Add function entry count metadata.

Summary:
This adds three Function methods to handle function entry counts:
setEntryCount() and getEntryCount().

Entry counts are stored under the MD_prof metadata node with the name
"function_entry_count". They are unsigned 64 bit values set by profilers
(instrumentation and sample profiler changes coming up).

Added documentation for new profile metadata and tests.

Reviewers: dexonsmith, bogner

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D9628

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237260 91177308-0d34-0410-b5e6-96231b3b80d8

docs/BranchWeightMetadata.rst

@@ -115,3 +115,26 @@ CFG Modifications
 Branch Weight Metatada is not proof against CFG changes. If terminator operands'
 are changed some action should be taken. In other case some misoptimizations may
 occur due to incorrent branch prediction information.
+
+Function Entry Counts
+=====================
+
+To allow comparing different functions durint inter-procedural analysis and
+optimization, ``MD_prof`` nodes can also be assigned to a function definition.
+The first operand is a string indicating the name of the associated counter.
+
+Currently, one counter is supported: "function_entry_count". This is a 64-bit
+counter that indicates the number of times that this function was invoked (in
+the case of instrumentation-based profiles). In the case of sampling-based
+profiles, this counter is an approximation of how many times the function was
+invoked.
+
+For example, in the code below, the instrumentation for function foo()
+indicates that it was called 2,590 times at runtime.
+
+.. code-block:: llvm
+
+  define i32 @foo() !prof !1 {
+    ret i32 0
+  }
+  !1 = !{!"function_entry_count", i64 2590}

include/llvm/IR/Function.h

@@ -19,6 +19,7 @@
 #define LLVM_IR_FUNCTION_H
 
 #include "llvm/ADT/iterator_range.h"
+#include "llvm/ADT/Optional.h"
 #include "llvm/IR/Argument.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
@@ -194,6 +195,12 @@ public:
                                  AttributeSet::FunctionIndex, Kind, Value));
   }
 
+  /// Set the entry count for this function.
+  void setEntryCount(uint64_t Count);
+
+  /// Get the entry count for this function.
+  Optional<uint64_t> getEntryCount() const;
+
   /// @brief Return true if the function has the attribute.
   bool hasFnAttribute(Attribute::AttrKind Kind) const {
     return AttributeSets.hasAttribute(AttributeSet::FunctionIndex, Kind);

include/llvm/IR/MDBuilder.h

@@ -60,6 +60,9 @@ public:
   /// \brief Return metadata containing a number of branch weights.
   MDNode *createBranchWeights(ArrayRef<uint32_t> Weights);
 
+  /// Return metadata containing the entry count for a function.
+  MDNode *createFunctionEntryCount(uint64_t Count);
+
   //===------------------------------------------------------------------===//
   // Range metadata.
   //===------------------------------------------------------------------===//

lib/IR/Function.cpp

@@ -19,10 +19,13 @@
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/CodeGen/ValueTypes.h"
 #include "llvm/IR/CallSite.h"
+#include "llvm/IR/Constants.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/InstIterator.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/MDBuilder.h"
+#include "llvm/IR/Metadata.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/ManagedStatic.h"
 #include "llvm/Support/RWMutex.h"
@@ -986,3 +989,19 @@ void llvm::overrideFunctionAttribute(StringRef Kind, StringRef Value,
   Attrs = Attrs.addAttribute(Ctx, AttributeSet::FunctionIndex, Kind, Value);
   F.setAttributes(Attrs);
 }
+
+void Function::setEntryCount(uint64_t Count) {
+  MDBuilder MDB(getContext());
+  setMetadata(LLVMContext::MD_prof, MDB.createFunctionEntryCount(Count));
+}
+
+Optional<uint64_t> Function::getEntryCount() const {
+  MDNode *MD = getMetadata(LLVMContext::MD_prof);
+  if (MD && MD->getOperand(0))
+    if (MDString *MDS = dyn_cast<MDString>(MD->getOperand(0)))
+      if (MDS->getString().equals("function_entry_count")) {
+        ConstantInt *CI = mdconst::extract<ConstantInt>(MD->getOperand(1));
+        return CI->getValue().getZExtValue();
+      }
+  return None;
+}

lib/IR/MDBuilder.cpp

@@ -53,6 +53,16 @@ MDNode *MDBuilder::createBranchWeights(ArrayRef<uint32_t> Weights) {
   return MDNode::get(Context, Vals);
 }
 
