TableGen: Emit static hash table for runtime libcalls

llvm/benchmarks/CMakeLists.txt

@@ -11,3 +11,20 @@ add_benchmark(FormatVariadicBM FormatVariadicBM.cpp PARTIAL_SOURCES_INTENDED)
 add_benchmark(GetIntrinsicInfoTableEntriesBM GetIntrinsicInfoTableEntriesBM.cpp PARTIAL_SOURCES_INTENDED)
 add_benchmark(SandboxIRBench SandboxIRBench.cpp PARTIAL_SOURCES_INTENDED)
 
+# Extract the list of symbols in a random utility as sample data.
+set(SYMBOL_TEST_DATA_FILE "sample_symbol_list.txt")
+set(SYMBOL_TEST_DATA_SOURCE_BINARY $<TARGET_FILE:llc>)
+
+add_custom_command(OUTPUT ${SYMBOL_TEST_DATA_FILE}
+  COMMAND $<TARGET_FILE:llvm-nm> --no-demangle --no-sort
+  --format=just-symbols
+  ${SYMBOL_TEST_DATA_SOURCE_BINARY} > ${SYMBOL_TEST_DATA_FILE}
+  DEPENDS "$<TARGET_FILE:llvm-nm>" "$<TARGET_FILE:llc>")
+
+add_custom_target(generate-runtime-libcalls-sample-symbol-list
+                  DEPENDS ${SYMBOL_TEST_DATA_FILE})
+add_benchmark(RuntimeLibcallsBench RuntimeLibcalls.cpp PARTIAL_SOURCES_INTENDED)
+
+add_dependencies(RuntimeLibcallsBench generate-runtime-libcalls-sample-symbol-list)
+target_compile_definitions(RuntimeLibcallsBench PRIVATE
+  -DSYMBOL_TEST_DATA_FILE="${CMAKE_CURRENT_BINARY_DIR}/${SYMBOL_TEST_DATA_FILE}")

