[CSSPGO] Turn on Profi by default

[hoy]

Summary

As titled.

[wenlei]

lgtm, thanks!

[wlei]

LGTM, thanks!

[spupyrev]

Awesome!

llvm/lib/Transforms/IPO/SampleProfile.cpp

if (Reader->profileIsCS()) {
 
     // For CSSPGO, we also allow recursive inline to best use context profile.
     if (!AllowRecursiveInline.getNumOccurrences())
       AllowRecursiveInline = true;
 
     // Enable iterative-BFI by default for CSSPGO.
     if (!UseIterativeBFIInference.getNumOccurrences())
       UseIterativeBFIInference = true;
+    // Enable Profi by default for CSSPGO.
+    if (!SampleProfileUseProfi.getNumOccurrences())
+      SampleProfileUseProfi = true;
 
     // Tracker for profiles under different context
     ContextTracker = std::make_unique<SampleContextTracker>(
         Reader->getProfiles(), &GUIDToFuncNameMap);
   }
 
   // Load pseudo probe descriptors for probe-based function samples.
   if (Reader->profileIsProbeBased()) {

llvm/test/Transforms/SampleProfile/csspgo-import-list.ll

 ; _Z5funcBi:446061515086924981
 ; _Z8funcLeafi:7102633082150537521
 ; _Z5funcBiLeaf2:3815895320998406042
 ; _Z8funcLeafi3:-2862076748587597320
 ; _Z5funcAi:6309742469962978389
 ; _Z3fibi:-2016976694713209516
 
 ; CHECK: distinct !DISubprogram(name: "main"
-; CHECK: !{!"function_entry_count", i64 3, i64 446061515086924981, i64 3815895320998406042, i64 7102633082150537521, i64 -2862076748587597320}
+; CHECK: !{!"function_entry_count", i64 1, i64 446061515086924981, i64 3815895320998406042, i64 7102633082150537521, i64 -2862076748587597320}
 
 ; CHECK-ORDERED: FuncOffsetTableSection {{.*}} {ordered}
 
-; THRESHOLD: !{!"function_entry_count", i64 3}
-; THRESHOLD-REPLAY: !{!"function_entry_count", i64 3, i64 446061515086924981, i64 3815895320998406042, i64 6309742469962978389, i64 7102633082150537521, i64 -2862076748587597320, i64 -2016976694713209516}
-; THRESHOLD-REPLAY-NO-FUNCA: !{!"function_entry_count", i64 3, i64 446061515086924981, i64 3815895320998406042, i64 6309742469962978389, i64 7102633082150537521, i64 -2862076748587597320}
+; THRESHOLD: !{!"function_entry_count", i64 1}
+; THRESHOLD-REPLAY: !{!"function_entry_count", i64 1, i64 446061515086924981, i64 3815895320998406042, i64 6309742469962978389, i64 7102633082150537521, i64 -2862076748587597320, i64 -2016976694713209516}
+; THRESHOLD-REPLAY-NO-FUNCA: !{!"function_entry_count", i64 1, i64 446061515086924981, i64 3815895320998406042, i64 6309742469962978389, i64 7102633082150537521, i64 -2862076748587597320}
 
 attributes #0 = { nofree noinline norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" "use-sample-profile" }
 
 !llvm.dbg.cu = !{!2}
 !llvm.module.flags = !{!14, !15, !16}
 !llvm.ident = !{!17}
 
 !0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())

llvm/test/Transforms/SampleProfile/csspgo-summary.ll

 ; Test for CSSPGO's profile summary computation with and without pre-merging context profiles
 
-; RUN: opt < %s -passes=sample-profile,print-profile-summary -sample-profile-file=%S/Inputs/profile-context-tracker.prof -profile-summary-cutoff-hot=999900 -profile-sample-accurate -profile-summary-contextless=0 -S -o /dev/null 2>&1 | FileCheck %s --check-prefix=SUMMARY-UNMERGED
-; RUN: opt < %s -passes=sample-profile,print-profile-summary -sample-profile-file=%S/Inputs/profile-context-tracker.prof -profile-summary-cutoff-hot=999900 -profile-sample-accurate -profile-summary-contextless=1 -S -o /dev/null 2>&1 | FileCheck %s --check-prefix=SUMMARY-MERGED
+; RUN: opt < %s -passes=sample-profile,print-profile-summary -sample-profile-use-profi=0 -sample-profile-file=%S/Inputs/profile-context-tracker.prof -profile-summary-cutoff-hot=999900 -profile-sample-accurate -profile-summary-contextless=0 -S -o /dev/null 2>&1 | FileCheck %s --check-prefix=SUMMARY-UNMERGED
+; RUN: opt < %s -passes=sample-profile,print-profile-summary -sample-profile-use-profi=0 -sample-profile-file=%S/Inputs/profile-context-tracker.prof -profile-summary-cutoff-hot=999900 -profile-sample-accurate -profile-summary-contextless=1 -S -o /dev/null 2>&1 | FileCheck %s --check-prefix=SUMMARY-MERGED
 
