1Copyright 2002, 2005 Free Software Foundation, Inc.
2
3This file is part of the GNU MP Library.
4
5The GNU MP Library is free software; you can redistribute it and/or modify
6it under the terms of either:
7
8  * the GNU Lesser General Public License as published by the Free
9    Software Foundation; either version 3 of the License, or (at your
10    option) any later version.
11
12or
13
14  * the GNU General Public License as published by the Free Software
15    Foundation; either version 2 of the License, or (at your option) any
16    later version.
17
18or both in parallel, as here.
19
20The GNU MP Library is distributed in the hope that it will be useful, but
21WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
22or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
23for more details.
24
25You should have received copies of the GNU General Public License and the
26GNU Lesser General Public License along with the GNU MP Library.  If not,
27see https://www.gnu.org/licenses/.
28
29
30
31
32
33                    POWERPC 32-BIT MPN SUBROUTINES
34
35
36This directory contains mpn functions for various 32-bit PowerPC chips.
37
38
39CODE ORGANIZATION
40
41	directory	  used for
42	================================================
43	powerpc           generic, 604, 604e, 744x, 745x
44	powerpc/750       740, 750, 7400, 7410
45
46
47The top-level powerpc directory is currently mostly aimed at 604/604e but
48should be reasonable on all powerpcs.
49
50
51
52STATUS
53
54The code is quite well optimized for the 604e, other chips have had less
55attention.
56
57Altivec SIMD available in 74xx might hold some promise, but unfortunately
58GMP only guarantees 32-bit data alignment, so there's lots of fiddling
59around with partial operations at the start and end of limb vectors.  A
60128-bit limb would be a novel idea, but is unlikely to be practical, since
61it would have to work with ordinary +, -, * etc in the C code.
62
63Also, Altivec isn't very well suited for the GMP multiplication needs.
64Using floating-point based multiplication has much better better performance
65potential for all current powerpcs, both the ones with slow integer multiply
66units (603, 740, 750, 7400, 7410) and those with fast (604, 604e, 744x,
67745x).  This is because all powerpcs do some level of pipelining in the FPU:
68
69603 and 750 can sustain one fmadd every 2nd cycle.
70604 and 604e can sustain one fmadd per cycle.
717400 and 7410 can sustain 3 fmadd in 4 cycles.
72744x and 745x can sustain 4 fmadd in 5 cycles.
73
74
75
76REGISTER NAMES
77
78The normal powerpc convention is to give registers as plain numbers, like
79"mtctr 6", but on Apple MacOS X (powerpc*-*-rhapsody* and
80powerpc*-*-darwin*) the assembler demands an "r" like "mtctr r6".  Note
81however when register 0 in an instruction means a literal zero the "r" is
82omitted, for instance "lwzx r6,0,r7".
83
84The GMP code uses the "r" forms, powerpc-defs.m4 transforms them to plain
85numbers according to what GMP_ASM_POWERPC_R_REGISTERS finds is needed.
86(Note that this style isn't fully general, as the identifier r4 and the
87register r4 will not be distinguishable on some systems.  However, this is
88not a problem for the limited GMP assembly usage.)
89
90
91
92GLOBAL REFERENCES
93
94Linux non-PIC
95	lis	9, __gmp_binvert_limb_table@ha
96	rlwinm	11, 5, 31, 25, 31
97	la	9, __gmp_binvert_limb_table@l(9)
98	lbzx	11, 9, 11
99
100Linux PIC (FIXME)
101.LCL0:
102	.long .LCTOC1-.LCF0
103	bcl	20, 31, .LCF0
104.LCF0:
105	mflr	30
106	lwz	7, .LCL0-.LCF0(30)
107	add	30, 7, 30
108	lwz	11, .LC0-.LCTOC1(30)
109	rlwinm	3, 5, 31, 25, 31
110	lbzx	7, 11, 3
111
112AIX (always PIC)
113LC..0:
114	.tc __gmp_binvert_limb_table[TC],__gmp_binvert_limb_table[RW]
115	lwz	9, LC..0(2)
116	rlwinm	0, 5, 31, 25, 31
117	lbzx	0, 9, 0
118
119Darwin (non-PIC)
120	lis	r2, ha16(___gmp_binvert_limb_table)
121	rlwinm	r9, r5, 31, 25, 31
122	la	r2, lo16(___gmp_binvert_limb_table)(r2)
123	lbzx	r0, r2, r9
124Darwin (PIC)
125	mflr	r0
126	bcl	20, 31, L0001$pb
127L0001$pb:
128	mflr	r7
129	mtlr	r0
130	addis	r2, r7, ha16(L___gmp_binvert_limb_table$non_lazy_ptr-L0001$pb)
131	rlwinm	r9, r5, 31, 25, 31
132	lwz	r2, lo16(L___gmp_binvert_limb_table$non_lazy_ptr-L0001$pb)(r2)
133	lbzx	r0, r2, r9
134------
135	.non_lazy_symbol_pointer
136L___gmp_binvert_limb_table$non_lazy_ptr:
137	.indirect_symbol ___gmp_binvert_limb_table
138	.long	0
139	.subsections_via_symbols
140
141
142For GNU/Linux and Darwin, we might want to duplicate __gmp_binvert_limb_table
143into the text section in this file.  We should thus be able to reach it like
144this:
145
146	blr	L0
147L0:	mflr	r2
148	rlwinm	r9, r5, 31, 25, 31
149	addi	r9, r9, lo16(local_binvert_table-L0)
150	lbzx	r0, r2, r9
151
152
153
154REFERENCES
155
156PowerPC Microprocessor Family: The Programming Environments for 32-bit
157Microprocessors, IBM document G522-0290-01, 2000.
158
159PowerPC 604e RISC Microprocessor User's Manual with Supplement for PowerPC
160604 Microprocessor, IBM document G552-0330-00, Freescale document
161MPC604EUM/AD, 3/1998.
162
163MPC7410/MPC7400 RISC Microprocessor User's Manual, Freescale document
164MPC7400UM/D, rev 1, 11/2002.
165
166MPC7450 RISC Microprocessor Family Reference Manual, Freescale document
167MPC7450UM, rev 5, 1/2005.
168
169The above are available online from
170
171	http://www.ibm.com/chips/techlib/techlib.nsf/productfamilies/PowerPC
172	http://www.freescale.com/PowerPC
173
174
175
176----------------
177Local variables:
178mode: text
179fill-column: 76
180End:
181