+MDNode *MDBuilder::createFunctionEntryCount(uint64_t Count) {
+  SmallVector<Metadata *, 2> Vals(2);
+  Vals[0] = createString("function_entry_count");
+
+  Type *Int64Ty = Type::getInt64Ty(Context);
+  Vals[1] = createConstant(ConstantInt::get(Int64Ty, Count));
+
+  return MDNode::get(Context, Vals);
+}
+
 MDNode *MDBuilder::createRange(const APInt &Lo, const APInt &Hi) {
   assert(Lo.getBitWidth() == Hi.getBitWidth() && "Mismatched bitwidths!");
 

lib/IR/Verifier.cpp

@@ -400,6 +400,8 @@ private:
                             bool isReturnValue, const Value *V);
   void VerifyFunctionAttrs(FunctionType *FT, AttributeSet Attrs,
                            const Value *V);
+  void VerifyFunctionMetadata(
+      const SmallVector<std::pair<unsigned, MDNode *>, 4> MDs);
 
   void VerifyConstantExprBitcastType(const ConstantExpr *CE);
   void VerifyStatepoint(ImmutableCallSite CS);
@@ -1463,6 +1465,36 @@ void Verifier::VerifyFunctionAttrs(FunctionType *FT, AttributeSet Attrs,
   }
 }
 
+void Verifier::VerifyFunctionMetadata(
+    const SmallVector<std::pair<unsigned, MDNode *>, 4> MDs) {
+  if (MDs.empty())
+    return;
+
+  for (unsigned i = 0; i < MDs.size(); i++) {
+    if (MDs[i].first == LLVMContext::MD_prof) {
+      MDNode *MD = MDs[i].second;
+      Assert(MD->getNumOperands() == 2,
+             "!prof annotations should have exactly 2 operands", MD);
+
+      // Check first operand.
+      Assert(MD->getOperand(0) != nullptr, "first operand should not be null",
+             MD);
+      Assert(isa<MDString>(MD->getOperand(0)),
+             "expected string with name of the !prof annotation", MD);
+      MDString *MDS = cast<MDString>(MD->getOperand(0));
+      StringRef ProfName = MDS->getString();
+      Assert(ProfName.equals("function_entry_count"),
+             "first operand should be 'function_entry_count'", MD);
+
+      // Check second operand.
+      Assert(MD->getOperand(1) != nullptr, "second operand should not be null",
+             MD);
+      Assert(isa<ConstantAsMetadata>(MD->getOperand(1)),
+             "expected integer argument to function_entry_count", MD);
+    }
+  }
+}
+
 void Verifier::VerifyConstantExprBitcastType(const ConstantExpr *CE) {
   if (CE->getOpcode() != Instruction::BitCast)
     return;
@@ -1713,6 +1745,7 @@ void Verifier::visitFunction(const Function &F) {
   SmallVector<std::pair<unsigned, MDNode *>, 4> MDs;
   F.getAllMetadata(MDs);
   assert(F.hasMetadata() != MDs.empty() && "Bit out-of-sync");
+  VerifyFunctionMetadata(MDs);
 
   if (F.isMaterializable()) {
     // Function has a body somewhere we can't see.

test/Verifier/function-metadata-bad.ll

@@ -0,0 +1,35 @@
+; RUN: not llvm-as < %s -o /dev/null 2>&1 | FileCheck %s
+
+define i32 @bad1() !prof !0 {
+  ret i32 0
+}
+
+!0 = !{i32 123, i32 3}
+; CHECK: assembly parsed, but does not verify as correct!
+; CHECK-NEXT: expected string with name of the !prof annotation
+; CHECK-NEXT: !0 = !{i32 123, i32 3}
+
+define i32 @bad2() !prof !1 {
+  ret i32 0
+}
+
+!1 = !{!"function_entry_count"}
+; CHECK-NEXT: !prof annotations should have exactly 2 operands
+; CHECK-NEXT: !1 = !{!"function_entry_count"}
+
+
+define i32 @bad3() !prof !2 {
+  ret i32 0
+}
+
+!2 = !{!"some_other_count", i64 200}
+; CHECK-NEXT: first operand should be 'function_entry_count'
+; CHECK-NEXT: !2 = !{!"some_other_count", i64 200}
+
+define i32 @bad4() !prof !3 {
+  ret i32 0
+}
+
+!3 = !{!"function_entry_count", !"string"}
+; CHECK-NEXT: expected integer argument to function_entry_count
+; CHECK-NEXT: !3 = !{!"function_entry_count", !"string"}

test/Verifier/function-metadata-good.ll

@@ -0,0 +1,8 @@
+; RUN: llvm-as < %s -o /dev/null 2>&1
+
+; Function foo() is called 2,304 times at runtime.
+define i32 @foo() !prof !0 {
+  ret i32 0
+}
+
+!0 = !{!"function_entry_count", i32 2304}

unittests/IR/MetadataTest.cpp

@@ -2272,4 +2272,12 @@ TEST_F(FunctionAttachmentTest, Verifier) {
   EXPECT_FALSE(verifyFunction(*F));
 }
 
+TEST_F(FunctionAttachmentTest, EntryCount) {
+  Function *F = getFunction("foo");
+  EXPECT_FALSE(F->getEntryCount().hasValue());
+  F->setEntryCount(12304);
+  EXPECT_TRUE(F->getEntryCount().hasValue());
+  EXPECT_EQ(12304u, *F->getEntryCount());
+}
+
 }