Index: include/llvm/CodeGen/TargetLowering.h
===================================================================
--- include/llvm/CodeGen/TargetLowering.h
+++ include/llvm/CodeGen/TargetLowering.h
@@ -2236,6 +2236,11 @@
return false;
}
+ // Return true if CodeGenPrepare should consider splitting large offset of a
+ // GEP to make the GEP fit into the addressing mode and can be sunk into the
+ // same blocks of its users.
+ virtual bool shouldConsiderGEPOffsetSplit() const { return false; }
+
//===--------------------------------------------------------------------===//
// Runtime Library hooks
//
Index: lib/CodeGen/CodeGenPrepare.cpp
===================================================================
--- lib/CodeGen/CodeGenPrepare.cpp
+++ lib/CodeGen/CodeGenPrepare.cpp
@@ -216,6 +216,11 @@
"addr-sink-combine-scaled-reg", cl::Hidden, cl::init(true),
cl::desc("Allow combining of ScaledReg field in Address sinking."));
+static cl::opt<bool>
+ EnableGEPOffsetSplit("cgp-split-large-offset-gep", cl::Hidden,
+ cl::init(true),
+ cl::desc("Enable splitting large offset of GEP."));
+
namespace {
using SetOfInstrs = SmallPtrSet<Instruction *, 16>;
@@ -261,6 +266,19 @@
/// Keep track of sext chains based on their initial value.
DenseMap<Value *, Instruction *> SeenChainsForSExt;
+ /// Keep track of GEPs accessing the same data structures such as structs or
+ /// arrays that are candidates to be split later because of their large
+ /// size.
+ DenseMap<AssertingVH<Value>,
+ SmallVector<std::pair<GetElementPtrInst *, int64_t>, 32>>
+ LargeOffsetGEPMap;
+
+ /// Keep track of new GEP base after splitting the GEPs having large offset.
+ SmallSet<AssertingVH<Value>, 2> NewGEPBases;
+
+ /// Map serial numbers to Large offset GEPs.
+ DenseMap<AssertingVH<GetElementPtrInst>, int> LargeOffsetGEPID;
+
/// Keep track of SExt promoted.
ValueToSExts ValToSExtendedUses;
@@ -322,6 +340,7 @@
SmallVectorImpl<Instruction *> &ProfitablyMovedExts,
unsigned CreatedInstsCost = 0);
bool mergeSExts(Function &F);
+ bool splitLargeGEPOffsets();
bool performAddressTypePromotion(
Instruction *&Inst,
bool AllowPromotionWithoutCommonHeader,
@@ -415,6 +434,8 @@
SeenChainsForSExt.clear();
ValToSExtendedUses.clear();
RemovedInsts.clear();
+ LargeOffsetGEPMap.clear();
+ LargeOffsetGEPID.clear();
for (Function::iterator I = F.begin(); I != F.end(); ) {
BasicBlock *BB = &*I++;
bool ModifiedDTOnIteration = false;
@@ -426,6 +447,8 @@
}
if (EnableTypePromotionMerge && !ValToSExtendedUses.empty())
MadeChange |= mergeSExts(F);
+ if (!LargeOffsetGEPMap.empty())
+ MadeChange |= splitLargeGEPOffsets();
// Really free removed instructions during promotion.
for (Instruction *I : RemovedInsts)
@@ -2528,22 +2551,23 @@
/// The ongoing transaction where every action should be registered.
TypePromotionTransaction &TPT;
+ // A GEP which has too large offset to be folded into the addressing mode.
+ std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP;
+
/// This is set to true when we should not do profitability checks.
/// When true, IsProfitableToFoldIntoAddressingMode always returns true.
bool IgnoreProfitability;
- AddressingModeMatcher(SmallVectorImpl<Instruction *> &AMI,
- const TargetLowering &TLI,
- const TargetRegisterInfo &TRI,
- Type *AT, unsigned AS,
- Instruction *MI, ExtAddrMode &AM,
- const SetOfInstrs &InsertedInsts,
- InstrToOrigTy &PromotedInsts,
- TypePromotionTransaction &TPT)
+ AddressingModeMatcher(
+ SmallVectorImpl<Instruction *> &AMI, const TargetLowering &TLI,
+ const TargetRegisterInfo &TRI, Type *AT, unsigned AS, Instruction *MI,
+ ExtAddrMode &AM, const SetOfInstrs &InsertedInsts,
+ InstrToOrigTy &PromotedInsts, TypePromotionTransaction &TPT,
+ std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP)
: AddrModeInsts(AMI), TLI(TLI), TRI(TRI),
DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
- PromotedInsts(PromotedInsts), TPT(TPT) {
+ PromotedInsts(PromotedInsts), TPT(TPT), LargeOffsetGEP(LargeOffsetGEP) {
IgnoreProfitability = false;
}
@@ -2555,20 +2579,19 @@
/// optimizations.
/// \p PromotedInsts maps the instructions to their type before promotion.
/// \p The ongoing transaction where every action should be registered.
- static ExtAddrMode Match(Value *V, Type *AccessTy, unsigned AS,
- Instruction *MemoryInst,
- SmallVectorImpl<Instruction*> &AddrModeInsts,
- const TargetLowering &TLI,
- const TargetRegisterInfo &TRI,
- const SetOfInstrs &InsertedInsts,
- InstrToOrigTy &PromotedInsts,
- TypePromotionTransaction &TPT) {
+ static ExtAddrMode
+ Match(Value *V, Type *AccessTy, unsigned AS, Instruction *MemoryInst,
+ SmallVectorImpl<Instruction *> &AddrModeInsts,
+ const TargetLowering &TLI, const TargetRegisterInfo &TRI,
+ const SetOfInstrs &InsertedInsts, InstrToOrigTy &PromotedInsts,
+ TypePromotionTransaction &TPT,
+ std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP) {
ExtAddrMode Result;
- bool Success = AddressingModeMatcher(AddrModeInsts, TLI, TRI,
- AccessTy, AS,
+ bool Success = AddressingModeMatcher(AddrModeInsts, TLI, TRI, AccessTy, AS,
MemoryInst, Result, InsertedInsts,
- PromotedInsts, TPT).matchAddr(V, 0);
+ PromotedInsts, TPT, LargeOffsetGEP)
+ .matchAddr(V, 0);
(void)Success; assert(Success && "Couldn't select *anything*?");
return Result;
}
@@ -3746,6 +3769,30 @@
// Check to see if we can fold the base pointer in too.
if (matchAddr(AddrInst->getOperand(0), Depth+1))
return true;
+ } else if (EnableGEPOffsetSplit && isa<GetElementPtrInst>(AddrInst) &&
+ TLI.shouldConsiderGEPOffsetSplit() && Depth == 0 &&
+ ConstantOffset > 0) {
+ // Record GEPs with non-zero offsets as candidates for splitting in the
+ // event that the offset cannot fit into the r+i addressing mode.
+ // Simple and common case that only one GEP is used in calculating the
+ // address for the memory access.
+ Value *Base = AddrInst->getOperand(0);
+ auto *BaseI = dyn_cast<Instruction>(Base);
+ auto *GEP = cast<GetElementPtrInst>(AddrInst);
+ if (isa<Argument>(Base) || isa<GlobalValue>(Base) ||
+ (BaseI && !isa<CastInst>(BaseI) &&
+ !isa<GetElementPtrInst>(BaseI))) {
+ // If the base is an instruction, make sure the GEP is not in the same
+ // basic block as the base. If the base is an argument or global
+ // value, make sure the GEP is not in the entry block. Otherwise,
+ // instruction selection can undo the split. Also make sure the
+ // parent block allows inserting non-PHI instructions before the
+ // terminator.
+ BasicBlock *Parent =
+ BaseI ? BaseI->getParent() : &GEP->getFunction()->getEntryBlock();
+ if (GEP->getParent() != Parent && !Parent->getTerminator()->isEHPad())
+ LargeOffsetGEP = std::make_pair(GEP, ConstantOffset);
+ }
}
AddrMode.BaseOffs -= ConstantOffset;
return false;
@@ -4156,12 +4203,13 @@
// will tell us if the addressing mode for the memory operation will
// *actually* cover the shared instruction.
