--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mcpu=btver2 %s -o - | FileCheck %s
+; Test desc: two functions (foo, bar) with byval arguments, should not have
+; reads/writes from/to byval storage re-ordered.
+; When broken, five "1" constants are written into the byval %struct.face,
+; but the subsequent byval read of that struct (call to bar) gets re-ordered
+; before those writes, illegally.
+;
+; FIXME: the output shown below is the broken output of llc, "movl $1" is
+; scheduled after the copy between byval arguments starts. This will be fixed
+; with the patch in review D45022.
+source_filename = "test.c"
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+%struct.face = type { [7 x i32] }
+
+; Function Attrs: noinline nounwind uwtable
+declare void @bar(%struct.face* byval nocapture readonly align 8);
+
+; Function Attrs: noinline nounwind uwtable
+define void @foo(%struct.face* byval nocapture align 8) local_unnamed_addr {
+; CHECK-LABEL: foo:
+; CHECK: # %bb.0:
+; CHECK-NEXT: subq $40, %rsp
+; CHECK-NEXT: .cfi_def_cfa_offset 48
+; CHECK-NEXT: vmovaps {{.*#+}} xmm0 = [1,1,1,1]
+; CHECK-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT: vmovups {{[0-9]+}}(%rsp), %xmm0
+; CHECK-NEXT: movl $1, {{[0-9]+}}(%rsp)
+; CHECK-NEXT: vmovups %xmm0, {{[0-9]+}}(%rsp)
+; CHECK-NEXT: vmovaps {{[0-9]+}}(%rsp), %xmm0
+; CHECK-NEXT: vmovups %xmm0, (%rsp)
+; CHECK-NEXT: callq bar
+; CHECK-NEXT: addq $40, %rsp
+; CHECK-NEXT: .cfi_def_cfa_offset 8
+; CHECK-NEXT: retq
+ %2 = bitcast %struct.face* %0 to <4 x i32>*
+ store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32>* %2, align 8
+ %3 = getelementptr inbounds %struct.face, %struct.face* %0, i64 0, i32 0, i64 4
+ store i32 1, i32* %3, align 8
+ call void @bar(%struct.face* byval nonnull align 8 %0)
+ ret void
+}