Use ProfileSummary:getProfileCount to get ScaledCount for ModuleSummary

[danielcdh]

Summary

ModuleSummary should use the standard interface of ProfileSummary::getProfileCount.

[tejohnson]

lib/Analysis/ModuleSummaryAnalysis.cpp

235

We already have the instruction (&I), no need to consult the CS.

test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll

53

Do we get a profile count on a call instruction that gives a different weight than the enclosing BB only for SamplePGO I guess?

[danielcdh]

update

[danielcdh]

test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll

53

Yes, only SamplePGO sets the profile count on call instructions.

[tejohnson]

LGTM

lib/Analysis/ModuleSummaryAnalysis.cpp

for (const Instruction &I : BB) {
         if (CI && CalledFunction->isIntrinsic()) {
           addIntrinsicToSummary(
               CI, TypeTests, TypeTestAssumeVCalls, TypeCheckedLoadVCalls,
               TypeTestAssumeConstVCalls, TypeCheckedLoadConstVCalls);
           continue;
         }
         // We should have named any anonymous globals
         assert(CalledFunction->hasName());
-        auto ScaledCount = BFI ? BFI->getBlockProfileCount(&BB) : None;
+        auto ScaledCount = ProfileSummaryInfo::getProfileCount(&I, BFI);
         auto Hotness = ScaledCount ? getHotness(ScaledCount.getValue(), PSI)
                                    : CalleeInfo::HotnessType::Unknown;
 
         // Use the original CalledValue, in case it was an alias. We want
         // to record the call edge to the alias in that case. Eventually
         // an alias summary will be created to associate the alias and
         // aliasee.
         CallGraphEdges[cast<GlobalValue>(CalledValue)].updateHotness(Hotness);
       } else {

test/Bitcode/thinlto-function-summary-callgraph-profile-summary.ll

 ; Test to check the callgraph in summary when there is PGO
 ; RUN: opt -module-summary %s -o %t.o
 ; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
 ; RUN: opt -module-summary %p/Inputs/thinlto-function-summary-callgraph-profile-summary.ll -o %t2.o
 ; RUN: llvm-lto -thinlto -o %t3 %t.o %t2.o
 ; RUN: llvm-bcanalyzer -dump %t3.thinlto.bc | FileCheck %s --check-prefix=COMBINED
 
 
 ; CHECK-LABEL:       <GLOBALVAL_SUMMARY_BLOCK
 ; CHECK-NEXT:    <VERSION
 ; See if the call to func is registered, using the expected callsite count
 ; and profile count, with value id matching the subsequent value symbol table.
-; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op4=[[HOT1:.*]] op5=3 op6=[[COLD:.*]] op7=1 op8=[[HOT2:.*]] op9=3 op10=[[NONE1:.*]] op11=2 op12=[[HOT3:.*]] op13=3 op14=[[NONE2:.*]] op15=2 op16=[[NONE3:.*]] op17=2 op18=[[LEGACY:.*]] op19=3/>
+; CHECK-NEXT:    <PERMODULE_PROFILE {{.*}} op4=[[HOT1:.*]] op5=3 op6=[[COLD:.*]] op7=1 op8=[[HOT2:.*]] op9=3 op10=[[HOT4:.*]] op11=3 op12=[[NONE1:.*]] op13=2 op14=[[HOT3:.*]] op15=3 op16=[[NONE2:.*]] op17=2 op18=[[NONE3:.*]] op19=2 op20=[[LEGACY:.*]] op21=3/>
 ; CHECK-NEXT:  </GLOBALVAL_SUMMARY_BLOCK>
 ; CHECK-LABEL:  <VALUE_SYMTAB
 ; CHECK-NEXT:       <FNENTRY {{.*}} record string = 'hot_function
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[NONE1]] {{.*}} record string = 'none1'
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[COLD]] {{.*}} record string = 'cold'
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[NONE2]] {{.*}} record string = 'none2'
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[NONE3]] {{.*}} record string = 'none3'
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[HOT1]] {{.*}} record string = 'hot1'
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[HOT2]] {{.*}} record string = 'hot2'
 ; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[HOT3]] {{.*}} record string = 'hot3'
+; CHECK-DAG:        <ENTRY abbrevid=6 op0=[[HOT4]] {{.*}} record string = 'hot4'
 ; CHECK-DAG:        <COMBINED_ENTRY abbrevid=11 op0=[[LEGACY]] op1=123/>
 ; CHECK-LABEL:  </VALUE_SYMTAB>
 
 ; COMBINED:       <GLOBALVAL_SUMMARY_BLOCK
 ; COMBINED-NEXT:    <VERSION
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=
 ; COMBINED-NEXT:    <COMBINED abbrevid=

 ; This function have high profile count, so entry block is hot.
 define void @hot_function(i1 %a, i1 %a2) !prof !20 {
 entry:
     call void @hot1()
     br i1 %a, label %Cold, label %Hot, !prof !41
 Cold:           ; 1/1000 goes here
   call void @cold()
   call void @hot2()
+  call void @hot4(), !prof !15
   call void @none1()
   br label %exit
 Hot:            ; 999/1000 goes here
   call void @hot2()
   call void @hot3()
   br i1 %a2, label %None1, label %None2, !prof !42
 None1:          ; half goes here
   call void @none1()
   call void @none2()
   br label %exit
 None2:          ; half goes here
   call void @none3()
   br label %exit
 exit:
   ret void
 }
 
 declare void @hot1() #1
 declare void @hot2() #1
 declare void @hot3() #1
+declare void @hot4() #1
 declare void @cold() #1
 declare void @none1() #1
 declare void @none2() #1
 declare void @none3() #1
 
 
 !41 = !{!"branch_weights", i32 1, i32 1000}
 !42 = !{!"branch_weights", i32 1, i32 1}

 !7 = !{!"MaxFunctionCount", i64 1000}
 !8 = !{!"NumCounts", i64 3}
 !9 = !{!"NumFunctions", i64 3}
 !10 = !{!"DetailedSummary", !11}
 !11 = !{!12, !13, !14}
 !12 = !{i32 10000, i64 100, i32 1}
 !13 = !{i32 999000, i64 100, i32 1}
 !14 = !{i32 999999, i64 1, i32 2}
+!15 = !{!"branch_weights", i32 100}