Пример #1
0
def config():
    parser = argparse.ArgumentParser(
        description=__doc__, formatter_class=argparse.RawTextHelpFormatter)
    parser.add_argument('--llvm-bin', help='llvm $prefix/bin path')
    parser.add_argument('--clang',
                        help='"clang" executable, defaults to $llvm_bin/clang')
    parser.add_argument(
        '--clang-args',
        help='Space-separated extra args to clang, e.g. --clang-args=-v')
    parser.add_argument('--opt',
                        help='"opt" executable, defaults to $llvm_bin/opt')
    parser.add_argument(
        '--functions',
        nargs='+',
        help='A list of function name regexes. '
        'If specified, update CHECK lines for functions matching at least one regex'
    )
    parser.add_argument(
        '--x86_extra_scrub',
        action='store_true',
        help=
        'Use more regex for x86 matching to reduce diffs between various subtargets'
    )
    parser.add_argument(
        '--function-signature',
        action='store_true',
        help='Keep function signature information around for the check line')
    parser.add_argument('tests', nargs='+')
    args = common.parse_commandline_args(parser)
    args.clang_args = shlex.split(args.clang_args or '')

    if args.clang is None:
        if args.llvm_bin is None:
            args.clang = 'clang'
        else:
            args.clang = os.path.join(args.llvm_bin, 'clang')
    if not distutils.spawn.find_executable(args.clang):
        print('Please specify --llvm-bin or --clang', file=sys.stderr)
        sys.exit(1)

    # Determine the builtin includes directory so that we can update tests that
    # depend on the builtin headers. See get_clang_builtin_include_dir() and
    # use_clang() in llvm/utils/lit/lit/llvm/config.py.
    try:
        builtin_include_dir = subprocess.check_output(
            [args.clang, '-print-file-name=include']).decode().strip()
        SUBST['%clang_cc1'] = [
            '-cc1', '-internal-isystem', builtin_include_dir, '-nostdsysteminc'
        ]
    except subprocess.CalledProcessError:
        common.warn('Could not determine clang builtins directory, some tests '
                    'might not update correctly.')

    if args.opt is None:
        if args.llvm_bin is None:
            args.opt = 'opt'
        else:
            args.opt = os.path.join(args.llvm_bin, 'opt')
    if not distutils.spawn.find_executable(args.opt):
        # Many uses of this tool will not need an opt binary, because it's only
        # needed for updating a test that runs clang | opt | FileCheck. So we
        # defer this error message until we find that opt is actually needed.
        args.opt = None

    return args
Пример #2
0
def main():
    from argparse import RawTextHelpFormatter
    parser = argparse.ArgumentParser(description=__doc__,
                                     formatter_class=RawTextHelpFormatter)
    parser.add_argument('--opt-binary',
                        default='opt',
                        help='The opt binary used to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument('-p',
                        '--preserve-names',
                        action='store_true',
                        help='Do not scrub IR names')
    parser.add_argument(
        '--function-signature',
        action='store_true',
        help='Keep function signature information around for the check line')
    parser.add_argument(
        '--scrub-attributes',
        action='store_true',
        help='Remove attribute annotations (#0) from the end of check line')
    parser.add_argument('--check-attributes',
                        action='store_true',
                        help='Check "Function Attributes" for functions')
    parser.add_argument(
        '--check-globals',
        action='store_true',
        help=
        'Check global entries (global variables, metadata, attribute sets, ...) for functions'
    )
    parser.add_argument('tests', nargs='+')
    initial_args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)
    opt_basename = os.path.basename(initial_args.opt_binary)
    if not re.match(r'^opt(-\d+)?(\.exe)?$', opt_basename):
        common.error('Unexpected opt name: ' + opt_basename)
        sys.exit(1)
    opt_basename = 'opt'

    for ti in common.itertests(initial_args.tests,
                               parser,
                               script_name='utils/' + script_name):
        # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces
        if ti.args.scrub_attributes:
            common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE
        else:
            common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE

        prefix_list = []
        for l in ti.run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            commands = [cmd.strip() for cmd in l.split('|')]
            assert len(commands) >= 2
            preprocess_cmd = None
            if len(commands) > 2:
                preprocess_cmd = " | ".join(commands[:-2])
            tool_cmd = commands[-2]
            filecheck_cmd = commands[-1]
            common.verify_filecheck_prefixes(filecheck_cmd)
            if not tool_cmd.startswith(opt_basename + ' '):
                common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l))
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            tool_cmd_args = tool_cmd[len(opt_basename):].strip()
            tool_cmd_args = tool_cmd_args.replace('< %s',
                                                  '').replace('%s',
                                                              '').strip()

            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            prefix_list.append((check_prefixes, tool_cmd_args, preprocess_cmd))

        global_vars_seen_dict = {}
        builder = common.FunctionTestBuilder(run_list=prefix_list,
                                             flags=ti.args,
                                             scrubber_args=[],
                                             path=ti.path)

        for prefixes, opt_args, preprocess_cmd in prefix_list:
            common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args)
            common.debug('Extracted FileCheck prefixes: ' + str(prefixes))

            raw_tool_output = common.invoke_tool(ti.args.opt_binary,
                                                 opt_args,
                                                 ti.path,
                                                 preprocess_cmd=preprocess_cmd,
                                                 verbose=ti.args.verbose)
            builder.process_run_line(common.OPT_FUNCTION_RE, common.scrub_body,
                                     raw_tool_output, prefixes, False)
            builder.processed_prefixes(prefixes)

        func_dict = builder.finish_and_get_func_dict()
        is_in_function = False
        is_in_function_start = False
        has_checked_pre_function_globals = False
        prefix_set = set(
            [prefix for prefixes, _, _ in prefix_list for prefix in prefixes])
        common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
        output_lines = []

        include_generated_funcs = common.find_arg_in_test(
            ti, lambda args: ti.args.include_generated_funcs,
            '--include-generated-funcs', True)

        if include_generated_funcs:
            # Generate the appropriate checks for each function.  We need to emit
            # these in the order according to the generated output so that CHECK-LABEL
            # works properly.  func_order provides that.

