[utils] De-duplicate utils/update_{llc_,}test_checks.py

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D42654

llvm-svn: 323718
diff --git a/llvm/utils/UpdateTestChecks/__init__.py b/llvm/utils/UpdateTestChecks/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/llvm/utils/UpdateTestChecks/__init__.py
diff --git a/llvm/utils/UpdateTestChecks/asm.py b/llvm/utils/UpdateTestChecks/asm.py
new file mode 100644
index 0000000..7630be4
--- /dev/null
+++ b/llvm/utils/UpdateTestChecks/asm.py
@@ -0,0 +1,199 @@
+import re
+import string
+
+from . import common
+
+# RegEx: this is where the magic happens.
+
+ASM_FUNCTION_X86_RE = re.compile(
+    r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n[^:]*?'
+    r'(?P<body>^##?[ \t]+[^:]+:.*?)\s*'
+    r'^\s*(?:[^:\n]+?:\s*\n\s*\.size|\.cfi_endproc|\.globl|\.comm|\.(?:sub)?section|#+ -- End function)',
+    flags=(re.M | re.S))
+
+ASM_FUNCTION_ARM_RE = re.compile(
+        r'^(?P<func>[0-9a-zA-Z_]+):\n' # f: (name of function)
+        r'\s+\.fnstart\n' # .fnstart
+        r'(?P<body>.*?)\n' # (body of the function)
+        r'.Lfunc_end[0-9]+:', # .Lfunc_end0: or # -- End function
+        flags=(re.M | re.S))
+
+ASM_FUNCTION_AARCH64_RE = re.compile(
+     r'^_?(?P<func>[^:]+):[ \t]*\/\/[ \t]*@(?P=func)\n'
+     r'[ \t]+.cfi_startproc\n'
+     r'(?P<body>.*?)\n'
+     # This list is incomplete
+     r'.Lfunc_end[0-9]+:\n',
+     flags=(re.M | re.S))
+
+ASM_FUNCTION_MIPS_RE = re.compile(
+    r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n[^:]*?' # f: (name of func)
+    r'(?:^[ \t]+\.(frame|f?mask|set).*?\n)+'  # Mips+LLVM standard asm prologue
+    r'(?P<body>.*?)\n'                        # (body of the function)
+    r'(?:^[ \t]+\.(set|end).*?\n)+'           # Mips+LLVM standard asm epilogue
+    r'(\$|\.L)func_end[0-9]+:\n',             # $func_end0: (mips32 - O32) or
+                                              # .Lfunc_end0: (mips64 - NewABI)
+    flags=(re.M | re.S))
+
+ASM_FUNCTION_PPC_RE = re.compile(
+    r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n'
+    r'\.Lfunc_begin[0-9]+:\n'
+    r'(?:[ \t]+.cfi_startproc\n)?'
+    r'(?:\.Lfunc_[gl]ep[0-9]+:\n(?:[ \t]+.*?\n)*)*'
+    r'(?P<body>.*?)\n'
+    # This list is incomplete
+    r'(?:^[ \t]*(?:\.long[ \t]+[^\n]+|\.quad[ \t]+[^\n]+)\n)*'
+    r'.Lfunc_end[0-9]+:\n',
+    flags=(re.M | re.S))
+
+ASM_FUNCTION_RISCV_RE = re.compile(
+    r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n[^:]*?'
+    r'(?P<body>^##?[ \t]+[^:]+:.*?)\s*'
+    r'.Lfunc_end[0-9]+:\n',
+    flags=(re.M | re.S))
+
+ASM_FUNCTION_SYSTEMZ_RE = re.compile(
+    r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n'
+    r'[ \t]+.cfi_startproc\n'
+    r'(?P<body>.*?)\n'
+    r'.Lfunc_end[0-9]+:\n',
+    flags=(re.M | re.S))
+
+
+SCRUB_LOOP_COMMENT_RE = re.compile(
+    r'# =>This Inner Loop Header:.*|# in Loop:.*', flags=re.M)
+
+SCRUB_X86_SHUFFLES_RE = (
+    re.compile(
+        r'^(\s*\w+) [^#\n]+#+ ((?:[xyz]mm\d+|mem)( \{%k\d+\}( \{z\})?)? = .*)$',
+        flags=re.M))
+SCRUB_X86_SP_RE = re.compile(r'\d+\(%(esp|rsp)\)')
+SCRUB_X86_RIP_RE = re.compile(r'[.\w]+\(%rip\)')
+SCRUB_X86_LCP_RE = re.compile(r'\.LCPI[0-9]+_[0-9]+')
+SCRUB_X86_RET_RE = re.compile(r'ret[l|q]')
+
+def scrub_asm_x86(asm, args):
+  # Scrub runs of whitespace out of the assembly, but leave the leading
+  # whitespace in place.