llvm/benchmarks/RuntimeLibcalls.cpp

@@ -0,0 +1,116 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/IR/RuntimeLibcalls.h"
+#include "benchmark/benchmark.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/LineIterator.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/TargetParser/Triple.h"
+#include <random>
+#include <string>
+using namespace llvm;
+
+static constexpr unsigned MaxFuncNameSize = 53;
+
+static std::vector<StringRef> getLibcallNameStringRefs() {
+  std::vector<StringRef> Names(RTLIB::NumLibcallImpls);
+  // Keep the strlens on the StringRef construction out of the benchmark loop.
+  for (RTLIB::LibcallImpl LC : RTLIB::libcall_impls()) {
+    const char *Name = RTLIB::RuntimeLibcallsInfo::getLibcallImplName(LC);
+    Names[LC] = StringRef(Name);
+  }
+
+  return Names;
+}
+
+static std::vector<std::string> getRandomFuncNames() {
+  std::mt19937_64 Rng;
+  std::uniform_int_distribution<> StringLengthDistribution(1, MaxFuncNameSize);
+  std::uniform_int_distribution<> CharDistribution(1, 255);
+  int NumTestFuncs = 1 << 10;
+  std::vector<std::string> TestFuncNames(NumTestFuncs);
+
+  for (std::string &TestFuncName : TestFuncNames) {
+    for (int I = 0, E = StringLengthDistribution(Rng); I != E; ++I)
+      TestFuncName += static_cast<char>(CharDistribution(Rng));
+  }
+
+  return TestFuncNames;
+}
+
+static std::vector<std::string> readSymbolsFromFile(StringRef InputFile) {
+  auto BufOrError = MemoryBuffer::getFileOrSTDIN(InputFile, /*IsText=*/true);
+  if (!BufOrError) {
+    reportFatalUsageError("failed to open \'" + Twine(InputFile) +
+                          "\': " + BufOrError.getError().message());
+  }
+
+  // Hackily figure out if there's a prefix on the symbol names - llvm-nm
+  // appears to not have a flag to skip this.
+  llvm::Triple HostTriple(LLVM_HOST_TRIPLE);
+  std::string DummyDatalayout = "e";
+  DummyDatalayout += DataLayout::getManglingComponent(HostTriple);
+
+  DataLayout DL(DummyDatalayout);
+  char GlobalPrefix = DL.getGlobalPrefix();
+
+  std::vector<std::string> Lines;
+  for (line_iterator LineIt(**BufOrError, /*SkipBlanks=*/true);
+       !LineIt.is_at_eof(); ++LineIt) {
+    StringRef SymbolName = *LineIt;
+    SymbolName.consume_front(StringRef(&GlobalPrefix, 1));
+
+    Lines.push_back(SymbolName.str());
+  }
+  return Lines;
+}
+
+static void BM_LookupRuntimeLibcallByNameKnownCalls(benchmark::State &State) {
+  std::vector<StringRef> Names = getLibcallNameStringRefs();
+
+  for (auto _ : State) {
+    for (StringRef Name : Names) {
+      benchmark::DoNotOptimize(
+          RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName(Name).empty());
+    }
+  }
+}
+
+static void BM_LookupRuntimeLibcallByNameRandomCalls(benchmark::State &State) {
+  std::vector<std::string> TestFuncNames = getRandomFuncNames();
+
+  for (auto _ : State) {
+    for (const std::string &Name : TestFuncNames) {
+      benchmark::DoNotOptimize(
+          RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName(StringRef(Name))
+              .empty());
+    }
+  }
+}
+
+// This isn't fully representative, it doesn't include any anonymous functions.
+// nm -n --no-demangle --format=just-symbols sample-binary > sample.txt
+static void BM_LookupRuntimeLibcallByNameSampleData(benchmark::State &State) {
+  std::vector<std::string> TestFuncNames =
+      readSymbolsFromFile(SYMBOL_TEST_DATA_FILE);
+  for (auto _ : State) {
+    for (const std::string &Name : TestFuncNames) {
+      benchmark::DoNotOptimize(
+          RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName(StringRef(Name))
+              .empty());
+    }
+  }
+}
+
+BENCHMARK(BM_LookupRuntimeLibcallByNameKnownCalls);
+BENCHMARK(BM_LookupRuntimeLibcallByNameRandomCalls);
+BENCHMARK(BM_LookupRuntimeLibcallByNameSampleData);
+
+BENCHMARK_MAIN();

llvm/include/llvm/IR/RuntimeLibcalls.h

@@ -132,11 +132,41 @@ struct RuntimeLibcallsInfo {
     return ImplToLibcall[Impl];
   }
 
+  /// Check if a function name is a recognized runtime call of any kind. This
+  /// does not consider if this call is available for any current compilation,
+  /// just that it is a known call somewhere. This returns the set of all
+  /// LibcallImpls which match the name; multiple implementations with the same
+  /// name may exist but differ in interpretation based on the target context.
+  ///
+  /// Generated by tablegen.
+  LLVM_ABI static inline iota_range<RTLIB::LibcallImpl>
+  lookupLibcallImplName(StringRef Name){
+  // Inlining the early exit on the string name appears to be worthwhile when
+  // querying a real set of symbols
+#define GET_LOOKUP_LIBCALL_IMPL_NAME_BODY
+#include "llvm/IR/RuntimeLibcalls.inc"
+#undef GET_LOOKUP_LIBCALL_IMPL_NAME_BODY
+  }
+
   /// Check if this is valid libcall for the current module, otherwise
   /// RTLIB::Unsupported.
-  LLVM_ABI RTLIB::LibcallImpl getSupportedLibcallImpl(StringRef FuncName) const;
+  LLVM_ABI RTLIB::LibcallImpl
+      getSupportedLibcallImpl(StringRef FuncName) const {
+    for (RTLIB::LibcallImpl Impl : lookupLibcallImplName(FuncName)) {
+      // FIXME: This should not depend on looking up ImplToLibcall, only the
+      // list of libcalls for the module.
+      RTLIB::LibcallImpl Recognized = LibcallImpls[ImplToLibcall[Impl]];
+      if (Recognized != RTLIB::Unsupported)
+        return Recognized;
+    }
+
+    return RTLIB::Unsupported;
+  }
 
