X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=test%2FCodeGen%2FAMDGPU%2Fmerge-stores.ll;h=62d372a398aa668c56bd0bbbaa5bd1da7a69aa0c;hb=3443ffa83371872bf32c7cf6259ba2bc5a8068b9;hp=dbf9d4481ffb1bb8943d50f6fdf21955d2e8e753;hpb=953c6814730951ad9a286d7991e9c8c481433d45;p=oota-llvm.git diff --git a/test/CodeGen/AMDGPU/merge-stores.ll b/test/CodeGen/AMDGPU/merge-stores.ll index dbf9d4481ff..62d372a398a 100644 --- a/test/CodeGen/AMDGPU/merge-stores.ll +++ b/test/CodeGen/AMDGPU/merge-stores.ll @@ -89,7 +89,11 @@ define void @merge_global_store_2_constants_i32_f32(i32 addrspace(1)* %out) #0 { } ; GCN-LABEL: {{^}}merge_global_store_2_constants_f32_i32: -; GCN: buffer_store_dwordx2 +; SI-DAG: s_mov_b32 [[SLO:s[0-9]+]], 4.0 +; SI-DAG: s_movk_i32 [[SHI:s[0-9]+]], 0x7b{{$}} +; SI-DAG: v_mov_b32_e32 v[[VLO:[0-9]+]], [[SLO]] +; SI-DAG: v_mov_b32_e32 v[[VHI:[0-9]+]], [[SHI]] +; GCN: buffer_store_dwordx2 v{{\[}}[[VLO]]:[[VHI]]{{\]}} define void @merge_global_store_2_constants_f32_i32(float addrspace(1)* %out) #0 { %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1 %out.gep.1.bc = bitcast float addrspace(1)* %out.gep.1 to i32 addrspace(1)* @@ -99,7 +103,11 @@ define void @merge_global_store_2_constants_f32_i32(float addrspace(1)* %out) #0 } ; GCN-LABEL: {{^}}merge_global_store_4_constants_i32: -; GCN: buffer_store_dwordx4 +; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0x14d{{$}} +; GCN-DAG: v_mov_b32_e32 v{{[0-9]+}}, 0x1c8{{$}} +; GCN-DAG: v_mov_b32_e32 v{{[0-9]+}}, 0x7b{{$}} +; GCN-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], 0x4d2{{$}} +; GCN: buffer_store_dwordx4 v{{\[}}[[LO]]:[[HI]]{{\]}} define void @merge_global_store_4_constants_i32(i32 addrspace(1)* %out) #0 { %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2 @@ -113,10 +121,7 @@ define void @merge_global_store_4_constants_i32(i32 addrspace(1)* %out) #0 { } ; GCN-LABEL: {{^}}merge_global_store_4_constants_f32_order: -; XGCN: buffer_store_dwordx4 -; GCN: buffer_store_dword v -; GCN: buffer_store_dword v -; GCN: buffer_store_dwordx2 v +; GCN: buffer_store_dwordx4 define void @merge_global_store_4_constants_f32_order(float addrspace(1)* %out) #0 { %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1 %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2 @@ -129,17 +134,9 @@ define void @merge_global_store_4_constants_f32_order(float addrspace(1)* %out) ret void } -; First store is out of order. Because of order of combines, the -; consecutive store fails because only some of the stores have been -; replaced with integer constant stores, and then won't merge because -; the types are different. - +; First store is out of order. ; GCN-LABEL: {{^}}merge_global_store_4_constants_f32: -; XGCN: buffer_store_dwordx4 -; GCN: buffer_store_dword v -; GCN: buffer_store_dword v -; GCN: buffer_store_dword v -; GCN: buffer_store_dword v +; GCN: buffer_store_dwordx4 define void @merge_global_store_4_constants_f32(float addrspace(1)* %out) #0 { %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1 %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2 @@ -152,6 +149,29 @@ define void @merge_global_store_4_constants_f32(float addrspace(1)* %out) #0 { ret void } +; FIXME: Should be able to merge this +; GCN-LABEL: {{^}}merge_global_store_4_constants_mixed_i32_f32: +; XGCN: buffer_store_dwordx4 +; GCN: buffer_store_dword +; GCN: buffer_store_dword +; GCN: buffer_store_dword +; GCN: buffer_store_dword +; GCN: s_endpgm +define void @merge_global_store_4_constants_mixed_i32_f32(float addrspace(1)* %out) #0 { + %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1 + %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2 + %out.gep.3 = getelementptr float, float addrspace(1)* %out, i32 3 + + %out.gep.1.bc = bitcast float addrspace(1)* %out.gep.1 to i32 addrspace(1)* + %out.gep.3.bc = bitcast float addrspace(1)* %out.gep.3 to i32 addrspace(1)* + + store i32 11, i32 addrspace(1)* %out.gep.1.bc + store float 2.0, float addrspace(1)* %out.gep.2 + store i32 17, i32 addrspace(1)* %out.gep.3.bc + store float 8.0, float addrspace(1)* %out + ret void +} + ; GCN-LABEL: {{^}}merge_global_store_3_constants_i32: ; SI-DAG: buffer_store_dwordx2 ; SI-DAG: buffer_store_dword @@ -500,10 +520,8 @@ define void @merge_local_store_2_constants_i8(i8 addrspace(3)* %out) #0 { } ; GCN-LABEL: {{^}}merge_local_store_2_constants_i32: -; GCN-DAG: s_movk_i32 [[SLO:s[0-9]+]], 0x1c8 -; GCN-DAG: s_movk_i32 [[SHI:s[0-9]+]], 0x7b -; GCN-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], [[SLO]] -; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[SHI]] +; GCN-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], 0x1c8 +; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0x7b ; GCN: ds_write2_b32 v{{[0-9]+}}, v[[LO]], v[[HI]] offset1:1{{$}} define void @merge_local_store_2_constants_i32(i32 addrspace(3)* %out) #0 { %out.gep.1 = getelementptr i32, i32 addrspace(3)* %out, i32 1 @@ -530,6 +548,95 @@ define void @merge_local_store_4_constants_i32(i32 addrspace(3)* %out) #0 { ret void } +; GCN-LABEL: {{^}}merge_global_store_5_constants_i32: +; GCN-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], 9{{$}} +; GCN-DAG: v_mov_b32_e32 v[[HI4:[0-9]+]], -12{{$}} +; GCN: buffer_store_dwordx4 v{{\[}}[[LO]]:[[HI4]]{{\]}} +; GCN: v_mov_b32_e32 v[[HI:[0-9]+]], 11{{$}} +; GCN: buffer_store_dword v[[HI]] +define void @merge_global_store_5_constants_i32(i32 addrspace(1)* %out) { + store i32 9, i32 addrspace(1)* %out, align 4 + %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1 + store i32 12, i32 addrspace(1)* %idx1, align 4 + %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2 + store i32 16, i32 addrspace(1)* %idx2, align 4 + %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3 + store i32 -12, i32 addrspace(1)* %idx3, align 4 + %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4 + store i32 11, i32 addrspace(1)* %idx4, align 4 + ret void +} + +; GCN-LABEL: {{^}}merge_global_store_6_constants_i32: +; GCN: buffer_store_dwordx4 +; GCN: buffer_store_dwordx2 +define void @merge_global_store_6_constants_i32(i32 addrspace(1)* %out) { + store i32 13, i32 addrspace(1)* %out, align 4 + %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1 + store i32 15, i32 addrspace(1)* %idx1, align 4 + %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2 + store i32 62, i32 addrspace(1)* %idx2, align 4 + %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3 + store i32 63, i32 addrspace(1)* %idx3, align 4 + %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4 + store i32 11, i32 addrspace(1)* %idx4, align 4 + %idx5 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 5 + store i32 123, i32 addrspace(1)* %idx5, align 4 + ret void +} + +; GCN-LABEL: {{^}}merge_global_store_7_constants_i32: +; GCN: buffer_store_dwordx4 +; GCN: buffer_store_dwordx2 +; GCN: buffer_store_dword v +define void @merge_global_store_7_constants_i32(i32 addrspace(1)* %out) { + store i32 34, i32 addrspace(1)* %out, align 4 + %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1 + store i32 999, i32 addrspace(1)* %idx1, align 4 + %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2 + store i32 65, i32 addrspace(1)* %idx2, align 4 + %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3 + store i32 33, i32 addrspace(1)* %idx3, align 4 + %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4 + store i32 98, i32 addrspace(1)* %idx4, align 4 + %idx5 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 5 + store i32 91, i32 addrspace(1)* %idx5, align 4 + %idx6 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 6 + store i32 212, i32 addrspace(1)* %idx6, align 4 + ret void +} + +; GCN-LABEL: {{^}}merge_global_store_8_constants_i32: +; XGCN: buffer_store_dwordx4 +; XGCN: buffer_store_dwordx4 + +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +; GCN: buffer_store_dword v +define void @merge_global_store_8_constants_i32(i32 addrspace(1)* %out) { + store i32 34, i32 addrspace(1)* %out, align 4 + %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1 + store i32 999, i32 addrspace(1)* %idx1, align 4 + %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2 + store i32 65, i32 addrspace(1)* %idx2, align 4 + %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3 + store i32 33, i32 addrspace(1)* %idx3, align 4 + %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4 + store i32 98, i32 addrspace(1)* %idx4, align 4 + %idx5 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 5 + store i32 91, i32 addrspace(1)* %idx5, align 4 + %idx6 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 6 + store i32 212, i32 addrspace(1)* %idx6, align 4 + %idx7 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 7 + store i32 999, i32 addrspace(1)* %idx7, align 4 + ret void +} + declare void @llvm.AMDGPU.barrier.local() #1 attributes #0 = { nounwind }