summaryrefslogtreecommitdiff
path: root/tools/opt-viewer/optrecord.py
blob: 2256b4dd24316b2c6882a154da0b33b649b4aa66 (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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
#!/usr/bin/env python2.7

from __future__ import print_function

import yaml
# Try to use the C parser.
try:
    from yaml import CLoader as Loader
except ImportError:
    print("For faster parsing, you may want to install libYAML for PyYAML")
    from yaml import Loader

import cgi
from collections import defaultdict
import fnmatch
import functools
from multiprocessing import Lock
import os, os.path
import subprocess
try:
    # The previously builtin function `intern()` was moved
    # to the `sys` module in Python 3.
    from sys import intern
except:
    pass

import optpmap

try:
    dict.iteritems
except AttributeError:
    # Python 3
    def itervalues(d):
        return iter(d.values())
    def iteritems(d):
        return iter(d.items())
else:
    # Python 2
    def itervalues(d):
        return d.itervalues()
    def iteritems(d):
        return d.iteritems()


def html_file_name(filename):
    return filename.replace('/', '_').replace('#', '_') + ".html"


def make_link(File, Line):
    return "\"{}#L{}\"".format(html_file_name(File), Line)


class Remark(yaml.YAMLObject):
    # Work-around for http://pyyaml.org/ticket/154.
    yaml_loader = Loader

    default_demangler = 'c++filt -n'
    demangler_proc = None

    @classmethod
    def set_demangler(cls, demangler):
        cls.demangler_proc = subprocess.Popen(demangler.split(), stdin=subprocess.PIPE, stdout=subprocess.PIPE)
        cls.demangler_lock = Lock()

    @classmethod
    def demangle(cls, name):
        with cls.demangler_lock:
            cls.demangler_proc.stdin.write((name + '\n').encode('utf-8'))
            cls.demangler_proc.stdin.flush()
            return cls.demangler_proc.stdout.readline().rstrip().decode('utf-8')

    # Intern all strings since we have lot of duplication across filenames,
    # remark text.
    #
    # Change Args from a list of dicts to a tuple of tuples.  This saves
    # memory in two ways.  One, a small tuple is significantly smaller than a
    # small dict.  Two, using tuple instead of list allows Args to be directly
    # used as part of the key (in Python only immutable types are hashable).
    def _reduce_memory(self):
        self.Pass = intern(self.Pass)
        self.Name = intern(self.Name)
        self.Function = intern(self.Function)

        def _reduce_memory_dict(old_dict):
            new_dict = dict()
            for (k, v) in iteritems(old_dict):
                if type(k) is str:
                    k = intern(k)

                if type(v) is str:
                    v = intern(v)
                elif type(v) is dict:
                    # This handles [{'Caller': ..., 'DebugLoc': { 'File': ... }}]
                    v = _reduce_memory_dict(v)
                new_dict[k] = v
            return tuple(new_dict.items())

        self.Args = tuple([_reduce_memory_dict(arg_dict) for arg_dict in self.Args])

    # The inverse operation of the dictonary-related memory optimization in
    # _reduce_memory_dict.  E.g.
    #     (('DebugLoc', (('File', ...) ... ))) -> [{'DebugLoc': {'File': ...} ....}]
    def recover_yaml_structure(self):
        def tuple_to_dict(t):
            d = dict()
            for (k, v) in t:
                if type(v) is tuple:
                    v = tuple_to_dict(v)
                d[k] = v
            return d

        self.Args = [tuple_to_dict(arg_tuple) for arg_tuple in self.Args]

    def canonicalize(self):
        if not hasattr(self, 'Hotness'):
            self.Hotness = 0
        if not hasattr(self, 'Args'):
            self.Args = []
        self._reduce_memory()

    @property
    def File(self):
        return self.DebugLoc['File']

    @property
    def Line(self):
        return int(self.DebugLoc['Line'])

    @property
    def Column(self):
        return self.DebugLoc['Column']

    @property
    def DebugLocString(self):
        return "{}:{}:{}".format(self.File, self.Line, self.Column)

    @property
    def DemangledFunctionName(self):
        return self.demangle(self.Function)

    @property
    def Link(self):
        return make_link(self.File, self.Line)

    def getArgString(self, mapping):
        mapping = dict(list(mapping))
        dl = mapping.get('DebugLoc')
        if dl:
            del mapping['DebugLoc']

        assert(len(mapping) == 1)
        (key, value) = list(mapping.items())[0]

        if key == 'Caller' or key == 'Callee':
            value = cgi.escape(self.demangle(value))

        if dl and key != 'Caller':
            dl_dict = dict(list(dl))
            return "<a href={}>{}</a>".format(
                make_link(dl_dict['File'], dl_dict['Line']), value)
        else:
            return value

