[FunctionSpecialization][nfc] Add a test for zero function entry count #160156
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This test is a follow up to llvm@7d748a9 which fixes an assertion crash that occurs if the profile count is 0. Additionally, modify `profile-counts.ll` to use `update_test_checks.py`.
alanzhao1
referenced
this pull request
Sep 22, 2025
… to zero We were hitting an assert discovered in #157768 (comment)
|
@llvm/pr-subscribers-llvm-transforms @llvm/pr-subscribers-function-specialization Author: Alan Zhao (alanzhao1) ChangesThis test is a follow up to 7d748a9 which fixes an assertion crash that occurs if the profile count is 0. Additionally, modify Full diff: https://github.com/llvm/llvm-project/pull/160156.diff 1 Files Affected:
diff --git a/llvm/test/Transforms/FunctionSpecialization/profile-counts.ll b/llvm/test/Transforms/FunctionSpecialization/profile-counts.ll
index bdf7690a71b69..4d26247ad09cb 100644
--- a/llvm/test/Transforms/FunctionSpecialization/profile-counts.ll
+++ b/llvm/test/Transforms/FunctionSpecialization/profile-counts.ll
@@ -1,20 +1,40 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 6
; RUN: opt -passes="ipsccp<func-spec>" -force-specialization -S < %s | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
@A = external dso_local constant i32, align 4
@B = external dso_local constant i32, align 4
-; CHECK: define dso_local i32 @bar(i32 %x, i32 %y, ptr %z) !prof ![[BAR_PROF:[0-9]]] {
+;.
+; CHECK: @A = external dso_local constant i32, align 4
+; CHECK: @B = external dso_local constant i32, align 4
+;.
define dso_local i32 @bar(i32 %x, i32 %y, ptr %z) !prof !0 {
+; CHECK-LABEL: define dso_local i32 @bar(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]], ptr [[Z:%.*]]) !prof [[PROF0:![0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[X]], 0
+; CHECK-NEXT: br i1 [[TOBOOL]], label %[[IF_THEN:.*]], label %[[IF_ELSE:.*]], !prof [[PROF1:![0-9]+]]
+; CHECK: [[IF_THEN]]:
+; CHECK-NEXT: [[CALL:%.*]] = call i32 @foo.specialized.1(i32 [[X]], ptr @A)
+; CHECK-NEXT: [[CALL1:%.*]] = call i32 @foo.specialized.2(i32 [[Y]], ptr @B)
+; CHECK-NEXT: [[CALL2:%.*]] = call i32 @foo.specialized.2(i32 [[Y]], ptr @B)
+; CHECK-NEXT: [[ADD:%.*]] = add i32 [[CALL]], [[CALL1]]
+; CHECK-NEXT: [[ADD1:%.*]] = add i32 [[ADD]], [[CALL2]]
+; CHECK-NEXT: br label %[[RETURN:.*]]
+; CHECK: [[IF_ELSE]]:
+; CHECK-NEXT: [[CALL3:%.*]] = call i32 @foo.specialized.2(i32 [[Y]], ptr @B)
+; CHECK-NEXT: br label %[[RETURN]]
+; CHECK: [[RETURN]]:
+; CHECK-NEXT: [[RETVAL_0:%.*]] = phi i32 [ [[ADD1]], %[[IF_THEN]] ], [ [[CALL3]], %[[IF_ELSE]] ]
+; CHECK-NEXT: [[CALL4:%.*]] = call i32 @foo(i32 [[X]], ptr [[Z]])
+; CHECK-NEXT: [[ADD2:%.*]] = add i32 [[RETVAL_0]], [[CALL4]]
+; CHECK-NEXT: ret i32 [[ADD2]]
+;
entry:
%tobool = icmp ne i32 %x, 0
-; CHECK: br i1 %tobool, label %if.then, label %if.else, !prof ![[BRANCH_PROF:[0-9]]]
br i1 %tobool, label %if.then, label %if.else, !prof !1
-; CHECK: if.then:
-; CHECK: call i32 @foo.specialized.1(i32 %x, ptr @A)
-; CHECK: call i32 @foo.specialized.2(i32 %y, ptr @B)
-; CHECK: call i32 @foo.specialized.2(i32 %y, ptr @B)
if.then:
%call = call i32 @foo(i32 %x, ptr @A)
%call1 = call i32 @foo(i32 %y, ptr @B)
@@ -23,14 +43,10 @@ if.then:
%add1 = add i32 %add, %call2
br label %return
