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
| from __future__ import print_function
import re
import string
import subprocess
import sys
import copy
if sys.version_info[0] > 2:
class string:
expandtabs = str.expandtabs
else:
import string
##### Common utilities for update_*test_checks.py
def should_add_line_to_output(input_line, prefix_set):
# Skip any blank comment lines in the IR.
if input_line.strip() == ';':
return False
# Skip any blank lines in the IR.
#if input_line.strip() == '':
# return False
# And skip any CHECK lines. We're building our own.
m = CHECK_RE.match(input_line)
if m and m.group(1) in prefix_set:
return False
return True
# Invoke the tool that is being tested.
def invoke_tool(exe, cmd_args, ir):
with open(ir) as ir_file:
# TODO Remove the str form which is used by update_test_checks.py and
# update_llc_test_checks.py
# The safer list form is used by update_cc_test_checks.py
if isinstance(cmd_args, list):
stdout = subprocess.check_output([exe] + cmd_args, stdin=ir_file)
else:
stdout = subprocess.check_output(exe + ' ' + cmd_args,
shell=True, stdin=ir_file)
if sys.version_info[0] > 2:
stdout = stdout.decode()
# Fix line endings to unix CR style.
return stdout.replace('\r\n', '\n')
##### LLVM IR parser
RUN_LINE_RE = re.compile('^\s*[;#]\s*RUN:\s*(.*)$')
CHECK_PREFIX_RE = re.compile('--?check-prefix(?:es)?[= ](\S+)')
PREFIX_RE = re.compile('^[a-zA-Z0-9_-]+$')
CHECK_RE = re.compile(r'^\s*[;#]\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
OPT_FUNCTION_RE = re.compile(
r'^\s*define\s+(?:internal\s+)?[^@]*@(?P<func>[\w-]+?)\s*\('
r'(\s+)?[^)]*[^{]*\{\n(?P<body>.*?)^\}$',
flags=(re.M | re.S))
ANALYZE_FUNCTION_RE = re.compile(
r'^\s*\'(?P<analysis>[\w\s-]+?)\'\s+for\s+function\s+\'(?P<func>[\w-]+?)\':'
r'\s*\n(?P<body>.*)$',
flags=(re.X | re.S))
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@(\w+)\s*\(')
TRIPLE_IR_RE = re.compile(r'^\s*target\s+triple\s*=\s*"([^"]+)"$')
TRIPLE_ARG_RE = re.compile(r'-mtriple[= ]([^ ]+)')
MARCH_ARG_RE = re.compile(r'-march[= ]([^ ]+)')
SCRUB_LEADING_WHITESPACE_RE = re.compile(r'^(\s+)')
SCRUB_WHITESPACE_RE = re.compile(r'(?!^(| \w))[ \t]+', flags=re.M)
SCRUB_TRAILING_WHITESPACE_RE = re.compile(r'[ \t]+$', flags=re.M)
SCRUB_KILL_COMMENT_RE = re.compile(r'^ *#+ +kill:.*\n')
SCRUB_LOOP_COMMENT_RE = re.compile(
r'# =>This Inner Loop Header:.*|# in Loop:.*', flags=re.M)
def error(msg, test_file=None):
if test_file:
msg = '{}: {}'.format(msg, test_file)
print('ERROR: {}'.format(msg), file=sys.stderr)
def warn(msg, test_file=None):
if test_file:
msg = '{}: {}'.format(msg, test_file)
print('WARNING: {}'.format(msg), file=sys.stderr)
def scrub_body(body):
# Scrub runs of whitespace out of the assembly, but leave the leading
# whitespace in place.
body = SCRUB_WHITESPACE_RE.sub(r' ', body)
# Expand the tabs used for indentation.
body = string.expandtabs(body, 2)
# Strip trailing whitespace.
body = SCRUB_TRAILING_WHITESPACE_RE.sub(r'', body)
return body
def do_scrub(body, scrubber, scrubber_args, extra):
if scrubber_args:
local_args = copy.deepcopy(scrubber_args)
local_args[0].extra_scrub = extra
return scrubber(body, *local_args)
return scrubber(body, *scrubber_args)
# Build up a dictionary of all the function bodies.
class function_body(object):
def __init__(self, string, extra):
self.scrub = string
self.extrascrub = extra
def __str__(self):
return self.scrub
def build_function_body_dictionary(function_re, scrubber, scrubber_args, raw_tool_output, prefixes, func_dict, verbose):
for m in function_re.finditer(raw_tool_output):
if not m:
continue
func = m.group('func')
body = m.group('body')
scrubbed_body = do_scrub(body, scrubber, scrubber_args, extra = False)
scrubbed_extra = do_scrub(body, scrubber, scrubber_args, extra = True)
if 'analysis' in m.groupdict():
analysis = m.group('analysis')
if analysis.lower() != 'cost model analysis':
warn('Unsupported analysis mode: %r!' % (analysis,))
if func.startswith('stress'):
# We only use the last line of the function body for stress tests.
scrubbed_body = '\n'.join(scrubbed_body.splitlines()[-1:])
if verbose:
print('Processing function: ' + func, file=sys.stderr)
for l in scrubbed_body.splitlines():
print(' ' + l, file=sys.stderr)
for prefix in prefixes:
if func in func_dict[prefix] and str(func_dict[prefix][func]) != scrubbed_body:
if func_dict[prefix][func] and func_dict[prefix][func].extrascrub == scrubbed_extra:
func_dict[prefix][func].scrub = scrubbed_extra
continue
else:
if prefix == prefixes[-1]:
warn('Found conflicting asm under the same prefix: %r!' % (prefix,))
else:
func_dict[prefix][func] = None
continue
func_dict[prefix][func] = function_body(scrubbed_body, scrubbed_extra)
##### Generator of LLVM IR CHECK lines
SCRUB_IR_COMMENT_RE = re.compile(r'\s*;.*')
# Match things that look at identifiers, but only if they are followed by
# spaces, commas, paren, or end of the string
IR_VALUE_RE = re.compile(r'(\s+)%([\w\.\-]+?)([,\s\(\)]|\Z)')