            # We can't predict where various passes might insert functions so we can't
            # be sure the input function order is maintained.  Therefore, first spit
            # out all the source lines.
            common.dump_input_lines(output_lines, ti, prefix_set, ';')

            args = ti.args
            if args.check_globals:
                common.add_global_checks(builder.global_var_dict(), ';',
                                         prefix_list, output_lines,
                                         global_vars_seen_dict,
                                         args.preserve_names, True)

            # Now generate all the checks.
            common.add_checks_at_end(
                output_lines, prefix_list, builder.func_order(), ';',
                lambda my_output_lines, prefixes, func: common.add_ir_checks(
                    my_output_lines,
                    ';',
                    prefixes,
                    func_dict,
                    func,
                    False,
                    args.function_signature,
                    global_vars_seen_dict,
                    is_filtered=builder.is_filtered()))
        else:
            # "Normal" mode.
            for input_line_info in ti.iterlines(output_lines):
                input_line = input_line_info.line
                args = input_line_info.args
                if is_in_function_start:
                    if input_line == '':
                        continue
                    if input_line.lstrip().startswith(';'):
                        m = common.CHECK_RE.match(input_line)
                        if not m or m.group(1) not in prefix_set:
                            output_lines.append(input_line)
                            continue

                    # Print out the various check lines here.
                    common.add_ir_checks(output_lines,
                                         ';',
                                         prefix_list,
                                         func_dict,
                                         func_name,
                                         args.preserve_names,
                                         args.function_signature,
                                         global_vars_seen_dict,
                                         is_filtered=builder.is_filtered())
                    is_in_function_start = False

                m = common.IR_FUNCTION_RE.match(input_line)
                if m and not has_checked_pre_function_globals:
                    if args.check_globals:
                        common.add_global_checks(builder.global_var_dict(),
                                                 ';', prefix_list,
                                                 output_lines,
                                                 global_vars_seen_dict,
                                                 args.preserve_names, True)
                    has_checked_pre_function_globals = True

                if common.should_add_line_to_output(input_line, prefix_set,
                                                    not is_in_function):
                    # This input line of the function body will go as-is into the output.
                    # Except make leading whitespace uniform: 2 spaces.
                    input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(
                        r'  ', input_line)
                    output_lines.append(input_line)
                    if input_line.strip() == '}':
                        is_in_function = False
                        continue

                if is_in_function:
                    continue

                m = common.IR_FUNCTION_RE.match(input_line)
                if not m:
                    continue
                func_name = m.group(1)
                if args.function is not None and func_name != args.function:
                    # When filtering on a specific function, skip all others.
                    continue
                is_in_function = is_in_function_start = True

        if args.check_globals:
            common.add_global_checks(builder.global_var_dict(), ';',
                                     prefix_list, output_lines,
                                     global_vars_seen_dict,
                                     args.preserve_names, False)
        common.debug('Writing %d lines to %s...' %
                     (len(output_lines), ti.path))

        with open(ti.path, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
Пример #3
0
def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        '--llc-binary',
        default='llc',
        help='The "llc" binary to use to generate the test case')
    parser.add_argument(
        '--opt-binary',
        default='opt',
        help=
        'The "opt" binary to use to generate the test case (if used for pre-processing)'
    )
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument(
        '--extra_scrub',
        action='store_true',
        help=
        'Always use additional regex to further reduce diffs between various subtargets'
    )
    parser.add_argument(
        '--x86_scrub_rip',
        action='store_true',
        default=True,
        help=
        'Use more regex for x86 matching to reduce diffs between various subtargets'
    )
    parser.add_argument('--no_x86_scrub_rip',
                        action='store_false',
                        dest='x86_scrub_rip')
    parser.add_argument('tests', nargs='+')
    args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)

    test_paths = [
        test for pattern in args.tests for test in glob.glob(pattern)
    ]
    for test in test_paths:
        with open(test) as f:
            input_lines = [l.rstrip() for l in f]

        first_line = input_lines[0] if input_lines else ""
        if 'autogenerated' in first_line and script_name not in first_line and not args.force_update:
            common.warn(
                "Skipping test which wasn't autogenerated by " + script_name,
                test)
            continue

        if args.update_only:
            if not first_line or 'autogenerated' not in first_line:
                common.warn("Skipping test which isn't autogenerated: " + test)
                continue

        triple_in_ir = None
        for l in input_lines:
            m = common.TRIPLE_IR_RE.match(l)
            if m:
                triple_in_ir = m.groups()[0]
                break

        run_lines = common.find_run_lines(test, input_lines)
        run_list = []
        for l in run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            commands = [cmd.strip() for cmd in l.split('|', 2)]
            preprocess_cmd = None
            # Allow pre-preocessing test inputs with sed, etc.
            if len(commands) == 3:
                # TODO: allow other tools
                first_command = commands[0]
                if first_command.startswith("%"):
                    first_command = first_command.replace(
                        "%cheri_purecap_opt",
                        "opt -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri128_purecap_opt",
                        "opt -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri256_purecap_opt",
                        "opt -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256"
                    )
                    first_command = first_command.replace(
                        "%cheri_opt",
                        "opt -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri128_opt",
                        "opt -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri256_opt",
                        "opt -mtriple=cheri-unknown-freebsd -mcpu=cheri256 -mattr=+cheri256"
                    )
                    first_command = first_command.replace(
                        "%riscv32_cheri_purecap_opt",
                        "opt -mtriple=riscv32-unknown-freebsd -target-abi il32pc64 -mattr=+xcheri,+cap-mode"
                    )
                    first_command = first_command.replace(
                        "%riscv64_cheri_purecap_opt",
                        "opt -mtriple=riscv64-unknown-freebsd -target-abi l64pc128 -mattr=+xcheri,+cap-mode"
                    )
                    first_command = first_command.replace(
                        "%riscv32_cheri_opt",
                        "opt -mtriple=riscv32-unknown-freebsd -mattr=+xcheri")
                    first_command = first_command.replace(
                        "%riscv64_cheri_opt",
                        "opt -mtriple=riscv64-unknown-freebsd -mattr=+xcheri")
                first_command_list = first_command.split()
                known_command = False
                if first_command_list[0] == "sed":
                    known_command = True
                elif first_command_list[0] == "opt":
                    known_command = True
                    first_command_list[0] = args.opt_binary
                    first_command = " ".join(first_command_list)
                if not known_command:
                    common.warn(
                        'WARNING: Skipping RUN line with more than two commands and unknown first tool: '
                        + l)
                    continue
                # Handle known pre-processing command
                preprocess_cmd = first_command
                commands = commands[1:]

