1;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck -check-prefixes=GCN,VERDE %s 2;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefix=GCN %s 3 4; GCN-LABEL: {{^}}tbuffer_store: 5; GCN: tbuffer_store_format_xyzw v[0:3], off, s[0:3], dfmt:12, nfmt:2, 0 6; GCN: tbuffer_store_format_xyzw v[4:7], off, s[0:3], dfmt:13, nfmt:3, 0 glc 7; GCN: tbuffer_store_format_xyzw v[8:11], off, s[0:3], dfmt:14, nfmt:4, 0 slc 8; GCN: tbuffer_store_format_xyzw v[8:11], off, s[0:3], dfmt:14, nfmt:4, 0 9define amdgpu_ps void @tbuffer_store(<4 x i32> inreg, <4 x float>, <4 x float>, <4 x float>) { 10main_body: 11 %in1 = bitcast <4 x float> %1 to <4 x i32> 12 %in2 = bitcast <4 x float> %2 to <4 x i32> 13 %in3 = bitcast <4 x float> %3 to <4 x i32> 14 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 12, i32 2, i1 0, i1 0) 15 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in2, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 13, i32 3, i1 1, i1 0) 16 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 4, i1 0, i1 1) 17 call void @llvm.amdgcn.tbuffer.store.v4f32(<4 x float> %3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 4, i1 0, i1 0) 18 ret void 19} 20 21; GCN-LABEL: {{^}}tbuffer_store_immoffs: 22; GCN: tbuffer_store_format_xyzw v[0:3], off, s[0:3], dfmt:5, nfmt:7, 0 offset:42 23define amdgpu_ps void @tbuffer_store_immoffs(<4 x i32> inreg, <4 x float>) { 24main_body: 25 %in1 = bitcast <4 x float> %1 to <4 x i32> 26 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 0, i32 42, i32 5, i32 7, i1 0, i1 0) 27 ret void 28} 29 30; GCN-LABEL: {{^}}tbuffer_store_scalar_and_imm_offs: 31; GCN: tbuffer_store_format_xyzw v[0:3], off, s[0:3], dfmt:5, nfmt:7, {{s[0-9]+}} offset:42 32define amdgpu_ps void @tbuffer_store_scalar_and_imm_offs(<4 x i32> inreg, <4 x float> %vdata, i32 inreg %soffset) { 33main_body: 34 %in1 = bitcast <4 x float> %vdata to <4 x i32> 35 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 %soffset, i32 42, i32 5, i32 7, i1 0, i1 0) 36 ret void 37} 38 39; GCN-LABEL: {{^}}buffer_store_idx: 40; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:15, nfmt:2, 0 idxen 41define amdgpu_ps void @buffer_store_idx(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex) { 42main_body: 43 %in1 = bitcast <4 x float> %vdata to <4 x i32> 44 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex, i32 0, i32 0, i32 0, i32 15, i32 2, i1 0, i1 0) 45 ret void 46} 47 48; GCN-LABEL: {{^}}buffer_store_ofs: 49; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:3, nfmt:7, 0 offen 50define amdgpu_ps void @buffer_store_ofs(<4 x i32> inreg, <4 x float> %vdata, i32 %voffset) { 51main_body: 52 %in1 = bitcast <4 x float> %vdata to <4 x i32> 53 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 %voffset, i32 0, i32 0, i32 3, i32 7, i1 0, i1 0) 54 ret void 55} 56 57; GCN-LABEL: {{^}}buffer_store_both: 58; GCN: tbuffer_store_format_xyzw v[0:3], v[4:5], s[0:3], dfmt:6, nfmt:4, 0 idxen offen 59define amdgpu_ps void @buffer_store_both(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex, i32 %voffset) { 60main_body: 61 %in1 = bitcast <4 x float> %vdata to <4 x i32> 62 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex, i32 %voffset, i32 0, i32 0, i32 6, i32 4, i1 0, i1 0) 63 ret void 64} 65 66; Ideally, the register allocator would avoid the wait here 67; 68; GCN-LABEL: {{^}}buffer_store_wait: 69; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:15, nfmt:3, 0 idxen 70; VERDE: s_waitcnt expcnt(0) 71; GCN: buffer_load_format_xyzw v[0:3], v5, s[0:3], 0 idxen 72; GCN: s_waitcnt vmcnt(0) 73; GCN: tbuffer_store_format_xyzw v[0:3], v6, s[0:3], dfmt:16, nfmt:2, 0 idxen 74define amdgpu_ps void @buffer_store_wait(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex.1, i32 %vindex.2, i32 %vindex.3) { 75main_body: 76 %in1 = bitcast <4 x float> %vdata to <4 x i32> 77 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex.1, i32 0, i32 0, i32 0, i32 15, i32 3, i1 0, i1 0) 78 %data = call <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32> %0, i32 %vindex.2, i32 0, i1 0, i1 0) 79 %data.i = bitcast <4 x float> %data to <4 x i32> 80 call void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32> %data.i, <4 x i32> %0, i32 %vindex.3, i32 0, i32 0, i32 0, i32 16, i32 2, i1 0, i1 0) 81 ret void 82} 83 84; GCN-LABEL: {{^}}buffer_store_x1: 85; GCN: tbuffer_store_format_x v0, v1, s[0:3], dfmt:13, nfmt:7, 0 idxen 86define amdgpu_ps void @buffer_store_x1(<4 x i32> inreg %rsrc, float %data, i32 %vindex) { 87main_body: 88 %data.i = bitcast float %data to i32 89 call void @llvm.amdgcn.tbuffer.store.i32(i32 %data.i, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 13, i32 7, i1 0, i1 0) 90 ret void 91} 92 93; GCN-LABEL: {{^}}buffer_store_x2: 94; GCN: tbuffer_store_format_xy v[0:1], v2, s[0:3], dfmt:1, nfmt:2, 0 idxen 95define amdgpu_ps void @buffer_store_x2(<4 x i32> inreg %rsrc, <2 x float> %data, i32 %vindex) { 96main_body: 97 %data.i = bitcast <2 x float> %data to <2 x i32> 98 call void @llvm.amdgcn.tbuffer.store.v2i32(<2 x i32> %data.i, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0, i32 1, i32 2, i1 0, i1 0) 99 ret void 100} 101 102declare void @llvm.amdgcn.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0 103declare void @llvm.amdgcn.tbuffer.store.v2i32(<2 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0 104declare void @llvm.amdgcn.tbuffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0 105declare void @llvm.amdgcn.tbuffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i32, i32, i32, i32, i1, i1) #0 106declare <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32>, i32, i32, i1, i1) #1 107 108attributes #0 = { nounwind } 109attributes #1 = { nounwind readonly } 110 111