xref: /netbsd-src/external/lgpl3/gmp/dist/mpn/x86/pentium4/copyd.asm (revision 0a3071956a3a9fdebdbf7f338cf2d439b45fc728)
1dnl  Pentium-4 mpn_copyd -- copy limb vector, decrementing.
2
3dnl  Copyright 1999-2001 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
31
32dnl  The std/rep/movsl/cld is very slow for small blocks on pentium4.  Its
33dnl  startup time seems to be about 165 cycles.  It then needs 2.6 c/l.
34dnl  We therefore use an open-coded 2 c/l copying loop.
35
36dnl  Ultimately, we may want to use 64-bit movq or 128-bit movdqu in some
37dnl  nifty unrolled arrangement.  Clearly, that could reach much higher
38dnl  speeds, at least for large blocks.
39
40include(`../config.m4')
41
42
43defframe(PARAM_SIZE, 12)
44defframe(PARAM_SRC, 8)
45defframe(PARAM_DST,  4)
46
47	TEXT
48	ALIGN(8)
49
50PROLOGUE(mpn_copyd)
51deflit(`FRAME',0)
52
53	movl	PARAM_SIZE, %ecx
54
55	movl	PARAM_SRC, %eax
56	movl	PARAM_DST, %edx
57	movl	%ebx, PARAM_SIZE
58	addl	$-1, %ecx
59	js	L(end)
60
61L(loop):
62	movl	(%eax,%ecx,4), %ebx
63	movl	%ebx, (%edx,%ecx,4)
64	addl	$-1, %ecx
65
66	jns	L(loop)
67L(end):
68	movl	PARAM_SIZE, %ebx
69	ret
70
71EPILOGUE()
72