; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgpu6.00 < %s | FileCheck %s

; Check we can compile this bugpoint-reduced test without an
; infinite loop in TLI.SimplifyDemandedBits() due to failure
; to use return value of TLO.DAG.UpdateNodeOperands()

; Check that code was generated; we know there will be
; a s_endpgm, so check for it.

@0 = external unnamed_addr addrspace(3) global [462 x float], align 4

declare i32 @llvm.amdgcn.workitem.id.y() #0
declare i32 @llvm.amdgcn.workitem.id.x() #0
declare float @llvm.fmuladd.f32(float, float, float) #0

define amdgpu_kernel void @foo(ptr addrspace(1) noalias nocapture readonly %arg, ptr addrspace(1) noalias nocapture readonly %arg1, ptr addrspace(1) noalias nocapture %arg2, float %arg3, i1 %c0, i1 %c1, i1 %c2, i1 %c3, i1 %c4, i1 %c5) local_unnamed_addr "amdgpu-flat-work-group-size"="128,128" !reqd_work_group_size !0 {
; CHECK-LABEL: foo:
; CHECK:       ; %bb.0: ; %bb
; CHECK-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x10
; CHECK-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
; CHECK-NEXT:    s_mov_b32 m0, -1
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    s_bitcmp1_b32 s0, 8
; CHECK-NEXT:    s_cselect_b64 s[8:9], -1, 0
; CHECK-NEXT:    s_bitcmp1_b32 s0, 16
; CHECK-NEXT:    s_cselect_b64 s[2:3], -1, 0
; CHECK-NEXT:    s_xor_b64 s[2:3], s[2:3], -1
; CHECK-NEXT:    s_bitcmp1_b32 s0, 24
; CHECK-NEXT:    s_cselect_b64 s[4:5], -1, 0
; CHECK-NEXT:    s_xor_b64 s[4:5], s[4:5], -1
; CHECK-NEXT:    s_bitcmp1_b32 s1, 0
; CHECK-NEXT:    s_cselect_b64 s[6:7], -1, 0
; CHECK-NEXT:    s_bitcmp1_b32 s1, 8
; CHECK-NEXT:    s_cselect_b64 s[10:11], -1, 0
; CHECK-NEXT:    s_movk_i32 s0, 0x54
; CHECK-NEXT:    v_mad_u32_u24 v0, v1, s0, v0
; CHECK-NEXT:    v_mov_b32_e32 v1, 0
; CHECK-NEXT:    s_and_b64 s[0:1], exec, s[4:5]
; CHECK-NEXT:    s_and_b64 s[2:3], exec, s[2:3]
; CHECK-NEXT:    s_and_b64 s[4:5], exec, s[10:11]
; CHECK-NEXT:    s_and_b64 s[6:7], exec, s[6:7]
; CHECK-NEXT:  .LBB0_1: ; %.loopexit145
; CHECK-NEXT:    ; =>This Loop Header: Depth=1
; CHECK-NEXT:    ; Child Loop BB0_3 Depth 2
; CHECK-NEXT:    ; Child Loop BB0_4 Depth 3
; CHECK-NEXT:    ; Child Loop BB0_5 Depth 2
; CHECK-NEXT:    v_mov_b32_e32 v2, v0
; CHECK-NEXT:    s_branch .LBB0_3
; CHECK-NEXT:  .LBB0_2: ; %.loopexit
; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=2
; CHECK-NEXT:    v_add_i32_e32 v2, vcc, 0x540, v2
; CHECK-NEXT:    s_mov_b64 vcc, s[2:3]
; CHECK-NEXT:    s_cbranch_vccnz .LBB0_5
; CHECK-NEXT:  .LBB0_3: ; %bb13
; CHECK-NEXT:    ; Parent Loop BB0_1 Depth=1
; CHECK-NEXT:    ; => This Loop Header: Depth=2
; CHECK-NEXT:    ; Child Loop BB0_4 Depth 3
; CHECK-NEXT:    s_and_b64 s[10:11], s[8:9], exec
; CHECK-NEXT:    s_cselect_b32 s10, 1, 0
; CHECK-NEXT:    s_cmp_lg_u32 s10, 1
; CHECK-NEXT:    v_mov_b32_e32 v3, v2
; CHECK-NEXT:    s_cbranch_scc1 .LBB0_2
; CHECK-NEXT:  .LBB0_4: ; %bb21
; CHECK-NEXT:    ; Parent Loop BB0_1 Depth=1
; CHECK-NEXT:    ; Parent Loop BB0_3 Depth=2
; CHECK-NEXT:    ; => This Inner Loop Header: Depth=3
; CHECK-NEXT:    ds_write_b32 v3, v1
; CHECK-NEXT:    v_add_i32_e32 v3, vcc, 32, v3
; CHECK-NEXT:    s_mov_b64 vcc, s[0:1]
; CHECK-NEXT:    s_cbranch_vccz .LBB0_4
; CHECK-NEXT:    s_branch .LBB0_2
; CHECK-NEXT:  .LBB0_5: ; %bb31
; CHECK-NEXT:    ; Parent Loop BB0_1 Depth=1
; CHECK-NEXT:    ; => This Inner Loop Header: Depth=2
; CHECK-NEXT:    s_mov_b64 vcc, s[4:5]
; CHECK-NEXT:    s_cbranch_vccz .LBB0_5
; CHECK-NEXT:  ; %bb.6: ; %bb30
; CHECK-NEXT:    ; in Loop: Header=BB0_1 Depth=1
; CHECK-NEXT:    s_mov_b64 vcc, s[6:7]
; CHECK-NEXT:    s_cbranch_vccz .LBB0_1
; CHECK-NEXT:  ; %bb.7: ; %bb11
; CHECK-NEXT:    s_endpgm
bb:
  %tmp = tail call i32 @llvm.amdgcn.workitem.id.y()
  %tmp4 = tail call i32 @llvm.amdgcn.workitem.id.x()
  %tmp5 = and i32 %tmp, 15
  %tmp6 = mul nuw nsw i32 %tmp5, 21
  %tmp7 = sub i32 %tmp6, 0
  %tmp8 = add i32 %tmp7, 0
  %tmp9 = add i32 %tmp8, 0
  br label %bb12

bb11:                                             ; preds = %bb30
  br i1 %c0, label %bb37, label %bb38

bb12:                                             ; preds = %bb30, %bb
  br i1 false, label %.preheader, label %.loopexit145

.loopexit145:                                     ; preds = %.preheader, %bb12
  br label %bb13

bb13:                                             ; preds = %.loopexit, %.loopexit145
  %tmp14 = phi i32 [ %tmp5, %.loopexit145 ], [ %tmp20, %.loopexit ]
  %tmp15 = add nsw i32 %tmp14, -3
  %tmp16 = mul i32 %tmp14, 21
  br i1 %c1, label %bb17, label %.loopexit

bb17:                                             ; preds = %bb13
  %tmp18 = mul i32 %tmp15, 224
  %tmp19 = add i32 0, %tmp18
  br label %bb21

.loopexit:                                        ; preds = %bb21, %bb13
  %tmp20 = add nuw nsw i32 %tmp14, 16
  br i1 %c2, label %bb13, label %bb26

bb21:                                             ; preds = %bb21, %bb17
  %tmp22 = phi i32 [ %tmp4, %bb17 ], [ %tmp25, %bb21 ]
  %tmp23 = add i32 %tmp22, %tmp16
  %tmp24 = getelementptr inbounds float, ptr addrspace(3) @0, i32 %tmp23
  store float 0.0, ptr addrspace(3) %tmp24, align 4
  %tmp25 = add nuw i32 %tmp22, 8
  br i1 %c3, label %bb21, label %.loopexit

bb26:                                             ; preds = %.loopexit
  br label %bb31

.preheader:                                       ; preds = %.preheader, %bb12
  %tmp27 = phi i32 [ %tmp28, %.preheader ], [ poison, %bb12 ]
  %tmp28 = add nuw i32 %tmp27, 128
  %tmp29 = icmp ult i32 %tmp28, 1568
  br i1 %tmp29, label %.preheader, label %.loopexit145

bb30:                                             ; preds = %bb31
  br i1 %c4, label %bb11, label %bb12

bb31:                                             ; preds = %bb31, %bb26
  %tmp32 = phi i32 [ %tmp9, %bb26 ], [ poison, %bb31 ]
  %tmp33 = getelementptr inbounds [462 x float], ptr addrspace(3) @0, i32 0, i32 %tmp32
  %tmp34 = load float, ptr addrspace(3) %tmp33, align 4
  %tmp35 = tail call float @llvm.fmuladd.f32(float %tmp34, float poison, float poison)
  %tmp36 = tail call float @llvm.fmuladd.f32(float poison, float poison, float %tmp35)
  br i1 %c5, label %bb30, label %bb31

bb37:                                             ; preds = %bb11
  br label %bb38

bb38:                                             ; preds = %bb37, %bb11
  ret void
}

attributes #0 = { nounwind readnone speculatable }

!0 = !{i32 8, i32 16, i32 1}