[UpdateTestChecks] Capture function signature variable definitions

[arichardson]

Summary

Currently, even when using --function-signature, the first use of an
argument will create a new FileCheck capture (e.g. [[X:%.*]]) even though
the value has already been captured in the CHECK-SAME line for the
function signature.
To fix this problem return the vars_seen set from genericize_check_lines()
and pass it to the second call so that it sees the variables captured
as part of the function signature.

[merge_guards_bot]

clang-format: pass.

Build artifacts: console-log.txt, diff.json

[jdoerfert]

Isn't this a copy of D69722 ? We need to get the testing stuff in so my pending patches can go in as well.

[arichardson]

In D71456#1783745, @jdoerfert wrote:

Isn't this a copy of D69722 ? We need to get the testing stuff in so my pending patches can go in as well.

Ah yes indeed, sorry about that. I should set up a rule to get notified about update script changes.

I'll commit the test change shortly (probably tomorrow UK time), just giving @MaskRay and @xbolva00 a chance to comment before.

[arichardson]

Duplicate of D69722 with a worse python implementation.

[jdoerfert]

In D71456#1784020, @arichardson wrote:

In D71456#1783745, @jdoerfert wrote:

Isn't this a copy of D69722 ? We need to get the testing stuff in so my pending patches can go in as well.

Ah yes indeed, sorry about that. I should set up a rule to get notified about update script changes.

I'll commit the test change shortly (probably tomorrow UK time), just giving @MaskRay and @xbolva00 a chance to comment before.

Perfect, thanks again for the testing infrastructure. Really appreciated!

llvm/test/tools/UpdateTestChecks/update_cc_test_checks/Inputs/mangled_names.c.funcsig.expected

 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // Example input for update_cc_test_checks
 // RUN: %clang_cc1 -triple=x86_64-unknown-linux-gnu -emit-llvm -o - %s | FileCheck %s
 
 // CHECK-LABEL: define {{[^@]+}}@test
 // CHECK-SAME: (i64 [[A:%.*]], i32 [[B:%.*]]) #0
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
 // CHECK-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
-// CHECK-NEXT:    store i64 [[A:%.*]], i64* [[A_ADDR]], align 8
-// CHECK-NEXT:    store i32 [[B:%.*]], i32* [[B_ADDR]], align 4
+// CHECK-NEXT:    store i64 [[A]], i64* [[A_ADDR]], align 8
+// CHECK-NEXT:    store i32 [[B]], i32* [[B_ADDR]], align 4
 // CHECK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[A_ADDR]], align 8
 // CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B_ADDR]], align 4
 // CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[TMP1]] to i64
 // CHECK-NEXT:    [[ADD:%.*]] = add nsw i64 [[TMP0]], [[CONV]]
 // CHECK-NEXT:    ret i64 [[ADD]]
 //
 long test(long a, int b) {
   return a + b;
 }
 
 // A function with a mangled name
 // CHECK-LABEL: define {{[^@]+}}@_Z4testlii
 // CHECK-SAME: (i64 [[A:%.*]], i32 [[B:%.*]], i32 [[C:%.*]]) #0
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[A_ADDR:%.*]] = alloca i64, align 8
 // CHECK-NEXT:    [[B_ADDR:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    [[C_ADDR:%.*]] = alloca i32, align 4
-// CHECK-NEXT:    store i64 [[A:%.*]], i64* [[A_ADDR]], align 8
-// CHECK-NEXT:    store i32 [[B:%.*]], i32* [[B_ADDR]], align 4
-// CHECK-NEXT:    store i32 [[C:%.*]], i32* [[C_ADDR]], align 4
+// CHECK-NEXT:    store i64 [[A]], i64* [[A_ADDR]], align 8
+// CHECK-NEXT:    store i32 [[B]], i32* [[B_ADDR]], align 4
+// CHECK-NEXT:    store i32 [[C]], i32* [[C_ADDR]], align 4
 // CHECK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[A_ADDR]], align 8
 // CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B_ADDR]], align 4
 // CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[TMP1]] to i64
 // CHECK-NEXT:    [[ADD:%.*]] = add nsw i64 [[TMP0]], [[CONV]]
 // CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[C_ADDR]], align 4
 // CHECK-NEXT:    [[CONV1:%.*]] = sext i32 [[TMP2]] to i64
 // CHECK-NEXT:    [[ADD2:%.*]] = add nsw i64 [[ADD]], [[CONV1]]
 // CHECK-NEXT:    ret i64 [[ADD2]]
 //
 __attribute__((overloadable)) long test(long a, int b, int c) {
   return a + b + c;
 }

llvm/test/tools/UpdateTestChecks/update_test_checks/Inputs/basic.ll.funcsig.expected

