IR: Function summary representation for type tests.

Each function summary has an attached list of type identifier GUIDs. The
idea is that during the regular LTO phase we would match these GUIDs to type
identifiers defined by the regular LTO module and store the resolutions in
a top-level "type identifier summary" (which will be implemented separately).

Differential Revision: https://reviews.llvm.org/D27967

llvm-svn: 290280

8 files changed, 102 insertions, 10 deletions

diff --git a/llvm/include/llvm/Bitcode/LLVMBitCodes.h b/llvm/include/llvm/Bitcode/LLVMBitCodes.h
index 32a7fa8b7f2..86d378df784 100644
--- a/llvm/include/llvm/Bitcode/LLVMBitCodes.h
+++ b/llvm/include/llvm/Bitcode/LLVMBitCodes.h
@@ -213,6 +213,8 @@ enum GlobalValueSummarySymtabCodes {
   FS_COMBINED_ORIGINAL_NAME = 9,
   // VERSION of the summary, bumped when adding flags for instance.
   FS_VERSION = 10,
+  // The list of llvm.type.test type identifiers used by the following function.
+  FS_TYPE_TESTS = 11,
 };
 
 enum MetadataCodes {
diff --git a/llvm/include/llvm/IR/ModuleSummaryIndex.h b/llvm/include/llvm/IR/ModuleSummaryIndex.h
index c2977fd0972..53df1bdb40c 100644
--- a/llvm/include/llvm/IR/ModuleSummaryIndex.h
+++ b/llvm/include/llvm/IR/ModuleSummaryIndex.h
@@ -284,12 +284,17 @@ private:
   /// List of <CalleeValueInfo, CalleeInfo> call edge pairs from this function.
   std::vector<EdgeTy> CallGraphEdgeList;
 
+  /// List of type identifiers used by this function, represented as GUIDs.
+  std::vector<GlobalValue::GUID> TypeIdList;
+
 public:
   /// Summary constructors.
   FunctionSummary(GVFlags Flags, unsigned NumInsts, std::vector<ValueInfo> Refs,
-                  std::vector<EdgeTy> CGEdges)
+                  std::vector<EdgeTy> CGEdges,
+                  std::vector<GlobalValue::GUID> TypeIds)
       : GlobalValueSummary(FunctionKind, Flags, std::move(Refs)),
-        InstCount(NumInsts), CallGraphEdgeList(std::move(CGEdges)) {}
+        InstCount(NumInsts), CallGraphEdgeList(std::move(CGEdges)),
+        TypeIdList(std::move(TypeIds)) {}
 
   /// Check if this is a function summary.
   static bool classof(const GlobalValueSummary *GVS) {
@@ -301,6 +306,9 @@ public:
 
   /// Return the list of <CalleeValueInfo, CalleeInfo> pairs.
   ArrayRef<EdgeTy> calls() const { return CallGraphEdgeList; }
+
+  /// Returns the list of type identifiers used by this function.
+  ArrayRef<GlobalValue::GUID> type_tests() const { return TypeIdList; }
 };
 
 /// \brief Global variable summary information to aid decisions and
diff --git a/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp b/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
index d5ceb18b951..cc256f9c829 100644
--- a/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
+++ b/llvm/lib/Analysis/ModuleSummaryAnalysis.cpp
@@ -22,6 +22,7 @@
 #include "llvm/Analysis/IndirectCallPromotionAnalysis.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/Analysis/TypeMetadataUtils.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/InstIterator.h"
@@ -92,6 +93,7 @@ static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
   // counts for all static calls to a given callee.
   MapVector<ValueInfo, CalleeInfo> CallGraphEdges;
   SetVector<ValueInfo> RefEdges;
+  SetVector<GlobalValue::GUID> TypeTests;
   ICallPromotionAnalysis ICallAnalysis;
 
