[llvm] f91b0f2 - [AutoFDO]Merge called target in body samples when flattening profiles

[Mingming Liu via llvm-commits]

Author: Mingming Liu
Date: 2023-03-31T13:24:59-07:00
New Revision: f91b0f23c2f85361a9d20821ceadea770727425d

URL: https://github.com/llvm/llvm-project/commit/f91b0f23c2f85361a9d20821ceadea770727425d
DIFF: https://github.com/llvm/llvm-project/commit/f91b0f23c2f85361a9d20821ceadea770727425d.diff

LOG: [AutoFDO]Merge called target in body samples when flattening profiles

- Body samples could have call targets, merge them as well.

Differential Revision: https://reviews.llvm.org/D147297

Added: 
    

Modified: 
    llvm/include/llvm/ProfileData/SampleProf.h
    llvm/test/tools/llvm-profdata/Inputs/sample-flatten-profile.proftext
    llvm/test/tools/llvm-profdata/sample-flatten-profile.test

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/ProfileData/SampleProf.h b/llvm/include/llvm/ProfileData/SampleProf.h
index 8e76af2316cea..cd376e3023129 100644
--- a/llvm/include/llvm/ProfileData/SampleProf.h
+++ b/llvm/include/llvm/ProfileData/SampleProf.h
@@ -777,6 +777,11 @@ class FunctionSamples {
         FName, Num, Weight);
   }
 
+  sampleprof_error addSampleRecord(LineLocation Location,
+                                   const SampleRecord &SampleRecord, uint64_t Weight = 1) {
+    return BodySamples[Location].merge(SampleRecord, Weight);
+  }
+
   // Remove a call target and decrease the body sample correspondingly. Return
   // the number of body samples actually decreased.
   uint64_t removeCalledTargetAndBodySample(uint32_t LineOffset,
@@ -1342,7 +1347,7 @@ class ProfileConverter {
     // To retain the context, checksum, attributes of the original profile, make
     // a copy of it if no profile is found.
     SampleContext &Context = FS.getContext();
-    auto Ret = OutputProfiles.emplace(Context, FS);
+    auto Ret = OutputProfiles.try_emplace(Context, FS);
     FunctionSamples &Profile = Ret.first->second;
     if (Ret.second) {
       // When it's the copy of the old profile, just clear all the inlinees'
@@ -1351,9 +1356,8 @@ class ProfileConverter {
       // We recompute TotalSamples later, so here set to zero.
       Profile.setTotalSamples(0);
     } else {
-      for (const auto &Line : FS.getBodySamples()) {
-        Profile.addBodySamples(Line.first.LineOffset, Line.first.Discriminator,
-                               Line.second.getSamples());
+      for (const auto &[LineLocation, SampleRecord] : FS.getBodySamples()) {
+        Profile.addSampleRecord(LineLocation, SampleRecord);
       }
     }
 

diff  --git a/llvm/test/tools/llvm-profdata/Inputs/sample-flatten-profile.proftext b/llvm/test/tools/llvm-profdata/Inputs/sample-flatten-profile.proftext
index bb0bf51c6a194..51be9e2b0074d 100644
--- a/llvm/test/tools/llvm-profdata/Inputs/sample-flatten-profile.proftext
+++ b/llvm/test/tools/llvm-profdata/Inputs/sample-flatten-profile.proftext
@@ -1,6 +1,8 @@
 baz:160:10
  1: 10
  3: 20
+ 4: 21 qux:5 quux:6 corge:10
+ 4.1: 12 quux:3 grault:4 thud:5
  5: foo:30
   1: 20
   3: bar:10
@@ -25,6 +27,7 @@ main:110:1
   !CFGChecksum: 3
   !Attributes: 3
  10: baz:20
+  4: 15 qux:3 quux:7 corge:5
   10: 1
   6: bar:3
    1: 2

diff  --git a/llvm/test/tools/llvm-profdata/sample-flatten-profile.test b/llvm/test/tools/llvm-profdata/sample-flatten-profile.test
index 90effcb25190e..f99021bc6b723 100644
--- a/llvm/test/tools/llvm-profdata/sample-flatten-profile.test
+++ b/llvm/test/tools/llvm-profdata/sample-flatten-profile.test
@@ -7,6 +7,8 @@
 ; CHECK:baz:169:10
 ; CHECK-NEXT: 1: 10
 ; CHECK-NEXT: 3: 20
+; CHECK-NEXT: 4: 36 corge:15 quux:13 qux:8
+; CHECK-NEXT: 4.1: 12 thud:5 grault:4 quux:3
 ; CHECK-NEXT: 5: 20 foo:20
 ; CHECK-NEXT: 6: 2 bar:2
 ; CHECK-NEXT: 10: 1
@@ -18,12 +20,12 @@
 ; CHECK-NEXT: 4: 1
 ; CHECK-NEXT: !CFGChecksum: 3
 ; CHECK-NEXT: !Attributes: 3
-; CHECK-NEXT:main:91:1
+; CHECK-NEXT:main:104:1
 ; CHECK-NEXT: 4: 1
 ; CHECK-NEXT: 4.2: 1
 ; CHECK-NEXT: 7: 1
 ; CHECK-NEXT: 9: 3 bar:2 foo:1
-; CHECK-NEXT: 10: 3 baz:2 foo:1
+; CHECK-NEXT: 10: 16 baz:15 foo:1
 ; CHECK-NEXT: !CFGChecksum: 2
 ; CHECK-NEXT: !Attributes: 2
 ; CHECK-NEXT:bar:15:14