2 files changed, 32 insertions, 0 deletions
diff --git a/test/CodeGen/ARM/Windows/vla-cpsr.ll b/test/CodeGen/ARM/Windows/vla-cpsr.ll
new file mode 100644
index 000000000000..de0f0b68a4d2
--- /dev/null
+++ b/test/CodeGen/ARM/Windows/vla-cpsr.ll
@@ -0,0 +1,13 @@
+; RUN: llc -mtriple thumbv7-windows-itanium -filetype asm -o /dev/null %s -print-machineinstrs=expand-isel-pseudos 2>&1 | FileCheck %s
+
+declare arm_aapcs_vfpcc void @g(i8*) local_unnamed_addr
+
+define arm_aapcs_vfpcc void @f(i32 %i) local_unnamed_addr {
+entry:
+  %vla = alloca i8, i32 %i, align 1
+  call arm_aapcs_vfpcc void @g(i8* nonnull %vla)
+  ret void
+}
+
+; CHECK: tBL pred:14, pred:%noreg, <es:__chkstk>, %LR<imp-def>, %SP<imp-use>, %R4<imp-use,kill>, %R4<imp-def>, %R12<imp-def,dead>, %CPSR<imp-def,dead>
+
diff --git a/test/CodeGen/ARM/vzip.ll b/test/CodeGen/ARM/vzip.ll
index 771bf5f05215..06b49ab94053 100644
--- a/test/CodeGen/ARM/vzip.ll
+++ b/test/CodeGen/ARM/vzip.ll
@@ -282,6 +282,25 @@ entry:
   ret <8 x i16> %0
 }
 
+; NOTE: The mask here looks like something that could be done with a vzip,
+; but which the current handling of two-result vzip can't do - thus ending up
+; as a vtrn.
+define <8 x i16> @vzip_lower_shufflemask_undef_rev(<4 x i16>* %A, <4 x i16>* %B) {
+; CHECK-LABEL: vzip_lower_shufflemask_undef_rev:
+; CHECK:       @ BB#0: @ %entry
+; CHECK-NEXT:    vldr d16, [r1]
+; CHECK-NEXT:    vldr d19, [r0]
+; CHECK-NEXT:    vtrn.16 d19, d16
+; CHECK-NEXT:    vmov r0, r1, d18
+; CHECK-NEXT:    vmov r2, r3, d19
+; CHECK-NEXT:    mov pc, lr
+entry:
+  %tmp1 = load <4 x i16>, <4 x i16>* %A
+  %tmp2 = load <4 x i16>, <4 x i16>* %B
+  %0 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 0, i32 4, i32 undef, i32 undef>
+  ret <8 x i16> %0
+}
+
 define <4 x i32> @vzip_lower_shufflemask_zeroed(<2 x i32>* %A) {
 ; CHECK-LABEL: vzip_lower_shufflemask_zeroed:
 ; CHECK:       @ BB#0: @ %entry