Index: llvm/include/llvm/InitializePasses.h =================================================================== --- llvm/include/llvm/InitializePasses.h +++ llvm/include/llvm/InitializePasses.h @@ -279,6 +279,7 @@ void initializeLowerTypeTestsPass(PassRegistry&); void initializeLowerMatrixIntrinsicsLegacyPassPass(PassRegistry &); void initializeLowerMatrixIntrinsicsMinimalLegacyPassPass(PassRegistry &); +void initializeLowerTableBasedCTZLegacyPassPass(PassRegistry &); void initializeMIRAddFSDiscriminatorsPass(PassRegistry &); void initializeMIRCanonicalizerPass(PassRegistry &); void initializeMIRNamerPass(PassRegistry &); Index: llvm/include/llvm/LinkAllPasses.h =================================================================== --- llvm/include/llvm/LinkAllPasses.h +++ llvm/include/llvm/LinkAllPasses.h @@ -143,6 +143,7 @@ (void) llvm::createLowerExpectIntrinsicPass(); (void) llvm::createLowerInvokePass(); (void) llvm::createLowerSwitchPass(); + (void) llvm::createLowerTableBasedCTZPass(); (void) llvm::createNaryReassociatePass(); (void) llvm::createObjCARCAAWrapperPass(); (void) llvm::createObjCARCAPElimPass(); Index: llvm/include/llvm/Transforms/Scalar.h =================================================================== --- llvm/include/llvm/Transforms/Scalar.h +++ llvm/include/llvm/Transforms/Scalar.h @@ -392,6 +392,12 @@ // Pass *createLowerMatrixIntrinsicsMinimalPass(); +//===----------------------------------------------------------------------===// +// +// LowerTableBasedCTZPass - Lower Table Based CTZ. +// +FunctionPass *createLowerTableBasedCTZPass(); + //===----------------------------------------------------------------------===// // // LowerWidenableCondition - Lower widenable condition to i1 true. Index: llvm/include/llvm/Transforms/Scalar/LowerTableBasedCTZ.h =================================================================== --- /dev/null +++ llvm/include/llvm/Transforms/Scalar/LowerTableBasedCTZ.h @@ -0,0 +1,25 @@ +//===- LowerTableBasedCTZ.h ---------------------------------------===// +// +// 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 +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_TRANSFORMS_SCALAR_LOWERTABLEBASEDCTZ_H +#define LLVM_TRANSFORMS_SCALAR_LOWERTABLEBASEDCTZ_H + +#include "llvm/IR/PassManager.h" + +namespace llvm { + +class LowerTableBasedCTZPass + : public PassInfoMixin { +public: + LowerTableBasedCTZPass() {} + PreservedAnalyses run(Function &F, FunctionAnalysisManager &); +}; + +} // end namespace llvm + +#endif // LLVM_TRANSFORMS_SCALAR_LOWERTABLEBASEDCTZ_H Index: llvm/lib/Passes/PassBuilder.cpp =================================================================== --- llvm/lib/Passes/PassBuilder.cpp +++ llvm/lib/Passes/PassBuilder.cpp @@ -185,6 +185,7 @@ #include "llvm/Transforms/Scalar/LowerExpectIntrinsic.h" #include "llvm/Transforms/Scalar/LowerGuardIntrinsic.h" #include "llvm/Transforms/Scalar/LowerMatrixIntrinsics.h" +#include "llvm/Transforms/Scalar/LowerTableBasedCTZ.h" #include "llvm/Transforms/Scalar/LowerWidenableCondition.h" #include "llvm/Transforms/Scalar/MakeGuardsExplicit.h" #include "llvm/Transforms/Scalar/MemCpyOptimizer.h" Index: llvm/lib/Passes/PassRegistry.def =================================================================== --- llvm/lib/Passes/PassRegistry.def +++ llvm/lib/Passes/PassRegistry.def @@ -255,6 +255,7 @@ FUNCTION_PASS("lower-expect", LowerExpectIntrinsicPass()) FUNCTION_PASS("lower-guard-intrinsic", LowerGuardIntrinsicPass()) FUNCTION_PASS("lower-constant-intrinsics", LowerConstantIntrinsicsPass()) +FUNCTION_PASS("lower-table-based-ctz", LowerTableBasedCTZPass()) FUNCTION_PASS("lower-widenable-condition", LowerWidenableConditionPass()) FUNCTION_PASS("guard-widening", GuardWideningPass()) FUNCTION_PASS("load-store-vectorizer", LoadStoreVectorizerPass()) Index: