| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc -march=amdgcn -mcpu=gfx90a -O3 < %s | FileCheck %s |
| |
| declare double @llvm.amdgcn.flat.atomic.fadd.f64.p0f64.f64(double* nocapture, double) #8 |
| |
| define protected amdgpu_kernel void @IllegalGEPConst(i32 %a, double addrspace(1)* %b, double %c) { |
| ; CHECK-LABEL: IllegalGEPConst: |
| ; CHECK: ; %bb.0: ; %entry |
| ; CHECK-NEXT: s_load_dword s2, s[0:1], 0x24 |
| ; CHECK-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x2c |
| ; CHECK-NEXT: s_waitcnt lgkmcnt(0) |
| ; CHECK-NEXT: s_ashr_i32 s3, s2, 31 |
| ; CHECK-NEXT: s_lshl_b64 s[0:1], s[2:3], 3 |
| ; CHECK-NEXT: s_add_u32 s0, s4, s0 |
| ; CHECK-NEXT: s_addc_u32 s1, s5, s1 |
| ; CHECK-NEXT: v_mov_b32_e32 v0, s6 |
| ; CHECK-NEXT: v_mov_b32_e32 v1, s7 |
| ; CHECK-NEXT: v_pk_mov_b32 v[2:3], s[0:1], s[0:1] op_sel:[0,1] |
| ; CHECK-NEXT: flat_atomic_add_f64 v[2:3], v[0:1] offset:65528 |
| ; CHECK-NEXT: s_endpgm |
| entry: |
| %i = add nsw i32 %a, -1 |
| %i.2 = sext i32 %i to i64 |
| %i.3 = getelementptr inbounds double, double addrspace(1)* %b, i64 %i.2 |
| %i.4 = addrspacecast double addrspace(1)* %i.3 to double* |
| %i.5 = tail call contract double @llvm.amdgcn.flat.atomic.fadd.f64.p0f64.f64(double* %i.4, double %c) #8 |
| ret void |
| } |
| |
| attributes #8 = { argmemonly mustprogress nounwind willreturn "target-cpu"="gfx90a" } |