1; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
2; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX81 %s
3; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX9 %s
4
5
6; GCN-LABEL: {{^}}tbuffer_store_d16_x:
7; GCN: s_load_dword s[[S_LO:[0-9]+]]
8; GCN: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]]
9; GCN: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
10define amdgpu_kernel void @tbuffer_store_d16_x(<4 x i32> %rsrc, [8 x i32], half %data, [8 x i32], i32 %vindex) {
11main_body:
12  call void @llvm.amdgcn.tbuffer.store.f16(half %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0)
13  ret void
14}
15
16; GCN-LABEL: {{^}}tbuffer_store_d16_xy:
17; GCN: s_load_dword [[S_DATA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x10
18; UNPACKED-DAG: s_lshr_b32 [[SHR:s[0-9]+]], [[S_DATA]], 16
19; UNPACKED-DAG: s_and_b32 [[MASKED:s[0-9]+]], [[S_DATA]], 0xffff{{$}}
20; UNPACKED-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], [[MASKED]]
21; UNPACKED-DAG: v_mov_b32_e32 v[[V_HI:[0-9]+]], [[SHR]]
22; UNPACKED: tbuffer_store_format_d16_xy v{{\[}}[[V_LO]]:[[V_HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
23
24; PACKED: tbuffer_store_format_d16_xy v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
25define amdgpu_kernel void @tbuffer_store_d16_xy(<4 x i32> %rsrc, <2 x half> %data, i32 %vindex) {
26main_body:
27  call void @llvm.amdgcn.tbuffer.store.v2f16(<2 x half> %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0)
28  ret void
29}
30
31; GCN-LABEL: {{^}}tbuffer_store_d16_xyzw:
32; GCN-DAG: s_load_dwordx2 s{{\[}}[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]{{\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x10
33
34; UNPACKED-DAG: s_mov_b32 [[K:s[0-9]+]], 0xffff{{$}}
35; UNPACKED-DAG: s_lshr_b32 [[SHR0:s[0-9]+]], s[[S_DATA_0]], 16
36; UNPACKED-DAG: s_and_b32 [[MASKED0:s[0-9]+]], s[[S_DATA_0]], [[K]]
37; UNPACKED-DAG: s_lshr_b32 [[SHR1:s[0-9]+]], s[[S_DATA_1]], 16
38; UNPACKED-DAG: s_and_b32 [[MASKED1:s[0-9]+]], s[[S_DATA_1]], [[K]]
39
40; UNPACKED-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], [[MASKED0]]
41; UNPACKED-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[SHR1]]
42; UNPACKED: tbuffer_store_format_d16_xyzw v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
43
44; PACKED-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s[[S_DATA_0]]
45; PACKED-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], s[[S_DATA_1]]
46; PACKED: tbuffer_store_format_d16_xyzw v{{\[}}[[LO]]:[[HI]]{{\]}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}],  dfmt:1,  nfmt:2, 0 idxen
47define amdgpu_kernel void @tbuffer_store_d16_xyzw(<4 x i32> %rsrc, <4 x half> %data, i32 %vindex) {
48main_body:
49  call void @llvm.amdgcn.tbuffer.store.v4f16(<4 x half> %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0)
50  ret void
51}
52
53declare void @llvm.amdgcn.tbuffer.store.f16(half, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
54declare void @llvm.amdgcn.tbuffer.store.v2f16(<2 x half>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
55declare void @llvm.amdgcn.tbuffer.store.v4f16(<4 x half>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1)
56