RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-02 18:31:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Revert '[LICM] Make Loop ICM profile aware' and 'Fix pass dependency for LICM'

Browse Source 
This reverts r368526 (git commit 7e71aa24bc0788690fea7f0d7eab400c6a784deb)
This reverts r368542 (git commit cb5a90fd314a7914cf293797bb4fd7a6841052cf)

llvm-svn: 368800
This commit is contained in:
David L. Jones 2019-08-14 04:50:33 +00:00
parent 0b85cce260
commit c2f2511312
7 changed files with 28 additions and 122 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
include/llvm/Transforms/Utils/LoopUtils.h
View File

@ -37,7 +37,6 @@ namespace llvm {
class AliasSet;
class AliasSetTracker;
class BasicBlock;
class BlockFrequencyInfo;
class DataLayout;
class Loop;
class LoopInfo;
@ -115,26 +114,26 @@ struct SinkAndHoistLICMFlags {
/// reverse depth first order w.r.t the DominatorTree. This allows us to visit
/// uses before definitions, allowing us to sink a loop body in one pass without
/// iteration. Takes DomTreeNode, AliasAnalysis, LoopInfo, DominatorTree,
/// BlockFrequencyInfo, TargetLibraryInfo, Loop, AliasSet information for all
/// DataLayout, TargetLibraryInfo, Loop, AliasSet information for all
/// instructions of the loop and loop safety information as
/// arguments. Diagnostics is emitted via \p ORE. It returns changed status.
bool sinkRegion(DomTreeNode *, AliasAnalysis *, LoopInfo *, DominatorTree *,
BlockFrequencyInfo *, TargetLibraryInfo *, TargetTransformInfo *,
Loop *, AliasSetTracker *, MemorySSAUpdater *, ICFLoopSafetyInfo *,
TargetLibraryInfo *, TargetTransformInfo *, Loop *,
AliasSetTracker *, MemorySSAUpdater *, ICFLoopSafetyInfo *,
SinkAndHoistLICMFlags &, OptimizationRemarkEmitter *);
/// Walk the specified region of the CFG (defined by all blocks
/// dominated by the specified block, and that are in the current loop) in depth
/// first order w.r.t the DominatorTree. This allows us to visit definitions
/// before uses, allowing us to hoist a loop body in one pass without iteration.
/// Takes DomTreeNode, AliasAnalysis, LoopInfo, DominatorTree, BlockFrequencyInfo,
/// Takes DomTreeNode, AliasAnalysis, LoopInfo, DominatorTree, DataLayout,
/// TargetLibraryInfo, Loop, AliasSet information for all instructions of the
/// loop and loop safety information as arguments. Diagnostics is emitted via \p
/// ORE. It returns changed status.
bool hoistRegion(DomTreeNode *, AliasAnalysis *, LoopInfo *, DominatorTree *,
BlockFrequencyInfo *, TargetLibraryInfo *, Loop *, AliasSetTracker *,
MemorySSAUpdater *, ICFLoopSafetyInfo *, SinkAndHoistLICMFlags &,
OptimizationRemarkEmitter *);
TargetLibraryInfo *, Loop *, AliasSetTracker *,
MemorySSAUpdater *, ICFLoopSafetyInfo *,
SinkAndHoistLICMFlags &, OptimizationRemarkEmitter *);
/// This function deletes dead loops. The caller of this function needs to
/// guarantee that the loop is infact dead.

