blob: 187dc9bbe75211e56ee1700817243b9a076a393d (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
|
Copyright 2002, 2005 Free Software Foundation, Inc.
This file is part of the GNU MP Library.
The GNU MP Library is free software; you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation; either version 3 of the License, or (at your
option) any later version.
The GNU MP Library is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public License
along with the GNU MP Library. If not, see https://www.gnu.org/licenses/.
This directory contains assembly code for nails-enabled 21264. The code is not
very well optimized.
For addmul_N, as N grows larger, we could make multiple loads together, then do
about 3.3 i/c. 10 cycles after the last load, we can increase to 4 i/c. This
would surely allow addmul_4 to run at 2 c/l, but the same should be possible
also for addmul_3 and perhaps even addmul_2.
current fair best
Routine c/l unroll c/l unroll c/l i/c
mul_1 3.25 2.75 2.75 3.273
addmul_1 4.0 4 3.5 4 14 3.25 3.385
addmul_2 4.0 1 2.5 2 10 2.25 3.333
addmul_3 3.0 1 2.33 2 14 2 3.333
addmul_4 2.5 1 2.125 2 17 2 3.135
addmul_5 2 1 10
addmul_6 2 1 12
addmul_7 2 1 14
(The "best" column doesn't account for bookkeeping instructions and
thereby assumes infinite unrolling.)
Basecase usages:
1 addmul_1
2 addmul_2
3 addmul_3
4 addmul_4
5 addmul_3 + addmul_2 2.3998
6 addmul_4 + addmul_2
7 addmul_4 + addmul_3
|