            llc_cmd = commands[0]
            if llc_cmd.startswith("%"):
                llc_cmd = llc_cmd.replace(
                    "%cheri_purecap_llc",
                    "llc -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri128_purecap_llc",
                    "llc -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri256_purecap_llc",
                    "llc -mtriple=cheri-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri_llc",
                    "llc -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri128_llc",
                    "llc -mtriple=cheri-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri256_llc",
                    "llc -mtriple=cheri-unknown-freebsd -mcpu=cheri256 -mattr=+cheri256"
                )
                llc_cmd = llc_cmd.replace(
                    "%riscv32_cheri_purecap_llc",
                    "llc -mtriple=riscv32-unknown-freebsd -target-abi il32pc64 -mattr=+xcheri,+cap-mode"
                )
                llc_cmd = llc_cmd.replace(
                    "%riscv64_cheri_purecap_llc",
                    "llc -mtriple=riscv64-unknown-freebsd -target-abi l64pc128 -mattr=+xcheri,+cap-mode"
                )
                llc_cmd = llc_cmd.replace(
                    "%riscv32_cheri_llc",
                    "llc -mtriple=riscv32-unknown-freebsd -mattr=+xcheri")
                llc_cmd = llc_cmd.replace(
                    "%riscv64_cheri_llc",
                    "llc -mtriple=riscv64-unknown-freebsd -mattr=+xcheri")
            llc_tool = llc_cmd.split(' ')[0]

            triple_in_cmd = None
            m = common.TRIPLE_ARG_RE.search(llc_cmd)
            if m:
                triple_in_cmd = m.groups()[0]

            march_in_cmd = None
            m = common.MARCH_ARG_RE.search(llc_cmd)
            if m:
                march_in_cmd = m.groups()[0]

            filecheck_cmd = ''
            if len(commands) > 1:
                filecheck_cmd = commands[1]
            if filecheck_cmd.startswith("%cheri_FileCheck"):
                filecheck_cmd = filecheck_cmd.replace(
                    "%cheri_FileCheck", "FileCheck '-D#CAP_SIZE=16'")
            common.verify_filecheck_prefixes(filecheck_cmd)
            if llc_tool != 'llc':
                common.warn('Skipping non-llc RUN line: ' + l)
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            llc_cmd_args = llc_cmd[len(llc_tool):].strip()
            llc_cmd_args = llc_cmd_args.replace('< %s',
                                                '').replace('%s', '').strip()
            if test.endswith('.mir'):
                llc_cmd_args += ' -x mir'
            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            run_list.append((check_prefixes, llc_cmd_args, triple_in_cmd,
                             preprocess_cmd, march_in_cmd))

        if test.endswith('.mir'):
            comment_sym = '#'
            check_indent = '  '
        else:
            comment_sym = ';'
            check_indent = ''
        autogenerated_note = (comment_sym + ADVERT + 'utils/' + script_name)

        func_dict = {}
        for p in run_list:
            prefixes = p[0]
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
        for prefixes, llc_args, triple_in_cmd, preprocess_cmd, march_in_cmd in run_list:
            common.debug('Extracted LLC cmd:', llc_tool, llc_args)
            common.debug('Extracted FileCheck prefixes:', str(prefixes))
            if preprocess_cmd:
                common.debug('Extracted pre-processing command: ' +
                             str(preprocess_cmd))

            raw_tool_output = common.invoke_tool(args.llc_binary, llc_args,
                                                 test, preprocess_cmd)
            triple = triple_in_cmd or triple_in_ir
            if not triple:
                triple = asm.get_triple_from_march(march_in_cmd)

            asm.build_function_body_dictionary_for_triple(
                args, raw_tool_output, triple, prefixes, func_dict)

        is_in_function = False
        is_in_function_start = False
        func_name = None
        prefix_set = set([prefix for p in run_list for prefix in p[0]])
        common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
        output_lines = []
        output_lines.append(autogenerated_note)

        for input_line in input_lines:
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                asm.add_asm_checks(output_lines, check_indent + ';', run_list,
                                   func_dict, func_name)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # Discard any previous script advertising.
            if input_line.startswith(comment_sym + ADVERT):
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' % (len(output_lines), test))

        with open(test, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        '--llc-binary',
        default=None,
        help='The "llc" binary to use to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument(
        '--extra_scrub',
        action='store_true',
        help=
        'Always use additional regex to further reduce diffs between various subtargets'
    )
    parser.add_argument(
        '--x86_scrub_rip',
        action='store_true',
        default=True,
        help=
        'Use more regex for x86 matching to reduce diffs between various subtargets'
    )
    parser.add_argument('--no_x86_scrub_rip',
                        action='store_false',
                        dest='x86_scrub_rip')
    parser.add_argument('--no_x86_scrub_mem_shuffle',
                        action='store_true',
                        default=False,
                        help='Reduce scrubbing shuffles with memory operands')
    parser.add_argument('tests', nargs='+')
    initial_args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)