   bool HasInlineAsmMaybeReferencingInternal = false;
@@ -123,11 +125,29 @@ static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
         assert(!CalledFunction && "Expected null called function in callsite for alias");
         CalledFunction = dyn_cast<Function>(GA->getBaseObject());
       }
-      // Check if this is a direct call to a known function.
+      // Check if this is a direct call to a known function or a known
+      // intrinsic, or an indirect call with profile data.
       if (CalledFunction) {
-        // Skip intrinsics.
-        if (CalledFunction->isIntrinsic())
-          continue;
+        if (CalledFunction->isIntrinsic()) {
+          if (CalledFunction->getIntrinsicID() != Intrinsic::type_test)
+            continue;
+          // Produce a summary from type.test intrinsics. We only summarize
+          // type.test intrinsics that are used other than by an llvm.assume
+          // intrinsic. Intrinsics that are assumed are relevant only to the
+          // devirtualization pass, not the type test lowering pass.
+          bool HasNonAssumeUses = llvm::any_of(CI->uses(), [](const Use &CIU) {
+            auto *AssumeCI = dyn_cast<CallInst>(CIU.getUser());
+            if (!AssumeCI)
+              return true;
+            Function *F = AssumeCI->getCalledFunction();
+            return !F || F->getIntrinsicID() != Intrinsic::assume;
+          });
+          if (HasNonAssumeUses) {
+            auto *TypeMDVal = cast<MetadataAsValue>(CI->getArgOperand(1));
+            if (auto *TypeId = dyn_cast<MDString>(TypeMDVal->getMetadata()))
+              TypeTests.insert(GlobalValue::getGUID(TypeId->getString()));
+          }
+        }
         // We should have named any anonymous globals
         assert(CalledFunction->hasName());
         auto ScaledCount = BFI ? BFI->getBlockProfileCount(&BB) : None;
@@ -160,7 +180,8 @@ static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
 
   GlobalValueSummary::GVFlags Flags(F);
   auto FuncSummary = llvm::make_unique<FunctionSummary>(
-      Flags, NumInsts, RefEdges.takeVector(), CallGraphEdges.takeVector());
+      Flags, NumInsts, RefEdges.takeVector(), CallGraphEdges.takeVector(),
+      TypeTests.takeVector());
   if (HasInlineAsmMaybeReferencingInternal)
     FuncSummary->setHasInlineAsmMaybeReferencingInternal();
   Index.addGlobalValueSummary(F.getName(), std::move(FuncSummary));
@@ -280,7 +301,8 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
             std::unique_ptr<FunctionSummary> Summary =
                 llvm::make_unique<FunctionSummary>(
                     GVFlags, 0, ArrayRef<ValueInfo>{},
-                    ArrayRef<FunctionSummary::EdgeTy>{});
+                    ArrayRef<FunctionSummary::EdgeTy>{},
+                    ArrayRef<GlobalValue::GUID>{});
             Summary->setNoRename();
             Index.addGlobalValueSummary(Name, std::move(Summary));
           } else {
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index b719313bbf4..55f2af65255 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -4847,6 +4847,7 @@ Error ModuleSummaryIndexBitcodeReader::parseEntireSummary(
   // "OriginalName" attachement.
   GlobalValueSummary *LastSeenSummary = nullptr;
   bool Combined = false;
+  std::vector<GlobalValue::GUID> PendingTypeTests;
 
   while (true) {
     BitstreamEntry Entry = Stream.advanceSkippingSubblocks();
@@ -4912,7 +4913,8 @@ Error ModuleSummaryIndexBitcodeReader::parseEntireSummary(
           ArrayRef<uint64_t>(Record).slice(CallGraphEdgeStartIndex),
           IsOldProfileFormat, HasProfile);
       auto FS = llvm::make_unique<FunctionSummary>(
-          Flags, InstCount, std::move(Refs), std::move(Calls));
+          Flags, InstCount, std::move(Refs), std::move(Calls),
+          std::move(PendingTypeTests));
       auto GUID = getGUIDFromValueId(ValueID);
       FS->setModulePath(TheIndex.addModulePath(ModulePath, 0)->first());
       FS->setOriginalName(GUID.second);
@@ -4985,7 +4987,8 @@ Error ModuleSummaryIndexBitcodeReader::parseEntireSummary(
           IsOldProfileFormat, HasProfile);
       GlobalValue::GUID GUID = getGUIDFromValueId(ValueID).first;
       auto FS = llvm::make_unique<FunctionSummary>(
-          Flags, InstCount, std::move(Refs), std::move(Edges));
+          Flags, InstCount, std::move(Refs), std::move(Edges),
+          std::move(PendingTypeTests));
       LastSeenSummary = FS.get();
       FS->setModulePath(ModuleIdMap[ModuleId]);
       TheIndex.addGlobalValueSummary(GUID, std::move(FS));
@@ -5041,6 +5044,13 @@ Error ModuleSummaryIndexBitcodeReader::parseEntireSummary(
       LastSeenSummary->setOriginalName(OriginalName);
       // Reset the LastSeenSummary
       LastSeenSummary = nullptr;
+      break;
+    }
+    case bitc::FS_TYPE_TESTS: {
+      assert(PendingTypeTests.empty());
+      PendingTypeTests.insert(PendingTypeTests.end(), Record.begin(),
+                              Record.end());
+      break;
     }
     }
   }
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index 7984292cb0c..d2abf7cb39a 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -3286,6 +3286,9 @@ void ModuleBitcodeWriter::writePerModuleFunctionSummaryRecord(
   NameVals.push_back(ValueID);
 