ExtAddrMode Result;
+ std::pair<AssertingVH<GetElementPtrInst>, int64_t> LargeOffsetGEP(nullptr,
+ 0);
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
TPT.getRestorationPoint();
- AddressingModeMatcher Matcher(MatchedAddrModeInsts, TLI, TRI,
- AddressAccessTy, AS,
- MemoryInst, Result, InsertedInsts,
- PromotedInsts, TPT);
+ AddressingModeMatcher Matcher(
+ MatchedAddrModeInsts, TLI, TRI, AddressAccessTy, AS, MemoryInst, Result,
+ InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP);
Matcher.IgnoreProfitability = true;
bool Success = Matcher.matchAddr(Address, 0);
(void)Success; assert(Success && "Couldn't select *anything*?");
@@ -4263,11 +4311,24 @@
// the result may differ depending on what other uses our candidate
// addressing instructions might have.
AddrModeInsts.clear();
+ std::pair<AssertingVH<GetElementPtrInst>, int64_t> LargeOffsetGEP(nullptr,
+ 0);
ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
V, AccessTy, AddrSpace, MemoryInst, AddrModeInsts, *TLI, *TRI,
- InsertedInsts, PromotedInsts, TPT);
- NewAddrMode.OriginalValue = V;
+ InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP);
+
+ GetElementPtrInst *GEP = LargeOffsetGEP.first;
+ if (GEP && GEP->getParent() != MemoryInst->getParent() &&
+ !NewGEPBases.count(GEP)) {
+ // If splitting the underlying data structure can reduce the offset of a
+ // GEP, collect the GEP. Skip the GEPs that are the new bases of
+ // previously split data structures.
+ LargeOffsetGEPMap[GEP->getPointerOperand()].push_back(LargeOffsetGEP);
+ if (LargeOffsetGEPID.find(GEP) == LargeOffsetGEPID.end())
+ LargeOffsetGEPID[GEP] = LargeOffsetGEPID.size();
+ }
+ NewAddrMode.OriginalValue = V;
if (!AddrModes.addNewAddrMode(NewAddrMode))
break;
}
@@ -4775,6 +4836,151 @@
return Changed;
}
+// Spliting large data structures so that the GEPs accessing them can have
+// smaller offsets so that they can be sunk to the same blocks as their users.
+// For example, a large struct starting from %base is splitted into two parts
+// where the second part starts from %new_base.
+//
+// Before:
+// BB0:
+// %base =
+//
+// BB1:
+// %gep0 = gep %base, off0
+// %gep1 = gep %base, off1
+// %gep2 = gep %base, off2
+//
+// BB2:
+// %load1 = load %gep0
+// %load2 = load %gep1
+// %load3 = load %gep2
+//
+// After:
+// BB0:
+// %base =
+// %new_base = gep %base, off0
+//
+// BB1:
+// %new_gep0 = %new_base
+// %new_gep1 = gep %new_base, off1 - off0
+// %new_gep2 = gep %new_base, off2 - off0
+//
+// BB2:
+// %load1 = load i32, i32* %new_gep0
+// %load2 = load i32, i32* %new_gep1
+// %load3 = load i32, i32* %new_gep2
+//
+// %new_gep1 and %new_gep2 can be sunk to BB2 now after the splitting because
+// their offsets are smaller enough to fit into the addressing mode.
+bool CodeGenPrepare::splitLargeGEPOffsets() {
+ bool Changed = false;
+ for (auto &Entry : LargeOffsetGEPMap) {
+ Value *OldBase = Entry.first;
+ SmallVectorImpl<std::pair<GetElementPtrInst *, int64_t>> &LargeOffsetGEPs =
+ Entry.second;
+ auto compareGEPOffset =
+ [&](const std::pair<GetElementPtrInst *, int64_t> &LHS,
+ const std::pair<GetElementPtrInst *, int64_t> &RHS) {
+ if (LHS.first == RHS.first)
+ return false;
+ if (LHS.second != RHS.second)
+ return LHS.second < RHS.second;
+ return LargeOffsetGEPID[LHS.first] < LargeOffsetGEPID[RHS.first];
+ };
+ // Sorting all the GEPs of the same data structures based on the offsets.
