diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp index dc8fa4379752f..4eab10c0bca57 100644 --- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp +++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp @@ -3790,6 +3790,11 @@ LSRInstance::CollectLoopInvariantFixupsAndFormulae() { continue; } + // Do not consider uses inside lifetime intrinsics. These are not + // actually materialized. + if (UserInst->isLifetimeStartOrEnd()) + continue; + std::pair P = getUse(S, LSRUse::Basic, MemAccessTy()); size_t LUIdx = P.first; diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/lifetime-use.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/lifetime-use.ll new file mode 100644 index 0000000000000..c7a0de22b200b --- /dev/null +++ b/llvm/test/Transforms/LoopStrengthReduce/X86/lifetime-use.ll @@ -0,0 +1,59 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5 +; RUN: opt -S -passes=loop-reduce -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s + +define void @test(ptr %p, i64 %idx) { +; CHECK-LABEL: define void @test( +; CHECK-SAME: ptr [[P:%.*]], i64 [[IDX:%.*]]) { +; CHECK-NEXT: [[ENTRY:.*]]: +; CHECK-NEXT: [[ALLOCA:%.*]] = alloca [4 x [4 x i32]], align 16 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 64, ptr [[ALLOCA]]) +; CHECK-NEXT: [[TMP0:%.*]] = shl i64 [[IDX]], 6 +; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i64 [[TMP0]], 48 +; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP1]] +; CHECK-NEXT: [[SCEVGEP3:%.*]] = getelementptr nuw i8, ptr [[ALLOCA]], i64 48 +; CHECK-NEXT: br label %[[LOOP:.*]] +; CHECK: [[LOOP]]: +; CHECK-NEXT: [[LSR_IV:%.*]] = phi i64 [ [[LSR_IV_NEXT:%.*]], %[[LOOP]] ], [ -8, %[[ENTRY]] ] +; CHECK-NEXT: [[TMP2:%.*]] = shl nsw i64 [[LSR_IV]], 2 +; CHECK-NEXT: [[SCEVGEP8:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP2]] +; CHECK-NEXT: [[SCEVGEP9:%.*]] = getelementptr i8, ptr [[SCEVGEP8]], i64 32 +; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[SCEVGEP9]], align 4 +; CHECK-NEXT: [[SCEVGEP6:%.*]] = getelementptr i8, ptr [[P]], i64 [[LSR_IV]] +; CHECK-NEXT: [[SCEVGEP7:%.*]] = getelementptr i8, ptr [[SCEVGEP6]], i64 8 +; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[SCEVGEP7]], align 4 +; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i8, ptr [[SCEVGEP3]], i64 [[LSR_IV]] +; CHECK-NEXT: [[SCEVGEP5:%.*]] = getelementptr i8, ptr [[SCEVGEP4]], i64 8 +; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[SCEVGEP5]], align 4 +; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[SCEVGEP]], i64 [[LSR_IV]] +; CHECK-NEXT: [[SCEVGEP2:%.*]] = getelementptr i8, ptr [[SCEVGEP1]], i64 8 +; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr [[SCEVGEP2]], align 4 +; CHECK-NEXT: [[LSR_IV_NEXT]] = add nsw i64 [[LSR_IV]], 4 +; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[LSR_IV_NEXT]], 0 +; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label %[[EXIT:.*]], label %[[LOOP]] +; CHECK: [[EXIT]]: +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 64, ptr [[ALLOCA]]) +; CHECK-NEXT: ret void +; +entry: + %alloca = alloca [4 x [4 x i32]], align 16 + call void @llvm.lifetime.start.p0(i64 64, ptr %alloca) + br label %loop + +loop: + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %loop ] + %gep1 = getelementptr [4 x [12 x [4 x [4 x i32]]]], ptr %p, i64 0, i64 0, i64 0, i64 %indvars.iv, i64 0 + %0 = load i32, ptr %gep1, align 4 + %gep2 = getelementptr [6 x [4 x [4 x i32]]], ptr %p, i64 0, i64 0, i64 0, i64 %indvars.iv + %1 = load i32, ptr %gep2, align 4 + %gep3 = getelementptr [4 x [4 x i32]], ptr %alloca, i64 0, i64 3, i64 %indvars.iv + %2 = load i32, ptr %gep3, align 4 + %gep4 = getelementptr [6 x [4 x [4 x i32]]], ptr %p, i64 0, i64 %idx, i64 3, i64 %indvars.iv + %3 = load i32, ptr %gep4, align 4 + %indvars.iv.next = add i64 %indvars.iv, 1 + %exitcond.not = icmp eq i64 %indvars.iv, 1 + br i1 %exitcond.not, label %exit, label %loop + +exit: + call void @llvm.lifetime.end.p0(i64 64, ptr %alloca) + ret void +}