93
lib/Transforms/Scalar/LICM.cpp
View File

@ -95,11 +95,6 @@ static cl::opt<bool> ControlFlowHoisting(
"licm-control-flow-hoisting", cl::Hidden, cl::init(false),
cl::desc("Enable control flow (and PHI) hoisting in LICM"));
static cl::opt<unsigned> HoistSinkColdnessThreshold(
"licm-coldness-threshold", cl::Hidden, cl::init(4),
cl::desc("Relative coldness Threshold of hoisting/sinking destination "
"block for LICM to be considered beneficial"));
static cl::opt<uint32_t> MaxNumUsesTraversed(
"licm-max-num-uses-traversed", cl::Hidden, cl::init(8),
cl::desc("Max num uses visited for identifying load "
@ -144,9 +139,8 @@ static void hoist(Instruction &I, const DominatorTree *DT, const Loop *CurLoop,
BasicBlock *Dest, ICFLoopSafetyInfo *SafetyInfo,
MemorySSAUpdater *MSSAU, OptimizationRemarkEmitter *ORE);
static bool sink(Instruction &I, LoopInfo *LI, DominatorTree *DT,
BlockFrequencyInfo *BFI, const Loop *CurLoop,
ICFLoopSafetyInfo *SafetyInfo, MemorySSAUpdater *MSSAU,
OptimizationRemarkEmitter *ORE);
const Loop *CurLoop, ICFLoopSafetyInfo *SafetyInfo,
MemorySSAUpdater *MSSAU, OptimizationRemarkEmitter *ORE);
static bool isSafeToExecuteUnconditionally(Instruction &Inst,
const DominatorTree *DT,
const Loop *CurLoop,
@ -174,8 +168,8 @@ namespace {
struct LoopInvariantCodeMotion {
using ASTrackerMapTy = DenseMap<Loop *, std::unique_ptr<AliasSetTracker>>;
bool runOnLoop(Loop *L, AliasAnalysis *AA, LoopInfo *LI, DominatorTree *DT,
BlockFrequencyInfo *BFI, TargetLibraryInfo *TLI,
TargetTransformInfo *TTI, ScalarEvolution *SE, MemorySSA *MSSA,
TargetLibraryInfo *TLI, TargetTransformInfo *TTI,
ScalarEvolution *SE, MemorySSA *MSSA,
OptimizationRemarkEmitter *ORE, bool DeleteAST);
ASTrackerMapTy &getLoopToAliasSetMap() { return LoopToAliasSetMap; }
@ -226,7 +220,6 @@ struct LegacyLICMPass : public LoopPass {
&getAnalysis<AAResultsWrapperPass>().getAAResults(),
&getAnalysis<LoopInfoWrapperPass>().getLoopInfo(),
&getAnalysis<DominatorTreeWrapperPass>().getDomTree(),
&getAnalysis<BlockFrequencyInfoWrapperPass>().getBFI(),
&getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(),
&getAnalysis<TargetTransformInfoWrapperPass>().getTTI(
*L->getHeader()->getParent()),
@ -237,7 +230,6 @@ struct LegacyLICMPass : public LoopPass {
/// loop preheaders be inserted into the CFG...
///
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<BlockFrequencyInfoWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addRequired<TargetLibraryInfoWrapperPass>();
@ -294,8 +286,7 @@ PreservedAnalyses LICMPass::run(Loop &L, LoopAnalysisManager &AM,
"cached at a higher level");
LoopInvariantCodeMotion LICM(LicmMssaOptCap, LicmMssaNoAccForPromotionCap);
auto BFI = FAM.getCachedResult<BlockFrequencyAnalysis>(*F);
if (!LICM.runOnLoop(&L, &AR.AA, &AR.LI, &AR.DT, BFI, &AR.TLI, &AR.TTI, &AR.SE,
if (!LICM.runOnLoop(&L, &AR.AA, &AR.LI, &AR.DT, &AR.TLI, &AR.TTI, &AR.SE,
AR.MSSA, ORE, true))
return PreservedAnalyses::all();
@ -313,7 +304,6 @@ char LegacyLICMPass::ID = 0;
INITIALIZE_PASS_BEGIN(LegacyLICMPass, "licm", "Loop Invariant Code Motion",
false, false)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(BlockFrequencyInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
@ -334,9 +324,8 @@ Pass *llvm::createLICMPass(unsigned LicmMssaOptCap,
///
bool LoopInvariantCodeMotion::runOnLoop(
Loop *L, AliasAnalysis *AA, LoopInfo *LI, DominatorTree *DT,
