[llvm] r209791 - Add LoadCombine pass.
Michael J. Spencer
bigcheesegs at gmail.com
Wed May 28 18:55:08 PDT 2014
Author: mspencer
Date: Wed May 28 20:55:07 2014
New Revision: 209791
URL: http://llvm.org/viewvc/llvm-project?rev=209791&view=rev
Log:
Add LoadCombine pass.
This pass is disabled by default. Use -combine-loads to enable in -O[1-3]
Differential revision: http://reviews.llvm.org/D3580
Added:
llvm/trunk/lib/Transforms/Scalar/LoadCombine.cpp
llvm/trunk/test/Transforms/LoadCombine/
llvm/trunk/test/Transforms/LoadCombine/load-combine.ll
Modified:
llvm/trunk/include/llvm/IR/IRBuilder.h
llvm/trunk/include/llvm/InitializePasses.h
llvm/trunk/include/llvm/Transforms/Scalar.h
llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp
llvm/trunk/lib/Transforms/Scalar/CMakeLists.txt
llvm/trunk/lib/Transforms/Scalar/Scalar.cpp
Modified: llvm/trunk/include/llvm/IR/IRBuilder.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/IR/IRBuilder.h?rev=209791&r1=209790&r2=209791&view=diff
==============================================================================
--- llvm/trunk/include/llvm/IR/IRBuilder.h (original)
+++ llvm/trunk/include/llvm/IR/IRBuilder.h Wed May 28 20:55:07 2014
@@ -1464,6 +1464,30 @@ public:
Value *Zeros = ConstantAggregateZero::get(VectorType::get(I32Ty, NumElts));
return CreateShuffleVector(V, Undef, Zeros, Name + ".splat");
}
+
+ /// \brief Return a value that has been extracted from a larger integer type.
+ Value *CreateExtractInteger(const DataLayout &DL, Value *From,
+ IntegerType *ExtractedTy, uint64_t Offset,
+ const Twine &Name) {
+ IntegerType *IntTy = cast<IntegerType>(From->getType());
+ assert(DL.getTypeStoreSize(ExtractedTy) + Offset <=
+ DL.getTypeStoreSize(IntTy) &&
+ "Element extends past full value");
+ uint64_t ShAmt = 8 * Offset;
+ Value *V = From;
+ if (DL.isBigEndian())
+ ShAmt = 8 * (DL.getTypeStoreSize(IntTy) -
+ DL.getTypeStoreSize(ExtractedTy) - Offset);
+ if (ShAmt) {
+ V = CreateLShr(V, ShAmt, Name + ".shift");
+ }
+ assert(ExtractedTy->getBitWidth() <= IntTy->getBitWidth() &&
+ "Cannot extract to a larger integer!");
+ if (ExtractedTy != IntTy) {
+ V = CreateTrunc(V, ExtractedTy, Name + ".trunc");
+ }
+ return V;
+ }
};
// Create wrappers for C Binding types (see CBindingWrapping.h).
Modified: llvm/trunk/include/llvm/InitializePasses.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/InitializePasses.h?rev=209791&r1=209790&r2=209791&view=diff
==============================================================================
--- llvm/trunk/include/llvm/InitializePasses.h (original)
+++ llvm/trunk/include/llvm/InitializePasses.h Wed May 28 20:55:07 2014
@@ -272,6 +272,7 @@ void initializeSLPVectorizerPass(PassReg
void initializeBBVectorizePass(PassRegistry&);
void initializeMachineFunctionPrinterPassPass(PassRegistry&);
void initializeStackMapLivenessPass(PassRegistry&);
+void initializeLoadCombinePass(PassRegistry&);
}
#endif
Modified: llvm/trunk/include/llvm/Transforms/Scalar.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Transforms/Scalar.h?rev=209791&r1=209790&r2=209791&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Transforms/Scalar.h (original)
+++ llvm/trunk/include/llvm/Transforms/Scalar.h Wed May 28 20:55:07 2014
@@ -19,6 +19,7 @@
namespace llvm {
+class BasicBlockPass;
class FunctionPass;
class Pass;
class GetElementPtrInst;
@@ -381,6 +382,12 @@ FunctionPass *createAddDiscriminatorsPas
//
FunctionPass *createSeparateConstOffsetFromGEPPass();
+//===----------------------------------------------------------------------===//
+//
+// LoadCombine - Combine loads into bigger loads.
