Index: llvm/test/Transforms/MemCpyOpt/stack-move.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/MemCpyOpt/stack-move.ll @@ -0,0 +1,399 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2 +%struct.Foo = type { i32, i32, i32 } + +@constant = private unnamed_addr constant %struct.Foo { i32 1, i32 2, i32 3 }, align 4 + +declare void @llvm.memcpy.p0.p0.i64(ptr noalias nocapture writeonly, ptr noalias nocapture readonly, i64, i1 immarg) +declare void @llvm.memmove.p0.p0.i64(ptr nocapture writeonly, ptr nocapture readonly, i64, i1 immarg) + +declare void @llvm.lifetime.start.p0(i64, ptr nocapture) +declare void @llvm.lifetime.end.p0(i64, ptr nocapture) +declare i32 @use_nocapture(ptr noundef nocapture) + +define void @basic_memcpy() { + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + + +define void @basic_memmove() { + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memmove.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memmove.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that the optimization succeeds with a load/store pair. +define void @load_store() { +; CHECK-LABEL: @load_store( +; CHECK-NEXT: [[SRC:%.*]] = alloca i32, align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca i32, align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 4, ptr [[SRC]]) +; CHECK-NEXT: store i32 42, ptr [[SRC]], align 4 +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 4, ptr [[SRC]]) +; CHECK-NEXT: ret void +; + %src = alloca i32, align 4 + %dest = alloca i32, align 4 + call void @llvm.lifetime.start.p0(i64 4, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 4, ptr nocapture %dest) + store i32 42, ptr %src + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + %2 = load i32, ptr %src + store i32 %2, ptr %dest + call void @llvm.lifetime.end.p0(i64 4, ptr nocapture %src) + %3 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 4, ptr nocapture %dest) + ret void +} + +; Tests that merging two allocas with different alignments results in an +; alloca with the broader alignment. +define void @align_up() { +; CHECK-LABEL: @align_up( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 8 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 8 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that we correctly remove extra lifetime intrinsics when performing the +; optimization. +define void @remove_extra_lifetime_intrinsics() { +; CHECK-LABEL: @remove_extra_lifetime_intrinsics( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: [[TMP3:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + %3 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that we remove scoped noalias metadata from a call. +define void @remove_scoped_noalias() { +; CHECK-LABEL: @remove_scoped_noalias( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]), !alias.scope !0 +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src), !alias.scope !2 + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest), !noalias !2 + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that we remove metadata on the merged alloca. +define void @remove_alloca_metadata() { +; CHECK-LABEL: @remove_alloca_metadata( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]), !alias.scope !0 +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr [[SRC]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4, !annotation !3 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src), !alias.scope !2 + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest), !noalias !2 + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that dynamically-sized allocas are never merged. +define void @dynamically_sized_alloca(i64 %i) { +; CHECK-LABEL: @dynamically_sized_alloca( +; CHECK-NEXT: [[SRC:%.*]] = alloca i8, i64 [[I:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca i8, i64 [[I]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 12, i1 false) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca i8, i64 %i, align 4 + %dest = alloca i8, i64 %i, align 4 + call void @llvm.lifetime.start.p0(i64 -1, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 -1, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 -1, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 -1, ptr nocapture %dest) + ret void +} + +; Tests that a memcpy with a dynamic size is never optimized. +define void @dynamically_sized_memcpy(i64 %size) { +; CHECK-LABEL: @dynamically_sized_memcpy( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 [[SIZE:%.*]], i1 false) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 %size, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that allocas with different sizes aren't merged together. +define void @mismatched_alloca_size() { +; CHECK-LABEL: @mismatched_alloca_size( +; CHECK-NEXT: [[SRC:%.