; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck %s ; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck %s declare i32 @llvm.amdgcn.ds.sub.gs.reg.rtn.i32(i32, i32 immarg) declare i64 @llvm.amdgcn.ds.sub.gs.reg.rtn.i64(i32, i32 immarg) define amdgpu_gs void @test_sub_32(i32 %arg) { ; CHECK-LABEL: test_sub_32: ; CHECK: ; %bb.0: ; CHECK-NEXT: ds_sub_gs_reg_rtn v[0:1], v0 offset:16 gds ; CHECK-NEXT: s_waitcnt lgkmcnt(0) ; CHECK-NEXT: s_nop 0 ; CHECK-NEXT: s_endpgm %unused = call i32 @llvm.amdgcn.ds.sub.gs.reg.rtn.i32(i32 %arg, i32 16) ret void } define amdgpu_gs void @test_sub_32_use(i32 %arg, ptr addrspace(1) %out) { ; CHECK-LABEL: test_sub_32_use: ; CHECK: ; %bb.0: ; CHECK-NEXT: ds_sub_gs_reg_rtn v[3:4], v0 offset:16 gds ; CHECK-NEXT: s_waitcnt lgkmcnt(0) ; CHECK-NEXT: global_store_b32 v[1:2], v3, off ; CHECK-NEXT: s_endpgm %res = call i32 @llvm.amdgcn.ds.sub.gs.reg.rtn.i32(i32 %arg, i32 16) store i32 %res, ptr addrspace(1) %out, align 4 ret void } define amdgpu_gs void @test_sub_32_s(i32 inreg %arg, ptr addrspace(1) %out) { ; CHECK-LABEL: test_sub_32_s: ; CHECK: ; %bb.0: ; CHECK-NEXT: v_mov_b32_e32 v2, s0 ; CHECK-NEXT: ds_sub_gs_reg_rtn v[2:3], v2 offset:16 gds ; CHECK-NEXT: s_waitcnt lgkmcnt(0) ; CHECK-NEXT: global_store_b32 v[0:1], v2, off ; CHECK-NEXT: s_endpgm %res = call i32 @llvm.amdgcn.ds.sub.gs.reg.rtn.i32(i32 %arg, i32 16) store i32 %res, ptr addrspace(1) %out, align 4 ret void } define amdgpu_gs void @test_sub_64(i32 %arg) { ; CHECK-LABEL: test_sub_64: ; CHECK: ; %bb.0: ; CHECK-NEXT: ds_sub_gs_reg_rtn v[0:1], v0 offset:32 gds ; CHECK-NEXT: s_waitcnt lgkmcnt(0) ; CHECK-NEXT: s_nop 0 ; CHECK-NEXT: s_endpgm %unused = call i64 @llvm.amdgcn.ds.sub.gs.reg.rtn.i64(i32 %arg, i32 32) ret void } define amdgpu_gs void @test_sub_64_use(i32 %arg, ptr addrspace(1) %out) { ; CHECK-LABEL: test_sub_64_use: ; CHECK: ; %bb.0: ; CHECK-NEXT: ds_sub_gs_reg_rtn v[3:4], v0 offset:32 gds ; CHECK-NEXT: s_waitcnt lgkmcnt(0) ; CHECK-NEXT: global_store_b64 v[1:2], v[3:4], off ; CHECK-NEXT: s_endpgm %res = call i64 @llvm.amdgcn.ds.sub.gs.reg.rtn.i64(i32 %arg, i32 32) store i64 %res, ptr addrspace(1) %out, align 4 ret void } define amdgpu_gs void @test_sub_64_s(i32 inreg %arg, ptr addrspace(1) %out) { ; CHECK-LABEL: test_sub_64_s: ; CHECK: ; %bb.0: ; CHECK-NEXT: v_mov_b32_e32 v2, s0 ; CHECK-NEXT: ds_sub_gs_reg_rtn v[2:3], v2 offset:32 gds ; CHECK-NEXT: s_waitcnt lgkmcnt(0) ; CHECK-NEXT: global_store_b64 v[0:1], v[2:3], off ; CHECK-NEXT: s_endpgm %res = call i64 @llvm.amdgcn.ds.sub.gs.reg.rtn.i64(i32 %arg, i32 32) store i64 %res, ptr addrspace(1) %out, align 8 ret void }