[NFC][MemProf] Move IndexedMemProfData to its own header. (#140503)

snehasish · web-flow · commit 0528848def29 · 2025-05-19T16:21:51.000-07:00
Part of a larger refactoring with the following goals
1. Reduce the size of MemProf.h 
2. Avoid including ModuleSummaryIndex just for a couple of types
diff --git a/llvm/include/llvm/ProfileData/IndexedMemProfData.h b/llvm/include/llvm/ProfileData/IndexedMemProfData.h
@@ -6,18 +6,84 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// MemProf data is serialized in writeMemProf provided in this header file.
+// This file implements IndexedMemProfData, a data structure to hold MemProf
+// in a space optimized format. It also provides utility methods for writing
+// MemProf data.
 //
 //===----------------------------------------------------------------------===//
 
+#ifndef LLVM_PROFILEDATA_INDEXEDMEMPROFDATA_H
+#define LLVM_PROFILEDATA_INDEXEDMEMPROFDATA_H
+
 #include "llvm/ProfileData/InstrProf.h"
 #include "llvm/ProfileData/MemProf.h"
 
 namespace llvm {
+namespace memprof {
+struct IndexedMemProfData {
+  // A map to hold memprof data per function. The lower 64 bits obtained from
+  // the md5 hash of the function name is used to index into the map.
+  llvm::MapVector<GlobalValue::GUID, IndexedMemProfRecord> Records;
+
+  // A map to hold frame id to frame mappings. The mappings are used to
+  // convert IndexedMemProfRecord to MemProfRecords with frame information
+  // inline.
+  llvm::MapVector<FrameId, Frame> Frames;
+
+  // A map to hold call stack id to call stacks.
+  llvm::MapVector<CallStackId, llvm::SmallVector<FrameId>> CallStacks;
+
+  FrameId addFrame(const Frame &F) {
+    const FrameId Id = hashFrame(F);
+    Frames.try_emplace(Id, F);
+    return Id;
+  }
+
+  CallStackId addCallStack(ArrayRef<FrameId> CS) {
+    CallStackId CSId = hashCallStack(CS);
+    CallStacks.try_emplace(CSId, CS);
+    return CSId;
+  }
+
+  CallStackId addCallStack(SmallVector<FrameId> &&CS) {
+    CallStackId CSId = hashCallStack(CS);
+    CallStacks.try_emplace(CSId, std::move(CS));
+    return CSId;
+  }
+
+private:
+  // Return a hash value based on the contents of the frame. Here we use a
+  // cryptographic hash function to minimize the chance of hash collisions.  We
+  // do persist FrameIds as part of memprof formats up to Version 2, inclusive.
+  // However, the deserializer never calls this function; it uses FrameIds
+  // merely as keys to look up Frames proper.
+  FrameId hashFrame(const Frame &F) const {
+    llvm::HashBuilder<llvm::TruncatedBLAKE3<8>, llvm::endianness::little>
+        HashBuilder;
+    HashBuilder.add(F.Function, F.LineOffset, F.Column, F.IsInlineFrame);
+    llvm::BLAKE3Result<8> Hash = HashBuilder.final();
+    FrameId Id;
+    std::memcpy(&Id, Hash.data(), sizeof(Hash));
+    return Id;
+  }
+
+  // Compute a CallStackId for a given call stack.
+  CallStackId hashCallStack(ArrayRef<FrameId> CS) const {
+    llvm::HashBuilder<llvm::TruncatedBLAKE3<8>, llvm::endianness::little>
+        HashBuilder;
+    for (FrameId F : CS)
+      HashBuilder.add(F);
+    llvm::BLAKE3Result<8> Hash = HashBuilder.final();
+    CallStackId CSId;
+    std::memcpy(&CSId, Hash.data(), sizeof(Hash));
+    return CSId;
+  }
+};
+} // namespace memprof
 
