summaryrefslogtreecommitdiff
path: root/benchtests/scripts/import_bench.py
blob: 08681aafdc200f64f3b24a9156bce9cedf121adf (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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
#!/usr/bin/python
# Copyright (C) 2015-2020 Free Software Foundation, Inc.
# This file is part of the GNU C Library.
#
# The GNU C 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 2.1 of the License, or (at your option) any later version.
#
# The GNU C 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 C Library; if not, see
# <https://www.gnu.org/licenses/>.
"""Functions to import benchmark data and process it"""

import json
try:
    import jsonschema as validator
except ImportError:
    print('Could not find jsonschema module.')
    raise


def mean(lst):
    """Compute and return mean of numbers in a list

    The numpy average function has horrible performance, so implement our
    own mean function.

    Args:
        lst: The list of numbers to average.
    Return:
        The mean of members in the list.
    """
    return sum(lst) / len(lst)


def split_list(bench, func, var):
    """ Split the list into a smaller set of more distinct points

    Group together points such that the difference between the smallest
    point and the mean is less than 1/3rd of the mean.  This means that
    the mean is at most 1.5x the smallest member of that group.

    mean - xmin < mean / 3
    i.e. 2 * mean / 3 < xmin
    i.e. mean < 3 * xmin / 2

    For an evenly distributed group, the largest member will be less than
    twice the smallest member of the group.
    Derivation:

    An evenly distributed series would be xmin, xmin + d, xmin + 2d...

    mean = (2 * n * xmin + n * (n - 1) * d) / 2 * n
    and max element is xmin + (n - 1) * d

    Now, mean < 3 * xmin / 2

    3 * xmin > 2 * mean
    3 * xmin > (2 * n * xmin + n * (n - 1) * d) / n
    3 * n * xmin > 2 * n * xmin + n * (n - 1) * d
    n * xmin > n * (n - 1) * d
    xmin > (n - 1) * d
    2 * xmin > xmin + (n-1) * d
    2 * xmin > xmax

    Hence, proved.

    Similarly, it is trivial to prove that for a similar aggregation by using
    the maximum element, the maximum element in the group must be at most 4/3
    times the mean.

    Args:
        bench: The benchmark object
        func: The function name
        var: The function variant name
    """
    means = []
    lst = bench['functions'][func][var]['timings']
    last = len(lst) - 1
    while lst:
        for i in range(last + 1):
            avg = mean(lst[i:])
            if avg > 0.75 * lst[last]:
                means.insert(0, avg)
                lst = lst[:i]
                last = i - 1
                break
    bench['functions'][func][var]['timings'] = means


def do_for_all_timings(bench, callback):
    """Call a function for all timing objects for each function and its
    variants.

    Args:
        bench: The benchmark object
        callback: The callback function
    """
    for func in bench['functions'].keys():
        for k in bench['functions'][func].keys():
            if 'timings' not in bench['functions'][func][k].keys():
                continue

            callback(bench, func, k)


def compress_timings(points):
    """Club points with close enough values into a single mean value

    See split_list for details on how the clubbing is done.

    Args:
        points: The set of points.
    """
    do_for_all_timings(points, split_list)


def parse_bench(filename, schema_filename):
    """Parse the input file

    Parse and validate the json file containing the benchmark outputs.  Return
    the resulting object.
    Args:
        filename: Name of the benchmark output file.
    Return:
        The bench dictionary.
    """
    with open(schema_filename, 'r') as schemafile:
        schema = json.load(schemafile)
        with open(filename, 'r') as benchfile:
            bench = json.load(benchfile)
            validator.validate(bench, schema)
            do_for_all_timings(bench, lambda b, f, v:
                    b['functions'][f][v]['timings'].sort())
            return bench