Index: lib/Transforms/Scalar/LICM.cpp =================================================================== --- lib/Transforms/Scalar/LICM.cpp +++ lib/Transforms/Scalar/LICM.cpp @@ -91,10 +91,11 @@ const Loop *CurLoop, AliasSetTracker *CurAST, const LoopSafetyInfo *SafetyInfo, OptimizationRemarkEmitter *ORE); -static bool isSafeToExecuteUnconditionally(const Instruction &Inst, +static bool isSafeToExecuteUnconditionally(Instruction &Inst, const DominatorTree *DT, const Loop *CurLoop, const LoopSafetyInfo *SafetyInfo, + OptimizationRemarkEmitter *ORE, const Instruction *CtxI = nullptr); static bool pointerInvalidatedByLoop(Value *V, uint64_t Size, const AAMDNodes &AAInfo, @@ -404,7 +405,7 @@ if (CurLoop->hasLoopInvariantOperands(&I) && canSinkOrHoistInst(I, AA, DT, CurLoop, CurAST, SafetyInfo, ORE) && isSafeToExecuteUnconditionally( - I, DT, CurLoop, SafetyInfo, + I, DT, CurLoop, SafetyInfo, ORE, CurLoop->getLoopPreheader()->getTerminator())) Changed |= hoist(I, DT, CurLoop, SafetyInfo, ORE); } @@ -779,15 +780,28 @@ /// Only sink or hoist an instruction if it is not a trapping instruction, /// or if the instruction is known not to trap when moved to the preheader. /// or if it is a trapping instruction and is guaranteed to execute. -static bool isSafeToExecuteUnconditionally(const Instruction &Inst, +static bool isSafeToExecuteUnconditionally(Instruction &Inst, const DominatorTree *DT, const Loop *CurLoop, const LoopSafetyInfo *SafetyInfo, + OptimizationRemarkEmitter *ORE, const Instruction *CtxI) { if (isSafeToSpeculativelyExecute(&Inst, CtxI, DT)) return true; - return isGuaranteedToExecute(Inst, DT, CurLoop, SafetyInfo); + bool GuaranteedToExecute = + isGuaranteedToExecute(Inst, DT, CurLoop, SafetyInfo); + + if (!GuaranteedToExecute) { + auto *LI = dyn_cast(&Inst); + if (LI && CurLoop->isLoopInvariant(LI->getPointerOperand())) + ORE->emit(OptimizationRemarkMissed( + DEBUG_TYPE, "LoadWithLoopInvariantAddressCondExecuted", LI) + << "failed to hoist load with loop-invariant address " + "because load is conditionally executed"); + } + + return GuaranteedToExecute; } namespace { @@ -976,14 +990,14 @@ // If there is an non-load/store instruction in the loop, we can't promote // it. - if (const LoadInst *Load = dyn_cast(UI)) { + if (LoadInst *Load = dyn_cast(UI)) { assert(!Load->isVolatile() && "AST broken"); if (!Load->isSimple()) return Changed; if (!GuaranteedToExecute && !CanSpeculateLoad) CanSpeculateLoad = isSafeToExecuteUnconditionally( - *Load, DT, CurLoop, SafetyInfo, Preheader->getTerminator()); + *Load, DT, CurLoop, SafetyInfo, ORE, Preheader->getTerminator()); } else if (const StoreInst *Store = dyn_cast(UI)) { // Stores *of* the pointer are not interesting, only stores *to* the // pointer. Index: test/Transforms/LICM/opt-remarks-conditional-load.ll =================================================================== --- /dev/null +++ test/Transforms/LICM/opt-remarks-conditional-load.ll @@ -0,0 +1,47 @@ +; RUN: opt < %s -licm -pass-remarks-missed=licm -o /dev/null 2>&1 | FileCheck %s +; RUN: opt -aa-pipeline=basic-aa -passes='require,require,require,require,loop(licm)' %s -o /dev/null -pass-remarks-missed=licm 2>&1 | FileCheck %s +target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128" + +; With the load from %p conditional, we can't optmize this and the remark +; should tell us about it. + +define void @test(i32* %array, i32* noalias %p) { +Entry: + br label %Loop + +Loop: + %j = phi i32 [ 0, %Entry ], [ %Next, %else] + %addr = getelementptr i32, i32* %array, i32 %j + %a = load i32, i32* %addr + %c = icmp eq i32 %a, 0 + br i1 %c, label %then, label %else + +then: +; CHECK: remark: /tmp/kk.c:2:20: failed to hoist load with loop-invariant address because load is conditionally executed + %b = load i32, i32* %p, !dbg !8 + %a2 = add i32 %a, %b + store i32 %a2, i32* %addr + br label %else + +else: + %Next = add i32 %j, 1 + %cond = icmp eq i32 %Next, 0 + br i1 %cond, label %Out, label %Loop + +Out: + ret void +} + +!llvm.dbg.cu = !{!0} +!llvm.module.flags = !{!3, !4} +!llvm.ident = !{!5} + +!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 3.9.0 ", isOptimized: true, runtimeVersion: 0, emissionKind: NoDebug, enums: !2) +!1 = !DIFile(filename: "/tmp/kk.c", directory: "/tmp") +!2 = !{} +!3 = !{i32 2, !"Debug Info Version", i32 3} +!4 = !{i32 1, !"PIC Level", i32 2} +!5 = !{!"clang version 3.9.0 "} +!6 = distinct !DISubprogram(name: "success", scope: !1, file: !1, line: 1, type: !7, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: true, unit: !0, variables: !2) +!7 = !DISubroutineType(types: !2) +!8 = !DILocation(line: 2, column: 20, scope: !6)