define void @test_subvec_memcpy(i8* %f) {
  %a = alloca <4 x float>, align 16
  %a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
  %a.cast2 = bitcast float* %a.gep2 to i8*
  %a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
  %a.cast3 = bitcast float* %a.gep3 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i1 false)
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %f, i8* %a.cast2, i32 8, i1 false)
  ; comment the load and it compiles fine
  %ret = load <4 x float>, <4 x float>* %a, align 16
  ret void
}

declare void @llvm.memcpy.p0i8.p0i8.i32(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i32, i1 immarg)

define void @test_subvec_memcpy(i8* %f) {
  %a.12.f.sroa_cast = bitcast i8* %f to float*
  %a.12.copyload = load float, float* %a.12.f.sroa_cast, align 1
  %a.12.vec.insert = insertelement <4 x float> undef, float %a.12.copyload, i32 3
  %a.8.f.sroa_cast = bitcast i8* %f to <2 x float>*
  %a.8.vec.extract = shufflevector <4 x float> %a.12.vec.insert, <4 x float> poison, <2 x i32> <i32 2, i32 3>
  store <2 x float> %a.8.vec.extract, <2 x float>* %a.8.f.sroa_cast, align 1
  ret void
}