    # Return a cached dictionary for the arguments.  The key for each entry is
    # the argument key (e.g. 'Callee' for inlining remarks.  The value is a
    # list containing the value (e.g. for 'Callee' the function) and
    # optionally a DebugLoc.
    def getArgDict(self):
        if hasattr(self, 'ArgDict'):
            return self.ArgDict
        self.ArgDict = {}
        for arg in self.Args:
            if len(arg) == 2:
                if arg[0][0] == 'DebugLoc':
                    dbgidx = 0
                else:
                    assert(arg[1][0] == 'DebugLoc')
                    dbgidx = 1

                key = arg[1 - dbgidx][0]
                entry = (arg[1 - dbgidx][1], arg[dbgidx][1])
            else:
                arg = arg[0]
                key = arg[0]
                entry = (arg[1], )

            self.ArgDict[key] = entry
        return self.ArgDict

    def getDiffPrefix(self):
        if hasattr(self, 'Added'):
            if self.Added:
                return '+'
            else:
                return '-'
        return ''

    @property
    def PassWithDiffPrefix(self):
        return self.getDiffPrefix() + self.Pass

    @property
    def message(self):
        # Args is a list of mappings (dictionaries)
        values = [self.getArgString(mapping) for mapping in self.Args]
        return "".join(values)

    @property
    def RelativeHotness(self):
        if self.max_hotness:
            return "{0:.2f}%".format(self.Hotness * 100. / self.max_hotness)
        else:
            return ''

    @property
    def key(self):
        return (self.__class__, self.PassWithDiffPrefix, self.Name, self.File,
                self.Line, self.Column, self.Function, self.Args)

    def __hash__(self):
        return hash(self.key)

    def __eq__(self, other):
        return self.key == other.key

    def __repr__(self):
        return str(self.key)


class Analysis(Remark):
    yaml_tag = '!Analysis'

    @property
    def color(self):
        return "white"


class AnalysisFPCommute(Analysis):
    yaml_tag = '!AnalysisFPCommute'


class AnalysisAliasing(Analysis):
    yaml_tag = '!AnalysisAliasing'


class Passed(Remark):
    yaml_tag = '!Passed'

    @property
    def color(self):
        return "green"


class Missed(Remark):
    yaml_tag = '!Missed'

    @property
    def color(self):
        return "red"


def get_remarks(input_file):
    max_hotness = 0
    all_remarks = dict()
    file_remarks = defaultdict(functools.partial(defaultdict, list))

    with open(input_file) as f:
        docs = yaml.load_all(f, Loader=Loader)
        for remark in docs:
            remark.canonicalize()
            # Avoid remarks withoug debug location or if they are duplicated
            if not hasattr(remark, 'DebugLoc') or remark.key in all_remarks:
                continue
            all_remarks[remark.key] = remark

            file_remarks[remark.File][remark.Line].append(remark)

            # If we're reading a back a diff yaml file, max_hotness is already
            # captured which may actually be less than the max hotness found
            # in the file.
            if hasattr(remark, 'max_hotness'):
                max_hotness = remark.max_hotness
            max_hotness = max(max_hotness, remark.Hotness)

    return max_hotness, all_remarks, file_remarks


def gather_results(filenames, num_jobs, should_print_progress):
    if should_print_progress:
        print('Reading YAML files...')
    if not Remark.demangler_proc:
        Remark.set_demangler(Remark.default_demangler)
    remarks = optpmap.pmap(
        get_remarks, filenames, num_jobs, should_print_progress)
    max_hotness = max(entry[0] for entry in remarks)

    def merge_file_remarks(file_remarks_job, all_remarks, merged):
        for filename, d in iteritems(file_remarks_job):
            for line, remarks in iteritems(d):
                for remark in remarks:
                    # Bring max_hotness into the remarks so that
                    # RelativeHotness does not depend on an external global.
                    remark.max_hotness = max_hotness
                    if remark.key not in all_remarks:
                        merged[filename][line].append(remark)

    all_remarks = dict()
    file_remarks = defaultdict(functools.partial(defaultdict, list))
    for _, all_remarks_job, file_remarks_job in remarks:
        merge_file_remarks(file_remarks_job, all_remarks, file_remarks)
        all_remarks.update(all_remarks_job)

    return all_remarks, file_remarks, max_hotness != 0


def find_opt_files(*dirs_or_files):
    all = []
    for dir_or_file in dirs_or_files:
        if os.path.isfile(dir_or_file):
            all.append(dir_or_file)
        else:
            for dir, subdirs, files in os.walk(dir_or_file):
                # Exclude mounted directories and symlinks (os.walk default).
                subdirs[:] = [d for d in subdirs
                              if not os.path.ismount(os.path.join(dir, d))]
                for file in files:
                    if fnmatch.fnmatch(file, "*.opt.yaml"):
                        all.append(os.path.join(dir, file))
    return all