    for ti in common.itertests(initial_args.tests,
                               parser,
                               script_name='utils/' + script_name):
        triple_in_ir = None
        for l in ti.input_lines:
            m = common.TRIPLE_IR_RE.match(l)
            if m:
                triple_in_ir = m.groups()[0]
                break

        run_list = []
        for l in ti.run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            commands = [cmd.strip() for cmd in l.split('|', 1)]
            llc_cmd = commands[0]
            llc_tool = llc_cmd.split(' ')[0]

            triple_in_cmd = None
            m = common.TRIPLE_ARG_RE.search(llc_cmd)
            if m:
                triple_in_cmd = m.groups()[0]

            march_in_cmd = None
            m = common.MARCH_ARG_RE.search(llc_cmd)
            if m:
                march_in_cmd = m.groups()[0]

            filecheck_cmd = ''
            if len(commands) > 1:
                filecheck_cmd = commands[1]
            common.verify_filecheck_prefixes(filecheck_cmd)
            if llc_tool not in LLC_LIKE_TOOLS:
                common.warn('Skipping non-llc RUN line: ' + l)
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            llc_cmd_args = llc_cmd[len(llc_tool):].strip()
            llc_cmd_args = llc_cmd_args.replace('< %s',
                                                '').replace('%s', '').strip()
            if ti.path.endswith('.mir'):
                llc_cmd_args += ' -x mir'
            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            run_list.append(
                (check_prefixes, llc_cmd_args, triple_in_cmd, march_in_cmd))

        if ti.path.endswith('.mir'):
            check_indent = '  '
        else:
            check_indent = ''

        func_dict = {}
        for p in run_list:
            prefixes = p[0]
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
        for prefixes, llc_args, triple_in_cmd, march_in_cmd in run_list:
            common.debug('Extracted LLC cmd:', llc_tool, llc_args)
            common.debug('Extracted FileCheck prefixes:', str(prefixes))

            raw_tool_output = common.invoke_tool(
                ti.args.llc_binary or llc_tool, llc_args, ti.path)
            triple = triple_in_cmd or triple_in_ir
            if not triple:
                triple = asm.get_triple_from_march(march_in_cmd)

            asm.build_function_body_dictionary_for_triple(
                ti.args, raw_tool_output, triple, prefixes, func_dict)

        is_in_function = False
        is_in_function_start = False
        func_name = None
        prefix_set = set([prefix for p in run_list for prefix in p[0]])
        common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
        output_lines = []
        for input_info in ti.iterlines(output_lines):
            input_line = input_info.line
            args = input_info.args
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                asm.add_asm_checks(output_lines, check_indent + ';', run_list,
                                   func_dict, func_name)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' %
                     (len(output_lines), ti.path))

        with open(ti.path, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
Пример #5
0
def main():
  from argparse import RawTextHelpFormatter
  parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter)
  parser.add_argument('--opt-binary', default='opt',
                      help='The opt binary used to generate the test case')
  parser.add_argument(
      '--function', help='The function in the test file to update')
  parser.add_argument('-p', '--preserve-names', action='store_true',
                      help='Do not scrub IR names')
  parser.add_argument('--function-signature', action='store_true',
                      help='Keep function signature information around for the check line')
  parser.add_argument('--scrub-attributes', action='store_true',
                      help='Remove attribute annotations (#0) from the end of check line')
  parser.add_argument('--enable', action='store_true', dest='enabled', default=True,
                      help='Activate CHECK line generation from this point forward')
  parser.add_argument('--disable', action='store_false', dest='enabled',
                      help='Deactivate CHECK line generation from this point forward')
  parser.add_argument('tests', nargs='+')
  args = common.parse_commandline_args(parser)

  script_name = os.path.basename(__file__)
  autogenerated_note = (ADVERT + 'utils/' + script_name)

  opt_basename = os.path.basename(args.opt_binary)
  if not re.match(r'^opt(-\d+)?$', opt_basename):
    common.error('Unexpected opt name: ' + opt_basename)
    sys.exit(1)
  opt_basename = 'opt'

  for test in args.tests:
    if not glob.glob(test):
      common.warn("Test file pattern '%s' was not found. Ignoring it." % (test,))
      continue

  # On Windows we must expand the patterns ourselves.
  test_paths = [test for pattern in args.tests for test in glob.glob(pattern)]
  for test in test_paths:
    argv = sys.argv[:]
    args = parser.parse_args()
    with open(test) as f:
      input_lines = [l.rstrip() for l in f]

    first_line = input_lines[0] if input_lines else ""
    if 'autogenerated' in first_line and script_name not in first_line:
      common.warn("Skipping test which wasn't autogenerated by " + script_name, test)
      continue
    if first_line and 'autogenerated' in first_line:
      args, argv = common.check_for_command(first_line, parser, args, argv)
    test_autogenerated_note = autogenerated_note + common.get_autogennote_suffix(parser, args)

    if args.update_only:
      if not first_line or 'autogenerated' not in first_line:
        common.warn("Skipping test which isn't autogenerated: " + test)
        continue

    run_lines = common.find_run_lines(test, input_lines)

    # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces
    if args.scrub_attributes:
      common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE
    else:
      common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE

    prefix_list = []
    for l in run_lines:
      if '|' not in l:
        common.warn('Skipping unparseable RUN line: ' + l)
        continue

      (tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
      common.verify_filecheck_prefixes(filecheck_cmd)
      if not tool_cmd.startswith(opt_basename + ' '):
        common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l))
        continue

      if not filecheck_cmd.startswith('FileCheck '):
        common.warn('Skipping non-FileChecked RUN line: ' + l)
        continue

      tool_cmd_args = tool_cmd[len(opt_basename):].strip()
      tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip()

      check_prefixes = [item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                               for item in m.group(1).split(',')]
      if not check_prefixes:
        check_prefixes = ['CHECK']

