diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll')
-rw-r--r-- | llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll | 42 |
1 files changed, 21 insertions, 21 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll b/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll index f812f4cf702..97cb9067f29 100644 --- a/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll +++ b/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll @@ -80,7 +80,7 @@ ; NOHSAOPT: call i32 @llvm.amdgcn.workitem.id.x(), !range !0 ; NOHSAOPT: call i32 @llvm.amdgcn.workitem.id.y(), !range !0 ; NOHSAOPT: call i32 @llvm.amdgcn.workitem.id.z(), !range !0 -define void @mova_same_clause(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 { +define amdgpu_kernel void @mova_same_clause(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 { entry: %stack = alloca [5 x i32], align 4 %0 = load i32, i32 addrspace(1)* %in, align 4 @@ -102,7 +102,7 @@ entry: ; OPT-LABEL: @high_alignment( ; OPT: getelementptr inbounds [256 x [8 x i32]], [256 x [8 x i32]] addrspace(3)* @high_alignment.stack, i32 0, i32 %{{[0-9]+}} -define void @high_alignment(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 { +define amdgpu_kernel void @high_alignment(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 { entry: %stack = alloca [8 x i32], align 16 %0 = load i32, i32 addrspace(1)* %in, align 4 @@ -127,7 +127,7 @@ entry: ; OPT: alloca [5 x i32] ; SI-NOT: ds_write -define void @no_replace_inbounds_gep(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 { +define amdgpu_kernel void @no_replace_inbounds_gep(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 { entry: %stack = alloca [5 x i32], align 4 %0 = load i32, i32 addrspace(1)* %in, align 4 @@ -162,7 +162,7 @@ entry: ; SI-NOT: v_movrel %struct.point = type { i32, i32 } -define void @multiple_structs(i32 addrspace(1)* %out) #0 { +define amdgpu_kernel void @multiple_structs(i32 addrspace(1)* %out) #0 { entry: %a = alloca %struct.point %b = alloca %struct.point @@ -191,7 +191,7 @@ entry: ; R600-NOT: MOVA_INT ; SI-NOT: v_movrel -define void @direct_loop(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 { +define amdgpu_kernel void @direct_loop(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 { entry: %prv_array_const = alloca [2 x i32] %prv_array = alloca [2 x i32] @@ -235,7 +235,7 @@ for.end: ; SI-PROMOTE: s_load_dword [[IDX:s[0-9]+]] ; SI-PROMOTE: s_lshl_b32 [[SCALED_IDX:s[0-9]+]], [[IDX]], 16 ; SI-PROMOTE: v_bfe_u32 v{{[0-9]+}}, v{{[0-9]+}}, [[SCALED_IDX]], 16 -define void @short_array(i32 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @short_array(i32 addrspace(1)* %out, i32 %index) #0 { entry: %0 = alloca [2 x i16] %1 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 0 @@ -258,7 +258,7 @@ entry: ; SI-ALLOCA-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding: [0x04,0x00,0x60,0xe0 ; SI-ALLOCA-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:5 ; encoding: [0x05,0x00,0x60,0xe0 -define void @char_array(i32 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @char_array(i32 addrspace(1)* %out, i32 %index) #0 { entry: %0 = alloca [2 x i8] %1 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 0 @@ -281,7 +281,7 @@ entry: ; ; A total of 5 bytes should be allocated and used. ; SI: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; -define void @no_overlap(i32 addrspace(1)* %out, i32 %in) #0 { +define amdgpu_kernel void @no_overlap(i32 addrspace(1)* %out, i32 %in) #0 { entry: %0 = alloca [3 x i8], align 1 %1 = alloca [2 x i8], align 1 @@ -305,7 +305,7 @@ entry: ret void } -define void @char_array_array(i32 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @char_array_array(i32 addrspace(1)* %out, i32 %index) #0 { entry: %alloca = alloca [2 x [2 x i8]] %gep0 = getelementptr [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 0 @@ -319,7 +319,7 @@ entry: ret void } -define void @i32_array_array(i32 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @i32_array_array(i32 addrspace(1)* %out, i32 %index) #0 { entry: %alloca = alloca [2 x [2 x i32]] %gep0 = getelementptr [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 0 @@ -332,7 +332,7 @@ entry: ret void } -define void @i64_array_array(i64 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @i64_array_array(i64 addrspace(1)* %out, i32 %index) #0 { entry: %alloca = alloca [2 x [2 x i64]] %gep0 = getelementptr [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 0 @@ -347,7 +347,7 @@ entry: %struct.pair32 = type { i32, i32 } -define void @struct_array_array(i32 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @struct_array_array(i32 addrspace(1)* %out, i32 %index) #0 { entry: %alloca = alloca [2 x [2 x %struct.pair32]] %gep0 = getelementptr [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 0, i32 1 @@ -360,7 +360,7 @@ entry: ret void } -define void @struct_pair32_array(i32 addrspace(1)* %out, i32 %index) #0 { +define amdgpu_kernel void @struct_pair32_array(i32 addrspace(1)* %out, i32 %index) #0 { entry: %alloca = alloca [2 x %struct.pair32] %gep0 = getelementptr [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 0, i32 1 @@ -373,7 +373,7 @@ entry: ret void } -define void @select_private(i32 addrspace(1)* %out, i32 %in) nounwind { +define amdgpu_kernel void @select_private(i32 addrspace(1)* %out, i32 %in) nounwind { entry: %tmp = alloca [2 x i32] %tmp1 = getelementptr [2 x i32], [2 x i32]* %tmp, i32 0, i32 0 @@ -394,7 +394,7 @@ entry: ; SI-NOT: ds_write ; SI: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ; SI: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen offset:5 ; -define void @ptrtoint(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 { +define amdgpu_kernel void @ptrtoint(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 { %alloca = alloca [16 x i32] %tmp0 = getelementptr [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a store i32 5, i32* %tmp0 @@ -410,7 +410,7 @@ define void @ptrtoint(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 { ; OPT-LABEL: @pointer_typed_alloca( ; OPT: getelementptr inbounds [256 x i32 addrspace(1)*], [256 x i32 addrspace(1)*] addrspace(3)* @pointer_typed_alloca.A.addr, i32 0, i32 %{{[0-9]+}} ; OPT: load i32 addrspace(1)*, i32 addrspace(1)* addrspace(3)* %{{[0-9]+}}, align 4 -define void @pointer_typed_alloca(i32 addrspace(1)* %A) { +define amdgpu_kernel void @pointer_typed_alloca(i32 addrspace(1)* %A) { entry: %A.addr = alloca i32 addrspace(1)*, align 4 store i32 addrspace(1)* %A, i32 addrspace(1)** %A.addr, align 4 @@ -462,7 +462,7 @@ entry: ; SI: buffer_load_dword ; SI: buffer_load_dword -define void @v16i32_stack(<16 x i32> addrspace(1)* %out, i32 %a) { +define amdgpu_kernel void @v16i32_stack(<16 x i32> addrspace(1)* %out, i32 %a) { %alloca = alloca [2 x <16 x i32>] %tmp0 = getelementptr [2 x <16 x i32>], [2 x <16 x i32>]* %alloca, i32 0, i32 %a %tmp5 = load <16 x i32>, <16 x i32>* %tmp0 @@ -506,7 +506,7 @@ define void @v16i32_stack(<16 x i32> addrspace(1)* %out, i32 %a) { ; SI: buffer_load_dword ; SI: buffer_load_dword -define void @v16float_stack(<16 x float> addrspace(1)* %out, i32 %a) { +define amdgpu_kernel void @v16float_stack(<16 x float> addrspace(1)* %out, i32 %a) { %alloca = alloca [2 x <16 x float>] %tmp0 = getelementptr [2 x <16 x float>], [2 x <16 x float>]* %alloca, i32 0, i32 %a %tmp5 = load <16 x float>, <16 x float>* %tmp0 @@ -522,7 +522,7 @@ define void @v16float_stack(<16 x float> addrspace(1)* %out, i32 %a) { ; SI: buffer_load_dword ; SI: buffer_load_dword -define void @v2float_stack(<2 x float> addrspace(1)* %out, i32 %a) { +define amdgpu_kernel void @v2float_stack(<2 x float> addrspace(1)* %out, i32 %a) { %alloca = alloca [16 x <2 x float>] %tmp0 = getelementptr [16 x <2 x float>], [16 x <2 x float>]* %alloca, i32 0, i32 %a %tmp5 = load <2 x float>, <2 x float>* %tmp0 @@ -533,7 +533,7 @@ define void @v2float_stack(<2 x float> addrspace(1)* %out, i32 %a) { ; OPT-LABEL: @direct_alloca_read_0xi32( ; OPT: store [0 x i32] undef, [0 x i32] addrspace(3)* ; OPT: load [0 x i32], [0 x i32] addrspace(3)* -define void @direct_alloca_read_0xi32([0 x i32] addrspace(1)* %out, i32 %index) { +define amdgpu_kernel void @direct_alloca_read_0xi32([0 x i32] addrspace(1)* %out, i32 %index) { entry: %tmp = alloca [0 x i32] store [0 x i32] [], [0 x i32]* %tmp @@ -545,7 +545,7 @@ entry: ; OPT-LABEL: @direct_alloca_read_1xi32( ; OPT: store [1 x i32] zeroinitializer, [1 x i32] addrspace(3)* ; OPT: load [1 x i32], [1 x i32] addrspace(3)* -define void @direct_alloca_read_1xi32([1 x i32] addrspace(1)* %out, i32 %index) { +define amdgpu_kernel void @direct_alloca_read_1xi32([1 x i32] addrspace(1)* %out, i32 %index) { entry: %tmp = alloca [1 x i32] store [1 x i32] [i32 0], [1 x i32]* %tmp |