 ; SUMMARY-UNMERGED: main :hot entry
 ; SUMMARY-MERGED-NOT: main :hot entry
 
 
 @factor = dso_local global i32 3, align 4, !dbg !0
 
 define dso_local i32 @main() local_unnamed_addr #0 !dbg !18 {

llvm/test/Transforms/SampleProfile/profile-context-tracker.ll

entry:
   %call = tail call i32 @_Z8funcLeafi(i32 %sub), !dbg !52
 ; _Z5funcBi is not inlined into main, so we main->_Z5funcBi->_Z8funcLeafi
 ; should be inlined based on promoted context profile
 ; INLINE-ALL-NOT: call i32 @_Z8funcLeafi
 ; INLINE-HOT-NOT: call i32 @_Z8funcLeafi
   ret i32 %call, !dbg !53
 }
 
-; INLINE-ALL-DAG: [[MAIN_PROF]] = !{!"function_entry_count", i64 13}
+; INLINE-ALL-DAG: [[MAIN_PROF]] = !{!"function_entry_count", i64 1}
 ; INLINE-ALL-DAG: [[FUNCA_PROF]] = !{!"function_entry_count", i64 0}
 ; INLINE-ALL-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 0}
-; INLINE-ALL-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 33}
+; INLINE-ALL-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 13}
 
-; INLINE-HOT-DAG: [[MAIN_PROF]] = !{!"function_entry_count", i64 13}
+; INLINE-HOT-DAG: [[MAIN_PROF]] = !{!"function_entry_count", i64 1}
 ; INLINE-HOT-DAG: [[FUNCA_PROF]] = !{!"function_entry_count", i64 12}
 ; INLINE-HOT-DAG-SAME: [[LEAF_PROF]] = !{!"function_entry_count", i64 0}
-; INLINE-HOT-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 33}
+; INLINE-HOT-DAG: [[FUNCB_PROF]] = !{!"function_entry_count", i64 13}
 
 declare i32 @_Z3fibi(i32)
 
 attributes #0 = { nofree noinline norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" "use-sample-profile" }
 attributes #1 = { nofree norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="none" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+cx8,+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" "use-sample-profile" }
 
 !llvm.dbg.cu = !{!2}
 !llvm.module.flags = !{!14, !15, !16}

llvm/test/Transforms/SampleProfile/pseudo-probe-inline.ll

 ; CHECK: call void @llvm.pseudoprobe(i64 [[#GUID2]], i64 6, i32 0, i64 -1)
   %x.addr.2 = phi i32 [ %x.addr.0, %while.cond ], [ %x.addr.1, %while.cond2 ]
   ret i32 %x.addr.2, !dbg !51
 }
 
 ; CHECK: !llvm.pseudo_probe_desc = !{![[#DESC0:]], ![[#DESC1:]]}
 ; CHECK: ![[#DESC0]] = !{i64 [[#GUID1]], i64 [[#HASH1:]], !"foo"}
 ; CHECK: ![[#DESC1]] = !{i64 [[#GUID2]], i64 [[#HASH2:]], !"zen"}
-; CHECK: ![[PD1]] = !{!"branch_weights", i32 25, i32 1}
-; CHECK: ![[PD2]] = !{!"branch_weights", i32 382916, i32 25}
+; CHECK: ![[PD1]] = !{!"branch_weights", i32 5, i32 0}
+; CHECK: ![[PD2]] = !{!"branch_weights", i32 382915, i32 5}
 
 ; Checking to see if YAML file is generated and contains remarks
 ;YAML: --- !Passed
 ;YAML-NEXT:  Pass:            sample-profile-inline
 ;YAML-NEXT:  Name:            Inlined
 ;YAML-NEXT:  DebugLoc:        { File: test.cpp, Line: 10, Column: 11 }
 ;YAML-NEXT:  Function:        foo
 ;YAML-NEXT:  Args: