[CSSPGO] Compute checksum mismatch recursively on nested profile

[wlei]

Summary

Follow-up diff for https://reviews.llvm.org/D158891. Compute the checksum mismatch based on the original nested profile. Additionally, use a recursive way to compute the children mismatched samples in the nested tree even the top-level func checksum is matched.

[wenlei]

llvm/lib/Transforms/IPO/SampleProfile.cpp

2170

nit: countMismatchedSamples?

2199

Given MismatchedFuncHashSamples is a member of SampleProfileMatcher, we probably don't need to pass it all the way through the recursive calls?

Same for other statistics that is a member of SampleProfileMatcher.

[wlei]

llvm/lib/Transforms/IPO/SampleProfile.cpp

2170

done!

2199

Ah, good catch, I was designing to use the variable outside of the function.

[wlei]

Updating D158900: [CSSPGO] Compute checksum mismatch recursively on nested profile

[wlei]

rebase

[wlei]

rebase

[wlei]

rebase

[wenlei]

lgtm, thanks.

llvm/include/llvm/Transforms/Utils/SampleProfileLoaderBaseImpl.h

 } // end namespace afdo_detail
 
 // This class serves sample counts correlation for SampleProfileLoader by
 // analyzing pseudo probes and their function descriptors injected by
 // SampleProfileProber.
 class PseudoProbeManager {
   DenseMap<uint64_t, PseudoProbeDescriptor> GUIDToProbeDescMap;
 
-  const PseudoProbeDescriptor *getDesc(const Function &F) const {
-    auto I = GUIDToProbeDescMap.find(
-        Function::getGUID(FunctionSamples::getCanonicalFnName(F)));
-    return I == GUIDToProbeDescMap.end() ? nullptr : &I->second;
-  }
-
 public:
   PseudoProbeManager(const Module &M) {
     if (NamedMDNode *FuncInfo =
             M.getNamedMetadata(PseudoProbeDescMetadataName)) {
       for (const auto *Operand : FuncInfo->operands()) {
         const auto *MD = cast<MDNode>(Operand);
         auto GUID = mdconst::dyn_extract<ConstantInt>(MD->getOperand(0))
                         ->getZExtValue();
         auto Hash = mdconst::dyn_extract<ConstantInt>(MD->getOperand(1))
                         ->getZExtValue();
         GUIDToProbeDescMap.try_emplace(GUID, PseudoProbeDescriptor(GUID, Hash));
       }
     }
   }
 
+  const PseudoProbeDescriptor *getDesc(uint64_t GUID) const {
+    auto I = GUIDToProbeDescMap.find(GUID);
+    return I == GUIDToProbeDescMap.end() ? nullptr : &I->second;
+  }
+
+  const PseudoProbeDescriptor *getDesc(StringRef FProfileName) const {
+    return getDesc(Function::getGUID(FProfileName));
+  }
+
+  const PseudoProbeDescriptor *getDesc(const Function &F) const {
+    return getDesc(Function::getGUID(FunctionSamples::getCanonicalFnName(F)));
+  }
+
+  bool profileIsHashMismatched(const PseudoProbeDescriptor &FuncDesc,
+                               const FunctionSamples &Samples) const {
+    return FuncDesc.getFunctionHash() != Samples.getFunctionHash();
+  }
+
   bool moduleIsProbed(const Module &M) const {
     return M.getNamedMetadata(PseudoProbeDescMetadataName);
   }
 
   bool profileIsValid(const Function &F, const FunctionSamples &Samples) const {
     const auto *Desc = getDesc(F);
     if (!Desc) {
       LLVM_DEBUG(dbgs() << "Probe descriptor missing for Function "

llvm/lib/Transforms/IPO/SampleProfile.cpp

if (It != FlattenedProfiles.end())
       return &It->second;
     return nullptr;
   }
   void runOnFunction(const Function &F);
   void findIRAnchors(const Function &F,
                      std::map<LineLocation, StringRef> &IRAnchors);
   void findProfileAnchors(const FunctionSamples &FS,
                           std::map<LineLocation, StringSet<>> &ProfileAnchors);
+  void countMismatchedSamples(const FunctionSamples &FS);
   void countProfileMismatches(
       const Function &F, const FunctionSamples &FS,
       const std::map<LineLocation, StringRef> &IRAnchors,
       const std::map<LineLocation, StringSet<>> &ProfileAnchors);
   void countProfileCallsiteMismatches(
       const FunctionSamples &FS,
       const std::map<LineLocation, StringRef> &IRAnchors,
       const std::map<LineLocation, StringSet<>> &ProfileAnchors,
for (auto &I : BB) {
                 R.first->second == CalleeName) &&
                "Overwrite non-call or different callee name location for "
                "pseudo probe callsite");
       }
     }
   }
 }
 
