Index: llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp =================================================================== --- llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp +++ llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp @@ -538,6 +538,9 @@ OutStreamer->emitRawComment( " WaveLimiterHint : " + Twine(MFI->needsWaveLimiter()), false); + OutStreamer->emitRawComment( + " COMPUTE_PGM_RSRC2:SCRATCH_EN: " + + Twine(G_00B84C_SCRATCH_EN(CurrentProgramInfo.ComputePGMRSrc2)), false); OutStreamer->emitRawComment( " COMPUTE_PGM_RSRC2:USER_SGPR: " + Twine(G_00B84C_USER_SGPR(CurrentProgramInfo.ComputePGMRSrc2)), false); Index: llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll =================================================================== --- llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll +++ llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll @@ -3,7 +3,14 @@ ; Make sure flat_scratch_init is set ; GCN-LABEL: {{^}}stack_object_addrspacecast_in_kernel_no_calls: -; GCN: .amdhsa_user_sgpr_flat_scratch_init 1 +; GCN: s_add_u32 flat_scratch_lo, s4, s7 +; GCN: s_addc_u32 flat_scratch_hi, s5, 0 +; GCN: flat_store_dword +; GCN: .amdhsa_user_sgpr_flat_scratch_init 1 +; GCN: .amdhsa_system_sgpr_private_segment_wavefront_offset +; GCN-NOT: .amdhsa_reserve_flat_scratch +; GCN: COMPUTE_PGM_RSRC2:SCRATCH_EN: 1 +; GCN: COMPUTE_PGM_RSRC2:USER_SGPR: 6 define amdgpu_kernel void @stack_object_addrspacecast_in_kernel_no_calls() { %alloca = alloca i32, addrspace(5) %cast = addrspacecast i32 addrspace(5)* %alloca to i32* @@ -13,7 +20,15 @@ ; TODO: Could optimize out in this case ; GCN-LABEL: {{^}}stack_object_in_kernel_no_calls: -; GCN: .amdhsa_user_sgpr_flat_scratch_init 1 +; GCN: s_add_u32 flat_scratch_lo, s4, s7 +; GCN: s_addc_u32 flat_scratch_hi, s5, 0 +; GCN: buffer_store_dword +; GCN: .amdhsa_user_sgpr_private_segment_buffer 1 +; GCN: .amdhsa_user_sgpr_flat_scratch_init 1 +; GCN: .amdhsa_system_sgpr_private_segment_wavefront_offset 1 +; GCN-NOT: .amdhsa_reserve_flat_scratch +; GCN: COMPUTE_PGM_RSRC2:SCRATCH_EN: 1 +; GCN: COMPUTE_PGM_RSRC2:USER_SGPR: 6 define amdgpu_kernel void @stack_object_in_kernel_no_calls() { %alloca = alloca i32, addrspace(5) store volatile i32 0, i32 addrspace(5)* %alloca @@ -21,7 +36,13 @@ } ; GCN-LABEL: {{^}}kernel_no_calls_no_stack: -; GCN: .amdhsa_user_sgpr_flat_scratch_init 0 +; GCN-NOT: flat_scratch +; GCN: .amdhsa_user_sgpr_private_segment_buffer 1 +; GCN: .amdhsa_user_sgpr_flat_scratch_init 0 +; GCN: .amdhsa_system_sgpr_private_segment_wavefront_offset 0 +; GCN: .amdhsa_reserve_flat_scratch 0 +; GCN: COMPUTE_PGM_RSRC2:SCRATCH_EN: 0 +; GCN: COMPUTE_PGM_RSRC2:USER_SGPR: 4 define amdgpu_kernel void @kernel_no_calls_no_stack() { ret void }