diff options
| -rw-r--r-- | llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp | 19 | ||||
| -rw-r--r-- | llvm/test/Transforms/InstCombine/multiple-uses-load-bitcast-select.ll | 30 |
2 files changed, 47 insertions, 2 deletions
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp index 29e0a091aa7..a729981a549 100644 --- a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp @@ -1344,9 +1344,24 @@ bool removeBitcastsFromLoadStoreOnMinMax(InstCombiner &IC, StoreInst &SI) { if (!isMinMaxWithLoads(LoadAddr)) return false; + if (!all_of(LI->users(), [LI](User *U) { + auto *SI = dyn_cast<StoreInst>(U); + return SI && SI->getPointerOperand() != LI && + !SI->getPointerOperand()->isSwiftError(); + })) + return false; + + IC.Builder.SetInsertPoint(LI); LoadInst *NewLI = combineLoadToNewType( IC, *LI, LoadAddr->getType()->getPointerElementType()); - combineStoreToNewValue(IC, SI, NewLI); + // Replace all the stores with stores of the newly loaded value. + for (auto *UI : LI->users()) { + auto *SI = cast<StoreInst>(UI); + IC.Builder.SetInsertPoint(SI); + combineStoreToNewValue(IC, *SI, NewLI); + IC.eraseInstFromFunction(*SI); + } + IC.eraseInstFromFunction(*LI); return true; } @@ -1375,7 +1390,7 @@ Instruction *InstCombiner::visitStoreInst(StoreInst &SI) { return eraseInstFromFunction(SI); if (removeBitcastsFromLoadStoreOnMinMax(*this, SI)) - return eraseInstFromFunction(SI); + return nullptr; // Replace GEP indices if possible. if (Instruction *NewGEPI = replaceGEPIdxWithZero(*this, Ptr, SI)) { diff --git a/llvm/test/Transforms/InstCombine/multiple-uses-load-bitcast-select.ll b/llvm/test/Transforms/InstCombine/multiple-uses-load-bitcast-select.ll new file mode 100644 index 00000000000..28509df6d2f --- /dev/null +++ b/llvm/test/Transforms/InstCombine/multiple-uses-load-bitcast-select.ll @@ -0,0 +1,30 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -instcombine -S -data-layout="E-m:e-i1:8:16-i8:8:16-i64:64-f128:64-v128:64-a:8:16-n32:64" | FileCheck %s + +define void @PR35618(i64* %st1, double* %st2) { +; CHECK-LABEL: @PR35618( +; CHECK-NEXT: [[Y1:%.*]] = alloca double, align 8 +; CHECK-NEXT: [[Z1:%.*]] = alloca double, align 8 +; CHECK-NEXT: [[LD1:%.*]] = load double, double* [[Y1]], align 8 +; CHECK-NEXT: [[LD2:%.*]] = load double, double* [[Z1]], align 8 +; CHECK-NEXT: [[TMP10:%.*]] = fcmp olt double [[LD1]], [[LD2]] +; CHECK-NEXT: [[TMP121:%.*]] = select i1 [[TMP10]], double [[LD1]], double [[LD2]] +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i64* [[ST1:%.*]] to double* +; CHECK-NEXT: store double [[TMP121]], double* [[TMP1]], align 8 +; CHECK-NEXT: store double [[TMP121]], double* [[ST2:%.*]], align 8 +; CHECK-NEXT: ret void +; + %y1 = alloca double + %z1 = alloca double + %ld1 = load double, double* %y1 + %ld2 = load double, double* %z1 + %tmp10 = fcmp olt double %ld1, %ld2 + %sel = select i1 %tmp10, double* %y1, double* %z1 + %tmp11 = bitcast double* %sel to i64* + %tmp12 = load i64, i64* %tmp11 + store i64 %tmp12, i64* %st1 + %bc = bitcast double* %st2 to i64* + store i64 %tmp12, i64* %bc + ret void +} + |
