The memcpy optimizer was happily doing call slot forwarding when the new memory

[oota-llvm.git] / test / Transforms / MemCpyOpt / align.ll

diff --git a/test/Transforms/MemCpyOpt/align.ll b/test/Transforms/MemCpyOpt/align.ll
index b1f900d9da4c6e7723809431ee748a4e97a99840..1b98f6ad383f9ebc4e0392bc3ac0e77480d6be3b 100644 (file)
--- a/test/Transforms/MemCpyOpt/align.ll
+++ b/test/Transforms/MemCpyOpt/align.ll
@@ -1,12 +1,15 @@
-; RUN: opt < %s -S -memcpyopt | FileCheck %s
+; RUN: opt < %s -S -basicaa -memcpyopt | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
 
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+
 ; The resulting memset is only 4-byte aligned, despite containing
 ; a 16-byte aligned store in the middle.
 
-; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 16, i32 4, i1 false)
-
 define void @foo(i32* %p) {
+; CHECK: @foo
+; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 16, i32 4, i1 false)
   %a0 = getelementptr i32* %p, i64 0
   store i32 0, i32* %a0, align 4
   %a1 = getelementptr i32* %p, i64 1
@@ -17,3 +20,18 @@ define void @foo(i32* %p) {
   store i32 0, i32* %a3, align 4
   ret void
 }
+
+; Replacing %a8 with %a4 in the memset requires boosting the alignment of %a4.
+
+define void @bar() {
+; CHECK: @bar
+; CHECK: %a4 = alloca i32, align 8
+; CHECK-NOT: memcpy
+  %a4 = alloca i32, align 4
+  %a8 = alloca i32, align 8
+  %a8.cast = bitcast i32* %a8 to i8*
+  %a4.cast = bitcast i32* %a4 to i8*
+  call void @llvm.memset.p0i8.i64(i8* %a8.cast, i8 0, i64 4, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a4.cast, i8* %a8.cast, i64 4, i32 4, i1 false)
+  ret void
+}