; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc %s -march=amdgcn  -o - | FileCheck %s

target triple = "amdgcn-amd-amdhsa"

define amdgpu_kernel void @my_kernel(i64 %foo, i32 %bar) {
; CHECK-LABEL: my_kernel:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    s_mov_b32 flat_scratch_lo, s13
; CHECK-NEXT:    s_add_i32 s12, s12, s17
; CHECK-NEXT:    s_lshr_b32 flat_scratch_hi, s12, 8
; CHECK-NEXT:    s_load_dword s0, s[8:9], 0x2
; CHECK-NEXT:    s_load_dwordx2 s[2:3], s[8:9], 0x0
; CHECK-NEXT:    s_mov_b64 s[4:5], 1
; CHECK-NEXT:    v_mov_b32_e32 v0, 0
; CHECK-NEXT:    v_mov_b32_e32 v1, 0
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    s_ashr_i32 s6, s0, 31
; CHECK-NEXT:    s_abs_i32 s7, s0
; CHECK-NEXT:    v_cvt_f32_u32_e32 v2, s7
; CHECK-NEXT:    s_sub_i32 s0, 0, s7
; CHECK-NEXT:    v_rcp_iflag_f32_e32 v2, v2
; CHECK-NEXT:    v_mul_f32_e32 v2, 0x4f7ffffe, v2
; CHECK-NEXT:    v_cvt_u32_f32_e32 v2, v2
; CHECK-NEXT:    v_mul_lo_u32 v3, s0, v2
; CHECK-NEXT:    v_mul_hi_u32 v3, v2, v3
; CHECK-NEXT:    v_add_i32_e32 v2, vcc, v2, v3
; CHECK-NEXT:    s_and_b64 s[0:1], exec, -1
; CHECK-NEXT:  .LBB0_1: ; %loop
; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    v_mov_b32_e32 v3, s4
; CHECK-NEXT:    v_mad_u64_u32 v[3:4], s[8:9], s2, v3, 1
; CHECK-NEXT:    s_mul_i32 s4, s3, s4
; CHECK-NEXT:    s_mul_i32 s5, s2, s5
; CHECK-NEXT:    v_add_i32_e32 v4, vcc, s4, v4
; CHECK-NEXT:    v_readfirstlane_b32 s4, v3
; CHECK-NEXT:    v_add_i32_e32 v4, vcc, s5, v4
; CHECK-NEXT:    s_ashr_i32 s5, s4, 31
; CHECK-NEXT:    s_abs_i32 s8, s4
; CHECK-NEXT:    s_xor_b32 s5, s5, s6
; CHECK-NEXT:    v_mul_hi_u32 v3, s8, v2
; CHECK-NEXT:    v_readfirstlane_b32 s9, v3
; CHECK-NEXT:    v_add_i32_e32 v5, vcc, 1, v3
; CHECK-NEXT:    s_mul_i32 s9, s9, s7
; CHECK-NEXT:    s_sub_i32 s8, s8, s9
; CHECK-NEXT:    s_sub_i32 s9, s8, s7
; CHECK-NEXT:    s_cmp_ge_u32 s8, s7
; CHECK-NEXT:    s_cselect_b64 vcc, -1, 0
; CHECK-NEXT:    v_cndmask_b32_e32 v3, v3, v5, vcc
; CHECK-NEXT:    s_cselect_b32 s8, s9, s8
; CHECK-NEXT:    v_add_i32_e32 v5, vcc, 1, v3
; CHECK-NEXT:    s_cmp_ge_u32 s8, s7
; CHECK-NEXT:    s_cselect_b64 vcc, -1, 0
; CHECK-NEXT:    v_cndmask_b32_e32 v3, v3, v5, vcc
; CHECK-NEXT:    v_xor_b32_e32 v3, s5, v3
; CHECK-NEXT:    v_subrev_i32_e32 v3, vcc, s5, v3
; CHECK-NEXT:    v_ashrrev_i32_e32 v5, 31, v3
; CHECK-NEXT:    v_or_b32_e32 v3, s4, v3
; CHECK-NEXT:    v_or_b32_e32 v4, v4, v5
; CHECK-NEXT:    flat_load_dwordx2 v[3:4], v[3:4]
; CHECK-NEXT:    s_waitcnt vmcnt(0)
; CHECK-NEXT:    flat_store_dwordx2 v[0:1], v[3:4]
; CHECK-NEXT:    s_mov_b64 s[4:5], 0
; CHECK-NEXT:    s_mov_b64 vcc, s[0:1]
; CHECK-NEXT:    s_cbranch_vccnz .LBB0_1
; CHECK-NEXT:  ; %bb.2: ; %DummyReturnBlock
; CHECK-NEXT:    s_endpgm
entry:
  br label %loop

loop: ; preds = %entry, %loop
  %i = phi i64 [ 1, %entry ], [ 0, %loop ]
  %mul = mul i64 %foo, %i
  %add = add i64 %mul, 1
  %trunc = trunc i64 %add to i32
  %div = sdiv i32 %trunc, %bar
  %sext = sext i32 %div to i64
  %or = or i64 %add, %sext
  %inttoptr = inttoptr i64 %or to ptr
  %addrspacecast = addrspacecast ptr %inttoptr to ptr addrspace(1)
  %val = load double, ptr addrspace(1) %addrspacecast, align 8
  store double %val, ptr addrspace(1) null, align 8
  br label %loop
}