[clang] [compiler-rt] [llvm] [TypeProf][InstrFDO]Implement more efficient comparison sequence for indirect-call-promotion with vtable profiles. (PR #81442)

[David Li via llvm-commits]

================
@@ -103,30 +110,222 @@ static cl::opt<bool>
     ICPDUMPAFTER("icp-dumpafter", cl::init(false), cl::Hidden,
                  cl::desc("Dump IR after transformation happens"));
 
+// This option is meant to be used by LLVM regression test and test the
+// transformation that compares vtables.
+static cl::opt<bool> ICPEnableVTableCmp(
+    "icp-enable-vtable-cmp", cl::init(false), cl::Hidden,
+    cl::desc("If ThinLTO and WPD is enabled and this option is true, "
+             "indirect-call promotion pass will compare vtables rather than "
+             "functions for speculative devirtualization of virtual calls."
+             " If set to false, indirect-call promotion pass will always "
+             "compare functions."));
+
+static cl::opt<float>
+    ICPVTableCountPercentage("icp-vtable-count-percentage", cl::init(0.99),
+                             cl::Hidden,
+                             cl::desc("Percentage of vtable count to compare"));
+
+static cl::opt<int> ICPNumAdditionalVTableLast(
+    "icp-num-additional-vtable-last", cl::init(0), cl::Hidden,
+    cl::desc("The number of additional instruction for the last candidate"));
+
 namespace {
 
+using VTableAddressPointOffsetValMap =
+    SmallDenseMap<const GlobalVariable *, SmallDenseMap<int, Constant *, 4>, 8>;
+
+// A struct to collect type information for a virtual call site.
+struct VirtualCallSiteInfo {
+  // The offset from the address point to virtual function in the vtable.
+  uint64_t FunctionOffset;
+  // The instruction that computes the address point of vtable.
+  Instruction *VPtr;
+  // The compatible type used in LLVM type intrinsics.
+  StringRef CompatibleTypeStr;
+};
+
+// The key is a virtual call, and value is its type information.
+using VirtualCallSiteTypeInfoMap =
+    SmallDenseMap<const CallBase *, VirtualCallSiteInfo, 8>;
+
+// Find the offset where type string is `CompatibleType`.
+static std::optional<uint64_t>
+getCompatibleTypeOffset(const GlobalVariable &VTableVar,
+                        StringRef CompatibleType) {
+  SmallVector<MDNode *, 2> Types; // type metadata associated with a vtable.
+  VTableVar.getMetadata(LLVMContext::MD_type, Types);
+
+  for (MDNode *Type : Types)
+    if (auto *TypeId = dyn_cast<MDString>(Type->getOperand(1).get());
+        TypeId && TypeId->getString() == CompatibleType)
+
+      return cast<ConstantInt>(
+                 cast<ConstantAsMetadata>(Type->getOperand(0))->getValue())
+          ->getZExtValue();
+
+  return std::nullopt;
+}
+
+// Returns a constant representing the vtable's address point specified by the
+// offset.
+static Constant *getVTableAddressPointOffset(GlobalVariable *VTable,
+                                             uint32_t AddressPointOffset) {
+  Module &M = *VTable->getParent();
+  LLVMContext &Context = M.getContext();
+  assert(AddressPointOffset <
+             M.getDataLayout().getTypeAllocSize(VTable->getValueType()) &&
+         "Out-of-bound access");
+
+  return ConstantExpr::getInBoundsGetElementPtr(
+      Type::getInt8Ty(Context), VTable,
+      llvm::ConstantInt::get(Type::getInt32Ty(Context), AddressPointOffset));
+}
+
+// Returns the basic block in which `Inst` by `Use`.
+static BasicBlock *getUserBasicBlock(Instruction *Inst, unsigned int OperandNo,
+                                     Instruction *UserInst) {
+  if (PHINode *PN = dyn_cast<PHINode>(UserInst))
+    return PN->getIncomingBlock(
+        PHINode::getIncomingValueNumForOperand(OperandNo));
+
+  return UserInst->getParent();
+}
+
+// `DestBB` is a suitable basic block to sink `Inst` into when the following
+// conditions are true:
+// 1) `Inst->getParent()` is the sole predecessor of `DestBB`. This way `DestBB`
+//    is dominated by `Inst->getParent()` and we don't need to sink across a
+//    critical edge.
+// 2) `Inst` have users and all users are in `DestBB`.
+static bool isDestBBSuitableForSink(Instruction *Inst, BasicBlock *DestBB) {
+  BasicBlock *BB = Inst->getParent();
+  assert(Inst->getParent() != DestBB &&
+         BB->getTerminator()->getNumSuccessors() == 2 &&
+         "Caller should guarantee");
+  // Do not sink across a critical edge for simplicity.
+  if (DestBB->getUniquePredecessor() != BB)
----------------
david-xl wrote:

this does not handle the diamond cfg case. Perhaps remove this check. Instead check if any use is a PHI. If yes, bail.

https://github.com/llvm/llvm-project/pull/81442