 private:
+  LLVM_ABI static iota_range<RTLIB::LibcallImpl>
+  lookupLibcallImplNameImpl(StringRef Name);
+
   /// Stores the implementation choice for each each libcall.
   RTLIB::LibcallImpl LibcallImpls[RTLIB::UNKNOWN_LIBCALL + 1] = {
       RTLIB::Unsupported};
@@ -157,13 +187,11 @@ struct RuntimeLibcallsInfo {
   /// Map from a concrete LibcallImpl implementation to its RTLIB::Libcall kind.
   LLVM_ABI static const RTLIB::Libcall ImplToLibcall[RTLIB::NumLibcallImpls];
 
-  /// Check if a function name is a recognized runtime call of any kind. This
-  /// does not consider if this call is available for any current compilation,
-  /// just that it is a known call somewhere. This returns the set of all
-  /// LibcallImpls which match the name; multiple implementations with the same
-  /// name may exist but differ in interpretation based on the target context.
-  LLVM_ABI static iterator_range<ArrayRef<uint16_t>::const_iterator>
-  getRecognizedLibcallImpls(StringRef FuncName);
+  /// Utility function for tablegenerated lookup function. Return a range of
+  /// enum values that apply for the function name at \p NameOffsetEntry with
+  /// the value \p StrOffset.
+  static inline iota_range<RTLIB::LibcallImpl>
+  libcallImplNameHit(uint16_t NameOffsetEntry, uint16_t StrOffset);
 
   static bool darwinHasSinCosStret(const Triple &TT) {
     if (!TT.isOSDarwin())

llvm/lib/IR/RuntimeLibcalls.cpp

@@ -9,6 +9,7 @@
 #include "llvm/IR/RuntimeLibcalls.h"
 #include "llvm/ADT/StringTable.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/xxhash.h"
 #include "llvm/TargetParser/ARMTargetParser.h"
 
 #define DEBUG_TYPE "runtime-libcalls-info"
@@ -18,9 +19,11 @@ using namespace RTLIB;
 
 #define GET_INIT_RUNTIME_LIBCALL_NAMES
 #define GET_SET_TARGET_RUNTIME_LIBCALL_SETS
+#define DEFINE_GET_LOOKUP_LIBCALL_IMPL_NAME
 #include "llvm/IR/RuntimeLibcalls.inc"
 #undef GET_INIT_RUNTIME_LIBCALL_NAMES
 #undef GET_SET_TARGET_RUNTIME_LIBCALL_SETS
+#undef DEFINE_GET_LOOKUP_LIBCALL_IMPL_NAME
 
 /// Set default libcall names. If a target wants to opt-out of a libcall it
 /// should be placed here.
@@ -58,49 +61,23 @@ void RuntimeLibcallsInfo::initLibcalls(const Triple &TT,
   }
 }
 
-RTLIB::LibcallImpl
-RuntimeLibcallsInfo::getSupportedLibcallImpl(StringRef FuncName) const {
-  const ArrayRef<uint16_t> RuntimeLibcallNameOffsets(
-      RuntimeLibcallNameOffsetTable);
-
-  iterator_range<ArrayRef<uint16_t>::const_iterator> Range =
-      getRecognizedLibcallImpls(FuncName);
-
-  for (auto I = Range.begin(); I != Range.end(); ++I) {
-    RTLIB::LibcallImpl Impl =
-        static_cast<RTLIB::LibcallImpl>(I - RuntimeLibcallNameOffsets.begin());
-
-    // FIXME: This should not depend on looking up ImplToLibcall, only the list
-    // of libcalls for the module.
-    RTLIB::LibcallImpl Recognized = LibcallImpls[ImplToLibcall[Impl]];
-    if (Recognized != RTLIB::Unsupported)
-      return Recognized;
+LLVM_ATTRIBUTE_ALWAYS_INLINE
+iota_range<RTLIB::LibcallImpl>
+RuntimeLibcallsInfo::libcallImplNameHit(uint16_t NameOffsetEntry,
+                                        uint16_t StrOffset) {
+  int NumAliases = 1;
+  for (uint16_t Entry : ArrayRef(RuntimeLibcallNameOffsetTable)
+                            .drop_front(NameOffsetEntry + 1)) {
+    if (Entry != StrOffset)
+      break;
+    ++NumAliases;
   }
 
