Add testcases for PR8411 (vget_low and vget_high implemented as shuffles).

llvm-svn: 122997

1 files changed, 37 insertions, 1 deletions

diff --git a/llvm/test/CodeGen/ARM/vcombine.ll b/llvm/test/CodeGen/ARM/vcombine.ll
index e6733051f26..527f93b6637 100644
--- a/llvm/test/CodeGen/ARM/vcombine.ll
+++ b/llvm/test/CodeGen/ARM/vcombine.ll
@@ -1,6 +1,9 @@
-; RUN: llc < %s -march=arm -mattr=+neon
+; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
 
 define <16 x i8> @vcombine8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+; CHECK: vcombine8
+; CHECK: vmov r0, r1, d16
+; CHECK: vmov r2, r3, d17
 	%tmp1 = load <8 x i8>* %A
 	%tmp2 = load <8 x i8>* %B
 	%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -8,6 +11,9 @@ define <16 x i8> @vcombine8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
 }
 
 define <8 x i16> @vcombine16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+; CHECK: vcombine16
+; CHECK: vmov r0, r1, d16
+; CHECK: vmov r2, r3, d17
 	%tmp1 = load <4 x i16>* %A
 	%tmp2 = load <4 x i16>* %B
 	%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
@@ -15,6 +21,9 @@ define <8 x i16> @vcombine16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
 }
 
 define <4 x i32> @vcombine32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+; CHECK: vcombine32
+; CHECK: vmov r0, r1, d16
+; CHECK: vmov r2, r3, d17
 	%tmp1 = load <2 x i32>* %A
 	%tmp2 = load <2 x i32>* %B
 	%tmp3 = shufflevector <2 x i32> %tmp1, <2 x i32> %tmp2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
@@ -22,6 +31,9 @@ define <4 x i32> @vcombine32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
 }
 
 define <4 x float> @vcombinefloat(<2 x float>* %A, <2 x float>* %B) nounwind {
+; CHECK: vcombinefloat
+; CHECK: vmov r0, r1, d16
+; CHECK: vmov r2, r3, d17
 	%tmp1 = load <2 x float>* %A
 	%tmp2 = load <2 x float>* %B
 	%tmp3 = shufflevector <2 x float> %tmp1, <2 x float> %tmp2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
@@ -29,8 +41,32 @@ define <4 x float> @vcombinefloat(<2 x float>* %A, <2 x float>* %B) nounwind {
 }
 
 define <2 x i64> @vcombine64(<1 x i64>* %A, <1 x i64>* %B) nounwind {
+; CHECK: vcombine64
+; CHECK: vmov r0, r1, d16
+; CHECK: vmov r2, r3, d17
 	%tmp1 = load <1 x i64>* %A
 	%tmp2 = load <1 x i64>* %B
 	%tmp3 = shufflevector <1 x i64> %tmp1, <1 x i64> %tmp2, <2 x i32> <i32 0, i32 1>
 	ret <2 x i64> %tmp3
 }
+
+; Check for vget_low and vget_high implemented with shufflevector.  PR8411.
+; They should not require storing to the stack.
+
+define <4 x i16> @vget_low16(<8 x i16>* %A) nounwind {
+; CHECK: vget_low16
+; CHECK-NOT: vst
+; CHECK: vmov r0, r1, d16
+	%tmp1 = load <8 x i16>* %A
+        %tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+        ret <4 x i16> %tmp2
+}
+
+define <8 x i8> @vget_high8(<16 x i8>* %A) nounwind {
+; CHECK: vget_high8
+; CHECK-NOT: vst
+; CHECK: vmov r0, r1, d17
+	%tmp1 = load <16 x i8>* %A
+        %tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+        ret <8 x i8> %tmp2
+}