+//
+BasicBlockPass *createLoadCombinePass();
+
} // End llvm namespace
#endif
Modified: llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp?rev=209791&r1=209790&r2=209791&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp (original)
+++ llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp Wed May 28 20:55:07 2014
@@ -53,6 +53,10 @@ static cl::opt<bool>
RunLoopRerolling("reroll-loops", cl::Hidden,
cl::desc("Run the loop rerolling pass"));
+static cl::opt<bool> RunLoadCombine("combine-loads", cl::init(false),
+ cl::Hidden,
+ cl::desc("Run the load combining pass"));
+
PassManagerBuilder::PassManagerBuilder() {
OptLevel = 2;
SizeLevel = 0;
@@ -65,6 +69,7 @@ PassManagerBuilder::PassManagerBuilder()
SLPVectorize = RunSLPVectorization;
LoopVectorize = RunLoopVectorization;
RerollLoops = RunLoopRerolling;
+ LoadCombine = RunLoadCombine;
}
PassManagerBuilder::~PassManagerBuilder() {
@@ -236,6 +241,9 @@ void PassManagerBuilder::populateModuleP
MPM.add(createLoopUnrollPass());
}
+ if (LoadCombine)
+ MPM.add(createLoadCombinePass());
+
MPM.add(createAggressiveDCEPass()); // Delete dead instructions
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
MPM.add(createInstructionCombiningPass()); // Clean up after everything.
@@ -352,6 +360,9 @@ void PassManagerBuilder::populateLTOPass
// More scalar chains could be vectorized due to more alias information
PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+ if (LoadCombine)
+ PM.add(createLoadCombinePass());
+
// Cleanup and simplify the code after the scalar optimizations.
PM.add(createInstructionCombiningPass());
addExtensionsToPM(EP_Peephole, PM);
Modified: llvm/trunk/lib/Transforms/Scalar/CMakeLists.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/CMakeLists.txt?rev=209791&r1=209790&r2=209791&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/CMakeLists.txt (original)
+++ llvm/trunk/lib/Transforms/Scalar/CMakeLists.txt Wed May 28 20:55:07 2014
@@ -12,6 +12,7 @@ add_llvm_library(LLVMScalarOpts
IndVarSimplify.cpp
JumpThreading.cpp
LICM.cpp
+ LoadCombine.cpp
LoopDeletion.cpp
LoopIdiomRecognize.cpp
LoopInstSimplify.cpp
Added: llvm/trunk/lib/Transforms/Scalar/LoadCombine.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/LoadCombine.cpp?rev=209791&view=auto
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/LoadCombine.cpp (added)
+++ llvm/trunk/lib/Transforms/Scalar/LoadCombine.cpp Wed May 28 20:55:07 2014
@@ -0,0 +1,268 @@
+//===- LoadCombine.cpp - Combine Adjacent Loads ---------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+/// \file
+/// This transformation combines adjacent loads.
+///
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Transforms/Scalar.h"
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/TargetFolder.h"
+#include "llvm/Pass.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/MathExtras.h"
+#include "llvm/Support/raw_ostream.h"
+
+using namespace llvm;
+
+#define DEBUG_TYPE "load-combine"
+
+STATISTIC(NumLoadsAnalyzed, "Number of loads analyzed for combining");
+STATISTIC(NumLoadsCombined, "Number of loads combined");
+
+namespace {
+struct PointerOffsetPair {
+ Value *Pointer;
+ uint64_t Offset;
+};
+
+struct LoadPOPPair {
+ LoadPOPPair(LoadInst *L, PointerOffsetPair P, unsigned O)
+ : Load(L), POP(P), InsertOrder(O) {}
+ LoadPOPPair() {}
+ LoadInst *Load;
+ PointerOffsetPair POP;
+ /// \brief The new load needs to be created before the first load in IR order.
