Index: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll +++ llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll @@ -4,9 +4,11 @@ ; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty: ; HSA: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 56 +; HSA: kernarg_segment_alignment = 4 ; MESA: enable_sgpr_kernarg_segment_ptr = 1 ; MESA: kernarg_segment_byte_size = 16 +; MESA: kernarg_segment_alignment = 4 ; GCN: s_load_dword s0, s[4:5], 0x0 define amdgpu_kernel void @kernel_implicitarg_ptr_empty() #0 { @@ -19,9 +21,11 @@ ; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty_0implicit: ; HSA: enable_sgpr_kernarg_segment_ptr = 0 ; HSA: kernarg_segment_byte_size = 0 +; HSA: kernarg_segment_alignment = 4 ; MESA: enable_sgpr_kernarg_segment_ptr = 1 ; MESA: kernarg_segment_byte_size = 16 +; MESA: kernarg_segment_alignment = 4 ; HSA: s_mov_b64 [[NULL:s\[[0-9]+:[0-9]+\]]], 0{{$}} ; HSA: s_load_dword s0, [[NULL]], 0x0 @@ -38,7 +42,10 @@ ; GCN: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 48 +; HSA: kernarg_segment_alignment = 4 + ; MESA: kernarg_segment_byte_size = 16 +; MESA: kernarg_segment_alignment = 4 ; HSA: s_load_dword s0, s[4:5], 0x0 define amdgpu_kernel void @opencl_kernel_implicitarg_ptr_empty() #1 { @@ -52,7 +59,10 @@ ; GCN: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 168 +; HSA: kernarg_segment_alignment = 4 + ; MESA: kernarg_segment_byte_size = 128 +; MESA: kernarg_segment_alignment = 4 ; HSA: s_load_dword s0, s[4:5], 0x1c define amdgpu_kernel void @kernel_implicitarg_ptr([112 x i8]) #0 { @@ -66,7 +76,10 @@ ; GCN: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 160 +; HSA: kernarg_segment_alignment = 4 + ; MESA: kernarg_segment_byte_size = 128 +; MESA: kernarg_segment_alignment = 4 ; HSA: s_load_dword s0, s[4:5], 0x1c define amdgpu_kernel void @opencl_kernel_implicitarg_ptr([112 x i8]) #1 { @@ -103,9 +116,11 @@ ; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty: ; HSA: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 56 +; HSA: kernarg_segment_alignment = 4 ; MESA: enable_sgpr_kernarg_segment_ptr = 1 ; MESA: kernarg_segment_byte_size = 16 +; MESA: kernarg_segment_alignment = 4 ; GCN-NOT: s[4:5] ; GCN-NOT: s4 @@ -119,9 +134,11 @@ ; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty_implicit0: ; HSA: enable_sgpr_kernarg_segment_ptr = 0 ; HSA: kernarg_segment_byte_size = 0 +; HSA: kernarg_segment_alignment = 4 ; MESA: enable_sgpr_kernarg_segment_ptr = 1 ; MESA: kernarg_segment_byte_size = 16 +; MESA: kernarg_segment_alignment = 4 ; HSA: s_mov_b64 s[4:5], 0{{$}} ; MESA-NOT: s[4:5] @@ -136,7 +153,9 @@ ; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func_empty: ; GCN: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 48 +; HSA: kernarg_segment_alignment = 4 ; MESA: kernarg_segment_byte_size = 16 +; MESA: kernarg_segment_alignment = 4 ; GCN-NOT: s[4:5] ; GCN-NOT: s4 ; GCN-NOT: s5 @@ -149,7 +168,9 @@ ; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func: ; GCN: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 168 +; HSA: kernarg_segment_alignment = 4 ; MESA: kernarg_segment_byte_size = 128 +; MESA: kernarg_segment_alignment = 4 ; HSA: s_add_u32 s4, s4, 0x70 ; MESA: s_add_u32 s4, s4, 0x70 @@ -164,7 +185,9 @@ ; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func: ; GCN: enable_sgpr_kernarg_segment_ptr = 1 ; HSA: kernarg_segment_byte_size = 160 +; HSA: kernarg_segment_alignment = 4 ; MESA: kernarg_segment_byte_size = 128 +; MESA: kernarg_segment_alignment = 4 ; GCN: s_add_u32 s4, s4, 0x70 ; GCN: s_addc_u32 s5, s5, 0{{$}} @@ -244,6 +267,57 @@ ret void } + +; HSA-LABEL: Kernels: +; HSA-LABEL: - Name: kernel_implicitarg_ptr_empty +; HSA: CodeProps: +; HSA: KernargSegmentSize: 56 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_implicitarg_ptr_empty_0implicit +; HSA: KernargSegmentSize: 0 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: opencl_kernel_implicitarg_ptr_empty +; HSA: KernargSegmentSize: 48 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_implicitarg_ptr +; HSA: KernargSegmentSize: 168 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: opencl_kernel_implicitarg_ptr +; HSA: KernargSegmentSize: 160 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_call_implicitarg_ptr_func_empty +; HSA: KernargSegmentSize: 56 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_call_implicitarg_ptr_func_empty_implicit0 +; HSA: KernargSegmentSize: 0 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: opencl_kernel_call_implicitarg_ptr_func_empty +; HSA: KernargSegmentSize: 48 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_call_implicitarg_ptr_func +; HSA: KernargSegmentSize: 168 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: opencl_kernel_call_implicitarg_ptr_func +; HSA: KernargSegmentSize: 160 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_call_kernarg_implicitarg_ptr_func +; HSA: KernargSegmentSize: 168 +; HSA: KernargSegmentAlign: 4 + +; HSA-LABEL: - Name: kernel_implicitarg_no_struct_align_padding +; HSA: KernargSegmentSize: 120 +; HSA: KernargSegmentAlign: 64 + declare i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() #2 declare i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr() #2