-  return RTLIB::Unsupported;
-}
-
-iterator_range<ArrayRef<uint16_t>::const_iterator>
-RuntimeLibcallsInfo::getRecognizedLibcallImpls(StringRef FuncName) {
-  StringTable::Iterator It = lower_bound(RuntimeLibcallImplNameTable, FuncName);
-  if (It == RuntimeLibcallImplNameTable.end() || *It != FuncName)
-    return iterator_range(ArrayRef<uint16_t>());
-
-  uint16_t IndexVal = It.offset().value();
-  const ArrayRef<uint16_t> TableRef(RuntimeLibcallNameOffsetTable);
-
-  ArrayRef<uint16_t>::const_iterator E = TableRef.end();
-  ArrayRef<uint16_t>::const_iterator EntriesBegin =
-      std::lower_bound(TableRef.begin(), E, IndexVal);
-  ArrayRef<uint16_t>::const_iterator EntriesEnd = EntriesBegin;
-
-  while (EntriesEnd != E && *EntriesEnd == IndexVal)
-    ++EntriesEnd;
-
-  assert(EntriesBegin != E &&
-         "libcall found in name table but not offset table");
-
-  return make_range(EntriesBegin, EntriesEnd);
+  RTLIB::LibcallImpl ImplStart = static_cast<RTLIB::LibcallImpl>(
+      &RuntimeLibcallNameOffsetTable[NameOffsetEntry] -
+      &RuntimeLibcallNameOffsetTable[0]);
+  return enum_seq(ImplStart,
+                  static_cast<RTLIB::LibcallImpl>(ImplStart + NumAliases));
 }
 
 bool RuntimeLibcallsInfo::isAAPCS_ABI(const Triple &TT, StringRef ABIName) {

llvm/lib/Object/IRSymtab.cpp

@@ -46,14 +46,18 @@ static cl::opt<bool> DisableBitcodeVersionUpgrade(
     "disable-bitcode-version-upgrade", cl::Hidden,
     cl::desc("Disable automatic bitcode upgrade for version mismatch"));
 
-static const char *PreservedSymbols[] = {
+static constexpr StringLiteral PreservedSymbols[] = {
     // There are global variables, so put it here instead of in
     // RuntimeLibcalls.td.
     // TODO: Are there similar such variables?
     "__ssp_canary_word",
     "__stack_chk_guard",
 };
 
+static bool isPreservedGlobalVarName(StringRef Name) {
+  return PreservedSymbols[0] == Name || PreservedSymbols[1] == Name;
+}
+
 namespace {
 
 const char *getExpectedProducerName() {
@@ -81,12 +85,16 @@ struct Builder {
   // The StringTableBuilder does not create a copy of any strings added to it,
   // so this provides somewhere to store any strings that we create.
   Builder(SmallVector<char, 0> &Symtab, StringTableBuilder &StrtabBuilder,
-          BumpPtrAllocator &Alloc)
-      : Symtab(Symtab), StrtabBuilder(StrtabBuilder), Saver(Alloc) {}
+          BumpPtrAllocator &Alloc, const Triple &TT)
+      : Symtab(Symtab), StrtabBuilder(StrtabBuilder), Saver(Alloc), TT(TT),
+        Libcalls(TT) {}
 