   FunctionSummary *FS = cast<FunctionSummary>(Summary);
+  if (!FS->type_tests().empty())
+    Stream.EmitRecord(bitc::FS_TYPE_TESTS, FS->type_tests());
+
   NameVals.push_back(getEncodedGVSummaryFlags(FS->flags()));
   NameVals.push_back(FS->instCount());
   NameVals.push_back(FS->refs().size());
@@ -3544,6 +3547,9 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
     }
 
     auto *FS = cast<FunctionSummary>(S);
+    if (!FS->type_tests().empty())
+      Stream.EmitRecord(bitc::FS_TYPE_TESTS, FS->type_tests());
+
     NameVals.push_back(ValueId);
     NameVals.push_back(Index.getModuleId(FS->modulePath()));
     NameVals.push_back(getEncodedGVSummaryFlags(FS->flags()));
diff --git a/llvm/test/Bitcode/thinlto-type-tests.ll b/llvm/test/Bitcode/thinlto-type-tests.ll
new file mode 100644
index 00000000000..4281fbba196
--- /dev/null
+++ b/llvm/test/Bitcode/thinlto-type-tests.ll
@@ -0,0 +1,30 @@
+; RUN: opt -module-summary %s -o %t.o
+; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
+; RUN: llvm-lto -thinlto -o %t2 %t.o
+; RUN: llvm-bcanalyzer -dump %t2.thinlto.bc | FileCheck --check-prefix=COMBINED %s
+
+; COMBINED: <TYPE_TESTS op0=-2012135647395072713/>
+; COMBINED: <TYPE_TESTS op0=6699318081062747564 op1=-2012135647395072713/>
+; COMBINED: <TYPE_TESTS op0=6699318081062747564/>
+
+; CHECK: <TYPE_TESTS op0=6699318081062747564/>
+define i1 @f() {
+  %p = call i1 @llvm.type.test(i8* null, metadata !"foo")
+  ret i1 %p
+}
+
+; CHECK: <TYPE_TESTS op0=6699318081062747564 op1=-2012135647395072713/>
+define i1 @g() {
+  %p = call i1 @llvm.type.test(i8* null, metadata !"foo")
+  %q = call i1 @llvm.type.test(i8* null, metadata !"bar")
+  %pq = and i1 %p, %q
+  ret i1 %pq
+}
+
+; CHECK: <TYPE_TESTS op0=-2012135647395072713/>
+define i1 @h() {
+  %p = call i1 @llvm.type.test(i8* null, metadata !"bar")
+  ret i1 %p
+}
+
+declare i1 @llvm.type.test(i8*, metadata) nounwind readnone
diff --git a/llvm/test/Bitcode/thinlto-unused-type-tests.ll b/llvm/test/Bitcode/thinlto-unused-type-tests.ll
new file mode 100644
index 00000000000..c2c5dd2f9a3
--- /dev/null
+++ b/llvm/test/Bitcode/thinlto-unused-type-tests.ll
@@ -0,0 +1,13 @@
+; RUN: opt -module-summary %s -o %t.o
+; RUN: llvm-bcanalyzer -dump %t.o | FileCheck %s
+
+; CHECK-NOT: <TYPE_TESTS
+define void @f() {
+  %p = call i1 @llvm.type.test(i8* null, metadata !"foo")
+  %q = call i1 @llvm.type.test(i8* null, metadata !"bar")
+  call void @llvm.assume(i1 %q)
+  ret void
+}
+
+declare i1 @llvm.type.test(i8*, metadata) nounwind readnone
+declare void @llvm.assume(i1)
diff --git a/llvm/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp b/llvm/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp
index d866201723a..e494343bf87 100644
--- a/llvm/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp
+++ b/llvm/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp
@@ -311,6 +311,7 @@ static const char *GetCodeName(unsigned CodeID, unsigned BlockID,
       STRINGIFY_CODE(FS, COMBINED_ALIAS)
       STRINGIFY_CODE(FS, COMBINED_ORIGINAL_NAME)
       STRINGIFY_CODE(FS, VERSION)
+      STRINGIFY_CODE(FS, TYPE_TESTS)
     }
   case bitc::METADATA_ATTACHMENT_ID:
     switch(CodeID) {