BlockFrequencyInfo *BFI, TargetLibraryInfo *TLI, TargetTransformInfo *TTI,
ScalarEvolution *SE, MemorySSA *MSSA, OptimizationRemarkEmitter *ORE,
bool DeleteAST) {
TargetLibraryInfo *TLI, TargetTransformInfo *TTI, ScalarEvolution *SE,
MemorySSA *MSSA, OptimizationRemarkEmitter *ORE, bool DeleteAST) {
bool Changed = false;
assert(L->isLCSSAForm(*DT) && "Loop is not in LCSSA form.");
@ -396,11 +385,11 @@ bool LoopInvariantCodeMotion::runOnLoop(
LicmMssaOptCap, LicmMssaNoAccForPromotionCap,
/*IsSink=*/true};
if (L->hasDedicatedExits())
Changed |= sinkRegion(DT->getNode(L->getHeader()), AA, LI, DT, BFI, TLI, TTI, L,
Changed |= sinkRegion(DT->getNode(L->getHeader()), AA, LI, DT, TLI, TTI, L,
CurAST.get(), MSSAU.get(), &SafetyInfo, Flags, ORE);
Flags.IsSink = false;
if (Preheader)
Changed |= hoistRegion(DT->getNode(L->getHeader()), AA, LI, DT, BFI, TLI, L,
Changed |= hoistRegion(DT->getNode(L->getHeader()), AA, LI, DT, TLI, L,
CurAST.get(), MSSAU.get(), &SafetyInfo, Flags, ORE);
// Now that all loop invariants have been removed from the loop, promote any
@ -502,10 +491,9 @@ bool LoopInvariantCodeMotion::runOnLoop(
/// definitions, allowing us to sink a loop body in one pass without iteration.
///
bool llvm::sinkRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
DominatorTree *DT, BlockFrequencyInfo *BFI,
TargetLibraryInfo *TLI, TargetTransformInfo *TTI,
Loop *CurLoop, AliasSetTracker *CurAST,
MemorySSAUpdater *MSSAU,
DominatorTree *DT, TargetLibraryInfo *TLI,
TargetTransformInfo *TTI, Loop *CurLoop,
AliasSetTracker *CurAST, MemorySSAUpdater *MSSAU,
ICFLoopSafetyInfo *SafetyInfo,
SinkAndHoistLICMFlags &Flags,
OptimizationRemarkEmitter *ORE) {
@ -554,7 +542,7 @@ bool llvm::sinkRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, MSSAU, true, &Flags,
ORE) &&
!I.mayHaveSideEffects()) {
if (sink(I, LI, DT, BFI, CurLoop, SafetyInfo, MSSAU, ORE)) {
if (sink(I, LI, DT, CurLoop, SafetyInfo, MSSAU, ORE)) {
if (!FreeInLoop) {
++II;
eraseInstruction(I, *SafetyInfo, CurAST, MSSAU);
@ -798,43 +786,13 @@ public:
};
} // namespace
// Hoisting/sinking instruction out of a loop isn't always beneficial. It's only
// only worthwhile if the destination block is actually colder than current
// block.
static bool worthSinkOrHoistInst(Instruction &I, BasicBlock *DstBlock,
OptimizationRemarkEmitter *ORE,
BlockFrequencyInfo *BFI) {
// Check block frequency only when runtime profile is available.
// to avoid pathological cases. With static profile, lean towards
// hosting because it helps canonicalize the loop for vectorizer.
if (!DstBlock->getParent()->hasProfileData())
return true;
if (!HoistSinkColdnessThreshold || !BFI)
return true;
BasicBlock *SrcBlock = I.getParent();
if (BFI->getBlockFreq(DstBlock).getFrequency() / HoistSinkColdnessThreshold >
BFI->getBlockFreq(SrcBlock).getFrequency()) {
ORE->emit([&]() {
return OptimizationRemarkMissed(DEBUG_TYPE, "SinkHoistInst", &I)
<< "failed to sink or hoist instruction because containing block "
"has lower frequency than destination block";
});
return false;
}
return true;
}
/// Walk the specified region of the CFG (defined by all blocks dominated by
/// the specified block, and that are in the current loop) in depth first
/// order w.r.t the DominatorTree. This allows us to visit definitions before
/// uses, allowing us to hoist a loop body in one pass without iteration.