+  asm = common.SCRUB_WHITESPACE_RE.sub(r' ', asm)
+  # Expand the tabs used for indentation.
+  asm = string.expandtabs(asm, 2)
+  # Detect shuffle asm comments and hide the operands in favor of the comments.
+  asm = SCRUB_X86_SHUFFLES_RE.sub(r'\1 {{.*#+}} \2', asm)
+  # Generically match the stack offset of a memory operand.
+  asm = SCRUB_X86_SP_RE.sub(r'{{[0-9]+}}(%\1)', asm)
+  # Generically match a RIP-relative memory operand.
+  asm = SCRUB_X86_RIP_RE.sub(r'{{.*}}(%rip)', asm)
+  # Generically match a LCP symbol.
+  asm = SCRUB_X86_LCP_RE.sub(r'{{\.LCPI.*}}', asm)
+  if args.x86_extra_scrub:
+    # Avoid generating different checks for 32- and 64-bit because of 'retl' vs 'retq'.
+    asm = SCRUB_X86_RET_RE.sub(r'ret{{[l|q]}}', asm)
+  # Strip kill operands inserted into the asm.
+  asm = common.SCRUB_KILL_COMMENT_RE.sub('', asm)
+  # Strip trailing whitespace.
+  asm = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', asm)
+  return asm
+
+def scrub_asm_arm_eabi(asm, args):
+  # Scrub runs of whitespace out of the assembly, but leave the leading
+  # whitespace in place.
+  asm = common.SCRUB_WHITESPACE_RE.sub(r' ', asm)
+  # Expand the tabs used for indentation.
+  asm = string.expandtabs(asm, 2)
+  # Strip kill operands inserted into the asm.
+  asm = common.SCRUB_KILL_COMMENT_RE.sub('', asm)
+  # Strip trailing whitespace.
+  asm = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', asm)
+  return asm
+
+def scrub_asm_powerpc64(asm, args):
+  # Scrub runs of whitespace out of the assembly, but leave the leading
+  # whitespace in place.
+  asm = common.SCRUB_WHITESPACE_RE.sub(r' ', asm)
+  # Expand the tabs used for indentation.
+  asm = string.expandtabs(asm, 2)
+  # Stripe unimportant comments
+  asm = SCRUB_LOOP_COMMENT_RE.sub(r'', asm)
+  # Strip trailing whitespace.
+  asm = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', asm)
+  return asm
+
+def scrub_asm_mips(asm, args):
+  # Scrub runs of whitespace out of the assembly, but leave the leading
+  # whitespace in place.
+  asm = common.SCRUB_WHITESPACE_RE.sub(r' ', asm)
+  # Expand the tabs used for indentation.
+  asm = string.expandtabs(asm, 2)
+  # Strip trailing whitespace.
+  asm = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', asm)
+  return asm
+
+def scrub_asm_riscv(asm, args):
+  # Scrub runs of whitespace out of the assembly, but leave the leading
+  # whitespace in place.
+  asm = common.SCRUB_WHITESPACE_RE.sub(r' ', asm)
+  # Expand the tabs used for indentation.
+  asm = string.expandtabs(asm, 2)
+  # Strip trailing whitespace.
+  asm = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', asm)
+  return asm
+
+def scrub_asm_systemz(asm, args):
+  # Scrub runs of whitespace out of the assembly, but leave the leading
+  # whitespace in place.
+  asm = common.SCRUB_WHITESPACE_RE.sub(r' ', asm)
+  # Expand the tabs used for indentation.
+  asm = string.expandtabs(asm, 2)
+  # Strip trailing whitespace.