llvm/lib/Target/AArch64/AArch64TargetMachine.cpp =================================================================== --- llvm/lib/Target/AArch64/AArch64TargetMachine.cpp +++ llvm/lib/Target/AArch64/AArch64TargetMachine.cpp @@ -547,6 +547,10 @@ addPass(createInterleavedAccessPass()); } + if (TM->getOptLevel() == CodeGenOpt::Aggressive) { + addPass(createLowerTableBasedCTZPass()); + } + if (TM->getOptLevel() == CodeGenOpt::Aggressive && EnableGEPOpt) { // Call SeparateConstOffsetFromGEP pass to extract constants within indices // and lower a GEP with multiple indices to either arithmetic operations or Index: llvm/lib/Transforms/Scalar/CMakeLists.txt =================================================================== --- llvm/lib/Transforms/Scalar/CMakeLists.txt +++ llvm/lib/Transforms/Scalar/CMakeLists.txt @@ -52,6 +52,7 @@ LowerExpectIntrinsic.cpp LowerGuardIntrinsic.cpp LowerMatrixIntrinsics.cpp + LowerTableBasedCTZ.cpp LowerWidenableCondition.cpp MakeGuardsExplicit.cpp MemCpyOptimizer.cpp Index: llvm/lib/Transforms/Scalar/LowerTableBasedCTZ.cpp =================================================================== --- /dev/null +++ llvm/lib/Transforms/Scalar/LowerTableBasedCTZ.cpp @@ -0,0 +1,284 @@ +//===- LowerTableBasedCTZ.cpp -------------------------------------===// +// +// 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 +// +//===----------------------------------------------------------------------===// +// +// Try to recognize table-based ctz implementation. +// E.g., example in C: +// int f(unsigned x) +// { +// static const char table[32] = +// {0, 1, 28, 2, 29, 14, 24, 3, 30, +// 22, 20, 15, 25, 17, 4, 8, 31, 27, +// 13, 23, 21, 19, 16, 7, 26, 12, 18, 6, 11, 5, 10, 9}; +// return table[((unsigned)((x & -x) * 0x077CB531U)) >> 27]; +// } +// this can be lowerer __builtin_ctz(x) (where x != 0 ? __builtin_ctz(x) : 0). +// +// Here are some examples or IR for AARCH64 target: +// +// CASE 1: +// %sub = sub i32 0, %x +// %and = and i32 %sub, %x +// %mul = mul i32 %and, 125613361 +// %shr = lshr i32 %mul, 27 +// %idxprom = zext i32 %shr to i64 +// %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @ctz1.table, i64 0, +// i64 %idxprom %0 = load i8, i8* %arrayidx, align 1, !tbaa !8 +// +// CASE 2: +// %sub = sub i32 0, %x +// %and = and i32 %sub, %x +// %mul = mul i32 %and, 72416175 +// %shr = lshr i32 %mul, 26 +// %idxprom = zext i32 %shr to i64 +// %arrayidx = getelementptr inbounds [64 x i16], [64 x i16]* @ctz2.table, i64 +// 0, i64 %idxprom %0 = load i16, i16* %arrayidx, align 2, !tbaa !8 +// +// CASE 3: +// %sub = sub i32 0, %x +// %and = and i32 %sub, %x +// %mul = mul i32 %and, 81224991 +// %shr = lshr i32 %mul, 27 +// %idxprom = zext i32 %shr to i64 +// %arrayidx = getelementptr inbounds [32 x i32], [32 x i32]* @ctz3.table, i64 +// 0, i64 %idxprom %0 = load i32, i32* %arrayidx, align 4, !tbaa !8 +// +// CASE 4: +// %sub = sub i64 0, %x +// %and = and i64 %sub, %x +// %mul = mul i64 %and, 283881067100198605 +// %shr = lshr i64 %mul, 58 +// %arrayidx = getelementptr inbounds [64 x i8], [64 x i8]* @table, i64 0, i64 +// %shr %0 = load i8, i8* %arrayidx, align 1, !tbaa !8 +// +// All this can be lowered to @llvm.cttz.i32/64 intrinsic. +// +//===----------------------------------------------------------------------===// + +#include "llvm/Transforms/Scalar/LowerTableBasedCTZ.h" +#include "llvm/ADT/SmallVector.h" +#include "llvm/IR/BasicBlock.h" +#include "llvm/IR/Function.h" +#include "llvm/IR/IRBuilder.h" +#include "llvm/IR/Instruction.h" +#include "llvm/IR/Instructions.h" +#include "llvm/IR/Module.h" +#include "llvm/IR/PassManager.h" +#include "llvm/IR/PatternMatch.h" +#include "llvm/IR/Type.h" +#include "llvm/IR/User.h" +#include "llvm/IR/Value.h" +#include "llvm/InitializePasses.h" +#include "llvm/Pass.h" +#include "llvm/Support/Casting.