# Create a FileCheck variable name based on an IR name.
def get_value_name(var):
if var.isdigit():
var = 'TMP' + var
var = var.replace('.', '_')
var = var.replace('-', '_')
return var.upper()
# Create a FileCheck variable from regex.
def get_value_definition(var):
return '[[' + get_value_name(var) + ':%.*]]'
# Use a FileCheck variable.
def get_value_use(var):
return '[[' + get_value_name(var) + ']]'
# Replace IR value defs and uses with FileCheck variables.
def genericize_check_lines(lines, is_analyze):
# This gets called for each match that occurs in
# a line. We transform variables we haven't seen
# into defs, and variables we have seen into uses.
def transform_line_vars(match):
var = match.group(2)
if var in vars_seen:
rv = get_value_use(var)
else:
vars_seen.add(var)
rv = get_value_definition(var)
# re.sub replaces the entire regex match
# with whatever you return, so we have
# to make sure to hand it back everything
# including the commas and spaces.
return match.group(1) + rv + match.group(3)
vars_seen = set()
lines_with_def = []
for i, line in enumerate(lines):
# An IR variable named '%.' matches the FileCheck regex string.
line = line.replace('%.', '%dot')
# Ignore any comments, since the check lines will too.
scrubbed_line = SCRUB_IR_COMMENT_RE.sub(r'', line)
if is_analyze:
lines[i] = scrubbed_line
else:
lines[i] = IR_VALUE_RE.sub(transform_line_vars, scrubbed_line)
return lines
def add_checks(output_lines, comment_marker, prefix_list, func_dict, func_name, check_label_format, is_asm, is_analyze):
printed_prefixes = []
for p in prefix_list:
checkprefixes = p[0]
for checkprefix in checkprefixes:
if checkprefix in printed_prefixes:
break
# TODO func_dict[checkprefix] may be None, '' or not exist.
# Fix the call sites.
if func_name not in func_dict[checkprefix] or not func_dict[checkprefix][func_name]:
continue
# Add some space between different check prefixes, but not after the last
# check line (before the test code).
if is_asm:
if len(printed_prefixes) != 0:
output_lines.append(comment_marker)
printed_prefixes.append(checkprefix)
output_lines.append(check_label_format % (checkprefix, func_name))
func_body = str(func_dict[checkprefix][func_name]).splitlines()
# For ASM output, just emit the check lines.
if is_asm:
output_lines.append('%s %s: %s' % (comment_marker, checkprefix, func_body[0]))
for func_line in func_body[1:]:
output_lines.append('%s %s-NEXT: %s' % (comment_marker, checkprefix, func_line))
break
# For IR output, change all defs to FileCheck variables, so we're immune
# to variable naming fashions.
func_body = genericize_check_lines(func_body, is_analyze)
# This could be selectively enabled with an optional invocation argument.
# Disabled for now: better to check everything. Be safe rather than sorry.
# Handle the first line of the function body as a special case because
# it's often just noise (a useless asm comment or entry label).
#if func_body[0].startswith("#") or func_body[0].startswith("entry:"):
# is_blank_line = True
#else:
# output_lines.append('%s %s: %s' % (comment_marker, checkprefix, func_body[0]))
# is_blank_line = False
is_blank_line = False
for func_line in func_body:
if func_line.strip() == '':
is_blank_line = True
continue
# Do not waste time checking IR comments.
func_line = SCRUB_IR_COMMENT_RE.sub(r'', func_line)
# Skip blank lines instead of checking them.
if is_blank_line:
output_lines.append('{} {}: {}'.format(
comment_marker, checkprefix, func_line))
else:
output_lines.append('{} {}-NEXT: {}'.format(
comment_marker, checkprefix, func_line))
is_blank_line = False
# Add space between different check prefixes and also before the first
# line of code in the test function.
output_lines.append(comment_marker)
break
def add_ir_checks(output_lines, comment_marker, prefix_list, func_dict,
func_name, preserve_names):
# Label format is based on IR string.
check_label_format = '{} %s-LABEL: @%s('.format(comment_marker)
add_checks(output_lines, comment_marker, prefix_list, func_dict, func_name,
check_label_format, False, preserve_names)
def add_analyze_checks(output_lines, comment_marker, prefix_list, func_dict, func_name):
check_label_format = '{} %s-LABEL: \'%s\''.format(comment_marker)
add_checks(output_lines, comment_marker, prefix_list, func_dict, func_name, check_label_format, False, True)
def check_prefix(prefix):
if not PREFIX_RE.match(prefix):
hint = ""
if ',' in prefix:
hint = " Did you mean '--check-prefixes=" + prefix + "'?"
warn(("Supplied prefix '%s' is invalid. Prefix must contain only alphanumeric characters, hyphens and underscores." + hint) %
(prefix))
def verify_filecheck_prefixes(fc_cmd):
fc_cmd_parts = fc_cmd.split()
for part in fc_cmd_parts:
if "check-prefix=" in part:
prefix = part.split('=', 1)[1]
check_prefix(prefix)
elif "check-prefixes=" in part:
prefixes = part.split('=', 1)[1].split(',')
for prefix in prefixes:
check_prefix(prefix)
if prefixes.count(prefix) > 1:
warn("Supplied prefix '%s' is not unique in the prefix list." % (prefix,))
|