+ unsigned InsertOrder;
+};
+
+class LoadCombine : public BasicBlockPass {
+ LLVMContext *C;
+ const DataLayout *DL;
+
+public:
+ LoadCombine()
+ : BasicBlockPass(ID),
+ C(nullptr), DL(nullptr) {
+ initializeSROAPass(*PassRegistry::getPassRegistry());
+ }
+ bool doInitialization(Function &) override;
+ bool runOnBasicBlock(BasicBlock &BB) override;
+ void getAnalysisUsage(AnalysisUsage &AU) const override;
+
+ const char *getPassName() const override { return "LoadCombine"; }
+ static char ID;
+
+ typedef IRBuilder<true, TargetFolder> BuilderTy;
+
+private:
+ BuilderTy *Builder;
+
+ PointerOffsetPair getPointerOffsetPair(LoadInst &);
+ bool combineLoads(DenseMap<const Value *, SmallVector<LoadPOPPair, 8>> &);
+ bool aggregateLoads(SmallVectorImpl<LoadPOPPair> &);
+ bool combineLoads(SmallVectorImpl<LoadPOPPair> &);
+};
+}
+
+bool LoadCombine::doInitialization(Function &F) {
+ DEBUG(dbgs() << "LoadCombine function: " << F.getName() << "\n");
+ C = &F.getContext();
+ DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
+ if (!DLP) {
+ DEBUG(dbgs() << " Skipping LoadCombine -- no target data!\n");
+ return false;
+ }
+ DL = &DLP->getDataLayout();
+ return true;
+}
+
+PointerOffsetPair LoadCombine::getPointerOffsetPair(LoadInst &LI) {
+ PointerOffsetPair POP;
+ POP.Pointer = LI.getPointerOperand();
+ POP.Offset = 0;
+ while (isa<BitCastInst>(POP.Pointer) || isa<GetElementPtrInst>(POP.Pointer)) {
+ if (auto *GEP = dyn_cast<GetElementPtrInst>(POP.Pointer)) {
+ unsigned BitWidth = DL->getPointerTypeSizeInBits(GEP->getType());
+ APInt Offset(BitWidth, 0);
+ if (GEP->accumulateConstantOffset(*DL, Offset))
+ POP.Offset += Offset.getZExtValue();
+ else
+ // Can't handle GEPs with variable indices.
+ return POP;
+ POP.Pointer = GEP->getPointerOperand();
+ } else if (auto *BC = dyn_cast<BitCastInst>(POP.Pointer))
+ POP.Pointer = BC->getOperand(0);
+ }
+ return POP;
+}
+
+bool LoadCombine::combineLoads(
+ DenseMap<const Value *, SmallVector<LoadPOPPair, 8>> &LoadMap) {
+ bool Combined = false;
+ for (auto &Loads : LoadMap) {
+ if (Loads.second.size() < 2)
+ continue;
+ std::sort(Loads.second.begin(), Loads.second.end(),
+ [](const LoadPOPPair &A, const LoadPOPPair &B) {
+ return A.POP.Offset < B.POP.Offset;
+ });
+ if (aggregateLoads(Loads.second))
+ Combined = true;
+ }
+ return Combined;
+}
+
+/// \brief Try to aggregate loads from a sorted list of loads to be combined.
+///
+/// It is guaranteed that no writes occur between any of the loads. All loads
+/// have the same base pointer. There are at least two loads.
+bool LoadCombine::aggregateLoads(SmallVectorImpl<LoadPOPPair> &Loads) {
+ assert(Loads.size() >= 2 && "Insufficient loads!");
+ LoadInst *BaseLoad = nullptr;
+ SmallVector<LoadPOPPair, 8> AggregateLoads;
+ bool Combined = false;
+ uint64_t PrevOffset = -1ull;
+ uint64_t PrevSize = 0;
+ for (auto &L : Loads) {
+ if (PrevOffset == -1ull) {
+ BaseLoad = L.Load;
+ PrevOffset = L.POP.Offset;
+ PrevSize = DL->getTypeStoreSize(L.Load->getType());
+ AggregateLoads.push_back(L);
+ continue;
+ }
+ if (L.Load->getAlignment() > BaseLoad->getAlignment())
+ continue;
+ if (L.POP.Offset > PrevOffset + PrevSize) {
+ // No other load will be combinable
+ if (combineLoads(AggregateLoads))
+ Combined = true;
+ AggregateLoads.clear();
+ PrevOffset = -1;
+ continue;
+ }
+ if (L.POP.Offset != PrevOffset + PrevSize)
+ // This load is offset less than the size of the last load.
+ // FIXME: We may want to handle this case.
+ continue;
+ PrevOffset = L.POP.Offset;
+ PrevSize = DL->getTypeStoreSize(L.Load->getType());
+ AggregateLoads.push_back(L);
+ }
+ if (combineLoads(AggregateLoads))
+ Combined = true;
+ return Combined;
+}
+
+/// \brief Given a list of combinable load. Combine the maximum number of them.
+bool LoadCombine::combineLoads(SmallVectorImpl<LoadPOPPair> &Loads) {
+ // Remove loads from the end while the size is not a power of 2.