+ llvm::sort(LargeOffsetGEPs.begin(), LargeOffsetGEPs.end(),
+ compareGEPOffset);
+ LargeOffsetGEPs.erase(
+ std::unique(LargeOffsetGEPs.begin(), LargeOffsetGEPs.end()),
+ LargeOffsetGEPs.end());
+ // Skip if all the GEPs have the same offsets.
+ if (LargeOffsetGEPs.front().second == LargeOffsetGEPs.back().second)
+ continue;
+ GetElementPtrInst *BaseGEP = LargeOffsetGEPs.begin()->first;
+ int64_t BaseOffset = LargeOffsetGEPs.begin()->second;
+ Value *NewBaseGEP = nullptr;
+ for (auto &LargeOffsetGEP : LargeOffsetGEPs) {
+ GetElementPtrInst *GEP = LargeOffsetGEP.first;
+ int64_t Offset = LargeOffsetGEP.second;
+ if (Offset != BaseOffset) {
+ TargetLowering::AddrMode AddrMode;
+ AddrMode.BaseOffs = Offset - BaseOffset;
+ // The result type of the GEP might not be the type of the memory
+ // access.
+ if (!TLI->isLegalAddressingMode(*DL, AddrMode,
+ GEP->getResultElementType(),
+ GEP->getAddressSpace())) {
+ // We need to create a new base if the offset to the current base is
+ // too large to fit into the addressing mode. So, a very large struct
+ // may be splitted into several parts.
+ BaseGEP = GEP;
+ BaseOffset = Offset;
+ NewBaseGEP = nullptr;
+ }
+ }
+
+ // Generate a new GEP to replace the current one.
+ IRBuilder<> Builder(GEP);
+ Type *IntPtrTy = DL->getIntPtrType(GEP->getType());
+ Type *I8PtrTy =
+ Builder.getInt8PtrTy(GEP->getType()->getPointerAddressSpace());
+ Type *I8Ty = Builder.getInt8Ty();
+
+ if (!NewBaseGEP) {
+ // Create a new base if we don't have one yet. Find the insertion
+ // pointer for the new base first.
+ BasicBlock::iterator NewBaseInsertPt;
+ BasicBlock *NewBaseInsertBB;
+ if (auto *BaseI = dyn_cast<Instruction>(OldBase)) {
+ // If the base of the struct is an instruction, the new base will be
+ // inserted close to it.
+ NewBaseInsertBB = BaseI->getParent();
+ if (isa<PHINode>(BaseI))
+ NewBaseInsertPt = NewBaseInsertBB->getFirstInsertionPt();
+ else if (InvokeInst *Invoke = dyn_cast<InvokeInst>(BaseI)) {
+ NewBaseInsertBB =
+ SplitEdge(NewBaseInsertBB, Invoke->getNormalDest());
+ NewBaseInsertPt = NewBaseInsertBB->getFirstInsertionPt();
+ } else
+ NewBaseInsertPt = std::next(BaseI->getIterator());
+ } else {
+ // If the current base is an argument or global value, the new base
+ // will be inserted to the entry block.
+ NewBaseInsertBB = &BaseGEP->getFunction()->getEntryBlock();
+ NewBaseInsertPt = NewBaseInsertBB->getFirstInsertionPt();
+ }
+ IRBuilder<> NewBaseBuilder(NewBaseInsertBB, NewBaseInsertPt);
+ // Create a new base.
