Fixed PR20411 - bug in getINSERTPS()

When we had a vector_shuffle where we had an input from each vector, we
could miscompile it because we were assuming the input from V2 wouldn't
be moved from where it was on the vector.

Added a test case.

llvm-svn: 213826

1 files changed, 18 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/sse41.ll b/llvm/test/CodeGen/X86/sse41.ll
index 6726a3ea9ff..986488f531e 100644
--- a/llvm/test/CodeGen/X86/sse41.ll
+++ b/llvm/test/CodeGen/X86/sse41.ll
@@ -714,3 +714,21 @@ define <4 x float> @pr20087(<4 x float> %a, <4 x float> *%ptr) {
   %ret = shufflevector <4 x float> %load, <4 x float> %a, <4 x i32> <i32 4, i32 undef, i32 6, i32 2>
   ret <4 x float> %ret
 }
+
+; Edge case for insertps where we end up with a shuffle with mask=<0, 7, -1, -1>
+define void @insertps_pr20411(i32* noalias nocapture %RET) #1 {
+; CHECK-LABEL: insertps_pr20411:
+; CHECK: movaps  {{[^,]*}}, %[[REG1:xmm.]]
+; CHECK: pshufd  {{.*}} ## [[REG2:xmm.]] = mem[3,0,0,0]
+; CHECK: insertps  {{.*}} ## xmm1 = [[REG2]][0],[[REG1]][3]{{.*}}
+
+  %gather_load = shufflevector <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, <8 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  %shuffle109 = shufflevector <4 x i32> <i32 4, i32 5, i32 6, i32 7>, <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>  ; 4 5 6 7
+
+  %shuffle116 = shufflevector <8 x i32> %gather_load, <8 x i32> undef, <4 x i32> <i32 3, i32 undef, i32 undef, i32 undef> ; 3 x x x
+  %shuffle117 = shufflevector <4 x i32> %shuffle109, <4 x i32> %shuffle116, <4 x i32> <i32 4, i32 3, i32 undef, i32 undef> ; 3 7 x x
+
+  %ptrcast = bitcast i32* %RET to <4 x i32>*
+  store <4 x i32> %shuffle117, <4 x i32>* %ptrcast, align 4
+  ret void
+}