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/ErrorHandling.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Target/TargetMachine.h" +#include "llvm/Transforms/Scalar.h" +#include "llvm/Transforms/Utils/Local.h" +#include +#include +#include + +using namespace llvm; +using namespace llvm::PatternMatch; + +namespace { + +/// A pass that tries to lower sequence of instructions to +/// llvm.cttz.*() intrinsic. +class LowerTableBasedCTZLegacyPass : public FunctionPass { +public: + static char ID; + + LowerTableBasedCTZLegacyPass() : FunctionPass(ID) { + initializeLowerTableBasedCTZLegacyPassPass( + *PassRegistry::getPassRegistry()); + } + + void getAnalysisUsage(AnalysisUsage &AU) const override { + AU.setPreservesCFG(); + } + + bool runOnFunction(Function &F) override; +}; + +/// This is an implementation for LowerTableBasedCTZ Pass. +class LowerTableBasedCTZ { +public: + LowerTableBasedCTZ() {} + + bool run(Function &F); + +private: + bool lower(LoadInst *LI); + void removeDeadInstrs(Function &F); +}; + +} // end anonymous namespace + +char LowerTableBasedCTZLegacyPass::ID = 0; + +INITIALIZE_PASS_BEGIN(LowerTableBasedCTZLegacyPass, "lower-table-based-ctz", + "Lower Table Based CTZ", false, false) +INITIALIZE_PASS_END(LowerTableBasedCTZLegacyPass, "lower-table-based-ctz", + "Lower Table Based CTZ", false, false) + +FunctionPass *llvm::createLowerTableBasedCTZPass() { + return new LowerTableBasedCTZLegacyPass(); +} + +bool LowerTableBasedCTZLegacyPass::runOnFunction(Function &F) { + if (skipFunction(F)) + return false; + + LowerTableBasedCTZ Impl; + return Impl.run(F); +} + +void LowerTableBasedCTZ::removeDeadInstrs(Function &F) { + SmallVector DeadInstsInBB; + for (BasicBlock &B : F) { + for (Instruction &I : B) { + if (isInstructionTriviallyDead(&I)) { + DeadInstsInBB.push_back(&I); + } + } + } + RecursivelyDeleteTriviallyDeadInstructions(DeadInstsInBB); +} + +bool LowerTableBasedCTZ::run(Function &F) { + bool Changed = false; + for (BasicBlock &B : F) { + for (BasicBlock::iterator I = B.begin(), IE = B.end(); I != IE;) + if (LoadInst *LI = dyn_cast(I++)) + Changed |= lower(LI); + } + + if (Changed) + removeDeadInstrs(F); + + return Changed; +} + +template +static bool isCTZTable(const ConstantDataArray &Table, IntType Mul, + IntType Shift) { + unsigned Length = Table.getNumElements(); + IntType IntWidth = sizeof(IntType); + IntType Bits = IntWidth * 8; + if (Length < Bits || Length > Bits * 2) + return false; + + IntType Mask = ((IntWidth << (Bits - Shift)) - 1) << Shift; + unsigned Matched = 0; + + for (unsigned i = 0; i < Length; i++) { + uint64_t Element = Table.getElementAsInteger(i); + if (Element < Bits && (((Mul << Element) & Mask) >> Shift) == i) + Matched++; + } + + return Matched == Bits; +} + +bool LowerTableBasedCTZ::lower(LoadInst *LI) { + Type *ElType = LI->getPointerOperandType()->getPointerElementType(); + if (!ElType->isIntegerTy()) + return false; + + GetElementPtrInst *GEP = + dyn_cast_or_null(LI->getPointerOperand()); + if (!GEP || !GEP->isInBounds() || GEP->getNumIndices() != 2) + return false; + + Type *GEPPointeeType = GEP->getPointerOperandType()->getPointerElementType(); + if (!GEPPointeeType->isArrayTy()) + return false; + + uint64_t ArraySize = GEPPointeeType->getArrayNumElements(); + if (ArraySize != 32 && ArraySize != 64) + return false; + + User *GEPUser = dyn_cast_or_null(GEP->getPointerOperand()); + if (!GEPUser) + return false; + + ConstantDataArray *ConstData = + dyn_cast_or_null(GEPUser->getOperand(0)); + if (!ConstData) + return false; + + Value *Idx1 = GEP->idx_begin()->get(); + Constant *Zero = dyn_cast_or_null(Idx1); + if (!Zero || !Zero->isZeroValue()) + return false; + + Value *Idx2 = std::next(GEP->idx_begin())->get(); + + bool ConstIsWide = !match(Idx2, m_ZExt(m_Value())); + + Value *X1, *X2; + uint64_t MulConst, ShiftConst; + // Aarch64 has i64 for getelementpointer index so this match will probably + // fail for other targets. + if (!match(Idx2, + m_ZExtOrSelf(m_LShr( + m_ZExtOrSelf(m_Mul( + m_And(m_Sub(m_SpecificInt(0), m_Value(X1)), m_Value(X2)), + m_ConstantInt(MulConst))), + m_ConstantInt(ShiftConst))))) + return false; + + unsigned InputBits = ConstIsWide ? 64 : 32; + + // Shift should extract top 5..7 bits. + if (ShiftConst < InputBits - 7 || ShiftConst > InputBits - 5) + return false; + + if (X1 != X2) + return false; + + Argument *ArgX = dyn_cast_or_null(X1); + if (!ArgX) + return false; + + Type *ArgXType = ArgX->getType(); + if (!ArgXType->isIntegerTy(InputBits)) + return false; + + if (ConstIsWide) { + if (!isCTZTable(*ConstData, MulConst, ShiftConst)) + return false; + } else { + if (!isCTZTable(*ConstData, MulConst, ShiftConst)) + return false; + } + + bool DefinedForZero = ConstData->getElementAsInteger(0) == InputBits; + + IRBuilder<> B(LI); + ConstantInt *BoolConst = DefinedForZero ? B.getTrue() : B.getFalse(); + auto Cttz = B.CreateIntrinsic(Intrinsic::cttz, {ArgXType}, {ArgX, BoolConst}); + auto ZExtOrTrunc = B.CreateZExtOrTrunc(Cttz, ElType); + + LI->replaceAllUsesWith(ZExtOrTrunc); + LI->eraseFromParent(); + return true; +} + +PreservedAnalyses LowerTableBasedCTZPass::run(Function &F, + FunctionAnalysisManager &AM) { + LowerTableBasedCTZ Impl; + if (!Impl.run(F)) + return PreservedAnalyses::all(); + PreservedAnalyses PA; + PA.preserveSet(); + return PA; +} Index: llvm/lib/Transforms/Scalar/Scalar.cpp =================================================================== --- llvm/lib/Transforms/Scalar/Scalar.cpp +++ llvm/lib/Transforms/Scalar/Scalar.cpp @@ -87,6 +87,7 @@ initializeLowerMatrixIntrinsicsLegacyPassPass(Registry); initializeLowerMatrixIntrinsicsMinimalLegacyPassPass(Registry); initializeLowerWidenableConditionLegacyPassPass(Registry); + initializeLowerTableBasedCTZLegacyPassPass(Registry); initializeMemCpyOptLegacyPassPass(Registry); initializeMergeICmpsLegacyPassPass(Registry); initializeMergedLoadStoreMotionLegacyPassPass(Registry); Index: llvm/test/CodeGen/AArch64/O3-pipeline.ll =================================================================== --- llvm/test/CodeGen/AArch64/O3-pipeline.ll +++ llvm/test/CodeGen/AArch64/O3-pipeline.ll @@ -76,6 +76,7 @@ ; CHECK-NEXT: Interleaved Load Combine Pass ; CHECK-NEXT: Dominator Tree Construction ; CHECK-NEXT: Interleaved Access Pass +; CHECK-NEXT: Lower Table Based CTZ ; CHECK-NEXT: Natural Loop Information ; CHECK-NEXT: Scalar Evolution Analysis ; CHECK-NEXT: Split GEPs to a variadic base and a constant offset for better CSE Index: llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/dereferencing-pointer.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/dereferencing-pointer.ll @@ -0,0 +1,63 @@ +; RUN: opt -lower-table-based-ctz -mtriple aarch64-linux-gnu -S < %s | FileCheck %s + +;; static const unsigned long long magic = 0x03f08c5392f756cdULL; +;; +;; static const int table[64] = { +;; 0, 1, 12, 2, 13, 22, 17, 3, +;; 14, 33, 23, 36, 18, 58, 28, 4, +;; 62, 15, 34, 26, 24, 48, 50, 37, +;; 19, 55, 59, 52, 29, 44, 39, 5, +;; 63, 11, 21, 16, 32, 35, 57, 27, +;; 61, 25, 47, 49, 54, 51, 43, 38, +;; 10, 20, 31, 56, 60, 46, 53, 42, +;; 9, 30, 45, 41, 8, 40, 7, 6, +;; }; +;; +;; int ctz6 (unsigned long long * const b) { +;; return table[(((*b) & -(*b)) * magic) >> 58]; +;; } + +;; This will be handled as a future work. +; XFAIL: * + +; CHECK: %0 = call i64 @llvm.cttz.i64 + +; ModuleID = 'test.c' +source_filename = "test.c" +target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" +target triple = "aarch64-unknown-linux-gnu" + +@table = internal unnamed_addr constant [64 x i32] [i32 0, i32 1, i32 12, i32 2, i32 13, i32 22, i32 17, i32 3, i32 14, i32 33, i32 23, i32 36, i32 18, i32 58, i32 28, i32 4, i32 62, i32 15, i32 34, i32 26, i32 24, i32 48, i32 50, i32 37, i32 19, i32 55, i32 59, i32 52, i32 29, i32 44, i32 39, i32 5, i32 63, i32 11, i32 21, i32 16, i32 32, i32 35, i32 57, i32 27, i32 61, i32 25, i32 47, i32 49, i32 54, i32 51, i32 43, i32 38, i32 10, i32 20, i32 31, i32 56, i32 60, i32 46, i32 53, i32 42, i32 9, i32 30, i32 45, i32 41, i32 8, i32 40, i32 7, i32 6], align 4 + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readonly uwtable willreturn +define dso_local i32 @ctz6(i64* nocapture readonly %b) local_unnamed_addr #0 { +entry: + %0 = load i64, i64* %b, align 8, !tbaa !8 + %sub = sub i64 0, %0 + %and = and i64 %0, %sub + %mul = mul i64 %and, 283881067100198605 + %shr = lshr i64 %mul, 58 + %arrayidx = getelementptr inbounds [64 x i32], [64 x i32]* @table, i64 0, i64 %shr + %1 = load i32, i32* %arrayidx, align 4, !tbaa !12 + ret i32 %1 +} + +attributes #0 = { mustprogress nofree norecurse nosync nounwind readonly uwtable willreturn "frame-pointer"="non-leaf" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon,+outline-atomics" } + +!llvm.module.flags = !{!0, !1, !2, !3, !4, !5, !6} +!llvm.ident = !{!7} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{i32 1, !"branch-target-enforcement", i32 0} +!2 = !{i32 1, !"sign-return-address", i32 0} +!3 = !{i32 1, !"sign-return-address-all", i32 0} +!4 = !{i32 1, !"sign-return-address-with-bkey", i32 0} +!5 = !{i32 7, !"uwtable", i32 1} +!6 = !{i32 7, !"frame-pointer", i32 1} +!7 = !{!"clang version 14.0.0 (https://github.com/llvm/llvm-project.git c2574e63ff71c1d3caea48cb6200c2422bd8f33d)"} +!8 = !{!9, !9, i64 0} +!9 = !{!"long long", !10, i64 0} +!10 = !{!"omnipotent char", !11, i64 0} +!11 = !{!"Simple C/C++ TBAA"} +!12 = !{!13, !13, i64 0} +!13 = !{!"int", !10, i64 0} Index: llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/lit.local.cfg =================================================================== --- /dev/null +++ llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/lit.local.cfg @@ -0,0 +1,2 @@ +if not 'AArch64' in config.root.targets: + config.unsupported = True Index: llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/lower-table-based-ctz-basics.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/lower-table-based-ctz-basics.ll @@ -0,0 +1,251 @@ +; RUN: opt -lower-table-based-ctz -mtriple aarch64-linux-gnu -S < %s | FileCheck %s + +;; C reproducers: +;; int ctz1 (unsigned x) +;; { +;; static const char table[32] = +;; { +;; 0, 1, 28, 2, 29, 14, 24, 3, 30, 22, 20, 15, 25, 17, 4, 8, +;; 31, 27, 13, 23, 21, 19, 16, 7, 26, 12, 18, 6, 11, 5, 10, 9 +;; }; +;; return table[((unsigned)((x & -x) * 0x077CB531U)) >> 27]; +;; } + +;; int ctz2(unsigned x) +;; { +;; #define u 0 +;; static short table[64] = +;; { +;; 32, 0, 1, 12, 2, 6, u, 13, 3, u, 7, u, u, u, u, 14, +;; 10, 4, u, u, 8, u, u, 25, u, u, u, u, u, 21, 27, 15, +;; 31, 11, 5, u, u, u, u, u, 9, u, u, 24, u, u, 20, 26, +;; 30, u, u, u, u, 23, u, 19, 29, u, 22, 18, 28, 17, 16, u +;; }; +;; x = (x & -x) * 0x0450FBAF; +;; return table[x >> 26]; +;; } + +;; int ctz3(unsigned x) +;;{ +;; static int table[32] = +;; { +;; 0, 1, 2, 24, 3, 19, 6, 25, 22, 4, 20, 10, 16, 7, 12, 26, +;; 31, 23, 18, 5, 21, 9, 15, 11, 30, 17, 8, 14, 29, 13, 28, 27 +;; }; +;; if (x == 0) return 32; +;; x = (x & -x) * 0x04D7651F; +;; return table[x >> 27]; +;; } + +;; static const unsigned long long magic = 0x03f08c5392f756cdULL; +;; +;; static const