From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Mon, 3 Oct 2016 12:16:39 +0000 (+0000)
Subject: [X86][SSE] Add PR30371 (shuffle constant folding) test case
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=d89ff9a37ef34c773011bc6113b36a1f6db2807c;p=llvm

[X86][SSE] Add PR30371 (shuffle constant folding) test case

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@283103 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/test/CodeGen/X86/vector-shuffle-combining.ll b/test/CodeGen/X86/vector-shuffle-combining.ll
index 12ce9a2b1df..a99e09870e5 100644
--- a/test/CodeGen/X86/vector-shuffle-combining.ll
+++ b/test/CodeGen/X86/vector-shuffle-combining.ll
@@ -2835,6 +2835,46 @@ define void @combine_scalar_load_with_blend_with_zero(double* %a0, <4 x float>*
   ret void
 }
 
+; PR30371
+define <4 x float> @combine_constant_insertion(float %f) {
+; SSE2-LABEL: combine_constant_insertion:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; SSE2-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; SSE2-NEXT:    unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; SSE2-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSE2-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: combine_constant_insertion:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; SSSE3-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; SSSE3-NEXT:    unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; SSSE3-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; SSSE3-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: combine_constant_insertion:
+; SSE41:       # BB#0:
+; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
+; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
+; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: combine_constant_insertion:
+; AVX:       # BB#0:
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
+; AVX-NEXT:    retq
+  %a0 = insertelement <4 x float> undef, float %f, i32 0
+  %ret = shufflevector <4 x float> %a0, <4 x float> <float undef, float 4.0, float 5.0, float 3.0>, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
+  ret <4 x float> %ret
+}
+
 define <4 x float> @PR22377(<4 x float> %a, <4 x float> %b) {
 ; SSE-LABEL: PR22377:
 ; SSE:       # BB#0: # %entry