+ unsigned TotalSize = 0;
+ for (const auto &L : Loads)
+ TotalSize += L.Load->getType()->getPrimitiveSizeInBits();
+ while (TotalSize != 0 && !isPowerOf2_32(TotalSize))
+ TotalSize -= Loads.pop_back_val().Load->getType()->getPrimitiveSizeInBits();
+ if (Loads.size() < 2)
+ return false;
+
+ DEBUG({
+ dbgs() << "***** Combining Loads ******\n";
+ for (const auto &L : Loads) {
+ dbgs() << L.POP.Offset << ": " << *L.Load << "\n";
+ }
+ });
+
+ // Find first load. This is where we put the new load.
+ LoadPOPPair FirstLP;
+ FirstLP.InsertOrder = -1u;
+ for (const auto &L : Loads)
+ if (L.InsertOrder < FirstLP.InsertOrder)
+ FirstLP = L;
+
+ unsigned AddressSpace =
+ FirstLP.POP.Pointer->getType()->getPointerAddressSpace();
+
+ Builder->SetInsertPoint(FirstLP.Load);
+ Value *Ptr = Builder->CreateConstGEP1_64(
+ Builder->CreatePointerCast(Loads[0].POP.Pointer,
+ Builder->getInt8PtrTy(AddressSpace)),
+ Loads[0].POP.Offset);
+ LoadInst *NewLoad = new LoadInst(
+ Builder->CreatePointerCast(
+ Ptr, PointerType::get(IntegerType::get(Ptr->getContext(), TotalSize),
+ Ptr->getType()->getPointerAddressSpace())),
+ Twine(Loads[0].Load->getName()) + ".combined", false,
+ Loads[0].Load->getAlignment(), FirstLP.Load);
+
+ for (const auto &L : Loads) {
+ Builder->SetInsertPoint(L.Load);
+ Value *V = Builder->CreateExtractInteger(
+ *DL, NewLoad, cast<IntegerType>(L.Load->getType()),
+ L.POP.Offset - Loads[0].POP.Offset, "combine.extract");
+ L.Load->replaceAllUsesWith(V);
+ }
+
+ NumLoadsCombined = NumLoadsCombined + Loads.size();
+ return true;
+}
+
+bool LoadCombine::runOnBasicBlock(BasicBlock &BB) {
+ if (skipOptnoneFunction(BB) || !DL)
+ return false;
+
+ IRBuilder<true, TargetFolder>
+ TheBuilder(BB.getContext(), TargetFolder(DL));
+ Builder = &TheBuilder;
+
+ DenseMap<const Value *, SmallVector<LoadPOPPair, 8>> LoadMap;
+
+ bool Combined = false;
+ unsigned Index = 0;
+ for (auto &I : BB) {
+ if (I.mayWriteToMemory() || I.mayThrow()) {
+ if (combineLoads(LoadMap))
+ Combined = true;
+ LoadMap.clear();
+ continue;
+ }
+ LoadInst *LI = dyn_cast<LoadInst>(&I);
+ if (!LI)
+ continue;
+ ++NumLoadsAnalyzed;
+ if (!LI->isSimple() || !LI->getType()->isIntegerTy())
+ continue;
+ auto POP = getPointerOffsetPair(*LI);
+ if (!POP.Pointer)
+ continue;
+ LoadMap[POP.Pointer].push_back(LoadPOPPair(LI, POP, Index++));
+ }
+ if (combineLoads(LoadMap))
+ Combined = true;
+ return Combined;
+}
+
+void LoadCombine::getAnalysisUsage(AnalysisUsage &AU) const {
+ AU.setPreservesCFG();
+}
+
+char LoadCombine::ID = 0;
+
+BasicBlockPass *llvm::createLoadCombinePass() {
+ return new LoadCombine();
+}
+
+INITIALIZE_PASS(LoadCombine, "load-combine", "Combine Adjacent Loads", false,
+ false)
Modified: llvm/trunk/lib/Transforms/Scalar/Scalar.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/Scalar.cpp?rev=209791&r1=209790&r2=209791&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/Scalar.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/Scalar.cpp Wed May 28 20:55:07 2014
@@ -65,6 +65,7 @@ void llvm::initializeScalarOpts(PassRegi
initializeSinkingPass(Registry);
initializeTailCallElimPass(Registry);
initializeSeparateConstOffsetFromGEPPass(Registry);
+ initializeLoadCombinePass(Registry);
}
void LLVMInitializeScalarOpts(LLVMPassRegistryRef R) {
Added: llvm/trunk/test/Transforms/LoadCombine/load-combine.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoadCombine/load-combine.ll?rev=209791&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/LoadCombine/load-combine.ll (added)
+++ llvm/trunk/test/Transforms/LoadCombine/load-combine.ll Wed May 28 20:55:07 2014
@@ -0,0 +1,190 @@
+; RUN: opt < %s -load-combine -instcombine -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Combine read from char* idiom.
