diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/array-ptr-calc-i32.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/array-ptr-calc-i32.ll | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/array-ptr-calc-i32.ll b/llvm/test/CodeGen/AMDGPU/array-ptr-calc-i32.ll index c1b8792c3d7..8e7f40abc79 100644 --- a/llvm/test/CodeGen/AMDGPU/array-ptr-calc-i32.ll +++ b/llvm/test/CodeGen/AMDGPU/array-ptr-calc-i32.ll @@ -20,12 +20,12 @@ declare void @llvm.amdgcn.s.barrier() #2 ; FIXME: The AMDGPUPromoteAlloca pass should be able to convert this ; alloca to a vector. It currently fails because it does not know how ; to interpret: -; getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 1, i32 %b +; getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 1, i32 %b ; SI-PROMOTE: v_add_i32_e32 [[PTRREG:v[0-9]+]], vcc, 64 ; SI-PROMOTE: ds_write_b32 [[PTRREG]] define amdgpu_kernel void @test_private_array_ptr_calc(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %inA, i32 addrspace(1)* noalias %inB) #0 { - %alloca = alloca [16 x i32], align 16 + %alloca = alloca [16 x i32], align 16, addrspace(5) %mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0); %tid = call i32 @llvm.amdgcn.mbcnt.hi(i32 -1, i32 %mbcnt.lo) %a_ptr = getelementptr inbounds i32, i32 addrspace(1)* %inA, i32 %tid @@ -33,11 +33,11 @@ define amdgpu_kernel void @test_private_array_ptr_calc(i32 addrspace(1)* noalias %a = load i32, i32 addrspace(1)* %a_ptr, !range !0 %b = load i32, i32 addrspace(1)* %b_ptr, !range !0 %result = add i32 %a, %b - %alloca_ptr = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 1, i32 %b - store i32 %result, i32* %alloca_ptr, align 4 + %alloca_ptr = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 1, i32 %b + store i32 %result, i32 addrspace(5)* %alloca_ptr, align 4 ; Dummy call call void @llvm.amdgcn.s.barrier() - %reload = load i32, i32* %alloca_ptr, align 4, !range !0 + %reload = load i32, i32 addrspace(5)* %alloca_ptr, align 4, !range !0 %out_ptr = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 %tid store i32 %reload, i32 addrspace(1)* %out_ptr, align 4 ret void |