int table[64] = { +;; 0, 1, 12, 2, 13, 22, 17, 3, 14, 33, 23, 36, 18, 58, 28, 4, +;; 62, 15, 34, 26, 24, 48, 50, 37, 19, 55, 59, 52, 29, 44, 39, 5, +;; 63, 11, 21, 16, 32, 35, 57, 27, 61, 25, 47, 49, 54, 51, 43, 38, +;; 10, 20, 31, 56, 60, 46, 53, 42, 9, 30, 45, 41, 8, 40, 7, 6, +;; }; +;; +;; int ctz4 (unsigned long long b) +;; { +;; unsigned long long lsb = b & -b; +;; return table[(lsb * magic) >> 58]; +;; } +;; +;; int ctz5(unsigned x) +;; { +;; static char table[32] = +;; { +;; 0, 1, 2, 24, 3, 19, 6, 25, 22, 4, 20, 10, 16, 7, 12, 26, +;; 31, 23, 18, 5, 21, 9, 15, 11, 30, 17, 8, 14, 29, 13, 28, 27 +;; }; +;; x = (x & -x)*0x04D7651F; +;; return table[x >> 27]; +;; } + +;; int indexes[] = { +;; 63, 0, 58, 1, 59, 47, 53, 2,60, 39, 48, 27, 54, 33, 42, 3, +;; 61, 51, 37, 40, 49, 18, 28, 20, 55, 30, 34, 11, 43, 14, 22, 4, +;; 62, 57, 46, 52, 38, 26, 32, 41, 50, 36, 17, 19, 29, 10, 13, 21, +;; 56, 45, 25, 31, 35, 16, 9, 12, 44, 24, 15, 8, 23, 7, 6, 5 +;; }; +;; +;; int ctz6(unsigned long n) +;; { +;; return indexes[((n & (~n + 1)) * 0x07EDD5E59A4E28C2ull) >> 58]; +;; } +;; +;; int ctz7(unsigned x) +;; { +;; static const char table[32] = "\x00\x01\x1c\x02\x1d\x0e\x18\x03\x1e\x16\x14" +;; "\x0f\x19\x11\x04\b\x1f\x1b\r\x17\x15\x13\x10\x07\x1a\f\x12\x06\v\x05\n\t"; +;; return table[((unsigned)((x & -x) * 0x077CB531U)) >> 27]; +;; } +;; +;; int ctz8(unsigned v) +;; { +;; static const int table[] = +;; { +;; 31 ,0 ,1 ,23 ,2 ,18 ,5 ,24 ,21 ,3 ,19 ,9 ,15 ,6 ,11 ,25 ,30 ,22 ,17 ,4 ,20 ;,8 ,14 ,10 ,29 ,16 ,7 ,13 ,28 ,12 ,27 ,26 +;; }; +;; unsigned x =(-v & v); +;; return table[(unsigned)(x * 0x9AECA3EU) >> 27]; +;; } + +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %x, i1 false) +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true) +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %x, i1 false) +; CHECK: %0 = call i64 @llvm.cttz.i64(i64 %b, i1 false) +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %x, i1 false) +; CHECK: %0 = call i64 @llvm.cttz.i64(i64 %n, i1 false) +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %x, i1 false) +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %v, i1 false) + +; ModuleID = 'ctz.c' +source_filename = "ctz.c" +target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" +target triple = "aarch64-unknown-linux-gnu" + +@ctz2.table = internal unnamed_addr constant [64 x i16] [i16 32, i16 0, i16 1, i16 12, i16 2, i16 6, i16 0, i16 13, i16 3, i16 0, i16 7, i16 0, i16 0, i16 0, i16 0, i16 14, i16 10, i16 4, i16 0, i16 0, i16 8, i16 0, i16 0, i16 25, i16 0, i16 0, i16 0, i16 0, i16 0, i16 21, i16 27, i16 15, i16 31, i16 11, i16 5, i16 0, i16 0, i16 0, i16 0, i16 0, i16 9, i16 0, i16 0, i16 24, i16 0, i16 0, i16 20, i16 26, i16 30, i16 0, i16 0, i16 0, i16 0, i16 23, i16 0, i16 19, i16 29, i16 0, i16 22, i16 18, i16 28, i16 17, i16 16, i16 0], align 2 +@ctz3.table = internal unnamed_addr constant [32 x i32] [i32 0, i32 1, i32 2, i32 24, i32 3, i32 19, i32 6, i32 25, i32 22, i32 4, i32 20, i32 10, i32 16, i32 7, i32 12, i32 26, i32 31, i32 23, i32 18, i32 5, i32 21, i32 9, i32 15, i32 11, i32 30, i32 17, i32 8, i32 14, i32 29, i32 13, i32 28, i32 27], align 4 +@table = internal unnamed_addr constant [64 x i32] [i32 0, i32 1, i32 12, i32 2, i32 13, i32 22, i32 17, i32 3, i32 14, i32 33, i32 23, i32 36, i32 18, i32 58, i32 28, i32 4, i32 62, i32 15, i32 34, i32 26, i32 24, i32 48, i32 50, i32 37, i32 19, i32 55, i32 59, i32 52, i32 29, i32 44, i32 39, i32 5, i32 63, i32 11, i32 21, i32 16, i32 32, i32 35, i32 57, i32 27, i32 61, i32 25, i32 47, i32 49, i32 54, i32 51, i32 43, i32 38, i32 10, i32 20, i32 31, i32 56, i32 60, i32 46, i32 53, i32 42, i32 9, i32 30, i32 45, i32 41, i32 8, i32 40, i32 7, i32 6], align 4 +@ctz5.table = internal