+ Value *BaseIndex = ConstantInt::get(IntPtrTy, BaseOffset);
+ NewBaseGEP = OldBase;
+ if (NewBaseGEP->getType() != I8PtrTy)
+ NewBaseGEP = NewBaseBuilder.CreatePointerCast(NewBaseGEP, I8PtrTy);
+ NewBaseGEP =
+ NewBaseBuilder.CreateGEP(I8Ty, NewBaseGEP, BaseIndex, "splitgep");
+ NewGEPBases.insert(NewBaseGEP);
+ }
+
+ Value *NewGEP = NewBaseGEP;
+ if (Offset == BaseOffset) {
+ if (GEP->getType() != I8PtrTy)
+ NewGEP = Builder.CreatePointerCast(NewGEP, GEP->getType());
+ } else {
+ // Calculate the new offset for the new GEP.
+ Value *Index = ConstantInt::get(IntPtrTy, Offset - BaseOffset);
+ NewGEP = Builder.CreateGEP(I8Ty, NewBaseGEP, Index);
+
+ if (GEP->getType() != I8PtrTy)
+ NewGEP = Builder.CreatePointerCast(NewGEP, GEP->getType());
+ }
+ GEP->replaceAllUsesWith(NewGEP);
+ LargeOffsetGEPID.erase(GEP);
+ GEP->eraseFromParent();
+ Changed = true;
+ }
+ }
+ return Changed;
+}
+
/// Return true, if an ext(load) can be formed from an extension in
/// \p MovedExts.
bool CodeGenPrepare::canFormExtLd(
Index: lib/Target/AArch64/AArch64ISelLowering.h
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.h
+++ lib/Target/AArch64/AArch64ISelLowering.h
@@ -335,6 +335,8 @@
bool isLegalAddImmediate(int64_t) const override;
bool isLegalICmpImmediate(int64_t) const override;
+ bool shouldConsiderGEPOffsetSplit() const override;
+
EVT getOptimalMemOpType(uint64_t Size, unsigned DstAlign, unsigned SrcAlign,
bool IsMemset, bool ZeroMemset, bool MemcpyStrSrc,
MachineFunction &MF) const override;
Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -8218,6 +8218,11 @@
return AM.Scale == 1 || (AM.Scale > 0 && (uint64_t)AM.Scale == NumBytes);
}
+bool AArch64TargetLowering::shouldConsiderGEPOffsetSplit() const {
+ // Consider splitting large offset of struct or array.
+ return true;
+}
+
int AArch64TargetLowering::getScalingFactorCost(const DataLayout &DL,
const AddrMode &AM, Type *Ty,
unsigned AS) const {
Index: test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
===================================================================
--- /dev/null
+++ test/Transforms/CodeGenPrepare/AArch64/large-offset-gep.ll
@@ -0,0 +1,147 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -verify-machineinstrs -o - %s | FileCheck %s
+
+%struct_type = type { [10000 x i32], i32, i32 }
+
+define void @test1(%struct_type** %s, i32 %n) {
+; CHECK-LABEL: test1
+entry:
+ %struct = load %struct_type*, %struct_type** %s
+ br label %while_cond
+
+while_cond:
+ %phi = phi i32 [ 0, %entry ], [ %i, %while_body ]
+; CHECK: mov w{{[0-9]+}}, #40000
+; CHECK-NOT: mov w{{[0-9]+}}, #40004
+ %gep0 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 1
+ %gep1 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 2
+ %cmp = icmp slt i32 %phi, %n
+ br i1 %cmp, label %while_body, label %while_end
+
+while_body:
+; CHECK: str w{{[0-9]+}}, [x{{[0-9]+}}, #4]
+ %i = add i32 %phi, 1
+ store i32 %i, i32* %gep0
+ store i32 %phi, i32* %gep1
+ br label %while_cond
+
+while_end:
+ ret void
+}
+
+define void @test2(%struct_type* %struct, i32 %n) {
+; CHECK-LABEL: test2
+entry:
+ %cmp = icmp eq %struct_type* %struct, null