      # FIXME: We should use multiple check prefixes to common check lines. For
      # now, we just ignore all but the last.
      prefix_list.append((check_prefixes, tool_cmd_args))

    func_dict = {}
    for prefixes, _ in prefix_list:
      for prefix in prefixes:
        func_dict.update({prefix: dict()})
    for prefixes, opt_args in prefix_list:
      common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args)
      common.debug('Extracted FileCheck prefixes: ' + str(prefixes))

      raw_tool_output = common.invoke_tool(args.opt_binary, opt_args, test)
      common.build_function_body_dictionary(
              common.OPT_FUNCTION_RE, common.scrub_body, [],
              raw_tool_output, prefixes, func_dict, args.verbose,
              args.function_signature)

    is_in_function = False
    is_in_function_start = False
    prefix_set = set([prefix for prefixes, _ in prefix_list for prefix in prefixes])
    common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
    output_lines = []
    output_lines.append(test_autogenerated_note)

    for input_line in input_lines:
      # Discard any previous script advertising.
      if input_line.startswith(ADVERT):
        continue

      args, argv = common.check_for_command(input_line, parser, args, argv)
      if not args.enabled:
          output_lines.append(input_line)
          continue
      if is_in_function_start:
        if input_line == '':
          continue
        if input_line.lstrip().startswith(';'):
          m = common.CHECK_RE.match(input_line)
          if not m or m.group(1) not in prefix_set:
            output_lines.append(input_line)
            continue

        # Print out the various check lines here.
        common.add_ir_checks(output_lines, ';', prefix_list, func_dict,
                             func_name, args.preserve_names, args.function_signature)
        is_in_function_start = False

      if is_in_function:
        if common.should_add_line_to_output(input_line, prefix_set):
          # This input line of the function body will go as-is into the output.
          # Except make leading whitespace uniform: 2 spaces.
          input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(r'  ', input_line)
          output_lines.append(input_line)
        else:
          continue
        if input_line.strip() == '}':
          is_in_function = False
        continue

      # 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
      func_name = m.group(1)
      if args.function is not None and func_name != args.function:
        # When filtering on a specific function, skip all others.
        continue
      is_in_function = is_in_function_start = True

    common.debug('Writing %d lines to %s...' % (len(output_lines), test))

    with open(test, 'wb') as f:
      f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])
Пример #6
0
def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        '--llc-binary',
        default=None,
        help='The "llc" binary to use to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument(
        '--extra_scrub',
        action='store_true',
        help=
        'Always use additional regex to further reduce diffs between various subtargets'
    )
    parser.add_argument(
        '--x86_scrub_sp',
        action='store_true',
        default=True,
        help=
        'Use regex for x86 sp matching to reduce diffs between various subtargets'
    )
    parser.add_argument('--no_x86_scrub_sp',
                        action='store_false',
                        dest='x86_scrub_sp')
    parser.add_argument(
        '--x86_scrub_rip',
        action='store_true',
        default=False,
        help=
        'Use more regex for x86 rip matching to reduce diffs between various subtargets'
    )
    parser.add_argument('--no_x86_scrub_rip',
                        action='store_false',
                        dest='x86_scrub_rip')
    parser.add_argument('--no_x86_scrub_mem_shuffle',
                        action='store_true',
                        default=False,
                        help='Reduce scrubbing shuffles with memory operands')
    parser.add_argument('tests', nargs='+')
    initial_args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)

    for ti in common.itertests(initial_args.tests,
                               parser,
                               script_name='utils/' + script_name):
        triple_in_ir = None
        for l in ti.input_lines:
            m = common.TRIPLE_IR_RE.match(l)
            if m:
                triple_in_ir = m.groups()[0]
                break

        run_list = []
        for l in ti.run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            commands = [cmd.strip() for cmd in l.split('|')]
            assert len(commands) >= 2
            preprocess_cmd = None
            if len(commands) > 2:
                preprocess_cmd = " | ".join(commands[:-2])
            llc_cmd = commands[-2]
            filecheck_cmd = commands[-1]
            llc_tool = llc_cmd.split(' ')[0]

            triple_in_cmd = None
            m = common.TRIPLE_ARG_RE.search(llc_cmd)
            if m:
                triple_in_cmd = m.groups()[0]

            march_in_cmd = None
            m = common.MARCH_ARG_RE.search(llc_cmd)
            if m:
                march_in_cmd = m.groups()[0]

            common.verify_filecheck_prefixes(filecheck_cmd)
            if llc_tool not in LLC_LIKE_TOOLS:
                common.warn('Skipping non-llc RUN line: ' + l)
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            llc_cmd_args = llc_cmd[len(llc_tool):].strip()
            llc_cmd_args = llc_cmd_args.replace('< %s',
                                                '').replace('%s', '').strip()
            if ti.path.endswith('.mir'):
                llc_cmd_args += ' -x mir'
            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            run_list.append((check_prefixes, llc_tool, llc_cmd_args,
                             preprocess_cmd, triple_in_cmd, march_in_cmd))

        if ti.path.endswith('.mir'):
            check_indent = '  '
        else:
            check_indent = ''

        builder = common.FunctionTestBuilder(
            run_list=run_list,
            flags=type(
                '', (object, ), {
                    'verbose': ti.args.verbose,
                    'function_signature': False,
                    'check_attributes': False,
                    'replace_value_regex': []
                }),
            scrubber_args=[ti.args],
            path=ti.path)

        for prefixes, llc_tool, llc_args, preprocess_cmd, triple_in_cmd, march_in_cmd in run_list:
            common.debug('Extracted LLC cmd:', llc_tool, llc_args)
            common.debug('Extracted FileCheck prefixes:', str(prefixes))

            raw_tool_output = common.invoke_tool(ti.args.llc_binary
                                                 or llc_tool,
                                                 llc_args,
                                                 ti.path,
                                                 preprocess_cmd,
                                                 verbose=ti.args.verbose)
            triple = triple_in_cmd or triple_in_ir
            if not triple:
                triple = asm.get_triple_from_march(march_in_cmd)

            scrubber, function_re = asm.get_run_handler(triple)
            builder.process_run_line(function_re, scrubber, raw_tool_output,
                                     prefixes)

        func_dict = builder.finish_and_get_func_dict()

        is_in_function = False
        is_in_function_start = False
        func_name = None
        prefix_set = set([prefix for p in run_list for prefix in p[0]])
        common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
        output_lines = []

        include_generated_funcs = common.find_arg_in_test(
            ti, lambda args: ti.args.include_generated_funcs,
            '--include-generated-funcs', True)

        if include_generated_funcs:
            # Generate the appropriate checks for each function.  We need to emit
            # these in the order according to the generated output so that CHECK-LABEL
            # works properly.  func_order provides that.

