https://github.com/arsenm created https://github.com/llvm/llvm-project/pull/150192
a96121089b9c94e08c6632f91f2dffc73c0ffa28 reverted a change to use a binary search on the string name table because it was too slow. This replaces it with a static string hash table based on the known set of libcall names. Microbenchmarking shows this is similarly fast to using DenseMap. It's possibly slightly slower than using StringSet, though these aren't an exact comparison. This also saves on the one time use construction of the map, so it could be better in practice. This search isn't simple set check, since it does find the range of possible matches with the same name. There's also an additional check for whether the current target supports the name. The runtime constructed set doesn't require this, since it only adds the symbols live for the target. Followed algorithm from this post http://0x80.pl/notesen/2023-04-30-lookup-in-strings.html I'm also thinking the 2 special case global symbols should just be added to RuntimeLibcalls. There are also other global references emitted in the backend that aren't tracked; we probably should just use this as a centralized database for all compiler selected symbols. >From 75713d9d40c3ecfeeda64a829d4259aad8dabb1d Mon Sep 17 00:00:00 2001 From: Matt Arsenault <matthew.arsena...@amd.com> Date: Sat, 19 Jul 2025 18:39:12 +0900 Subject: [PATCH] TableGen: Emit perfect hash function for runtime libcalls a96121089b9c94e08c6632f91f2dffc73c0ffa28 reverted a change to use a binary search on the string name table because it was too slow. This replaces it with a static string hash table based on the known set of libcall names. Microbenchmarking shows this is similarly fast to using DenseMap. It's possibly slightly slower than using StringSet, though these aren't an exact comparison. This also saves on the one time use construction of the map, so it could be better in practice. This search isn't simple set check, since it does find the range of possible matches with the same name. There's also an additional check for whether the current target supports the name. The runtime constructed set doesn't require this, since it only adds the symbols live for the target. Followed algorithm from this post http://0x80.pl/notesen/2023-04-30-lookup-in-strings.html I'm also thinking the 2 special case global symbols should just be added to RuntimeLibcalls. There are also other global references emitted in the backend that aren't tracked; we probably should just use this as a centralized database for all compiler selected symbols. --- llvm/benchmarks/CMakeLists.txt | 17 ++ llvm/benchmarks/RuntimeLibcalls.cpp | 116 ++++++++++ llvm/include/llvm/IR/RuntimeLibcalls.h | 44 +++- llvm/lib/IR/RuntimeLibcalls.cpp | 58 ++--- llvm/lib/Object/IRSymtab.cpp | 46 ++-- llvm/test/TableGen/RuntimeLibcallEmitter.td | 32 ++- llvm/unittests/IR/CMakeLists.txt | 1 + llvm/unittests/IR/RuntimeLibcallsTest.cpp | 63 ++++++ .../TableGen/Basic/RuntimeLibcallsEmitter.cpp | 212 ++++++++++++++++-- 9 files changed, 500 insertions(+), 89 deletions(-) create mode 100644 llvm/benchmarks/RuntimeLibcalls.cpp create mode 100644 llvm/unittests/IR/RuntimeLibcallsTest.cpp diff --git a/llvm/benchmarks/CMakeLists.txt b/llvm/benchmarks/CMakeLists.txt index 1078efa55f497..9613678d2e0ac 100644 --- a/llvm/benchmarks/CMakeLists.txt +++ b/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}") diff --git a/llvm/benchmarks/RuntimeLibcalls.cpp b/llvm/benchmarks/RuntimeLibcalls.cpp new file mode 100644 index 0000000000000..47f68abff1e0d --- /dev/null +++ b/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(); diff --git a/llvm/include/llvm/IR/RuntimeLibcalls.h b/llvm/include/llvm/IR/RuntimeLibcalls.h index 89ad4e5bc6ca4..acd220f08160b 100644 --- a/llvm/include/llvm/IR/RuntimeLibcalls.h +++ b/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. - 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); + static const RTLIB::LibcallImpl DefaultLibcallImpls[RTLIB::UNKNOWN_LIBCALL + 1]; @@ -160,13 +190,11 @@ 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()) diff --git a/llvm/lib/IR/RuntimeLibcalls.cpp b/llvm/lib/IR/RuntimeLibcalls.cpp index 5936ac7d0287f..51f8a146f86a7 100644 --- a/llvm/lib/IR/RuntimeLibcalls.cpp +++ b/llvm/lib/IR/RuntimeLibcalls.cpp @@ -8,15 +8,18 @@ #include "llvm/IR/RuntimeLibcalls.h" #include "llvm/ADT/StringTable.h" +#include "llvm/Support/xxhash.h" using namespace llvm; 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 static void setARMLibcallNames(RuntimeLibcallsInfo &Info, const Triple &TT, FloatABI::ABIType FloatABIType, @@ -135,49 +138,22 @@ 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 (int E = std::size(RuntimeLibcallNameOffsetTable); + NameOffsetEntry + NumAliases != E && + RuntimeLibcallNameOffsetTable[NameOffsetEntry + NumAliases] == StrOffset; + ++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::darwinHasExp10(const Triple &TT) { diff --git a/llvm/lib/Object/IRSymtab.cpp b/llvm/lib/Object/IRSymtab.cpp index 0f194953787e6..7bba6f15dd1b5 100644 --- a/llvm/lib/Object/IRSymtab.cpp +++ b/llvm/lib/Object/IRSymtab.cpp @@ -54,6 +54,11 @@ static const char *PreservedSymbols[] = { "__stack_chk_guard", }; +static bool isPreservedGlobalVarName(StringRef Name) { + return StringRef(PreservedSymbols[0]) == Name || + StringRef(PreservedSymbols[1]) == Name; +} + namespace { const char *getExpectedProducerName() { @@ -81,12 +86,16 @@ 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 +107,10 @@ 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 +226,6 @@ 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 +279,11 @@ 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 +350,6 @@ 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 +375,8 @@ 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 diff --git a/llvm/test/TableGen/RuntimeLibcallEmitter.td b/llvm/test/TableGen/RuntimeLibcallEmitter.td index 579e3c7dd62ab..2bebe2b2082eb 100644 --- a/llvm/test/TableGen/RuntimeLibcallEmitter.td +++ b/llvm/test/TableGen/RuntimeLibcallEmitter.td @@ -95,8 +95,8 @@ def BlahLibrary : SystemRuntimeLibrary<isBlahArch, (add calloc, LibraryWithCondi // CHECK-NEXT: __lshrdi3 = 4, // __lshrdi3 // CHECK-NEXT: bzero = 5, // bzero // CHECK-NEXT: calloc = 6, // calloc -// CHECK-NEXT: sqrtl_f80 = 7, // sqrtl -// CHECK-NEXT: sqrtl_f128 = 8, // sqrtl +// CHECK-NEXT: sqrtl_f128 = 7, // sqrtl +// CHECK-NEXT: sqrtl_f80 = 8, // sqrtl // CHECK-NEXT: NumLibcallImpls = 9 // CHECK-NEXT: }; // CHECK-NEXT: } // End namespace RTLIB @@ -157,10 +157,36 @@ def BlahLibrary : SystemRuntimeLibrary<isBlahArch, (add calloc, LibraryWithCondi // CHECK-NEXT: RTLIB::SRL_I64, // RTLIB::__lshrdi3 // CHECK-NEXT: RTLIB::BZERO, // RTLIB::bzero // CHECK-NEXT: RTLIB::CALLOC, // RTLIB::calloc -// CHECK-NEXT: RTLIB::SQRT_F80, // RTLIB::sqrtl_f80 // CHECK-NEXT: RTLIB::SQRT_F128, // RTLIB::sqrtl_f128 +// CHECK-NEXT: RTLIB::SQRT_F80, // RTLIB::sqrtl_f80 // CHECK-NEXT: }; +// CHECK: #ifdef GET_LOOKUP_LIBCALL_IMPL_NAME_BODY +// CHECK-NEXT: size_t Size = Name.size(); +// CHECK-NEXT: if (Size == 0 || Size > 9) +// CHECK-NEXT: return enum_seq(RTLIB::Unsupported, RTLIB::Unsupported); +// CHECK-NEXT: return lookupLibcallImplNameImpl(Name); +// CHECK-NEXT: #endif + +// CHECK: #ifdef DEFINE_GET_LOOKUP_LIBCALL_IMPL_NAME +// CHECK-NEXT: static inline uint64_t hash(StringRef Str) { +// CHECK-NEXT: return static_cast<uint32_t>(xxh3_64bits(Str)); +// CHECK-NEXT: } + +// CHECK: iota_range<RTLIB::LibcallImpl> RTLIB::RuntimeLibcallsInfo::lookupLibcallImplNameImpl(StringRef Name) { +// CHECK: static const std::pair<uint16_t, uint16_t> HashTableNameToEnum[16] = { +// CHECK: {2, 9}, // 0x000000705301b8, ___memset +// CHECK: {0, 0}, +// CHECK: {6, 6}, // 0x0000001417a2af, calloc +// CHECK: {0, 0}, +// CHECK: }; + +// CHECK: unsigned Idx = (hash(Name) % 8) * 2; +// CHECK: for (int I = 0; I != 2; ++I) { +// CHECK: return libcallImplNameHit(Entry, StrOffset); + +// CHECK: return enum_seq(RTLIB::Unsupported, RTLIB::Unsupported); +// CHECK-NEXT: } // CHECK: void llvm::RTLIB::RuntimeLibcallsInfo::setTargetRuntimeLibcallSets(const llvm::Triple &TT, FloatABI::ABIType FloatABI) { // CHECK-NEXT: struct LibcallImplPair { diff --git a/llvm/unittests/IR/CMakeLists.txt b/llvm/unittests/IR/CMakeLists.txt index b66eae93f9339..8b7bd3997ea27 100644 --- a/llvm/unittests/IR/CMakeLists.txt +++ b/llvm/unittests/IR/CMakeLists.txt @@ -43,6 +43,7 @@ add_llvm_unittest(IRTests PatternMatch.cpp ShuffleVectorInstTest.cpp StructuralHashTest.cpp + RuntimeLibcallsTest.cpp TimePassesTest.cpp TypesTest.cpp UseTest.cpp diff --git a/llvm/unittests/IR/RuntimeLibcallsTest.cpp b/llvm/unittests/IR/RuntimeLibcallsTest.cpp new file mode 100644 index 0000000000000..1ef79e74f9a4b --- /dev/null +++ b/llvm/unittests/IR/RuntimeLibcallsTest.cpp @@ -0,0 +1,63 @@ +//===----------------------------------------------------------------------===// +// +// 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 "llvm/ADT/STLExtras.h" +#include "gtest/gtest.h" +using namespace llvm; + +namespace { + +TEST(RuntimeLibcallsTest, LibcallImplByName) { + EXPECT_TRUE(RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("").empty()); + EXPECT_TRUE( + RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("unknown").empty()); + EXPECT_TRUE( + RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("Unsupported").empty()); + EXPECT_TRUE( + RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("unsupported").empty()); + + for (RTLIB::LibcallImpl LC : RTLIB::libcall_impls()) { + const char *Name = RTLIB::RuntimeLibcallsInfo::getLibcallImplName(LC); + EXPECT_FALSE( + RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName(Name).empty()); + } + + // Test first libcall name + EXPECT_EQ( + RTLIB::arm64ec__Unwind_Resume, + *RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("#_Unwind_Resume") + .begin()); + // Test longest libcall names + EXPECT_EQ(RTLIB::__hexagon_memcpy_likely_aligned_min32bytes_mult8bytes, + *RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName( + "__hexagon_memcpy_likely_aligned_min32bytes_mult8bytes") + .begin()); + + { + auto SquirtleSquad = + RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("sqrtl"); + ASSERT_EQ(size(SquirtleSquad), 3); + auto I = SquirtleSquad.begin(); + EXPECT_EQ(*I++, RTLIB::sqrt_f128); + EXPECT_EQ(*I++, RTLIB::sqrt_f80); + EXPECT_EQ(*I++, RTLIB::sqrt_ppcf128); + } + + // Last libcall + { + auto Truncs = RTLIB::RuntimeLibcallsInfo::lookupLibcallImplName("truncl"); + ASSERT_EQ(size(Truncs), 3); + auto I = Truncs.begin(); + EXPECT_EQ(*I++, RTLIB::trunc_f128); + EXPECT_EQ(*I++, RTLIB::trunc_f80); + EXPECT_EQ(*I++, RTLIB::trunc_ppcf128); + } +} + +} // namespace diff --git a/llvm/utils/TableGen/Basic/RuntimeLibcallsEmitter.cpp b/llvm/utils/TableGen/Basic/RuntimeLibcallsEmitter.cpp index 7f90d6b4fdacc..35577826a25bd 100644 --- a/llvm/utils/TableGen/Basic/RuntimeLibcallsEmitter.cpp +++ b/llvm/utils/TableGen/Basic/RuntimeLibcallsEmitter.cpp @@ -6,10 +6,15 @@ // //===----------------------------------------------------------------------===// +#define DEBUG_TYPE "runtime-libcall-emitter" + +#include "llvm/ADT/DenseSet.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/Debug.h" +#include "llvm/Support/Format.h" #include "llvm/Support/FormatVariadic.h" #include "llvm/Support/raw_ostream.h" +#include "llvm/Support/xxhash.h" #include "llvm/TableGen/Error.h" #include "llvm/TableGen/Record.h" #include "llvm/TableGen/SetTheory.h" @@ -215,6 +220,9 @@ class RuntimeLibcallEmitter { private: void emitGetRuntimeLibcallEnum(raw_ostream &OS) const; + void emitNameMatchHashTable(raw_ostream &OS, + StringToOffsetTable &OffsetTable) const; + void emitGetInitRuntimeLibcallNames(raw_ostream &OS) const; void emitSystemRuntimeLibrarySetCalls(raw_ostream &OS) const; @@ -242,11 +250,10 @@ class RuntimeLibcallEmitter { SmallVector<const Record *, 1024> AllRuntimeLibcallImpls( AllRuntimeLibcallImplsRaw); - // Sort by libcall impl name, not the enum name. This keeps the order - // suitable for using the name table for libcall recognition binary search. - llvm::sort(AllRuntimeLibcallImpls, [](const Record *A, const Record *B) { - return A->getValueAsString("LibCallFuncName") < - B->getValueAsString("LibCallFuncName"); + // Sort by libcall impl name and secondarily by the enum name. + sort(AllRuntimeLibcallImpls, [](const Record *A, const Record *B) { + return std::pair(A->getValueAsString("LibCallFuncName"), A->getName()) < + std::pair(B->getValueAsString("LibCallFuncName"), B->getName()); }); RuntimeLibcallImplDefList.reserve(AllRuntimeLibcallImpls.size()); @@ -256,12 +263,9 @@ class RuntimeLibcallEmitter { RuntimeLibcallImplDefList.emplace_back(LibCallImplDef, Def2RuntimeLibcall, LibCallImplEnumVal++); - RuntimeLibcallImpl &LibCallImpl = RuntimeLibcallImplDefList.back(); - + const RuntimeLibcallImpl &LibCallImpl = RuntimeLibcallImplDefList.back(); Def2RuntimeLibcallImpl[LibCallImplDef] = &LibCallImpl; - // const RuntimeLibcallImpl &LibCallImpl = - // RuntimeLibcallImplDefList.back(); if (LibCallImpl.isDefault()) { const RuntimeLibcall *Provides = LibCallImpl.getProvides(); if (!Provides) @@ -283,6 +287,13 @@ class RuntimeLibcallEmitter { void run(raw_ostream &OS); }; +/// Helper struct for the name hash table. +struct LookupEntry { + StringRef FuncName; + uint64_t Hash = 0; + unsigned TableValue = 0; +}; + } // End anonymous namespace. void RuntimeLibcallEmitter::emitGetRuntimeLibcallEnum(raw_ostream &OS) const { @@ -296,8 +307,6 @@ void