Esempio n. 1
0
def main():
  parser = argparse.ArgumentParser(description=__doc__)
  parser.add_argument('-v', '--verbose', action='store_true',
                      help='Show verbose output')
  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(
      '--x86_extra_scrub', action='store_true',
      help='Use more regex for x86 matching to reduce diffs between various subtargets')
  parser.add_argument('tests', nargs='+')
  args = parser.parse_args()

  autogenerated_note = (ADVERT + 'utils/' + 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:
      input_lines = [l.rstrip() for l in f]

    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 >>sys.stderr, 'Found %d RUN lines:' % (len(run_lines),)
      for l in run_lines:
        print >>sys.stderr, '  RUN: ' + l

    run_list = []
    for l in run_lines:
      commands = [cmd.strip() for cmd in l.split('|', 1)]
      llc_cmd = commands[0]
      if llc_cmd.startswith("%cheri_"):
        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("%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")

      triple_in_cmd = None
      m = common.TRIPLE_ARG_RE.search(llc_cmd)
      if m:
        triple_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'")
      if not llc_cmd.startswith('llc '):
        print >>sys.stderr, 'WARNING: Skipping non-llc RUN line: ' + l
        continue

      if not filecheck_cmd.startswith('FileCheck '):
        print >>sys.stderr, 'WARNING: Skipping non-FileChecked RUN line: ' + l
        continue

      llc_cmd_args = llc_cmd[len('llc'):].strip()
      llc_cmd_args = llc_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.
      run_list.append((check_prefixes, llc_cmd_args, triple_in_cmd))

    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 in run_list:
      if args.verbose:
        print >>sys.stderr, 'Extracted LLC cmd: llc ' + llc_args
        print >>sys.stderr, 'Extracted FileCheck prefixes: ' + str(prefixes)

      raw_tool_output = common.invoke_tool(args.llc_binary, llc_args, test)
      if not (triple_in_cmd or triple_in_ir):
        print >>sys.stderr, "Cannot find a triple. Assume 'x86'"

      asm.build_function_body_dictionary_for_triple(args, raw_tool_output,
          triple_in_cmd or triple_in_ir or 'x86', 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 >>sys.stderr, 'Rewriting FileCheck prefixes: %s' % (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, ';', 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(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>>sys.stderr, 'Writing %d lines to %s...' % (len(output_lines), test)

    with open(test, 'wb') as f:
      f.writelines([l + '\n' for l in output_lines])
def main():
  parser = argparse.ArgumentParser(description=__doc__)
  parser.add_argument('-v', '--verbose', action='store_true',
                      help='Show verbose output')
  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 = parser.parse_args()

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

  for test in args.tests:
    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]

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

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

      filecheck_cmd = ''
      if len(commands) > 1:
        filecheck_cmd = commands[1]
      if not llc_cmd.startswith('llc '):
        print('WARNING: Skipping non-llc RUN line: ' + l, file=sys.stderr)
        continue

      if not filecheck_cmd.startswith('FileCheck '):
        print('WARNING: Skipping non-FileChecked RUN line: ' + l, file=sys.stderr)
        continue

      llc_cmd_args = llc_cmd[len('llc'):].strip()
      llc_cmd_args = llc_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.
      run_list.append((check_prefixes, llc_cmd_args, triple_in_cmd))

    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 in run_list:
      if args.verbose:
        print('Extracted LLC cmd: llc ' + 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)
      if not (triple_in_cmd or triple_in_ir):
        print("Cannot find a triple. Assume 'x86'", file=sys.stderr)

      asm.build_function_body_dictionary_for_triple(args, raw_tool_output,
          triple_in_cmd or triple_in_ir or 'x86', 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, ';', 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(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([l + '\n' for l in output_lines])
Esempio n. 3
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=True,
        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('|', 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 = {}
        func_order = {}
        for p in run_list:
            prefixes = p[0]
            for prefix in prefixes:
                func_dict.update({prefix: dict()})
                func_order.update({prefix: []})
        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,
                func_order)

        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, 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])
Esempio n. 4
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('--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:
            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('|', 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'
            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 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, 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(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]])
        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])
Esempio n. 5
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(
        '--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(
        '--scrub-stack-indices',
        action='store_true',
        help=
        'Use additional regex to further reduce diffs between 32/64-bit targets'
    )
    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('|', 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=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri128_purecap_opt",
                        "opt -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri256_purecap_opt",
                        "opt -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256"
                    )
                    first_command = first_command.replace(
                        "%cheri_opt",
                        "opt -mtriple=mips64-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri128_opt",
                        "opt -mtriple=mips64-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                    )
                    first_command = first_command.replace(
                        "%cheri256_opt",
                        "opt -mtriple=mips64-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] = ti.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=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri128_purecap_llc",
                    "llc -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri256_purecap_llc",
                    "llc -mtriple=mips64-unknown-freebsd -target-abi purecap -relocation-model pic -mcpu=cheri256 -mattr=+cheri256"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri_llc",
                    "llc -mtriple=mips64-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri128_llc",
                    "llc -mtriple=mips64-unknown-freebsd -mcpu=cheri128 -mattr=+cheri128"
                )
                llc_cmd = llc_cmd.replace(
                    "%cheri256_llc",
                    "llc -mtriple=mips64-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("%cheri64_FileCheck"):
                filecheck_cmd = filecheck_cmd.replace(
                    "%cheri64_FileCheck", "FileCheck '-D#CAP_SIZE=8'")
            elif filecheck_cmd.startswith("%cheri128_FileCheck"):
                filecheck_cmd = filecheck_cmd.replace(
                    "%cheri128_FileCheck", "FileCheck '-D#CAP_SIZE=16'")
            elif 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 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,
                             preprocess_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, 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(
                ti.args.llc_binary or llc_tool, llc_args, ti.path,
                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(
                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])