reorganize llc checks script to allow more flexibility, part 2; NFCI

The goal is to enhance this script to be used with opt and clang:
Break 'main' into functions and change variable names to be more
generic because we want to handle more than x86 asm output.

llvm-svn: 264307
This commit is contained in:
Sanjay Patel 2016-03-24 17:15:42 +00:00
parent fe26864440
commit f3c5f46ed1

View File

@ -9,6 +9,8 @@ a single test function.
import argparse
import itertools
# Could be used to advertise this file's name ("autogenerated_note").
# import os
import string
import subprocess
import sys
@ -40,7 +42,7 @@ SCRUB_KILL_COMMENT_RE = re.compile(r'^ *#+ +kill:.*\n')
RUN_LINE_RE = re.compile('^\s*;\s*RUN:\s*(.*)$')
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@(\w+)\s*\(')
ASM_FUNCTION_RE = re.compile(
r'^_?(?P<f>[^:]+):[ \t]*#+[ \t]*@(?P=f)\n[^:]*?'
r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n[^:]*?'
r'(?P<body>^##?[ \t]+[^:]+:.*?)\s*'
r'^\s*(?:[^:\n]+?:\s*\n\s*\.size|\.cfi_endproc|\.globl|\.comm|\.(?:sub)?section)',
flags=(re.M | re.S))
@ -67,6 +69,70 @@ def scrub_asm(asm):
return asm
# Build up a dictionary of all the function bodies.
def build_function_body_dictionary(raw_tool_output, prefixes, func_dict, verbose):
for m in ASM_FUNCTION_RE.finditer(raw_tool_output):
if not m:
continue
func = m.group('func')
scrubbed_body = scrub_asm(m.group('body'))
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 >>sys.stderr, 'Processing function: ' + func
for l in scrubbed_body.splitlines():
print >>sys.stderr, ' ' + l
for prefix in prefixes:
if func in func_dict[prefix] and func_dict[prefix][func] != scrubbed_body:
if prefix == prefixes[-1]:
print >>sys.stderr, ('WARNING: Found conflicting asm under the '
'same prefix: %r!' % (prefix,))
else:
func_dict[prefix][func] = None
continue
func_dict[prefix][func] = scrubbed_body
def add_checks(output_lines, prefix_list, func_dict, func_name):
printed_prefixes = []
for checkprefixes, _ in prefix_list:
for checkprefix in checkprefixes:
if checkprefix in printed_prefixes:
break
if not func_dict[checkprefix][func_name]:
continue
# Add some space between different check prefixes.
if len(printed_prefixes) != 0:
output_lines.append(';')
printed_prefixes.append(checkprefix)
output_lines.append('; %s-LABEL: %s:' % (checkprefix, func_name))
func_body = func_dict[checkprefix][func_name].splitlines()
output_lines.append('; %s: %s' % (checkprefix, func_body[0]))
for func_line in func_body[1:]:
output_lines.append('; %s-NEXT: %s' % (checkprefix, func_line))
# Add space between different check prefixes and the first line of code.
# output_lines.append(';')
break
return output_lines
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
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('-v', '--verbose', action='store_true',
@ -78,23 +144,25 @@ def main():
parser.add_argument('tests', nargs='+')
args = parser.parse_args()
# FIXME: we don't need to hardcode this name.
autogenerated_note = ('; NOTE: Assertions have been autogenerated by '
'utils/update_llc_test_checks.py')
# + os.path.basename(__file__))
for test in args.tests:
if args.verbose:
print >>sys.stderr, 'Scanning for RUN lines in test file: %s' % (test,)
with open(test) as f:
test_lines = [l.rstrip() for l in f]
input_lines = [l.rstrip() for l in f]
run_lines = [m.group(1)
for m in [RUN_LINE_RE.match(l) for l in test_lines] if m]
for m in [RUN_LINE_RE.match(l) for l in input_lines] if m]
if args.verbose:
print >>sys.stderr, 'Found %d RUN lines:' % (len(run_lines),)
for l in run_lines:
print >>sys.stderr, ' RUN: ' + l
checks = []
prefix_list = []
for l in run_lines:
(llc_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
if not llc_cmd.startswith('llc '):
@ -115,96 +183,59 @@ def main():
# FIXME: We should use multiple check prefixes to common check lines. For
# now, we just ignore all but the last.
checks.append((check_prefixes, llc_cmd_args))