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Example input for update_llc_test_checks (taken from test/Transforms/InstSimplify/add.ll)
 ; RUN: opt < %s -instsimplify -S | FileCheck %s
 
 define i32 @common_sub_operand(i32 %X, i32 %Y) {
 ; CHECK-LABEL: define {{[^@]+}}@common_sub_operand
 ; CHECK-SAME: (i32 [[X:%.*]], i32 [[Y:%.*]])
-; CHECK-NEXT:    ret i32 [[X:%.*]]
+; CHECK-NEXT:    ret i32 [[X]]
 ;
   %Z = sub i32 %X, %Y
   %Q = add i32 %Z, %Y
   ret i32 %Q
 }
 
 define i32 @negated_operand(i32 %x) {
 ; CHECK-LABEL: define {{[^@]+}}@negated_operand

llvm/utils/UpdateTestChecks/common.py

def get_value_definition(var):
   return '[[' + get_value_name(var) + ':%.*]]'
 
 
 # Use a FileCheck variable.
 def get_value_use(var):
   return '[[' + get_value_name(var) + ']]'
 
 # Replace IR value defs and uses with FileCheck variables.
-def genericize_check_lines(lines, is_analyze):
+def genericize_check_lines(lines, is_analyze, vars_seen=None):
   # This gets called for each match that occurs in
   # a line. We transform variables we haven't seen
   # into defs, and variables we have seen into uses.
   def transform_line_vars(match):
     var = match.group(2)
     if var in vars_seen:
       rv = get_value_use(var)
     else:
       vars_seen.add(var)
       rv = get_value_definition(var)
     # re.sub replaces the entire regex match
     # with whatever you return, so we have
     # to make sure to hand it back everything
     # including the commas and spaces.
     return match.group(1) + rv + match.group(3)
 
+  if vars_seen is None:
     vars_seen = set()
   lines_with_def = []
 
   for i, line in enumerate(lines):
     # An IR variable named '%.' matches the FileCheck regex string.
     line = line.replace('%.', '%dot')
     # Ignore any comments, since the check lines will too.
     scrubbed_line = SCRUB_IR_COMMENT_RE.sub(r'', line)
     if is_analyze:
       lines[i] = scrubbed_line
     else:
       lines[i] = IR_VALUE_RE.sub(transform_line_vars, scrubbed_line)
-  return lines
+  return lines, vars_seen
 
 
 def add_checks(output_lines, comment_marker, prefix_list, func_dict, func_name, check_label_format, is_asm, is_analyze):
   printed_prefixes = []
   for p in prefix_list:
     checkprefixes = p[0]
     for checkprefix in checkprefixes:
       if checkprefix in printed_prefixes:
         break
       # TODO func_dict[checkprefix] may be None, '' or not exist.
       # Fix the call sites.
       if func_name not in func_dict[checkprefix] or not func_dict[checkprefix][func_name]:
         continue
 
       # Add some space between different check prefixes, but not after the last
       # check line (before the test code).
       if is_asm:
         if len(printed_prefixes) != 0:
           output_lines.append(comment_marker)
 
       printed_prefixes.append(checkprefix)
       args_and_sig = str(func_dict[checkprefix][func_name].args_and_sig)
-      args_and_sig = genericize_check_lines([args_and_sig], is_analyze)[0]
+      args_and_sig, vars_seen = genericize_check_lines([args_and_sig], is_analyze)
+      assert len(args_and_sig) == 1
+      args_and_sig = args_and_sig[0]
       if '[[' in args_and_sig:
         output_lines.append(check_label_format % (checkprefix, func_name, ''))
         output_lines.append('%s %s-SAME: %s' % (comment_marker, checkprefix, args_and_sig))
       else:
         output_lines.append(check_label_format % (checkprefix, func_name, args_and_sig))
       func_body = str(func_dict[checkprefix][func_name]).splitlines()
 
       # For ASM output, just emit the check lines.
       if is_asm:
         output_lines.append('%s %s:       %s' % (comment_marker, checkprefix, func_body[0]))
         for func_line in func_body[1:]:
           if func_line.strip() == '':
             output_lines.append('%s %s-EMPTY:' % (comment_marker, checkprefix))
           else:
             output_lines.append('%s %s-NEXT:  %s' % (comment_marker, checkprefix, func_line))
         break
 
       # For IR output, change all defs to FileCheck variables, so we're immune
       # to variable naming fashions.
-      func_body = genericize_check_lines(func_body, is_analyze)
+      func_body, vars_seen = genericize_check_lines(func_body, is_analyze, vars_seen)
 
       # This could be selectively enabled with an optional invocation argument.
       # Disabled for now: better to check everything. Be safe rather than sorry.
 
       # Handle the first line of the function body as a special case because
       # it's often just noise (a useless asm comment or entry label).
       #if func_body[0].startswith("#") or func_body[0].startswith("entry:"):
       #  is_blank_line = True