            # We can't predict where various passes might insert functions so we can't
            # be sure the input function order is maintained.  Therefore, first spit
            # out all the source lines.
            common.dump_input_lines(output_lines, ti, prefix_set, ';')

            # Now generate all the checks.
            common.add_checks_at_end(
                output_lines, run_list, builder.func_order(),
                check_indent + ';',
                lambda my_output_lines, prefixes, func: asm.add_asm_checks(
                    my_output_lines, check_indent + ';', prefixes, func_dict,
                    func))
        else:
            for input_info in ti.iterlines(output_lines):
                input_line = input_info.line
                args = input_info.args
                if is_in_function_start:
                    if input_line == '':
                        continue
                    if input_line.lstrip().startswith(';'):
                        m = common.CHECK_RE.match(input_line)
                        if not m or m.group(1) not in prefix_set:
                            output_lines.append(input_line)
                            continue

                    # Print out the various check lines here.
                    asm.add_asm_checks(output_lines, check_indent + ';',
                                       run_list, func_dict, func_name)
                    is_in_function_start = False

                if is_in_function:
                    if common.should_add_line_to_output(
                            input_line, prefix_set):
                        # This input line of the function body will go as-is into the output.
                        output_lines.append(input_line)
                    else:
                        continue
                    if input_line.strip() == '}':
                        is_in_function = False
                    continue

                # If it's outside a function, it just gets copied to the output.
                output_lines.append(input_line)

                m = common.IR_FUNCTION_RE.match(input_line)
                if not m:
                    continue
                func_name = m.group(1)
                if args.function is not None and func_name != args.function:
                    # When filtering on a specific function, skip all others.
                    continue
                is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' %
                     (len(output_lines), ti.path))

        with open(ti.path, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
Пример #7
0
def main():
    from argparse import RawTextHelpFormatter
    parser = argparse.ArgumentParser(description=__doc__,
                                     formatter_class=RawTextHelpFormatter)
    parser.add_argument('--opt-binary',
                        default='opt',
                        help='The opt binary used to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument('-p',
                        '--preserve-names',
                        action='store_true',
                        help='Do not scrub IR names')
    parser.add_argument(
        '--function-signature',
        action='store_true',
        help='Keep function signature information around for the check line')
    parser.add_argument(
        '--scrub-attributes',
        action='store_true',
        help='Remove attribute annotations (#0) from the end of check line')
    parser.add_argument('--check-attributes',
                        action='store_true',
                        help='Check "Function Attributes" for functions')
    parser.add_argument('tests', nargs='+')
    initial_args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)
    opt_basename = os.path.basename(initial_args.opt_binary)
    if not re.match(r'^opt(-\d+)?$', opt_basename):
        common.error('Unexpected opt name: ' + opt_basename)
        sys.exit(1)
    opt_basename = 'opt'

    for ti in common.itertests(initial_args.tests,
                               parser,
                               script_name='utils/' + script_name):
        # If requested we scrub trailing attribute annotations, e.g., '#0', together with whitespaces
        if ti.args.scrub_attributes:
            common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_AND_ATTRIBUTES_RE
        else:
            common.SCRUB_TRAILING_WHITESPACE_TEST_RE = common.SCRUB_TRAILING_WHITESPACE_RE

        prefix_list = []
        for l in ti.run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            (tool_cmd,
             filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])

            if tool_cmd.startswith("%"):
                tool_cmd = tool_cmd.replace(
                    "%cheri_purecap_opt",
                    "opt -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                )
                tool_cmd = tool_cmd.replace(
                    "%cheri128_purecap_opt",
                    "opt -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                )
                tool_cmd = tool_cmd.replace(
                    "%cheri256_purecap_opt",
                    "opt -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256"
                )
                tool_cmd = tool_cmd.replace(
                    "%cheri_opt",
                    "opt -mtriple=mips64-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                )
                tool_cmd = tool_cmd.replace(
                    "%cheri128_opt",
                    "opt -mtriple=mips64-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                )
                tool_cmd = tool_cmd.replace(
                    "%cheri256_opt",
                    "opt -mtriple=mips64-unknown-freebsd -mcpu=cheri256 -mattr=+cheri256"
                )
                tool_cmd = tool_cmd.replace(
                    "%riscv32_cheri_purecap_opt",
                    "opt -mtriple=riscv32-unknown-freebsd -target-abi il32pc64 -mattr=+xcheri,+cap-mode"
                )
                tool_cmd = tool_cmd.replace(
                    "%riscv64_cheri_purecap_opt",
                    "opt -mtriple=riscv64-unknown-freebsd -target-abi l64pc128 -mattr=+xcheri,+cap-mode"
                )
                tool_cmd = tool_cmd.replace(
                    "%riscv32_cheri_opt",
                    "opt -mtriple=riscv32-unknown-freebsd -mattr=+xcheri")
                tool_cmd = tool_cmd.replace(
                    "%riscv64_cheri_opt",
                    "opt -mtriple=riscv64-unknown-freebsd -mattr=+xcheri")

            common.verify_filecheck_prefixes(filecheck_cmd)
            if not tool_cmd.startswith(opt_basename + ' '):
                common.warn('Skipping non-%s RUN line: %s' % (opt_basename, l))
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            tool_cmd_args = tool_cmd[len(opt_basename):].strip()
            tool_cmd_args = tool_cmd_args.replace('< %s',
                                                  '').replace('%s',
                                                              '').strip()