+ br i1 %cmp, label %while_end, label %while_cond
+
+while_cond:
+ %phi = phi i32 [ 0, %entry ], [ %i, %while_body ]
+; CHECK: mov w{{[0-9]+}}, #40000
+; CHECK-NOT: mov w{{[0-9]+}}, #40004
+ %gep0 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 1
+ %gep1 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 2
+ %cmp1 = icmp slt i32 %phi, %n
+ br i1 %cmp1, label %while_body, label %while_end
+
+while_body:
+; CHECK: str w{{[0-9]+}}, [x{{[0-9]+}}, #4]
+ %i = add i32 %phi, 1
+ store i32 %i, i32* %gep0
+ store i32 %phi, i32* %gep1
+ br label %while_cond
+
+while_end:
+ ret void
+}
+
+define void @test3(%struct_type* %s1, %struct_type* %s2, i1 %cond, i32 %n) {
+; CHECK-LABEL: test3
+entry:
+ br i1 %cond, label %if_true, label %if_end
+
+if_true:
+ br label %if_end
+
+if_end:
+ %struct = phi %struct_type* [ %s1, %entry ], [ %s2, %if_true ]
+ %cmp = icmp eq %struct_type* %struct, null
+ br i1 %cmp, label %while_end, label %while_cond
+
+while_cond:
+ %phi = phi i32 [ 0, %if_end ], [ %i, %while_body ]
+; CHECK: mov w{{[0-9]+}}, #40000
+; CHECK-NOT: mov w{{[0-9]+}}, #40004
+ %gep0 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 1
+ %gep1 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 2
+ %cmp1 = icmp slt i32 %phi, %n
+ br i1 %cmp1, label %while_body, label %while_end
+
+while_body:
+; CHECK: str w{{[0-9]+}}, [x{{[0-9]+}}, #4]
+ %i = add i32 %phi, 1
+ store i32 %i, i32* %gep0
+ store i32 %phi, i32* %gep1
+ br label %while_cond
+
+while_end:
+ ret void
+}
+
+declare %struct_type* @foo()
+
+define void @test4(i32 %n) personality i32 (...)* @__FrameHandler {
+; CHECK-LABEL: test4
+entry:
+ %struct = invoke %struct_type* @foo() to label %while_cond unwind label %cleanup
+
+while_cond:
+ %phi = phi i32 [ 0, %entry ], [ %i, %while_body ]
+; CHECK: mov w{{[0-9]+}}, #40000
+; CHECK-NOT: mov w{{[0-9]+}}, #40004
+ %gep0 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 1
+ %gep1 = getelementptr %struct_type, %struct_type* %struct, i64 0, i32 2
+ %cmp = icmp slt i32 %phi, %n
+ br i1 %cmp, label %while_body, label %while_end
+
+while_body:
+; CHECK: str w{{[0-9]+}}, [x{{[0-9]+}}, #4]
+ %i = add i32 %phi, 1
+ store i32 %i, i32* %gep0
+ store i32 %phi, i32* %gep1
+ br label %while_cond
+
+while_end:
+ ret void
+
+cleanup:
+ landingpad { i8*, i32 } cleanup
+ unreachable
+}
+
+declare i32 @__FrameHandler(...)
+
+define void @test5([65536 x i32]** %s, i32 %n) {
+; CHECK-LABEL: test5
+entry:
+ %struct = load [65536 x i32]*, [65536 x i32]** %s
+ br label %while_cond
+
+while_cond:
+ %phi = phi i32 [ 0, %entry ], [ %i, %while_body ]
+; CHECK: mov w{{[0-9]+}}, #14464
+; CHECK-NOT: mov w{{[0-9]+}}, #14468
+ %gep0 = getelementptr [65536 x i32], [65536 x i32]* %struct, i64 0, i32 20000
+ %gep1 = getelementptr [65536 x i32], [65536 x i32]* %struct, i64 0, i32 20001
+ %cmp = icmp slt i32 %phi, %n
+ br i1 %cmp, label %while_body, label %while_end
+
+while_body:
+; CHECK: str w{{[0-9]+}}, [x{{[0-9]+}}, #4]
+ %i = add i32 %phi, 1
+ store i32 %i, i32* %gep0
+ store i32 %phi, i32* %gep1
+ br label %while_cond
+
+while_end:
+ ret void
+}