   DenseMap<const Comdat *, int> ComdatMap;
   Mangler Mang;
-  Triple TT;
+  const Triple &TT;
+
+  // FIXME: This shouldn't be here.
+  RTLIB::RuntimeLibcallsInfo Libcalls;
 
   std::vector<storage::Comdat> Comdats;
   std::vector<storage::Module> Mods;
@@ -98,6 +106,10 @@ struct Builder {
 
   std::vector<storage::Str> DependentLibraries;
 
+  bool isPreservedLibFuncName(StringRef Name) {
+    return Libcalls.getSupportedLibcallImpl(Name) != RTLIB::Unsupported;
+  }
+
   void setStr(storage::Str &S, StringRef Value) {
     S.Offset = StrtabBuilder.add(Value);
     S.Size = Value.size();
@@ -213,19 +225,6 @@ Expected<int> Builder::getComdatIndex(const Comdat *C, const Module *M) {
   return P.first->second;
 }
 
-static StringSet<> buildPreservedSymbolsSet(const Triple &TT) {
-  StringSet<> PreservedSymbolSet;
-  PreservedSymbolSet.insert(std::begin(PreservedSymbols),
-                            std::end(PreservedSymbols));
-  // FIXME: Do we need to pass in ABI fields from TargetOptions?
-  RTLIB::RuntimeLibcallsInfo Libcalls(TT);
-  for (RTLIB::LibcallImpl Impl : Libcalls.getLibcallImpls()) {
-    if (Impl != RTLIB::Unsupported)
-      PreservedSymbolSet.insert(Libcalls.getLibcallImplName(Impl));
-  }
-  return PreservedSymbolSet;
-}
-
 Error Builder::addSymbol(const ModuleSymbolTable &Msymtab,
                          const SmallPtrSet<GlobalValue *, 4> &Used,
                          ModuleSymbolTable::Symbol Msym) {
@@ -279,13 +278,11 @@ Error Builder::addSymbol(const ModuleSymbolTable &Msymtab,
     return Error::success();
   }
 
-  setStr(Sym.IRName, GV->getName());
-
-  static const StringSet<> PreservedSymbolsSet =
-      buildPreservedSymbolsSet(GV->getParent()->getTargetTriple());
-  bool IsPreservedSymbol = PreservedSymbolsSet.contains(GV->getName());
+  StringRef GVName = GV->getName();
+  setStr(Sym.IRName, GVName);
 
-  if (Used.count(GV) || IsPreservedSymbol)
+  if (Used.count(GV) || isPreservedLibFuncName(GVName) ||
+      isPreservedGlobalVarName(GVName))
     Sym.Flags |= 1 << storage::Symbol::FB_used;
   if (GV->isThreadLocal())
     Sym.Flags |= 1 << storage::Symbol::FB_tls;
@@ -352,7 +349,6 @@ Error Builder::build(ArrayRef<Module *> IRMods) {
   setStr(Hdr.Producer, kExpectedProducerName);
   setStr(Hdr.TargetTriple, IRMods[0]->getTargetTriple().str());
   setStr(Hdr.SourceFileName, IRMods[0]->getSourceFileName());
-  TT = IRMods[0]->getTargetTriple();
 
   for (auto *M : IRMods)
     if (Error Err = addModule(M))
@@ -378,7 +374,8 @@ Error Builder::build(ArrayRef<Module *> IRMods) {
 Error irsymtab::build(ArrayRef<Module *> Mods, SmallVector<char, 0> &Symtab,
                       StringTableBuilder &StrtabBuilder,
                       BumpPtrAllocator &Alloc) {
-  return Builder(Symtab, StrtabBuilder, Alloc).build(Mods);
+  const Triple &TT = Mods[0]->getTargetTriple();
+  return Builder(Symtab, StrtabBuilder, Alloc, TT).build(Mods);
 }
 
 // Upgrade a vector of bitcode modules created by an old version of LLVM by