RuntimeLibcallEmitter::emitGetRuntimeLibcallEnum(raw_ostream &OS) const { OS << " " << Name << " = " << LibCall.getEnumVal() << ",\n"; } - // TODO: Emit libcall names as string offset table. - OS << " UNKNOWN_LIBCALL = " << RuntimeLibcallDefList.size() << "\n};\n\n" "enum LibcallImpl : unsigned short {\n" @@ -316,8 +325,183 @@ void RuntimeLibcallEmitter::emitGetRuntimeLibcallEnum(raw_ostream &OS) const { "#endif\n\n"; } +// StringMap uses xxh3_64bits, truncated to uint32_t. +static uint64_t hash(StringRef Str) { + return static_cast<uint32_t>(xxh3_64bits(Str)); +} + +static void emitHashFunction(raw_ostream &OS) { + OS << "static inline uint64_t hash(StringRef Str) {\n" + " return static_cast<uint32_t>(xxh3_64bits(Str));\n" + "}\n\n"; +} + +/// Return the table size, maximum number of collisions for the set of hashes +static std::pair<int, int> +computePerfectHashParameters(ArrayRef<uint64_t> Hashes) { + const int SizeOverhead = 10; + const int NumHashes = Hashes.size(); + + // Index derived from hash -> number of collisions. + DenseMap<uint64_t, int> Table; + + for (int MaxCollisions = 1;; ++MaxCollisions) { + for (int N = NumHashes; N < SizeOverhead * NumHashes; ++N) { + Table.clear(); + + bool NeedResize = false; + for (uint64_t H : Hashes) { + uint64_t Idx = H % static_cast<uint64_t>(N); + if (++Table[Idx] > MaxCollisions) { + // Need to resize the final table if we increased the collision count. + NeedResize = true; + break; + } + } + + if (!NeedResize) + return {N, MaxCollisions}; + } + } + + llvm_unreachable("loop should terminate"); +} + +static std::vector<LookupEntry> +constructPerfectHashTable(ArrayRef<RuntimeLibcallImpl> Keywords, + ArrayRef<uint64_t> Hashes, int Size, int Collisions, + StringToOffsetTable &OffsetTable) { + DenseSet<StringRef> Seen; + std::vector<LookupEntry> Lookup(Size * Collisions); + + for (const RuntimeLibcallImpl &LibCallImpl : Keywords) { + StringRef ImplName = LibCallImpl.getLibcallFuncName(); + + // We do not want to add repeated entries for cases with the same name, only + // an entry for the first, with the name collision enum values immediately + // following. + if (!Seen.insert(ImplName).second) + continue; + + uint64_t HashValue = Hashes[LibCallImpl.getEnumVal() - 1]; + + uint64_t Idx = (HashValue % static_cast<uint64_t>(Size)) * + static_cast<uint64_t>(Collisions); + + bool Found = false; + for (int J = 0; J < Collisions; ++J) { + LookupEntry &Entry = Lookup[Idx + J]; + if (Entry.TableValue == 0) { + Entry.FuncName = ImplName; + Entry.TableValue = LibCallImpl.getEnumVal(); + Entry.Hash = HashValue; + Found = true; + break; + } + } + + if (!Found) + reportFatalInternalError("failure to hash " + ImplName); + } + + return Lookup; +} + +/// Generate hash table based lookup by name. +void RuntimeLibcallEmitter::emitNameMatchHashTable( + raw_ostream &OS, StringToOffsetTable &OffsetTable) const { + std::vector<uint64_t> Hashes(RuntimeLibcallImplDefList.size()); + + size_t MaxFuncNameSize = 0; + size_t Index = 0; + for (const RuntimeLibcallImpl &LibCallImpl : RuntimeLibcallImplDefList) { + StringRef ImplName = LibCallImpl.getLibcallFuncName(); + MaxFuncNameSize = std::max(MaxFuncNameSize, ImplName.size()); + Hashes[Index++] = hash(ImplName); + } + + LLVM_DEBUG({ + for (const RuntimeLibcallImpl &LibCallImpl : RuntimeLibcallImplDefList) { + StringRef ImplName = LibCallImpl.getLibcallFuncName(); + if (ImplName.size() == MaxFuncNameSize) { + dbgs() << "Maximum runtime libcall name size: " << ImplName << '(' + << MaxFuncNameSize << ")\n"; + } + } + }); + + // Early exiting on the symbol name provides a significant speedup in the miss + // case on the set of symbols in a clang binary. Emit this as an inlinable + // precondition in the header. + // + // The empty check is also used to get sensible behavior on anonymous + // functions. + // + // TODO: It may make more sense to split the search by string size more. There + // are a few outliers, most call names are small. + OS << "#ifdef GET_LOOKUP_LIBCALL_IMPL_NAME_BODY\n" + " size_t Size = Name.size();\n" + " if (Size == 0 || Size > " + << MaxFuncNameSize + << ")\n" + " return enum_seq(RTLIB::Unsupported, RTLIB::Unsupported);\n" + " return lookupLibcallImplNameImpl(Name);\n" + "#endif\n"; + + auto [Size, Collisions] = computePerfectHashParameters(Hashes); + std::vector<LookupEntry> Lookup = constructPerfectHashTable( + RuntimeLibcallImplDefList, Hashes, Size, Collisions, OffsetTable); + + LLVM_DEBUG(dbgs() << "Runtime libcall perfect hashing parameters: Size = " + << Size << ", maximum collisions = " << Collisions << '\n'); + + OS << "#ifdef DEFINE_GET_LOOKUP_LIBCALL_IMPL_NAME\n"; + emitHashFunction(OS); + + OS << "iota_range<RTLIB::LibcallImpl> RTLIB::RuntimeLibcallsInfo::" + "lookupLibcallImplNameImpl(StringRef Name) {\n"; + + // Emit pair of RTLIB::LibcallImpl, size of the string name. It's important to + // avoid strlen on the string table entries. + OS << " static const std::pair<uint16_t, uint16_t> HashTableNameToEnum[" + << Lookup.size() << "] = {\n"; + + for (auto [FuncName, Hash, TableVal] : Lookup) { + OS << " {" << TableVal << ", " << FuncName.size() << "},"; + + if (TableVal != 0) { + OS << " // " << format_hex(Hash, 16) << ", " << FuncName; + } + + OS << '\n'; + } + + OS << " };\n\n"; + + OS << " unsigned Idx = (hash(Name) % " << Size << ") * " << Collisions + << ";\n\n" + " for (int I = 0; I != " + << Collisions << R"(; ++I) { + auto [Entry, StringSize] = HashTableNameToEnum[Idx + I]; + const uint16_t StrOffset = RuntimeLibcallNameOffsetTable[Entry]; + StringRef Str( + &RTLIB::RuntimeLibcallsInfo::RuntimeLibcallImplNameTableStorage[StrOffset], + StringSize); + if (Str == Name) + return libcallImplNameHit(Entry, StrOffset); + } + + return enum_seq(RTLIB::Unsupported, RTLIB::Unsupported); +} +)"; + + OS << "#endif\n\n"; +} + void RuntimeLibcallEmitter::emitGetInitRuntimeLibcallNames( raw_ostream &OS) const { + OS << "#ifdef GET_INIT_RUNTIME_LIBCALL_NAMES\n"; + OS << "const RTLIB::LibcallImpl " "llvm::RTLIB::RuntimeLibcallsInfo::" "DefaultLibcallImpls[RTLIB::UNKNOWN_LIBCALL + 1] = {\n"; @@ -375,6 +559,10 @@ const uint16_t RTLIB::RuntimeLibcallsInfo::RuntimeLibcallNameOffsetTable[] = { OS << '\n'; } OS << "};\n\n"; + + OS << "#endif\n\n"; + + emitNameMatchHashTable(OS, Table); } void RuntimeLibcallEmitter::emitSystemRuntimeLibrarySetCalls( @@ -559,9 +747,7 @@ void RuntimeLibcallEmitter::run(raw_ostream &OS) { emitSourceFileHeader("Runtime LibCalls Source Fragment", OS, Records); emitGetRuntimeLibcallEnum(OS); - OS << "#ifdef GET_INIT_RUNTIME_LIBCALL_NAMES\n"; emitGetInitRuntimeLibcallNames(OS); - OS << "#endif\n\n"; OS << "#ifdef GET_SET_TARGET_RUNTIME_LIBCALL_SETS\n"; emitSystemRuntimeLibrarySetCalls(OS); _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