///
bool llvm::hoistRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
DominatorTree *DT, BlockFrequencyInfo *BFI,
TargetLibraryInfo *TLI, Loop *CurLoop,
DominatorTree *DT, TargetLibraryInfo *TLI, Loop *CurLoop,
AliasSetTracker *CurAST, MemorySSAUpdater *MSSAU,
ICFLoopSafetyInfo *SafetyInfo,
SinkAndHoistLICMFlags &Flags,
@ -885,15 +843,13 @@ bool llvm::hoistRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
// Try hoisting the instruction out to the preheader. We can only do
// this if all of the operands of the instruction are loop invariant and
// if it is safe to hoist the instruction. We also check block frequency
// to make sure instruction only gets hoisted into colder blocks.
// if it is safe to hoist the instruction.
// TODO: It may be safe to hoist if we are hoisting to a conditional block
// and we have accurately duplicated the control flow from the loop header
// to that block.
if (CurLoop->hasLoopInvariantOperands(&I) &&
canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, MSSAU, true, &Flags,
ORE) &&
worthSinkOrHoistInst(I, CurLoop->getLoopPreheader(), ORE, BFI) &&
isSafeToExecuteUnconditionally(
I, DT, CurLoop, SafetyInfo, ORE,
CurLoop->getLoopPreheader()->getTerminator())) {
@ -1594,9 +1550,8 @@ static void splitPredecessorsOfLoopExit(PHINode *PN, DominatorTree *DT,
/// position, and may either delete it or move it to outside of the loop.
///
static bool sink(Instruction &I, LoopInfo *LI, DominatorTree *DT,
BlockFrequencyInfo *BFI, const Loop *CurLoop,
ICFLoopSafetyInfo *SafetyInfo, MemorySSAUpdater *MSSAU,
OptimizationRemarkEmitter *ORE) {
const Loop *CurLoop, ICFLoopSafetyInfo *SafetyInfo,
MemorySSAUpdater *MSSAU, OptimizationRemarkEmitter *ORE) {
LLVM_DEBUG(dbgs() << "LICM sinking instruction: " << I << "\n");
ORE->emit([&]() {
return OptimizationRemark(DEBUG_TYPE, "InstSunk", &I)
@ -1672,10 +1627,7 @@ static bool sink(Instruction &I, LoopInfo *LI, DominatorTree *DT,
// If this instruction is only used outside of the loop, then all users are
// PHI nodes in exit blocks due to LCSSA form. Just RAUW them with clones of
// the instruction.
// First check if I is worth sinking for all uses. Sink only when it is worth
// across all uses.
SmallSetVector<User*, 8> Users(I.user_begin(), I.user_end());
SmallVector<PHINode*, 8> ExitPNs;
for (auto *UI : Users) {
auto *User = cast<Instruction>(UI);
@ -1685,15 +1637,6 @@ static bool sink(Instruction &I, LoopInfo *LI, DominatorTree *DT,
PHINode *PN = cast<PHINode>(User);
assert(ExitBlockSet.count(PN->getParent()) &&
"The LCSSA PHI is not in an exit block!");
if (!worthSinkOrHoistInst(I, PN->getParent(), ORE, BFI)) {
return Changed;
}
ExitPNs.push_back(PN);
}
for (auto *PN: ExitPNs) {
// The PHI must be trivially replaceable.
Instruction *New = sinkThroughTriviallyReplaceablePHI(
PN, &I, LI, SunkCopies, SafetyInfo, CurLoop, MSSAU);
@ -2027,7 +1970,7 @@ bool llvm::promoteLoopAccessesToScalars(
// Note that proving a load safe to speculate requires proving
// sufficient alignment at the target location. Proving it guaranteed
// to execute does as well. Thus we can increase our guaranteed
// alignment as well.
// alignment as well.
if (!DereferenceableInPH || (InstAlignment > Alignment))
if (isSafeToExecuteUnconditionally(*Load, DT, CurLoop, SafetyInfo,
ORE, Preheader->getTerminator())) {

