[PGO] Function section hotness prefix should look at all blocks
Summary:
The function section prefix for PGO based layout (e.g. hot/unlikely)
should look at the hotness of all blocks not just the entry BB.
A function with a cold entry but a very hot loop should be placed in the
hot section, for example, so that it is located close to other hot
functions it may call. For SamplePGO it was already looking at the
branch weights on calls, and I made that code conditional on whether
this is SamplePGO since it was essentially a noop for instrumentation
PGO anyway.
Reviewers: davidxl
Subscribers: eraman, llvm-commits
Differential Revision: https://reviews.llvm.org/D41395
llvm-svn: 321197
diff --git a/llvm/test/Transforms/CodeGenPrepare/section.ll b/llvm/test/Transforms/CodeGenPrepare/section.ll
index 4f3144e..30598ba 100644
--- a/llvm/test/Transforms/CodeGenPrepare/section.ll
+++ b/llvm/test/Transforms/CodeGenPrepare/section.ll
@@ -4,33 +4,59 @@
; This tests that hot/cold functions get correct section prefix assigned
-; CHECK: hot_func{{.*}}!section_prefix ![[HOT_ID:[0-9]+]]
+; CHECK: hot_func1{{.*}}!section_prefix ![[HOT_ID:[0-9]+]]
; The entry is hot
-define void @hot_func() !prof !15 {
+define void @hot_func1() !prof !15 {
ret void
}
-; For instrumentation based PGO, we should only look at entry counts,
+; CHECK: hot_func2{{.*}}!section_prefix ![[HOT_ID:[0-9]+]]
+; Entry is cold but inner block is hot
+define void @hot_func2(i32 %n) !prof !16 {
+entry:
+ %n.addr = alloca i32, align 4
+ %i = alloca i32, align 4
+ store i32 %n, i32* %n.addr, align 4
+ store i32 0, i32* %i, align 4
+ br label %for.cond
+
+for.cond:
+ %0 = load i32, i32* %i, align 4
+ %1 = load i32, i32* %n.addr, align 4
+ %cmp = icmp slt i32 %0, %1
+ br i1 %cmp, label %for.body, label %for.end, !prof !19
+
+for.body:
+ %2 = load i32, i32* %i, align 4
+ %inc = add nsw i32 %2, 1
+ store i32 %inc, i32* %i, align 4
+ br label %for.cond
+
+for.end:
+ ret void
+}
+
+; For instrumentation based PGO, we should only look at block counts,
; not call site VP metadata (which can exist on value profiled memcpy,
; or possibly left behind after static analysis based devirtualization).
; CHECK: cold_func1{{.*}}!section_prefix ![[COLD_ID:[0-9]+]]
define void @cold_func1() !prof !16 {
- call void @hot_func(), !prof !17
- call void @hot_func(), !prof !17
+ call void @hot_func1(), !prof !17
+ call void @hot_func1(), !prof !17
ret void
}
-; CHECK: cold_func2{{.*}}!section_prefix
+; CHECK: cold_func2{{.*}}!section_prefix ![[COLD_ID]]
define void @cold_func2() !prof !16 {
- call void @hot_func(), !prof !17
- call void @hot_func(), !prof !18
- call void @hot_func(), !prof !18
+ call void @hot_func1(), !prof !17
+ call void @hot_func1(), !prof !18
+ call void @hot_func1(), !prof !18
ret void
}
; CHECK: cold_func3{{.*}}!section_prefix ![[COLD_ID]]
define void @cold_func3() !prof !16 {
- call void @hot_func(), !prof !18
+ call void @hot_func1(), !prof !18
ret void
}
@@ -55,3 +81,4 @@
!16 = !{!"function_entry_count", i64 1}
!17 = !{!"branch_weights", i32 80}
!18 = !{!"branch_weights", i32 1}
+!19 = !{!"branch_weights", i32 1000, i32 1}