 // Write the MemProf data to OS.
 Error writeMemProf(ProfOStream &OS, memprof::IndexedMemProfData &MemProfData,
                    memprof::IndexedVersion MemProfVersionRequested,
                    bool MemProfFullSchema);
-
 } // namespace llvm
+#endif
diff --git a/llvm/include/llvm/ProfileData/InstrProfWriter.h b/llvm/include/llvm/ProfileData/InstrProfWriter.h
@@ -19,8 +19,8 @@
 #include "llvm/ADT/StringMap.h"
 #include "llvm/IR/GlobalValue.h"
 #include "llvm/Object/BuildID.h"
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/InstrProf.h"
-#include "llvm/ProfileData/MemProf.h"
 #include "llvm/Support/Error.h"
 #include <cstdint>
 #include <memory>
diff --git a/llvm/include/llvm/ProfileData/MemProf.h b/llvm/include/llvm/ProfileData/MemProf.h
@@ -842,57 +842,6 @@ struct LineLocation {
 
 // A pair of a call site location and its corresponding callee GUID.
 using CallEdgeTy = std::pair<LineLocation, uint64_t>;
-
-struct IndexedMemProfData {
-  // A map to hold memprof data per function. The lower 64 bits obtained from
-  // the md5 hash of the function name is used to index into the map.
-  llvm::MapVector<GlobalValue::GUID, IndexedMemProfRecord> Records;
-
-  // A map to hold frame id to frame mappings. The mappings are used to
-  // convert IndexedMemProfRecord to MemProfRecords with frame information
-  // inline.
-  llvm::MapVector<FrameId, Frame> Frames;
-
-  // A map to hold call stack id to call stacks.
-  llvm::MapVector<CallStackId, llvm::SmallVector<FrameId>> CallStacks;
-
-  FrameId addFrame(const Frame &F) {
-    const FrameId Id = hashFrame(F);
-    Frames.try_emplace(Id, F);
-    return Id;
-  }
-
-  CallStackId addCallStack(ArrayRef<FrameId> CS) {
-    CallStackId CSId = hashCallStack(CS);
-    CallStacks.try_emplace(CSId, CS);
-    return CSId;
-  }
-
-  CallStackId addCallStack(SmallVector<FrameId> &&CS) {
-    CallStackId CSId = hashCallStack(CS);
-    CallStacks.try_emplace(CSId, std::move(CS));
-    return CSId;
-  }
-
-private:
-  // Return a hash value based on the contents of the frame. Here we use a
-  // cryptographic hash function to minimize the chance of hash collisions.  We
-  // do persist FrameIds as part of memprof formats up to Version 2, inclusive.
-  // However, the deserializer never calls this function; it uses FrameIds
-  // merely as keys to look up Frames proper.
-  FrameId hashFrame(const Frame &F) const {
-    llvm::HashBuilder<llvm::TruncatedBLAKE3<8>, llvm::endianness::little>
-        HashBuilder;
-    HashBuilder.add(F.Function, F.LineOffset, F.Column, F.IsInlineFrame);
-    llvm::BLAKE3Result<8> Hash = HashBuilder.final();
-    FrameId Id;
-    std::memcpy(&Id, Hash.data(), sizeof(Hash));
-    return Id;
-  }
-
-  // Compute a CallStackId for a given call stack.
-  CallStackId hashCallStack(ArrayRef<FrameId> CS) const;
-};
 } // namespace memprof
 } // namespace llvm
 
diff --git a/llvm/include/llvm/ProfileData/MemProfRadixTree.h b/llvm/include/llvm/ProfileData/MemProfRadixTree.h
@@ -13,6 +13,7 @@
 #ifndef LLVM_PROFILEDATA_MEMPROFRADIXTREE_H
 #define LLVM_PROFILEDATA_MEMPROFRADIXTREE_H
 
