[CGData][MachineOutliner] Global Outlining

llvm/include/llvm/ADT/StableHashing.h

@@ -53,6 +53,12 @@ inline stable_hash stable_hash_combine(stable_hash A, stable_hash B,
 // Removes suffixes introduced by LLVM from the name to enhance stability and
 // maintain closeness to the original name across different builds.
 inline StringRef get_stable_name(StringRef Name) {
+  // Return the part after ".content." that represents contents.
+  auto [P0, S0] = Name.rsplit(".content.");
+  if (!S0.empty())
+    return S0;
+
+  // Ignore these suffixes.
   auto [P1, S1] = Name.rsplit(".llvm.");
   auto [P2, S2] = P1.rsplit(".__uniq.");
   return P2;

llvm/include/llvm/CodeGen/MachineOutliner.h

@@ -18,6 +18,7 @@
 #include "llvm/CodeGen/LiveRegUnits.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineStableHash.h"
 #include <initializer_list>
 
 namespace llvm {
@@ -234,11 +235,11 @@ struct OutlinedFunction {
   unsigned FrameConstructionID = 0;
 
   /// Return the number of candidates for this \p OutlinedFunction.
-  unsigned getOccurrenceCount() const { return Candidates.size(); }
+  virtual unsigned getOccurrenceCount() const { return Candidates.size(); }
 
   /// Return the number of bytes it would take to outline this
   /// function.
-  unsigned getOutliningCost() const {
+  virtual unsigned getOutliningCost() const {
     unsigned CallOverhead = 0;
     for (const Candidate &C : Candidates)
       CallOverhead += C.getCallOverhead();
@@ -272,7 +273,42 @@ struct OutlinedFunction {
   }
 
   OutlinedFunction() = delete;
+  virtual ~OutlinedFunction() = default;
 };
+
+/// The information necessary to create an outlined function that is matched
+/// globally.
+struct GlobalOutlinedFunction : public OutlinedFunction {
+  explicit GlobalOutlinedFunction(std::unique_ptr<OutlinedFunction> OF,
+                                  unsigned GlobalOccurrenceCount)
+      : OutlinedFunction(*OF), GlobalOccurrenceCount(GlobalOccurrenceCount) {}
+
+  unsigned GlobalOccurrenceCount;
+
+  /// Return the number of times that appear globally.
+  /// Global outlining candidate is uniquely created per each match, but this
+  /// might be erased out when it's overlapped with the previous outlining
+  /// instance.
+  unsigned getOccurrenceCount() const override {
+    assert(Candidates.size() <= 1);
+    return Candidates.empty() ? 0 : GlobalOccurrenceCount;
+  }
+
+  /// Return the outlining cost using the global occurrence count
+  /// with the same cost as the first (unique) candidate.
+  unsigned getOutliningCost() const override {
+    assert(Candidates.size() <= 1);
+    unsigned CallOverhead =
+        Candidates.empty()
+            ? 0
+            : Candidates[0].getCallOverhead() * getOccurrenceCount();
+    return CallOverhead + SequenceSize + FrameOverhead;
+  }
+
+  GlobalOutlinedFunction() = delete;
+  ~GlobalOutlinedFunction() = default;
+};
+
 } // namespace outliner
 } // namespace llvm
 

llvm/lib/CGData/CodeGenData.cpp

@@ -24,6 +24,13 @@
 using namespace llvm;
 using namespace cgdata;
 
+cl::opt<bool>
+    CodeGenDataGenerate("codegen-data-generate", cl::init(false), cl::Hidden,
+                        cl::desc("Emit CodeGen Data into custom sections"));
+cl::opt<std::string>
+    CodeGenDataUsePath("codegen-data-use-path", cl::init(""), cl::Hidden,
+                       cl::desc("File path to where .cgdata file is read"));
+
 static std::string getCGDataErrString(cgdata_error Err,
                                       const std::string &ErrMsg = "") {
   std::string Msg;
@@ -132,7 +139,24 @@ CodeGenData &CodeGenData::getInstance() {
   std::call_once(CodeGenData::OnceFlag, []() {
     Instance = std::unique_ptr<CodeGenData>(new CodeGenData());
 
-    // TODO: Initialize writer or reader mode for the client optimization.
+    if (CodeGenDataGenerate)
+      Instance->EmitCGData = true;
+    else if (!CodeGenDataUsePath.empty()) {
+      // Initialize the global CGData if the input file name is given.
+      // We do not error-out when failing to parse the input file.
+      // Instead, just emit an warning message and fall back as if no CGData
+      // were available.
+      auto FS = vfs::getRealFileSystem();
+      auto ReaderOrErr = CodeGenDataReader::create(CodeGenDataUsePath, *FS);
+      if (Error E = ReaderOrErr.takeError()) {
+        warn(std::move(E), CodeGenDataUsePath);
+        return;
+      }
+      // Publish each CGData based on the data type in the header.
+      auto Reader = ReaderOrErr->get();
+      if (Reader->hasOutlinedHashTree())
+        Instance->publishOutlinedHashTree(Reader->releaseOutlinedHashTree());
+    }
   });
   return *(Instance.get());
 }

llvm/lib/CodeGen/CMakeLists.txt

@@ -267,6 +267,7 @@ add_llvm_component_library(LLVMCodeGen
   Analysis
   BitReader
   BitWriter
+  CGData
   CodeGenTypes
   Core
   MC