*]] = alloca i8, i64 24, align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca i8, i64 12, align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 24, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 12, i1 false) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 24, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca i8, i64 24, align 4 + %dest = alloca i8, i64 12, align 4 + call void @llvm.lifetime.start.p0(i64 24, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 24, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that allocas with mismatched address spaces aren't combined. +define void @mismatched_alloca_addrspace() { +; CHECK-LABEL: @mismatched_alloca_addrspace( +; CHECK-NEXT: [[SRC:%.*]] = alloca i8, i64 24, align 4, addrspace(1) +; CHECK-NEXT: [[DEST:%.*]] = alloca i8, i64 12, align 4, addrspace(2) +; CHECK-NEXT: call void @llvm.lifetime.start.p1(i64 24, ptr addrspace(1) nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p2(i64 12, ptr addrspace(2) nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p1.p0.i64(ptr addrspace(1) align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr addrspace(1) nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p2.p1.i64(ptr addrspace(2) align 4 [[DEST]], ptr addrspace(1) align 4 [[SRC]], i64 12, i1 false) +; CHECK-NEXT: call void @llvm.lifetime.end.p1(i64 24, ptr addrspace(1) nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr addrspace(2) nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p2(i64 12, ptr addrspace(2) nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca i8, i64 24, align 4, addrspace(1) + %dest = alloca i8, i64 12, align 4, addrspace(2) + call void @llvm.lifetime.start.p1(i64 24, ptr addrspace(1) nocapture %src) + call void @llvm.lifetime.start.p2(i64 12, ptr addrspace(2) nocapture %dest) + call void @llvm.memcpy.p1.p0.i64(ptr addrspace(1) align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr addrspace(1) noundef nocapture %src) + call void @llvm.memcpy.p2.p1.i64(ptr addrspace(2) align 4 %dest, ptr addrspace(1) align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p1(i64 24, ptr addrspace(1) nocapture %src) + %2 = call i32 @use_nocapture(ptr addrspace(2) noundef nocapture %dest) + call void @llvm.lifetime.end.p2(i64 12, ptr addrspace(2) nocapture %dest) + ret void +} + +; Tests that volatile memcpys aren't removed. +define void @volatile_memcpy() { +; CHECK-LABEL: @volatile_memcpy( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 true) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 12, i1 true) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 true) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 true) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that the optimization isn't performed when the destination is captured. +define void @dest_captured() { +; CHECK-LABEL: @dest_captured( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 12, i1 false) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_capture(ptr noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_capture(ptr noundef %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that the optimization isn't performed when the source is captured. +define void @src_captured() { +; CHECK-LABEL: @src_captured( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_capture(ptr noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 [[SRC]], i64 12, i1 false) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + %1 = call i32 @use_capture(ptr noundef %src) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +} + +; Tests that the optimization isn't performed when the source and destination +; are simultaneously live within the basic block. +define void @local_liveness_conflict() { +; CHECK-LABEL: @local_liveness_conflict( +; CHECK-NEXT: [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4 +; CHECK-NEXT: [[DEST:%.*]] = alloca [[STRUCT_FOO]], align 4 +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[SRC]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DEST]], ptr align 4 @constant, i64 12, i1 false) +; CHECK-NEXT: [[TMP1:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[SRC]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[SRC]]) +; CHECK-NEXT: [[TMP2:%.*]] = call i32 @use_nocapture(ptr nocapture noundef [[DEST]]) +; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 12, ptr nocapture [[DEST]]) +; CHECK-NEXT: ret void +; + %src = alloca %struct.Foo, align 4 + %dest = alloca %struct.Foo, align 4 + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %src) + call void @llvm.lifetime.start.p0(i64 12, ptr nocapture %dest) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %src, ptr align 4 @constant, i64 12, i1 false) + call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dest, ptr align 4 %src, i64 12, i1 false) + %1 = call i32 @use_nocapture(ptr noundef nocapture %src) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %src) + %2 = call i32 @use_nocapture(ptr noundef nocapture %dest) + call void @llvm.lifetime.end.p0(i64 12, ptr nocapture %dest) + ret void +}