[X86] Add PR40318 shuffle test case

The other test case is already covered by the PR40306 test case, which was mainly concerned with SSSE3 codegen.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@351201 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/CodeGen/X86/vector-shuffle-128-v8.ll b/test/CodeGen/X86/vector-shuffle-128-v8.ll
index fd1098a..9f2a0cc 100644 (file)
--- a/test/CodeGen/X86/vector-shuffle-128-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v8.ll
@@ -2506,6 +2506,38 @@ define <8 x i16> @shuffle_v8i16_9zzzuuuu(<8 x i16> %x) {
   ret <8 x i16> %r
 }
 
+; PR40318
+define <8 x i16> @shuffle_v8i16_2zzzuuuu(<8 x i16> %x) {
+; SSE2-LABEL: shuffle_v8i16_2zzzuuuu:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    pxor %xmm1, %xmm1
+; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[3,1,2,0]
+; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,0,4,5,6,7]
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: shuffle_v8i16_2zzzuuuu:
+; SSSE3:       # %bb.0:
+; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[4,5],zero,zero,zero,zero,zero,zero,xmm0[u,u,u,u,u,u,u,u]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: shuffle_v8i16_2zzzuuuu:
+; SSE41:       # %bb.0:
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
+; SSE41-NEXT:    pmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_2zzzuuuu:
+; AVX:       # %bb.0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
+; AVX-NEXT:    vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
+; AVX-NEXT:    retq
+  %r = shufflevector <8 x i16> %x, <8 x i16> zeroinitializer, <8 x i32> <i32 2, i32 9, i32 10, i32 11, i32 undef, i32 undef, i32 undef, i32 undef>
+  ret <8 x i16> %r
+}
+
 define <8 x i16> @mask_v8i16_012345ef(<8 x i16> %a, <8 x i16> %b) {
 ; SSE2-LABEL: mask_v8i16_012345ef:
 ; SSE2:       # %bb.0: