-define void @test(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
- %b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
- %a = load <4 x i32> addrspace(1) * %in
- %b = load <4 x i32> addrspace(1) * %b_ptr
+;EG-LABEL: {{^}}test2:
+;EG: CF_END
+;SI-LABEL: {{^}}test2:
+;SI: s_endpgm
+
+define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
+ %b_ptr = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %in, i32 1
+ %a = load <2 x i32>, <2 x i32> addrspace(1) * %in
+ %b = load <2 x i32>, <2 x i32> addrspace(1) * %b_ptr
+ %result = udiv <2 x i32> %a, %b
+ store <2 x i32> %result, <2 x i32> addrspace(1)* %out
+ ret void
+}
+
+;EG-LABEL: {{^}}test4:
+;EG: CF_END
+;SI-LABEL: {{^}}test4:
+;SI: s_endpgm
+
+define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
+ %b_ptr = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %in, i32 1
+ %a = load <4 x i32>, <4 x i32> addrspace(1) * %in
+ %b = load <4 x i32>, <4 x i32> addrspace(1) * %b_ptr