-; CHECK: if.else:
-; CHECK: call i32 @foo.specialized.2(i32 %y, ptr @B)
if.else:
%call3 = call i32 @foo(i32 %y, ptr @B)
br label %return
-; CHECK: return:
-; CHECK: call i32 @foo(i32 %x, ptr %z)
return:
%retval.0 = phi i32 [ %add1, %if.then ], [ %call3, %if.else ]
%call4 = call i32 @foo(i32 %x, ptr %z);
@@ -38,21 +54,62 @@ return:
ret i32 %add2
}
-; CHECK: define internal i32 @foo(i32 %x, ptr %b) !prof ![[FOO_UNSPEC_PROF:[0-9]]]
-; CHECK: define internal i32 @foo.specialized.1(i32 %x, ptr %b) !prof ![[FOO_SPEC_1_PROF:[0-9]]]
-; CHECK: define internal i32 @foo.specialized.2(i32 %x, ptr %b) !prof ![[FOO_SPEC_2_PROF:[0-9]]]
-define internal i32 @foo(i32 %x, ptr %b) !prof !2 {
+define dso_local i32 @baz(i32 %x, i32 %y) !prof !2 {
+; CHECK-LABEL: define dso_local i32 @baz(
+; CHECK-SAME: i32 [[X:%.*]], i32 [[Y:%.*]]) !prof [[PROF2:![0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[X]], 0
+; CHECK-NEXT: br i1 [[TOBOOL]], label %[[IF_THEN:.*]], label %[[IF_ELSE:.*]]
+; CHECK: [[IF_THEN]]:
+; CHECK-NEXT: [[CALL:%.*]] = call i32 @foo.specialized.1(i32 [[X]], ptr @A)
+; CHECK-NEXT: br label %[[RETURN:.*]]
+; CHECK: [[IF_ELSE]]:
+; CHECK-NEXT: [[CALL1:%.*]] = call i32 @foo.specialized.2(i32 [[Y]], ptr @B)
+; CHECK-NEXT: br label %[[RETURN]]
+; CHECK: [[RETURN]]:
+; CHECK-NEXT: [[RETVAL_0:%.*]] = phi i32 [ [[CALL]], %[[IF_THEN]] ], [ [[CALL1]], %[[IF_ELSE]] ]
+; CHECK-NEXT: ret i32 [[RETVAL_0]]
+;
+entry:
+ %tobool = icmp ne i32 %x, 0
+ br i1 %tobool, label %if.then, label %if.else
+
+if.then:
+ %call = call i32 @foo(i32 %x, ptr @A)
+ br label %return
+
+if.else:
+ %call1 = call i32 @foo(i32 %y, ptr @B)
+ br label %return
+
+return:
+ %retval.0 = phi i32 [ %call, %if.then ], [ %call1, %if.else ]
+ ret i32 %retval.0
+}
+
+define internal i32 @foo(i32 %x, ptr %b) !prof !3 {
+; CHECK-LABEL: define internal i32 @foo(
+; CHECK-SAME: i32 [[X:%.*]], ptr [[B:%.*]]) !prof [[PROF3:![0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[B]], align 4
+; CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[X]], [[TMP0]]
+; CHECK-NEXT: ret i32 [[ADD]]
+;
entry:
%0 = load i32, ptr %b, align 4
%add = add nsw i32 %x, %0
ret i32 %add
}
-; CHECK: ![[BAR_PROF]] = !{!"function_entry_count", i64 1000}
-; CHECK: ![[BRANCH_PROF]] = !{!"branch_weights", i32 1, i32 3}
-; CHECK: ![[FOO_UNSPEC_PROF]] = !{!"function_entry_count", i64 500}
-; CHECK: ![[FOO_SPEC_1_PROF]] = !{!"function_entry_count", i64 250}
-; CHECK: ![[FOO_SPEC_2_PROF]] = !{!"function_entry_count", i64 1250}
!0 = !{!"function_entry_count", i64 1000}
!1 = !{!"branch_weights", i32 1, i32 3}
-!2 = !{!"function_entry_count", i64 2000}
+!2 = !{!"function_entry_count", i64 0}
+!3 = !{!"function_entry_count", i64 2000}
+;.
+; CHECK: [[PROF0]] = !{!"function_entry_count", i64 1000}
+; CHECK: [[PROF1]] = !{!"branch_weights", i32 1, i32 3}
+; CHECK: [[PROF2]] = !{!"function_entry_count", i64 0}
+; CHECK: [[PROF3]] = !{!"function_entry_count", i64 500}
+; CHECK: [[META4:![0-9]+]] = !{!"function_entry_count", i64 250}
+; CHECK: [[META5:![0-9]+]] = !{!"function_entry_count", i64 1250}
+;.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This test is a follow up to 7d748a9 which fixes an assertion crash that occurs if the profile count is 0.
Additionally, modify
profile-counts.llto useupdate_test_checks.py.