            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            prefix_list.append((check_prefixes, tool_cmd_args))

        global_vars_seen_dict = {}
        func_dict = {}
        for prefixes, _ in prefix_list:
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
        for prefixes, opt_args in prefix_list:
            common.debug('Extracted opt cmd: ' + opt_basename + ' ' + opt_args)
            common.debug('Extracted FileCheck prefixes: ' + str(prefixes))

            raw_tool_output = common.invoke_tool(ti.args.opt_binary, opt_args,
                                                 ti.path)
            common.build_function_body_dictionary(common.OPT_FUNCTION_RE,
                                                  common.scrub_body, [],
                                                  raw_tool_output, prefixes,
                                                  func_dict, ti.args.verbose,
                                                  ti.args.function_signature,
                                                  ti.args.check_attributes)

        is_in_function = False
        is_in_function_start = False
        prefix_set = set(
            [prefix for prefixes, _ in prefix_list for prefix in prefixes])
        common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
        output_lines = []
        for input_line_info in ti.iterlines(output_lines):
            input_line = input_line_info.line
            args = input_line_info.args
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                common.add_ir_checks(output_lines, ';', prefix_list, func_dict,
                                     func_name, args.preserve_names,
                                     args.function_signature,
                                     global_vars_seen_dict)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    # Except make leading whitespace uniform: 2 spaces.
                    input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(
                        r'  ', input_line)
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' %
                     (len(output_lines), ti.path))

        with open(ti.path, 'wb') as f:
            if initial_args.verbose:
                sys.stderr.writelines(['{}\n'.format(l) for l in output_lines])
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
Пример #8
0
def main():
    from argparse import RawTextHelpFormatter
    parser = argparse.ArgumentParser(description=__doc__,
                                     formatter_class=RawTextHelpFormatter)
    parser.add_argument('--opt-binary',
                        default='opt',
                        help='The opt binary used to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument('tests', nargs='+')
    args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)
    autogenerated_note = (ADVERT + 'utils/' + script_name)

    opt_basename = os.path.basename(args.opt_binary)
    if (opt_basename != "opt"):
        common.error('Unexpected opt name: ' + opt_basename)
        sys.exit(1)

    test_paths = [
        test for pattern in args.tests for test in glob.glob(pattern)
    ]
    for test in test_paths:
        with open(test) as f:
            input_lines = [l.rstrip() for l in f]

        first_line = input_lines[0] if input_lines else ""
        if 'autogenerated' in first_line and script_name not in first_line:
            common.warn("Skipping test which wasn't autogenerated by " +
                        script_name + ": " + test)
            continue

        if args.update_only:
            if not first_line or 'autogenerated' not in first_line:
                common.warn("Skipping test which isn't autogenerated: " + test)
                continue

        run_lines = common.find_run_lines(test, input_lines)
        prefix_list = []
        for l in run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            (tool_cmd,
             filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
            common.verify_filecheck_prefixes(filecheck_cmd)

            if not tool_cmd.startswith(opt_basename + ' '):
                common.warn('WSkipping non-%s RUN line: %s' %
                            (opt_basename, l))
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            tool_cmd_args = tool_cmd[len(opt_basename):].strip()
            tool_cmd_args = tool_cmd_args.replace('< %s',
                                                  '').replace('%s',
                                                              '').strip()

            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            prefix_list.append((check_prefixes, tool_cmd_args))

        builder = common.FunctionTestBuilder(
            run_list=prefix_list,
            flags=type(
                '', (object, ), {
                    'verbose': args.verbose,
                    'function_signature': False,
                    'check_attributes': False,
                    'replace_value_regex': []
                }),
            scrubber_args=[],
            path=test)

        for prefixes, opt_args in prefix_list:
            common.debug('Extracted opt cmd:',
                         opt_basename,
                         opt_args,
                         file=sys.stderr)
            common.debug('Extracted FileCheck prefixes:',
                         str(prefixes),
                         file=sys.stderr)

            raw_tool_outputs = common.invoke_tool(args.opt_binary, opt_args,
                                                  test)

            # Split analysis outputs by "Printing analysis " declarations.
            for raw_tool_output in re.split(r'Printing analysis ',
                                            raw_tool_outputs):
                builder.process_run_line(common.ANALYZE_FUNCTION_RE,
                                         common.scrub_body, raw_tool_output,
                                         prefixes)

        func_dict = builder.finish_and_get_func_dict()
        is_in_function = False
        is_in_function_start = False
        prefix_set = set(
            [prefix for prefixes, _ in prefix_list for prefix in prefixes])
        common.debug('Rewriting FileCheck prefixes:',
                     str(prefix_set),
                     file=sys.stderr)
        output_lines = []
        output_lines.append(autogenerated_note)

        for input_line in input_lines:
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                common.add_analyze_checks(output_lines, ';', prefix_list,
                                          func_dict, func_name)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    # Except make leading whitespace uniform: 2 spaces.
                    input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(
                        r'  ', input_line)
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # Discard any previous script advertising.
            if input_line.startswith(ADVERT):
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        common.debug('Writing %d lines to %s...' % (len(output_lines), test))

        with open(test, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])
def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        '--llc-binary',
        default='llc',
        help='The "llc" binary to use to generate the test case')
    parser.add_argument('--function',
                        help='The function in the test file to update')
    parser.add_argument(
        '--extra_scrub',
        action='store_true',
        help=
        'Always use additional regex to further reduce diffs between various subtargets'
    )
    parser.add_argument(
        '--x86_scrub_rip',
        action='store_true',
        default=True,
        help=
        'Use more regex for x86 matching to reduce diffs between various subtargets'
    )
    parser.add_argument('--no_x86_scrub_rip',
                        action='store_false',
                        dest='x86_scrub_rip')
    parser.add_argument('tests', nargs='+')
    args = common.parse_commandline_args(parser)