unnamed_addr constant [32 x i8] c"\00\01\02\18\03\13\06\19\16\04\14\0A\10\07\0C\1A\1F\17\12\05\15\09\0F\0B\1E\11\08\0E\1D\0D\1C\1B", align 1 +@indexes = dso_local local_unnamed_addr global [64 x i32] [i32 63, i32 0, i32 58, i32 1, i32 59, i32 47, i32 53, i32 2, i32 60, i32 39, i32 48, i32 27, i32 54, i32 33, i32 42, i32 3, i32 61, i32 51, i32 37, i32 40, i32 49, i32 18, i32 28, i32 20, i32 55, i32 30, i32 34, i32 11, i32 43, i32 14, i32 22, i32 4, i32 62, i32 57, i32 46, i32 52, i32 38, i32 26, i32 32, i32 41, i32 50, i32 36, i32 17, i32 19, i32 29, i32 10, i32 13, i32 21, i32 56, i32 45, i32 25, i32 31, i32 35, i32 16, i32 9, i32 12, i32 44, i32 24, i32 15, i32 8, i32 23, i32 7, i32 6, i32 5], align 4 +@ctz7.table = internal unnamed_addr constant [32 x i8] c"\00\01\1C\02\1D\0E\18\03\1E\16\14\0F\19\11\04\08\1F\1B\0D\17\15\13\10\07\1A\0C\12\06\0B\05\0A\09", align 1 +@ctz8.table = internal unnamed_addr constant [32 x i32] [i32 31, i32 0, i32 1, i32 23, i32 2, i32 18, i32 5, i32 24, i32 21, i32 3, i32 19, i32 9, i32 15, i32 6, i32 11, i32 25, i32 30, i32 22, i32 17, i32 4, i32 20, i32 8, i32 14, i32 10, i32 29, i32 16, i32 7, i32 13, i32 28, i32 12, i32 27, i32 26], align 4 + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz1(i32 %x) local_unnamed_addr #0 { +entry: + %sub = sub i32 0, %x + %and = and i32 %sub, %x + %mul = mul i32 %and, 125613361 + %shr = lshr i32 %mul, 27 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @ctz7.table, i64 0, i64 %idxprom + %0 = load i8, i8* %arrayidx, align 1, !tbaa !8 + %conv = zext i8 %0 to i32 + ret i32 %conv +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz2(i32 %x) local_unnamed_addr #0 { +entry: + %sub = sub i32 0, %x + %and = and i32 %sub, %x + %mul = mul i32 %and, 72416175 + %shr = lshr i32 %mul, 26 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [64 x i16], [64 x i16]* @ctz2.table, i64 0, i64 %idxprom + %0 = load i16, i16* %arrayidx, align 2, !tbaa !11 + %conv = sext i16 %0 to i32 + ret i32 %conv +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz3(i32 %x) local_unnamed_addr #0 { +entry: + %cmp = icmp eq i32 %x, 0 + br i1 %cmp, label %return, label %if.end + +if.end: ; preds = %entry + %sub = sub i32 0, %x + %and = and i32 %sub, %x + %mul = mul i32 %and, 81224991 + %shr = lshr i32 %mul, 27 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [32 x i32], [32 x i32]* @ctz3.table, i64 0, i64 %idxprom + %0 = load i32, i32* %arrayidx, align 4, !tbaa !13 + br label %return + +return: ; preds = %entry, %if.end + %retval.0 = phi i32 [ %0, %if.end ], [ 32, %entry ] + ret i32 %retval.0 +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz4(i64 %b) local_unnamed_addr #0 { +entry: + %sub = sub i64 0, %b + %and = and i64 %sub, %b + %mul = mul i64 %and, 283881067100198605 + %shr = lshr i64 %mul, 58 + %arrayidx = getelementptr inbounds [64 x i32], [64 x i32]* @table, i64 0, i64 %shr + %0 = load i32, i32* %arrayidx, align 4, !tbaa !13 + ret i32 %0 +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz5(i32 %x) local_unnamed_addr #0 { +entry: + %sub = sub i32 0, %x + %and = and i32 %sub, %x + %mul = mul i32 %and, 81224991 + %shr = lshr i32 %mul, 27 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @ctz5.table, i64 0, i64 %idxprom + %0 = load i8, i8* %arrayidx, align 1, !tbaa !8 + %conv = zext i8 %0 to i32 + ret i32 %conv +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readonly uwtable willreturn +define dso_local i32 @ctz6(i64 %n) local_unnamed_addr #1 { +entry: + %add = sub i64 0, %n + %and = and i64 %add, %n + %mul = mul i64 %and, 571347909858961602 + %shr = lshr i64 %mul, 58 + %arrayidx = getelementptr inbounds [64 x i32], [64 x i32]* @indexes, i64 0, i64 %shr + %0 = load i32, i32* %arrayidx, align 4, !tbaa !13 + ret