+define i64 @LoadU64_x64_0(i64* %pData) {
+ %1 = bitcast i64* %pData to i8*
+ %2 = load i8* %1, align 1
+ %3 = zext i8 %2 to i64
+ %4 = shl nuw i64 %3, 56
+ %5 = getelementptr inbounds i8* %1, i64 1
+ %6 = load i8* %5, align 1
+ %7 = zext i8 %6 to i64
+ %8 = shl nuw nsw i64 %7, 48
+ %9 = or i64 %8, %4
+ %10 = getelementptr inbounds i8* %1, i64 2
+ %11 = load i8* %10, align 1
+ %12 = zext i8 %11 to i64
+ %13 = shl nuw nsw i64 %12, 40
+ %14 = or i64 %9, %13
+ %15 = getelementptr inbounds i8* %1, i64 3
+ %16 = load i8* %15, align 1
+ %17 = zext i8 %16 to i64
+ %18 = shl nuw nsw i64 %17, 32
+ %19 = or i64 %14, %18
+ %20 = getelementptr inbounds i8* %1, i64 4
+ %21 = load i8* %20, align 1
+ %22 = zext i8 %21 to i64
+ %23 = shl nuw nsw i64 %22, 24
+ %24 = or i64 %19, %23
+ %25 = getelementptr inbounds i8* %1, i64 5
+ %26 = load i8* %25, align 1
+ %27 = zext i8 %26 to i64
+ %28 = shl nuw nsw i64 %27, 16
+ %29 = or i64 %24, %28
+ %30 = getelementptr inbounds i8* %1, i64 6
+ %31 = load i8* %30, align 1
+ %32 = zext i8 %31 to i64
+ %33 = shl nuw nsw i64 %32, 8
+ %34 = or i64 %29, %33
+ %35 = getelementptr inbounds i8* %1, i64 7
+ %36 = load i8* %35, align 1
+ %37 = zext i8 %36 to i64
+ %38 = or i64 %34, %37
+ ret i64 %38
+; CHECK-LABEL: @LoadU64_x64_0(
+; CHECK: load i64* %{{.*}}, align 1
+; CHECK-NOT: load
+}
+
+; Combine simple adjacent loads.
+define i32 @"2xi16_i32"(i16* %x) {
+ %1 = load i16* %x, align 2
+ %2 = getelementptr inbounds i16* %x, i64 1
+ %3 = load i16* %2, align 2
+ %4 = zext i16 %3 to i32
+ %5 = shl nuw i32 %4, 16
+ %6 = zext i16 %1 to i32
+ %7 = or i32 %5, %6
+ ret i32 %7
+; CHECK-LABEL: @"2xi16_i32"(
+; CHECK: load i32* %{{.*}}, align 2
+; CHECK-NOT: load
+}
+
+; Don't combine loads across stores.
+define i32 @"2xi16_i32_store"(i16* %x, i16* %y) {
+ %1 = load i16* %x, align 2
+ store i16 0, i16* %y, align 2
+ %2 = getelementptr inbounds i16* %x, i64 1
+ %3 = load i16* %2, align 2
+ %4 = zext i16 %3 to i32
+ %5 = shl nuw i32 %4, 16
+ %6 = zext i16 %1 to i32
+ %7 = or i32 %5, %6
+ ret i32 %7
+; CHECK-LABEL: @"2xi16_i32_store"(
+; CHECK: load i16* %{{.*}}, align 2
+; CHECK: store
+; CHECK: load i16* %{{.*}}, align 2
+}
+
+; Don't combine loads with a gap.
+define i32 @"2xi16_i32_gap"(i16* %x) {
+ %1 = load i16* %x, align 2
+ %2 = getelementptr inbounds i16* %x, i64 2
+ %3 = load i16* %2, align 2
+ %4 = zext i16 %3 to i32
+ %5 = shl nuw i32 %4, 16
+ %6 = zext i16 %1 to i32
+ %7 = or i32 %5, %6
+ ret i32 %7
+; CHECK-LABEL: @"2xi16_i32_gap"(
+; CHECK: load i16* %{{.*}}, align 2
+; CHECK: load i16* %{{.*}}, align 2
+}
+
+; Combine out of order loads.
