r10, r6
124          mulhdu    r12, r10, r6
125          subfc     r11, r9, r7
126          subfe     r7, r8, r11
127          std       r11, 0(r3)
128L(e1):    subfc     r11, r5, r7
129          std       r11, 8(r3)
130          subfe     r3, r12, r11
131          blr
132EPILOGUE()
133