diff options
Diffstat (limited to 'test/CodeGen/R600/si-triv-disjoint-mem-access.ll')
-rw-r--r-- | test/CodeGen/R600/si-triv-disjoint-mem-access.ll | 100 |
1 files changed, 50 insertions, 50 deletions
diff --git a/test/CodeGen/R600/si-triv-disjoint-mem-access.ll b/test/CodeGen/R600/si-triv-disjoint-mem-access.ll index a4475c0..5a6129a 100644 --- a/test/CodeGen/R600/si-triv-disjoint-mem-access.ll +++ b/test/CodeGen/R600/si-triv-disjoint-mem-access.ll @@ -14,14 +14,14 @@ declare void @llvm.AMDGPU.barrier.local() #2 ; CI-NEXT: ds_read_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:8 ; CI: buffer_store_dword define void @reorder_local_load_global_store_local_load(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 { - %ptr0 = load i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 + %ptr0 = load i32 addrspace(3)*, i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 - %ptr1 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 1 - %ptr2 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 2 - %tmp1 = load i32 addrspace(3)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(3)* %ptr1, align 4 store i32 99, i32 addrspace(1)* %gptr, align 4 - %tmp2 = load i32 addrspace(3)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(3)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -34,14 +34,14 @@ define void @reorder_local_load_global_store_local_load(i32 addrspace(1)* %out, ; CI: buffer_store_dword ; CI: ds_read_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:8 define void @no_reorder_local_load_volatile_global_store_local_load(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 { - %ptr0 = load i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 + %ptr0 = load i32 addrspace(3)*, i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 - %ptr1 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 1 - %ptr2 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 2 - %tmp1 = load i32 addrspace(3)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(3)* %ptr1, align 4 store volatile i32 99, i32 addrspace(1)* %gptr, align 4 - %tmp2 = load i32 addrspace(3)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(3)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -54,15 +54,15 @@ define void @no_reorder_local_load_volatile_global_store_local_load(i32 addrspac ; CI: ds_read_b32 {{v[0-9]+}}, {{v[0-9]+}} offset:8 ; CI: buffer_store_dword define void @no_reorder_barrier_local_load_global_store_local_load(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 { - %ptr0 = load i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 + %ptr0 = load i32 addrspace(3)*, i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 - %ptr1 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 1 - %ptr2 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 2 - %tmp1 = load i32 addrspace(3)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(3)* %ptr1, align 4 store i32 99, i32 addrspace(1)* %gptr, align 4 call void @llvm.AMDGPU.barrier.local() #2 - %tmp2 = load i32 addrspace(3)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(3)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -79,14 +79,14 @@ define void @no_reorder_barrier_local_load_global_store_local_load(i32 addrspace ; CI: buffer_load_dword ; CI: buffer_store_dword define void @no_reorder_constant_load_global_store_constant_load(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 { - %ptr0 = load i32 addrspace(2)* addrspace(3)* @stored_constant_ptr, align 8 + %ptr0 = load i32 addrspace(2)*, i32 addrspace(2)* addrspace(3)* @stored_constant_ptr, align 8 - %ptr1 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 1 - %ptr2 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 2 - %tmp1 = load i32 addrspace(2)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(2)* %ptr1, align 4 store i32 99, i32 addrspace(1)* %gptr, align 4 - %tmp2 = load i32 addrspace(2)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(2)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -100,14 +100,14 @@ define void @no_reorder_constant_load_global_store_constant_load(i32 addrspace(1 ; CI: ds_write_b32 ; CI: buffer_store_dword define void @reorder_constant_load_local_store_constant_load(i32 addrspace(1)* %out, i32 addrspace(3)* %lptr) #0 { - %ptr0 = load i32 addrspace(2)* addrspace(3)* @stored_constant_ptr, align 8 + %ptr0 = load i32 addrspace(2)*, i32 addrspace(2)* addrspace(3)* @stored_constant_ptr, align 8 - %ptr1 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 1 - %ptr2 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 2 - %tmp1 = load i32 addrspace(2)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(2)* %ptr1, align 4 store i32 99, i32 addrspace(3)* %lptr, align 4 - %tmp2 = load i32 addrspace(2)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(2)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -122,12 +122,12 @@ define void @reorder_constant_load_local_store_constant_load(i32 addrspace(1)* % ; CI: ds_write_b32 ; CI: buffer_store_dword define void @reorder_smrd_load_local_store_smrd_load(i32 addrspace(1)* %out, i32 addrspace(3)* noalias %lptr, i32 addrspace(2)* %ptr0) #0 { - %ptr1 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 1 - %ptr2 = getelementptr inbounds i32 addrspace(2)* %ptr0, i64 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 2 - %tmp1 = load i32 addrspace(2)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(2)* %ptr1, align 4 store i32 99, i32 addrspace(3)* %lptr, align 4 - %tmp2 = load i32 addrspace(2)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(2)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -141,12 +141,12 @@ define void @reorder_smrd_load_local_store_smrd_load(i32 addrspace(1)* %out, i32 ; CI: ds_write_b32 ; CI: buffer_store_dword define void @reorder_global_load_local_store_global_load(i32 addrspace(1)* %out, i32 addrspace(3)* %lptr, i32 addrspace(1)* %ptr0) #0 { - %ptr1 = getelementptr inbounds i32 addrspace(1)* %ptr0, i64 1 - %ptr2 = getelementptr inbounds i32 addrspace(1)* %ptr0, i64 2 + %ptr1 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i64 1 + %ptr2 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i64 2 - %tmp1 = load i32 addrspace(1)* %ptr1, align 4 + %tmp1 = load i32, i32 addrspace(1)* %ptr1, align 4 store i32 99, i32 addrspace(3)* %lptr, align 4 - %tmp2 = load i32 addrspace(1)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(1)* %ptr2, align 4 %add = add nsw i32 %tmp1, %tmp2 @@ -163,15 +163,15 @@ define void @reorder_global_load_local_store_global_load(i32 addrspace(1)* %out, ; CI: buffer_store_dword ; CI: s_endpgm define void @reorder_local_offsets(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* noalias nocapture readnone %gptr, i32 addrspace(3)* noalias nocapture %ptr0) #0 { - %ptr1 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 3 - %ptr2 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 100 - %ptr3 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 101 + %ptr1 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 3 + %ptr2 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 100 + %ptr3 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 101 store i32 123, i32 addrspace(3)* %ptr1, align 4 - %tmp1 = load i32 addrspace(3)* %ptr2, align 4 - %tmp2 = load i32 addrspace(3)* %ptr3, align 4 + %tmp1 = load i32, i32 addrspace(3)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(3)* %ptr3, align 4 store i32 123, i32 addrspace(3)* %ptr2, align 4 - %tmp3 = load i32 addrspace(3)* %ptr1, align 4 + %tmp3 = load i32, i32 addrspace(3)* %ptr1, align 4 store i32 789, i32 addrspace(3)* %ptr3, align 4 %add.0 = add nsw i32 %tmp2, %tmp1 @@ -189,15 +189,15 @@ define void @reorder_local_offsets(i32 addrspace(1)* nocapture %out, i32 addrspa ; CI: buffer_store_dword ; CI: s_endpgm define void @reorder_global_offsets(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* noalias nocapture readnone %gptr, i32 addrspace(1)* noalias nocapture %ptr0) #0 { - %ptr1 = getelementptr inbounds i32 addrspace(1)* %ptr0, i32 3 - %ptr2 = getelementptr inbounds i32 addrspace(1)* %ptr0, i32 100 - %ptr3 = getelementptr inbounds i32 addrspace(1)* %ptr0, i32 101 + %ptr1 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i32 3 + %ptr2 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i32 100 + %ptr3 = getelementptr inbounds i32, i32 addrspace(1)* %ptr0, i32 101 store i32 123, i32 addrspace(1)* %ptr1, align 4 - %tmp1 = load i32 addrspace(1)* %ptr2, align 4 - %tmp2 = load i32 addrspace(1)* %ptr3, align 4 + %tmp1 = load i32, i32 addrspace(1)* %ptr2, align 4 + %tmp2 = load i32, i32 addrspace(1)* %ptr3, align 4 store i32 123, i32 addrspace(1)* %ptr2, align 4 - %tmp3 = load i32 addrspace(1)* %ptr1, align 4 + %tmp3 = load i32, i32 addrspace(1)* %ptr1, align 4 store i32 789, i32 addrspace(1)* %ptr3, align 4 %add.0 = add nsw i32 %tmp2, %tmp1 @@ -211,19 +211,19 @@ define void @reorder_global_offsets(i32 addrspace(1)* nocapture %out, i32 addrsp ; XCI: TBUFFER_STORE_FORMAT ; XCI: ds_read_b32 {{v[0-9]+}}, {{v[0-9]+}}, 0x8 ; define void @reorder_local_load_tbuffer_store_local_load(i32 addrspace(1)* %out, i32 %a1, i32 %vaddr) #1 { -; %ptr0 = load i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 +; %ptr0 = load i32 addrspace(3)*, i32 addrspace(3)* addrspace(3)* @stored_lds_ptr, align 4 -; %ptr1 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 1 -; %ptr2 = getelementptr inbounds i32 addrspace(3)* %ptr0, i32 2 +; %ptr1 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 1 +; %ptr2 = getelementptr inbounds i32, i32 addrspace(3)* %ptr0, i32 2 -; %tmp1 = load i32 addrspace(3)* %ptr1, align 4 +; %tmp1 = load i32, i32 addrspace(3)* %ptr1, align 4 ; %vdata = insertelement <4 x i32> undef, i32 %a1, i32 0 ; call void @llvm.SI.tbuffer.store.v4i32(<16 x i8> undef, <4 x i32> %vdata, ; i32 4, i32 %vaddr, i32 0, i32 32, i32 14, i32 4, i32 1, i32 0, i32 1, ; i32 1, i32 0) -; %tmp2 = load i32 addrspace(3)* %ptr2, align 4 +; %tmp2 = load i32, i32 addrspace(3)* %ptr2, align 4 ; %add = add nsw i32 %tmp1, %tmp2 |