+void SampleProfileMatcher::countMismatchedSamples(const FunctionSamples &FS) {
+  const auto *FuncDesc = ProbeManager->getDesc(FS.getName());
+  // Skip the function that is external or renamed.
+  if (!FuncDesc)
+    return;
+
+  if (ProbeManager->profileIsHashMismatched(*FuncDesc, FS)) {
+    MismatchedFuncHashSamples += FS.getTotalSamples();
+    return;
+  }
+  for (const auto &I : FS.getCallsiteSamples())
+    for (const auto &CS : I.second)
+      countMismatchedSamples(CS.second);
+}
+
 void SampleProfileMatcher::countProfileMismatches(
     const Function &F, const FunctionSamples &FS,
     const std::map<LineLocation, StringRef> &IRAnchors,
     const std::map<LineLocation, StringSet<>> &ProfileAnchors) {
   bool IsFuncHashMismatch = false;
   if (FunctionSamples::ProfileIsProbeBased) {
-    uint64_t Count = FS.getTotalSamples();
-    TotalFuncHashSamples += Count;
+    TotalFuncHashSamples += FS.getTotalSamples();
     TotalProfiledFunc++;
-    if (!ProbeManager->profileIsValid(F, FS)) {
-      MismatchedFuncHashSamples += Count;
+    const auto *FuncDesc = ProbeManager->getDesc(F);
+    if (FuncDesc) {
+      if (ProbeManager->profileIsHashMismatched(*FuncDesc, FS)) {
         NumMismatchedFuncHash++;
         IsFuncHashMismatch = true;
       }
+      countMismatchedSamples(FS);
+    }
   }
 
   uint64_t FuncMismatchedCallsites = 0;
   uint64_t FuncProfiledCallsites = 0;
   countProfileCallsiteMismatches(FS, IRAnchors, ProfileAnchors,
                                  FuncMismatchedCallsites,
                                  FuncProfiledCallsites);
   TotalProfiledCallsites += FuncProfiledCallsites;

llvm/test/Transforms/SampleProfile/Inputs/pseudo-probe-profile-mismatch-nested.prof

+main:300:0
+ 1: 0
+ 12: 10 matched:10
+ 20: 10 bar:10
+ 13: bar:200
+  1: 100
+  !CFGChecksum: 123
+ !CFGChecksum: 844635331715433
+bar:11:11
+ 1: 11
+# Original CFGChecksum is 4294967295
+ !CFGChecksum: 123

llvm/test/Transforms/SampleProfile/pseudo-probe-profile-mismatch.ll

 ; REQUIRES: x86_64-linux
 ; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/pseudo-probe-profile-mismatch.prof -report-profile-staleness -persist-profile-staleness -S 2>%t -o %t.ll
 ; RUN: FileCheck %s --input-file %t
 ; RUN: FileCheck %s --input-file %t.ll -check-prefix=CHECK-MD
 ; RUN: llc < %t.ll -filetype=obj -o %t.obj
 ; RUN: llvm-objdump --section-headers %t.obj | FileCheck %s --check-prefix=CHECK-OBJ
 ; RUN: llc < %t.ll -filetype=asm -o - | FileCheck %s --check-prefix=CHECK-ASM
 
+; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/pseudo-probe-profile-mismatch-nested.prof -report-profile-staleness -persist-profile-staleness -S 2>&1 | FileCheck %s --check-prefix=CHECK-NESTED
+
+
 ; CHECK: (1/3) of functions' profile are invalid and (10/50) of samples are discarded due to function hash mismatch.
 ; CHECK: (2/3) of callsites' profile are invalid and (20/30) of samples are discarded due to callsite location mismatch.
 
 ; CHECK-MD: ![[#]] = !{!"NumMismatchedFuncHash", i64 1, !"TotalProfiledFunc", i64 3, !"MismatchedFuncHashSamples", i64 10, !"TotalFuncHashSamples", i64 50, !"NumMismatchedCallsites", i64 2, !"TotalProfiledCallsites", i64 3, !"MismatchedCallsiteSamples", i64 20, !"TotalCallsiteSamples", i64 30}
 
 ; CHECK-OBJ: .llvm_stats
 
 ; CHECK-ASM: .section  .llvm_stats,"",@progbits

 ; CHECK-ASM: .ascii  "MismatchedCallsiteSamples"
 ; CHECK-ASM: .byte 4
 ; CHECK-ASM: .ascii  "MjA="
 ; CHECK-ASM: .byte 20
 ; CHECK-ASM: .ascii  "TotalCallsiteSamples"
 ; CHECK-ASM: .byte 4
 ; CHECK-ASM: .ascii  "MzA="
 
+; CHECK-NESTED: (1/2) of functions' profile are invalid and (211/311) of samples are discarded due to function hash mismatch.
+
+
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @x = dso_local global i32 0, align 4, !dbg !0
 
 ; Function Attrs: nounwind uwtable
 define dso_local i32 @foo(i32 noundef %x) #0 !dbg !16 {
 entry: