; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx950 < %s | FileCheck %s

declare void @llvm.amdgcn.sched.barrier(i32 %mask)
declare void @llvm.amdgcn.load.to.lds(ptr %in, ptr addrspace(3) %lds_out, i32 %size, i32 %offset, i32 %aux)

define amdgpu_kernel void @test_waitcnt(ptr addrspace(1) %global_buffer, ptr addrspace(3) %lds_buffer1, ptr addrspace(3) %lds_buffer2) #0 {
; This test checks if SIInsertWaitcnts pass inserts S_WAITCNT VMCNT(0) before DS_READ
; CHECK-LABEL: test_waitcnt:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    s_load_dwordx4 s[0:3], s[4:5], 0x0
; CHECK-NEXT:    v_mov_b32_e32 v0, 0
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    s_add_u32 s4, s0, 64
; CHECK-NEXT:    s_addc_u32 s5, s1, 0
; CHECK-NEXT:    s_mov_b32 m0, s2
; CHECK-NEXT:    s_nop 0
; CHECK-NEXT:    global_load_lds_dword v0, s[4:5] offset:4
; CHECK-NEXT:    s_load_dword s4, s[0:1], 0x0
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    v_mov_b32_e32 v3, s4
; CHECK-NEXT:    global_store_dword v0, v3, s[0:1] offset:64
; CHECK-NEXT:    ; sched_barrier mask(0x00000000)
; CHECK-NEXT:    v_mov_b32_e32 v1, s2
; CHECK-NEXT:    v_mov_b32_e32 v2, s3
; CHECK-NEXT:    ds_write_b32 v1, v3
; CHECK-NEXT:    ds_write_b32 v2, v3
; CHECK-NEXT:    ; sched_barrier mask(0x00000000)
; CHECK-NEXT:    ds_read_b32 v1, v1
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    global_store_dword v0, v1, s[0:1] offset:16
; CHECK-NEXT:    global_store_dword v0, v3, s[0:1] offset:32
; CHECK-NEXT:    s_endpgm
entry:
  ; VMEM accesses with alias.scope
  %vmem_load = load i32, ptr addrspace(1) %global_buffer
  %gepvmem = getelementptr i32, ptr addrspace(1) %global_buffer, i32 16
  store i32 %vmem_load, ptr addrspace(1) %gepvmem, align 4, !alias.scope !0

  ; Global to LDS load
  %gepvmem.ascast = addrspacecast ptr addrspace(1) %gepvmem to ptr
  call void @llvm.amdgcn.load.to.lds(ptr %gepvmem.ascast, ptr addrspace(3) %lds_buffer1, i32 4, i32 4, i32 0), !alias.scope !9, !noalias !14

  ; Insert scheduling barrier
  call void @llvm.amdgcn.sched.barrier(i32 0)

  ; DS_WRITEs with alias.scope and noalias
  store i32 %vmem_load, ptr addrspace(3) %lds_buffer1, align 4, !alias.scope !1, !noalias !12
  store i32 %vmem_load, ptr addrspace(3) %lds_buffer2, align 4, !alias.scope !6, !noalias !13

  ; Insert scheduling barrier
  call void @llvm.amdgcn.sched.barrier(i32 0)

  ; DS_READ with alias.scope missing
  %lds_load = load i32, ptr addrspace(3) %lds_buffer1, align 4, !noalias !12

  ; VMEM write
  %gep = getelementptr i32, ptr addrspace(1) %global_buffer, i32 4
  %gep2 = getelementptr i32, ptr addrspace(1) %global_buffer, i32 8
  store i32 %lds_load, ptr addrspace(1) %gep, align 4, !alias.scope !0
  store i32 %vmem_load, ptr addrspace(1) %gep2, align 4, !alias.scope !0

  ret void
}

; VMEM alias domain and scope
!5 = !{!"vmem.domain"}
!4 = !{!"vmem.scope", !5}
!0 = !{!4}

; LDS alias domains and scopes
!3 = !{!"lds1.domain"}
!2 = !{!"lds1.scope", !3}
!1 = !{!2}

!8 = !{!"lds2.domain"}
!7 = !{!"lds2.scope", !8}
!6 = !{!7}

!11 = !{!"lds1_off4.domain"}
!10 = !{!"lds1_off4.scope", !11}
!9 = !{!10}

; Noalias lists
!12 = !{!7, !10}
!13 = !{!2, !10}
!14 = !{!2, !7}

attributes #0 = { nounwind }