2 files changed, 63 insertions, 3 deletions
diff --git a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-dbgloc.ll b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-dbgloc.ll
index 3f577f0..edd64e5 100644
--- a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-dbgloc.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-dbgloc.ll
@@ -7,14 +7,14 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 declare void @llvm.memset.p0.i64(ptr nocapture, i8, i64, i1)
 declare void @llvm.memcpy.p0.p0.i64(ptr nocapture, ptr nocapture readonly, i64, i1)
 
-define void @test_constant(i64 %src_size, ptr %dst, i64 %dst_size, i8 %c) !dbg !5 {
+define void @test_constant(i64 %src_size, ptr %dst, i64 %dst_size, i8 %c) !dbg !5 !prof !14 {
 ; CHECK-LABEL: define void @test_constant(
-; CHECK-SAME: i64 [[SRC_SIZE:%.*]], ptr [[DST:%.*]], i64 [[DST_SIZE:%.*]], i8 [[C:%.*]]) !dbg [[DBG5:![0-9]+]] {
+; CHECK-SAME: i64 [[SRC_SIZE:%.*]], ptr [[DST:%.*]], i64 [[DST_SIZE:%.*]], i8 [[C:%.*]]) !dbg [[DBG5:![0-9]+]] !prof {{.*}} {
 ; CHECK-NEXT:    [[NON_ZERO:%.*]] = icmp ne i64 [[SRC_SIZE]], 0
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[NON_ZERO]])
 ; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i64 [[DST_SIZE]], [[SRC_SIZE]], !dbg [[DBG11:![0-9]+]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 [[DST_SIZE]], [[SRC_SIZE]], !dbg [[DBG11]]
-; CHECK-NEXT:    [[TMP3:%.*]] = select i1 [[TMP1]], i64 0, i64 [[TMP2]], !dbg [[DBG11]]
+; CHECK-NEXT:    [[TMP3:%.*]] = select i1 [[TMP1]], i64 0, i64 [[TMP2]], !dbg [[DBG11]], !prof [[SELPROF:![0-9]+]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i8, ptr [[DST]], i64 [[SRC_SIZE]], !dbg [[DBG11]]
 ; CHECK-NEXT:    call void @llvm.memset.p0.i64(ptr align 1 [[TMP4]], i8 [[C]], i64 [[TMP3]], i1 false), !dbg [[DBG11]]
 ; CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr [[DST]], ptr @C, i64 [[SRC_SIZE]], i1 false), !dbg [[DBG12:![0-9]+]]
@@ -29,6 +29,7 @@ define void @test_constant(i64 %src_size, ptr %dst, i64 %dst_size, i8 %c) !dbg !
 
 ; Validate that the memset is mapped to DILocation for the original memset.
 ; CHECK: [[DBG11]] = !DILocation(line: 1,
+; CHECK: [[SELPROF]] = !{!"unknown", !"memcpyopt"}
 ; CHECK: [[DBG12]] = !DILocation(line: 2,
 ; CHECK: [[DBG13]] = !DILocation(line: 3,
 
@@ -50,3 +51,4 @@ define void @test_constant(i64 %src_size, ptr %dst, i64 %dst_size, i8 %c) !dbg !
 !11 = !DILocation(line: 1, column: 1, scope: !5)
 !12 = !DILocation(line: 2, column: 1, scope: !5)
 !13 = !DILocation(line: 3, column: 1, scope: !5)
+!14 = !{!"function_entry_count", i32 10}
+\ No newline at end of file
diff --git a/llvm/test/Transforms/MemCpyOpt/stack-move.ll b/llvm/test/Transforms/MemCpyOpt/stack-move.ll
index 940e30e..0c2e05f 100644
--- a/llvm/test/Transforms/MemCpyOpt/stack-move.ll
+++ b/llvm/test/Transforms/MemCpyOpt/stack-move.ll
@@ -1729,3 +1729,61 @@ define i32 @test_ret_only_capture() {
   %v = load i32, ptr %a
   ret i32 %v
 }
+
+declare ptr @captures_address_only(ptr captures(address))
+
+; Can transform: Only one address captured.
+define void @test_captures_address_captures_none() {
+; CHECK-LABEL: define void @test_captures_address_captures_none() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
+; CHECK-NEXT:    call void @captures_address_only(ptr [[SRC]])
+; CHECK-NEXT:    call void @use_nocapture(ptr [[SRC]])
+; CHECK-NEXT:    ret void
+;
+  %src = alloca %struct.Foo, align 4
+  %dst = alloca %struct.Foo, align 4
+  store %struct.Foo { i32 10, i32 20, i32 30 }, ptr %src
+  call void @captures_address_only(ptr %src)
+  call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr align 4 %src, i64 12, i1 false)
+  call void @use_nocapture(ptr %dst)
+  ret void
+}
+
+; Can transform: Only one address captured.
+define void @test_captures_none_and_captures_address() {
+; CHECK-LABEL: define void @test_captures_none_and_captures_address() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
+; CHECK-NEXT:    call void @use_nocapture(ptr [[SRC]])
+; CHECK-NEXT:    call void @captures_address_only(ptr [[SRC]])
+; CHECK-NEXT:    ret void
+;
+  %src = alloca %struct.Foo, align 4
+  %dst = alloca %struct.Foo, align 4
+  store %struct.Foo { i32 10, i32 20, i32 30 }, ptr %src
+  call void @use_nocapture(ptr %src)
+  call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr align 4 %src, i64 12, i1 false)
+  call void @captures_address_only(ptr %dst)
+  ret void
+}
+
+; Cannot transform: Both addresses captured.
+define void @test_captures_address_and_captures_address() {
+; CHECK-LABEL: define void @test_captures_address_and_captures_address() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    [[DST:%.*]] = alloca [[STRUCT_FOO]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
+; CHECK-NEXT:    call void @captures_address_only(ptr [[SRC]])
+; CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DST]], ptr align 4 [[SRC]], i64 12, i1 false)
+; CHECK-NEXT:    call void @captures_address_only(ptr [[DST]])
+; CHECK-NEXT:    ret void
+;
+  %src = alloca %struct.Foo, align 4
+  %dst = alloca %struct.Foo, align 4
+  store %struct.Foo { i32 10, i32 20, i32 30 }, ptr %src
+  call void @captures_address_only(ptr %src)
+  call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr align 4 %src, i64 12, i1 false)
+  call void @captures_address_only(ptr %dst)
+  ret void
+}