+define i32 @"2xi16_i32_order"(i16* %x) {
+ %1 = getelementptr inbounds i16* %x, i64 1
+ %2 = load i16* %1, align 2
+ %3 = zext i16 %2 to i32
+ %4 = load i16* %x, align 2
+ %5 = shl nuw i32 %3, 16
+ %6 = zext i16 %4 to i32
+ %7 = or i32 %5, %6
+ ret i32 %7
+; CHECK-LABEL: @"2xi16_i32_order"(
+; CHECK: load i32* %{{.*}}, align 2
+; CHECK-NOT: load
+}
+
+; Overlapping loads.
+define i32 @"2xi16_i32_overlap"(i8* %x) {
+ %1 = bitcast i8* %x to i16*
+ %2 = load i16* %1, align 2
+ %3 = getelementptr inbounds i8* %x, i64 1
+ %4 = bitcast i8* %3 to i16*
+ %5 = load i16* %4, align 2
+ %6 = zext i16 %5 to i32
+ %7 = shl nuw i32 %6, 16
+ %8 = zext i16 %2 to i32
+ %9 = or i32 %7, %8
+ ret i32 %9
+; CHECK-LABEL: @"2xi16_i32_overlap"(
+; CHECK: load i16* %{{.*}}, align 2
+; CHECK: load i16* %{{.*}}, align 2
+}
+
+; Combine valid alignments.
+define i64 @"2xi16_i64_align"(i8* %x) {
+ %1 = bitcast i8* %x to i32*
+ %2 = load i32* %1, align 4
+ %3 = getelementptr inbounds i8* %x, i64 4
+ %4 = bitcast i8* %3 to i16*
+ %5 = load i16* %4, align 2
+ %6 = getelementptr inbounds i8* %x, i64 6
+ %7 = bitcast i8* %6 to i16*
+ %8 = load i16* %7, align 2
+ %9 = zext i16 %8 to i64
+ %10 = shl nuw i64 %9, 48
+ %11 = zext i16 %5 to i64
+ %12 = shl nuw nsw i64 %11, 32
+ %13 = zext i32 %2 to i64
+ %14 = or i64 %12, %13
+ %15 = or i64 %14, %10
+ ret i64 %15
+; CHECK-LABEL: @"2xi16_i64_align"(
+; CHECK: load i64* %{{.*}}, align 4
+}
+
+; Non power of two.
+define i64 @"2xi16_i64_npo2"(i8* %x) {
+ %1 = load i8* %x, align 1
+ %2 = zext i8 %1 to i64
+ %3 = getelementptr inbounds i8* %x, i64 1
+ %4 = load i8* %3, align 1
+ %5 = zext i8 %4 to i64
+ %6 = shl nuw nsw i64 %5, 8
+ %7 = or i64 %6, %2
+ %8 = getelementptr inbounds i8* %x, i64 2
+ %9 = load i8* %8, align 1
+ %10 = zext i8 %9 to i64
+ %11 = shl nuw nsw i64 %10, 16
+ %12 = or i64 %11, %7
+ %13 = getelementptr inbounds i8* %x, i64 3
+ %14 = load i8* %13, align 1
+ %15 = zext i8 %14 to i64
+ %16 = shl nuw nsw i64 %15, 24
+ %17 = or i64 %16, %12
+ %18 = getelementptr inbounds i8* %x, i64 4
+ %19 = load i8* %18, align 1
+ %20 = zext i8 %19 to i64
+ %21 = shl nuw nsw i64 %20, 32
+ %22 = or i64 %21, %17
+ %23 = getelementptr inbounds i8* %x, i64 5
+ %24 = load i8* %23, align 1
+ %25 = zext i8 %24 to i64
+ %26 = shl nuw nsw i64 %25, 40
+ %27 = or i64 %26, %22
+ %28 = getelementptr inbounds i8* %x, i64 6
+ %29 = load i8* %28, align 1
+ %30 = zext i8 %29 to i64
+ %31 = shl nuw nsw i64 %30, 48
+ %32 = or i64 %31, %27
+ ret i64 %32
+; CHECK-LABEL: @"2xi16_i64_npo2"(
+; CHECK: load i32* %{{.*}}, align 1
+}
More information about the llvm-commits
mailing list