+  asm = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', asm)
+  return asm
+
+
+def build_function_body_dictionary_for_triple(args, raw_tool_output, triple, prefixes, func_dict):
+  target_handlers = {
+      'x86_64': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
+      'i686': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
+      'x86': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
+      'i386': (scrub_asm_x86, ASM_FUNCTION_X86_RE),
+      'aarch64': (scrub_asm_arm_eabi, ASM_FUNCTION_AARCH64_RE),
+      'arm-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumb-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv6': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv6-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv6t2': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv6t2-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv6m': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv6m-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv7': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv7-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv7m': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv7m-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv8-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv8m.base': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'thumbv8m.main': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'armv6': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'armv7': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'armv7-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'armeb-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'armv7eb-eabi': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'armv7eb': (scrub_asm_arm_eabi, ASM_FUNCTION_ARM_RE),
+      'mips': (scrub_asm_mips, ASM_FUNCTION_MIPS_RE),
+      'powerpc64': (scrub_asm_powerpc64, ASM_FUNCTION_PPC_RE),
+      'powerpc64le': (scrub_asm_powerpc64, ASM_FUNCTION_PPC_RE),
+      'riscv32': (scrub_asm_riscv, ASM_FUNCTION_RISCV_RE),
+      'riscv64': (scrub_asm_riscv, ASM_FUNCTION_RISCV_RE),
+      's390x': (scrub_asm_systemz, ASM_FUNCTION_SYSTEMZ_RE),
+  }
+  handlers = None
+  for prefix, s in target_handlers.items():
+    if triple.startswith(prefix):
+      handlers = s
+      break
+  else:
+    raise KeyError('Triple %r is not supported' % (triple))
+
+  scrubber, function_re = handlers
+  common.build_function_body_dictionary(
+          function_re, scrubber, [args], raw_tool_output, prefixes,
+          func_dict, args.verbose)
diff --git a/llvm/utils/UpdateTestChecks/common.py b/llvm/utils/UpdateTestChecks/common.py
new file mode 100644
index 0000000..f8f75c8
--- /dev/null
+++ b/llvm/utils/UpdateTestChecks/common.py
@@ -0,0 +1,65 @@
+import re
+import subprocess
+
+RUN_LINE_RE = re.compile('^\s*;\s*RUN:\s*(.*)$')
+CHECK_PREFIX_RE = re.compile('--?check-prefix(?:es)?=(\S+)')
+CHECK_RE = re.compile(r'^\s*;\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
+
+IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@(\w+)\s*\(')
+TRIPLE_IR_RE = re.compile(r'^target\s+triple\s*=\s*"([^"]+)"$')
+TRIPLE_ARG_RE = re.compile(r'-mtriple=([^ ]+)')
+
+SCRUB_LEADING_WHITESPACE_RE = re.compile(r'^(\s+)')
+SCRUB_WHITESPACE_RE = re.compile(r'(?!^(|  \w))[ \t]+', flags=re.M)
+SCRUB_TRAILING_WHITESPACE_RE = re.compile(r'[ \t]+$', flags=re.M)
+SCRUB_KILL_COMMENT_RE = re.compile(r'^ *#+ +kill:.*\n')
+SCRUB_LOOP_COMMENT_RE = re.compile(
+    r'# =>This Inner Loop Header:.*|# in Loop:.*', flags=re.M)
+
+def should_add_line_to_output(input_line, prefix_set):
+  # Skip any blank comment lines in the IR.
+  if input_line.strip() == ';':
+    return False
+  # Skip any blank lines in the IR.
+  #if input_line.strip() == '':
+  #  return False
+  # And skip any CHECK lines. We're building our own.
+  m = CHECK_RE.match(input_line)
+  if m and m.group(1) in prefix_set:
+    return False
+
+  return True
+
+# Invoke the tool that is being tested.
+def invoke_tool(exe, cmd_args, ir):
+  with open(ir) as ir_file:
+    stdout = subprocess.check_output(exe + ' ' + cmd_args,
+                                     shell=True, stdin=ir_file)
+  # Fix line endings to unix CR style.
+  stdout = stdout.replace('\r\n', '\n')
+  return stdout
+
+# Build up a dictionary of all the function bodies.
+def build_function_body_dictionary(function_re, scrubber, scrubber_args, raw_tool_output, prefixes, func_dict, verbose):
+  for m in function_re.finditer(raw_tool_output):
+    if not m:
+      continue
+    func = m.group('func')
+    scrubbed_body = scrubber(m.group('body'), *scrubber_args)
+    if func.startswith('stress'):
+      # We only use the last line of the function body for stress tests.
+      scrubbed_body = '\n'.join(scrubbed_body.splitlines()[-1:])
+    if verbose:
+      print >>sys.stderr, 'Processing function: ' + func
+      for l in scrubbed_body.splitlines():
+        print >>sys.stderr, '  ' + l
+    for prefix in prefixes:
+      if func in func_dict[prefix] and func_dict[prefix][func] != scrubbed_body:
+        if prefix == prefixes[-1]:
+          print >>sys.stderr, ('WARNING: Found conflicting asm under the '
+                               'same prefix: %r!' % (prefix,))
+        else:
+          func_dict[prefix][func] = None
+          continue
+
+      func_dict[prefix][func] = scrubbed_body