10
test/Other/opt-O2-pipeline.ll
View File

@ -102,11 +102,7 @@
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Unswitch loops
; CHECK-NEXT: Simplify the CFG
; CHECK-NEXT: Dominator Tree Construction
@ -158,15 +154,12 @@
; CHECK-NEXT: Memory Dependence Analysis
; CHECK-NEXT: Dead Store Elimination
; CHECK-NEXT: Natural Loop Information
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Canonicalize natural loops
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Basic Alias Analysis (stateless AA impl)
; CHECK-NEXT: Function Alias Analysis Results
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@ -253,13 +246,10 @@
; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Combine redundant instructions
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Canonicalize natural loops
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis

10
test/Other/opt-O3-pipeline.ll
View File

@ -107,11 +107,7 @@
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Unswitch loops
; CHECK-NEXT: Simplify the CFG
; CHECK-NEXT: Dominator Tree Construction
@ -163,15 +159,12 @@
; CHECK-NEXT: Memory Dependence Analysis
; CHECK-NEXT: Dead Store Elimination
; CHECK-NEXT: Natural Loop Information
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Canonicalize natural loops
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Basic Alias Analysis (stateless AA impl)
; CHECK-NEXT: Function Alias Analysis Results
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@ -258,13 +251,10 @@
; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Combine redundant instructions
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Canonicalize natural loops
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis

10
test/Other/opt-Os-pipeline.ll
View File

@ -89,11 +89,7 @@
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Rotate Loops
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Unswitch loops
; CHECK-NEXT: Simplify the CFG
; CHECK-NEXT: Dominator Tree Construction
@ -145,15 +141,12 @@
; CHECK-NEXT: Memory Dependence Analysis
; CHECK-NEXT: Dead Store Elimination
; CHECK-NEXT: Natural Loop Information
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Canonicalize natural loops
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Basic Alias Analysis (stateless AA impl)
; CHECK-NEXT: Function Alias Analysis Results
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Post-Dominator Tree Construction
@ -240,13 +233,10 @@
; CHECK-NEXT: Lazy Block Frequency Analysis
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Combine redundant instructions
; CHECK-NEXT: Branch Probability Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Canonicalize natural loops
; CHECK-NEXT: LCSSA Verifier
; CHECK-NEXT: Loop-Closed SSA Form Pass
; CHECK-NEXT: Scalar Evolution Analysis
; CHECK-NEXT: Block Frequency Analysis
; CHECK-NEXT: Loop Pass Manager
; CHECK-NEXT: Loop Invariant Code Motion
; CHECK-NEXT: Lazy Branch Probability Analysis

2
test/Other/pass-pipelines.ll
View File

@ -52,7 +52,7 @@
; CHECK-O2-NEXT: FunctionPass Manager
; CHECK-O2-NOT: Manager
; CHECK-O2: Loop Pass Manager
; Requiring block frequency for LICM will place ICM and rotation under separate Loop Pass Manager
; CHECK-O2-NOT: Manager
; FIXME: We shouldn't be pulling out to simplify-cfg and instcombine and
; causing new loop pass managers.
; CHECK-O2: Simplify the CFG

10
test/Transforms/LICM/sink.ll
View File

@ -1,10 +1,8 @@
; RUN: opt -S -licm -licm -licm-coldness-threshold=0 < %s | FileCheck %s --check-prefix=CHECK-LICM
; RUN: opt -S -licm -licm < %s | FileCheck %s --check-prefix=CHECK-BFI-LICM
; RUN: opt -S -licm < %s | FileCheck %s --check-prefix=CHECK-LICM
; RUN: opt -S -licm < %s | opt -S -loop-sink | FileCheck %s --check-prefix=CHECK-SINK
; RUN: opt -S < %s -passes='require<opt-remark-emit>,loop(licm),loop-sink' \
; RUN: | FileCheck %s --check-prefix=CHECK-SINK
; RUN: opt -S -licm -licm-coldness-threshold=0 -enable-mssa-loop-dependency=true -verify-memoryssa < %s | FileCheck %s --check-prefix=CHECK-LICM
; RUN: opt -S -licm -enable-mssa-loop-dependency=true -verify-memoryssa < %s | FileCheck %s --check-prefix=CHECK-BFI-LICM
; RUN: opt -S -licm -enable-mssa-loop-dependency=true -verify-memoryssa < %s | FileCheck %s --check-prefix=CHECK-LICM
; Original source code:
; int g;
@ -31,10 +29,6 @@ define i32 @foo(i32, i32) #0 !prof !2 {
; CHECK-LICM: load i32, i32* @g
; CHECK-LICM: br label %.lr.ph
; CHECK-BFI-LICM: .lr.ph.preheader:
; CHECK-BFI-LICM-NOT: load i32, i32* @g
; CHECK-BFI-LICM: br label %.lr.ph
.lr.ph:
%.03 = phi i32 [ %8, %.combine ], [ 0, %.lr.ph.preheader ]
%.012 = phi i32 [ %.1, %.combine ], [ %1, %.lr.ph.preheader ]