1 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN %s
2 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
4 declare float @llvm.amdgcn.div.fixup.f32(float, float, float) nounwind readnone
5 declare double @llvm.amdgcn.div.fixup.f64(double, double, double) nounwind readnone
7 ; GCN-LABEL: {{^}}test_div_fixup_f32:
8 ; SI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x13
9 ; SI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x1c
10 ; SI-DAG: s_load_dword [[SC:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x25
12 ; VI-DAG: s_load_dword [[SA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x4c
13 ; VI-DAG: s_load_dword [[SB:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x70
14 ; VI-DAG: s_load_dword [[SC:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x94
16 ; GCN-DAG: v_mov_b32_e32 [[VC:v[0-9]+]], [[SC]]
17 ; GCN-DAG: v_mov_b32_e32 [[VB:v[0-9]+]], [[SB]]
18 ; GCN: v_div_fixup_f32 [[RESULT:v[0-9]+]], [[SA]], [[VB]], [[VC]]
19 ; GCN: buffer_store_dword [[RESULT]],
21 define amdgpu_kernel void @test_div_fixup_f32(float addrspace(1)* %out, [8 x i32], float %a, [8 x i32], float %b, [8 x i32], float %c) nounwind {
22 %result = call float @llvm.amdgcn.div.fixup.f32(float %a, float %b, float %c) nounwind readnone
23 store float %result, float addrspace(1)* %out, align 4
27 ; GCN-LABEL: {{^}}test_div_fixup_f64:
28 ; GCN: v_div_fixup_f64
29 define amdgpu_kernel void @test_div_fixup_f64(double addrspace(1)* %out, double %a, double %b, double %c) nounwind {
30 %result = call double @llvm.amdgcn.div.fixup.f64(double %a, double %b, double %c) nounwind readnone
31 store double %result, double addrspace(1)* %out, align 8