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/MemProf.h"
 
 namespace llvm {
diff --git a/llvm/include/llvm/ProfileData/MemProfReader.h b/llvm/include/llvm/ProfileData/MemProfReader.h
@@ -21,6 +21,7 @@
 #include "llvm/IR/GlobalValue.h"
 #include "llvm/Object/Binary.h"
 #include "llvm/Object/ObjectFile.h"
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/InstrProfReader.h"
 #include "llvm/ProfileData/MemProfData.inc"
 #include "llvm/ProfileData/MemProfRadixTree.h"
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -61,6 +61,7 @@
 #include "llvm/MC/StringTableBuilder.h"
 #include "llvm/MC/TargetRegistry.h"
 #include "llvm/Object/IRSymtab.h"
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/MemProf.h"
 #include "llvm/ProfileData/MemProfRadixTree.h"
 #include "llvm/Support/AtomicOrdering.h"
diff --git a/llvm/lib/ProfileData/InstrProfWriter.cpp b/llvm/lib/ProfileData/InstrProfWriter.cpp
@@ -18,7 +18,6 @@
 #include "llvm/IR/ProfileSummary.h"
 #include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/InstrProf.h"
-#include "llvm/ProfileData/MemProf.h"
 #include "llvm/ProfileData/ProfileCommon.h"
 #include "llvm/Support/Compression.h"
 #include "llvm/Support/Endian.h"
diff --git a/llvm/lib/ProfileData/MemProf.cpp b/llvm/lib/ProfileData/MemProf.cpp
@@ -3,10 +3,8 @@
 #include "llvm/IR/Function.h"
 #include "llvm/ProfileData/InstrProf.h"
 #include "llvm/ProfileData/SampleProf.h"
-#include "llvm/Support/BLAKE3.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/EndianStream.h"
-#include "llvm/Support/HashBuilder.h"
 
 namespace llvm {
 namespace memprof {
@@ -384,16 +382,5 @@ Expected<MemProfSchema> readMemProfSchema(const unsigned char *&Buffer) {
   Buffer = Ptr;
   return Result;
 }
-
-CallStackId IndexedMemProfData::hashCallStack(ArrayRef<FrameId> CS) const {
-  llvm::HashBuilder<llvm::TruncatedBLAKE3<8>, llvm::endianness::little>
-      HashBuilder;
-  for (FrameId F : CS)
-    HashBuilder.add(F);
-  llvm::BLAKE3Result<8> Hash = HashBuilder.final();
-  CallStackId CSId;
-  std::memcpy(&CSId, Hash.data(), sizeof(Hash));
-  return CSId;
-}
 } // namespace memprof
 } // namespace llvm
diff --git a/llvm/unittests/ProfileData/InstrProfTest.cpp b/llvm/unittests/ProfileData/InstrProfTest.cpp
@@ -12,6 +12,7 @@
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/InstrProfReader.h"
 #include "llvm/ProfileData/InstrProfWriter.h"
 #include "llvm/ProfileData/MemProf.h"
diff --git a/llvm/unittests/ProfileData/MemProfTest.cpp b/llvm/unittests/ProfileData/MemProfTest.cpp
@@ -14,10 +14,10 @@
 #include "llvm/DebugInfo/Symbolize/SymbolizableModule.h"
 #include "llvm/IR/Value.h"
 #include "llvm/Object/ObjectFile.h"
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/MemProfData.inc"
 #include "llvm/ProfileData/MemProfRadixTree.h"
 #include "llvm/ProfileData/MemProfReader.h"
-#include "llvm/ProfileData/MemProfYAML.h"
 #include "llvm/Support/raw_ostream.h"
 #include "gmock/gmock.h"
 #include "gtest/gtest.h"
diff --git a/llvm/unittests/Transforms/Instrumentation/MemProfUseTest.cpp b/llvm/unittests/Transforms/Instrumentation/MemProfUseTest.cpp
@@ -11,6 +11,7 @@
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Passes/PassBuilder.h"
+#include "llvm/ProfileData/IndexedMemProfData.h"
 #include "llvm/ProfileData/InstrProfReader.h"
 #include "llvm/ProfileData/InstrProfWriter.h"
 #include "llvm/ProfileData/MemProf.h"