    script_name = os.path.basename(__file__)

    test_paths = [
        test for pattern in args.tests for test in glob.glob(pattern)
    ]
    for test in test_paths:
        if args.verbose:
            print('Scanning for RUN lines in test file: %s' % (test, ),
                  file=sys.stderr)
        with open(test) as f:
            input_lines = [l.rstrip() for l in f]

        first_line = input_lines[0] if input_lines else ""
        if 'autogenerated' in first_line and script_name not in first_line:
            common.warn(
                "Skipping test which wasn't autogenerated by " + script_name,
                test)
            continue

        if args.update_only:
            if not first_line or 'autogenerated' not in first_line:
                common.warn("Skipping test which isn't autogenerated: " + test)
                continue

        triple_in_ir = None
        for l in input_lines:
            m = common.TRIPLE_IR_RE.match(l)
            if m:
                triple_in_ir = m.groups()[0]
                break

        raw_lines = [
            m.group(1)
            for m in [common.RUN_LINE_RE.match(l) for l in input_lines] if m
        ]
        run_lines = [raw_lines[0]] if len(raw_lines) > 0 else []
        for l in raw_lines[1:]:
            if run_lines[-1].endswith("\\"):
                run_lines[-1] = run_lines[-1].rstrip("\\") + " " + l
            else:
                run_lines.append(l)

        if args.verbose:
            print('Found %d RUN lines:' % (len(run_lines), ), file=sys.stderr)
            for l in run_lines:
                print('  RUN: ' + l, file=sys.stderr)

        run_list = []
        for l in run_lines:
            if '|' not in l:
                common.warn('Skipping unparseable RUN line: ' + l)
                continue

            commands = [cmd.strip() for cmd in l.split('|', 1)]
            llc_cmd = commands[0]
            llc_tool = llc_cmd.split(' ')[0]

            triple_in_cmd = None
            m = common.TRIPLE_ARG_RE.search(llc_cmd)
            if m:
                triple_in_cmd = m.groups()[0]

            march_in_cmd = None
            m = common.MARCH_ARG_RE.search(llc_cmd)
            if m:
                march_in_cmd = m.groups()[0]

            filecheck_cmd = ''
            if len(commands) > 1:
                filecheck_cmd = commands[1]
            common.verify_filecheck_prefixes(filecheck_cmd)
            if llc_tool != 'llc':
                common.warn('Skipping non-llc RUN line: ' + l)
                continue

            if not filecheck_cmd.startswith('FileCheck '):
                common.warn('Skipping non-FileChecked RUN line: ' + l)
                continue

            llc_cmd_args = llc_cmd[len(llc_tool):].strip()
            llc_cmd_args = llc_cmd_args.replace('< %s',
                                                '').replace('%s', '').strip()
            if test.endswith('.mir'):
                llc_cmd_args += ' -x mir'
                comment_sym = '#'
                check_indent = '  '
            else:
                comment_sym = ';'
                check_indent = ''

            check_prefixes = [
                item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                for item in m.group(1).split(',')
            ]
            if not check_prefixes:
                check_prefixes = ['CHECK']

            # FIXME: We should use multiple check prefixes to common check lines. For
            # now, we just ignore all but the last.
            run_list.append(
                (check_prefixes, llc_cmd_args, triple_in_cmd, march_in_cmd))

        autogenerated_note = (comment_sym + ADVERT + 'utils/' + script_name)

        func_dict = {}
        for p in run_list:
            prefixes = p[0]
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
        for prefixes, llc_args, triple_in_cmd, march_in_cmd in run_list:
            if args.verbose:
                print('Extracted LLC cmd: ' + llc_tool + ' ' + llc_args,
                      file=sys.stderr)
                print('Extracted FileCheck prefixes: ' + str(prefixes),
                      file=sys.stderr)

            raw_tool_output = common.invoke_tool(args.llc_binary, llc_args,
                                                 test)
            triple = triple_in_cmd or triple_in_ir
            if not triple:
                triple = asm.get_triple_from_march(march_in_cmd)

            asm.build_function_body_dictionary_for_triple(
                args, raw_tool_output, triple, prefixes, func_dict)

        is_in_function = False
        is_in_function_start = False
        func_name = None
        prefix_set = set([prefix for p in run_list for prefix in p[0]])
        if args.verbose:
            print('Rewriting FileCheck prefixes: %s' % (prefix_set, ),
                  file=sys.stderr)
        output_lines = []
        output_lines.append(autogenerated_note)

        for input_line in input_lines:
            if is_in_function_start:
                if input_line == '':
                    continue
                if input_line.lstrip().startswith(';'):
                    m = common.CHECK_RE.match(input_line)
                    if not m or m.group(1) not in prefix_set:
                        output_lines.append(input_line)
                        continue

                # Print out the various check lines here.
                asm.add_asm_checks(output_lines, check_indent + ';', run_list,
                                   func_dict, func_name)
                is_in_function_start = False

            if is_in_function:
                if common.should_add_line_to_output(input_line, prefix_set):
                    # This input line of the function body will go as-is into the output.
                    output_lines.append(input_line)
                else:
                    continue
                if input_line.strip() == '}':
                    is_in_function = False
                continue

            # Discard any previous script advertising.
            if input_line.startswith(comment_sym + ADVERT):
                continue

            # If it's outside a function, it just gets copied to the output.
            output_lines.append(input_line)

            m = common.IR_FUNCTION_RE.match(input_line)
            if not m:
                continue
            func_name = m.group(1)
            if args.function is not None and func_name != args.function:
                # When filtering on a specific function, skip all others.
                continue
            is_in_function = is_in_function_start = True

        if args.verbose:
            print('Writing %d lines to %s...' % (len(output_lines), test),
                  file=sys.stderr)

        with open(test, 'wb') as f:
            f.writelines(
                ['{}\n'.format(l).encode('utf-8') for l in output_lines])