i32 %0 +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz7(i32 %x) local_unnamed_addr #0 { +entry: + %sub = sub i32 0, %x + %and = and i32 %sub, %x + %mul = mul i32 %and, 125613361 + %shr = lshr i32 %mul, 27 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @ctz7.table, i64 0, i64 %idxprom + %0 = load i8, i8* %arrayidx, align 1, !tbaa !8 + %conv = zext i8 %0 to i32 + ret i32 %conv +} + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @ctz8(i32 %v) local_unnamed_addr #0 { +entry: + %sub = sub i32 0, %v + %and = and i32 %sub, %v + %mul = mul i32 %and, 162449982 + %shr = lshr i32 %mul, 27 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [32 x i32], [32 x i32]* @ctz8.table, i64 0, i64 %idxprom + %0 = load i32, i32* %arrayidx, align 4, !tbaa !13 + ret i32 %0 +} + +attributes #0 = { mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn "frame-pointer"="non-leaf" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" } +attributes #1 = { mustprogress nofree norecurse nosync nounwind readonly uwtable willreturn "frame-pointer"="non-leaf" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" } + +!llvm.module.flags = !{!0, !1, !2, !3, !4, !5, !6} +!llvm.ident = !{!7} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{i32 1, !"branch-target-enforcement", i32 0} +!2 = !{i32 1, !"sign-return-address", i32 0} +!3 = !{i32 1, !"sign-return-address-all", i32 0} +!4 = !{i32 1, !"sign-return-address-with-bkey", i32 0} +!5 = !{i32 7, !"uwtable", i32 1} +!6 = !{i32 7, !"frame-pointer", i32 1} +!7 = !{!"clang version 14.0.0 (https://github.com/llvm/llvm-project.git c2574e63ff71c1d3caea48cb6200c2422bd8f33d)"} +!8 = !{!9, !9, i64 0} +!9 = !{!"omnipotent char", !10, i64 0} +!10 = !{!"Simple C/C++ TBAA"} +!11 = !{!12, !12, i64 0} +!12 = !{!"short", !9, i64 0} +!13 = !{!14, !14, i64 0} +!14 = !{!"int", !9, i64 0} Index: llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/lower-table-based-ctz.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/LowerTableBasedCTZ/AARCH64/lower-table-based-ctz.ll @@ -0,0 +1,41 @@ +; RUN: opt -lower-table-based-ctz -mtriple aarch64-linux-gnu -S < %s | FileCheck %s + +; CHECK: %0 = call i32 @llvm.cttz.i32(i32 %x, i1 false + +; ModuleID = 'test.c' +source_filename = "test.c" +target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" +target triple = "aarch64-unknown-linux" + +@f.table = internal unnamed_addr constant [32 x i8] c"\00\01\1C\02\1D\0E\18\03\1E\16\14\0F\19\11\04\08\1F\1B\0D\17\15\13\10\07\1A\0C\12\06\0B\05\0A\09", align 1 + +; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn +define dso_local i32 @f(i32 %x) local_unnamed_addr #0 { +entry: + %sub = sub i32 0, %x + %and = and i32 %sub, %x + %mul = mul i32 %and, 125613361 + %shr = lshr i32 %mul, 27 + %idxprom = zext i32 %shr to i64 + %arrayidx = getelementptr inbounds [32 x i8], [32 x i8]* @f.table, i64 0, i64 %idxprom + %0 = load i8, i8* %arrayidx, align 1, !tbaa !8 + %conv = zext i8 %0 to i32 + ret i32 %conv +} + +attributes #0 = { mustprogress nofree norecurse nosync nounwind readnone uwtable willreturn "frame-pointer"="non-leaf" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" } + +!llvm.module.flags = !{!0, !1, !2, !3, !4, !5, !6} +!llvm.ident = !{!7} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{i32 1, !"branch-target-enforcement", i32 0} +!2 = !{i32 1, !"sign-return-address", i32 0} +!3 = !{i32 1, !"sign-return-address-all", i32 0} +!4 = !{i32 1, !"sign-return-address-with-bkey", i32 0} +!5 = !{i32 7, !"uwtable", i32 1} +!6 = !{i32 7, !"frame-pointer", i32 1} +!7 = !{!"clang version 14.0.0 (https://github.com/llvm/llvm-project.git 267862c26891210ea21dd82014ddcce5d611492d)"} +!8 = !{!9, !9, i64 0} +!9 = !{!"omnipotent char", !10, i64 0} +!10 = !{!"Simple C/C++ TBAA"}