prefix_list.append((check_prefixes, llc_cmd_args))
asm = {}
for prefixes, _ in checks:
func_dict = {}
for prefixes, _ in prefix_list:
for prefix in prefixes:
asm.update({prefix: dict()})
for prefixes, llc_args in checks:
func_dict.update({prefix: dict()})
for prefixes, llc_args in prefix_list:
if args.verbose:
print >>sys.stderr, 'Extracted LLC cmd: llc ' + llc_args
print >>sys.stderr, 'Extracted FileCheck prefixes: ' + str(prefixes)
raw_asm = llc(args, llc_args, test)
# Build up a dictionary of all the function bodies.
for m in ASM_FUNCTION_RE.finditer(raw_asm):
if not m:
continue
f = m.group('f')
f_asm = scrub_asm(m.group('body'))
if f.startswith('stress'):
# We only use the last line of the asm for stress tests.
f_asm = '\n'.join(f_asm.splitlines()[-1:])
if args.verbose:
print >>sys.stderr, 'Processing asm for function: ' + f
for l in f_asm.splitlines():
print >>sys.stderr, ' ' + l
for prefix in prefixes:
if f in asm[prefix] and asm[prefix][f] != f_asm:
if prefix == prefixes[-1]:
print >>sys.stderr, ('WARNING: Found conflicting asm under the '
'same prefix: %r!' % (prefix,))
else:
asm[prefix][f] = None
continue
asm[prefix][f] = f_asm
raw_tool_output = llc(args, llc_args, test)
build_function_body_dictionary(raw_tool_output, prefixes, func_dict, args.verbose)
is_in_function = False
is_in_function_start = False
prefix_set = set([prefix for prefixes, _ in checks for prefix in prefixes])
prefix_set = set([prefix for prefixes, _ in prefix_list for prefix in prefixes])
if args.verbose:
print >>sys.stderr, 'Rewriting FileCheck prefixes: %s' % (prefix_set,)
fixed_lines = []
fixed_lines.append(autogenerated_note)
output_lines = []
output_lines.append(autogenerated_note)
for l in test_lines:
for input_line in input_lines:
if is_in_function_start:
if l.lstrip().startswith(';'):
m = CHECK_RE.match(l)
if input_line == '':
continue
if input_line.lstrip().startswith(';'):
m = CHECK_RE.match(input_line)
if not m or m.group(1) not in prefix_set:
fixed_lines.append(l)
output_lines.append(input_line)
continue
# Print out the various check lines here
printed_prefixes = []
for prefixes, _ in checks:
for prefix in prefixes:
if prefix in printed_prefixes:
break
if not asm[prefix][name]:
continue
if len(printed_prefixes) != 0:
fixed_lines.append(';')
printed_prefixes.append(prefix)
fixed_lines.append('; %s-LABEL: %s:' % (prefix, name))
asm_lines = asm[prefix][name].splitlines()
fixed_lines.append('; %s: %s' % (prefix, asm_lines[0]))
for asm_line in asm_lines[1:]:
fixed_lines.append('; %s-NEXT: %s' % (prefix, asm_line))
break
# Print out the various check lines here.
output_lines = add_checks(output_lines, prefix_list, func_dict, name)
is_in_function_start = False
if is_in_function:
# Skip any blank comment lines in the IR.
if l.strip() == ';':
if should_add_line_to_output(input_line, prefix_set) == True:
# This input line of the function body will go as-is into the output.
output_lines.append(input_line)
else:
continue
# And skip any CHECK lines. We'll build our own.
m = CHECK_RE.match(l)
if m and m.group(1) in prefix_set:
continue
# Collect the remaining lines in the function body and look for the end
# of the function.
fixed_lines.append(l)
if l.strip() == '}':
if input_line.strip() == '}':
is_in_function = False
continue
if l == autogenerated_note:
if input_line == autogenerated_note:
continue
fixed_lines.append(l)
m = IR_FUNCTION_RE.match(l)
# If it's outside a function, it just gets copied to the output.
output_lines.append(input_line)
m = IR_FUNCTION_RE.match(input_line)
if not m:
continue
name = m.group(1)
@ -214,10 +245,10 @@ def main():
is_in_function = is_in_function_start = True
if args.verbose:
print>>sys.stderr, 'Writing %d fixed lines to %s...' % (
len(fixed_lines), test)
print>>sys.stderr, 'Writing %d lines to %s...' % (len(output_lines), test)
with open(test, 'wb') as f:
f.writelines([l + '\n' for l in fixed_lines])
f.writelines([l + '\n' for l in output_lines])
if __name__ == '__main__':