# RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -run-pass machine-scheduler -o - %s | FileCheck -check-prefix=GCN %s

# GCN-LABEL: name: flat_load_clustering
# GCN:      FLAT_LOAD_DWORD
# GCN-NEXT: FLAT_LOAD_DWORD
--- |
  define amdgpu_kernel void @flat_load_clustering(i32 addrspace(1)* nocapture %arg, i32 addrspace(4)* nocapture readonly %arg1) {
  bb:
    %tid = tail call i32 @llvm.amdgcn.workitem.id.x()
    %idxprom = sext i32 %tid to i64
    %gep1 = getelementptr inbounds i32, i32 addrspace(4)* %arg1, i64 %idxprom
    %load1 = load i32, i32 addrspace(4)* %gep1, align 4
    %gep2 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i64 %idxprom
    %gep34 = getelementptr inbounds i32, i32 addrspace(4)* %gep1, i64 4
    %load2 = load i32, i32 addrspace(4)* %gep34, align 4
    %gep4 = getelementptr inbounds i32, i32 addrspace(1)* %gep2, i64 4
    store i32 %load1, i32 addrspace(1)* %gep2, align 4
    store i32 %load2, i32 addrspace(1)* %gep4, align 4
    ret void
  }

  declare i32 @llvm.amdgcn.workitem.id.x()

...
---
name:            flat_load_clustering
alignment:       1
exposesReturnsTwice: false
legalized:       false
regBankSelected: false
selected:        false
tracksRegLiveness: true
registers:
  - { id: 0, class: vgpr_32 }
  - { id: 1, class: sgpr_64 }
  - { id: 2, class: vgpr_32 }
  - { id: 3, class: sreg_64_xexec }
  - { id: 4, class: sreg_64_xexec }
  - { id: 5, class: vgpr_32 }
  - { id: 6, class: vgpr_32 }
  - { id: 7, class: vgpr_32 }
  - { id: 8, class: vgpr_32 }
  - { id: 9, class: vreg_64 }
  - { id: 10, class: vreg_64 }
  - { id: 11, class: vgpr_32 }
  - { id: 12, class: vreg_64 }
  - { id: 13, class: vreg_64 }
liveins:
  - { reg: '$vgpr0', virtual-reg: '%0' }
  - { reg: '$sgpr4_sgpr5', virtual-reg: '%1' }
body:             |
  bb.0.bb:
    liveins: $vgpr0, $sgpr4_sgpr5

    %1 = COPY $sgpr4_sgpr5
    %0 = COPY $vgpr0
    %3 = S_LOAD_DWORDX2_IMM %1, 0, 0 :: (non-temporal dereferenceable invariant load (s64) from `i64 addrspace(4)* undef`)
    %4 = S_LOAD_DWORDX2_IMM %1, 8, 0 :: (non-temporal dereferenceable invariant load (s64) from `i64 addrspace(4)* undef`)
    %7 = V_LSHLREV_B32_e32 2, %0, implicit $exec
    %2 = V_MOV_B32_e32 0, implicit $exec
    undef %12.sub0 = V_ADD_CO_U32_e32 %4.sub0, %7, implicit-def $vcc, implicit $exec
    %11 = COPY %4.sub1
    %12.sub1 = V_ADDC_U32_e32 %11, %2, implicit-def dead $vcc, implicit killed $vcc, implicit $exec
    %5 = FLAT_LOAD_DWORD %12, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %ir.gep1)
    undef %9.sub0 = V_ADD_CO_U32_e32 %3.sub0, %7, implicit-def $vcc, implicit $exec
    %8 = COPY %3.sub1
    %9.sub1 = V_ADDC_U32_e32 %8, %2, implicit-def dead $vcc, implicit killed $vcc, implicit $exec
    undef %13.sub0 = V_ADD_CO_U32_e32 16, %12.sub0, implicit-def $vcc, implicit $exec
    %13.sub1 = V_ADDC_U32_e32 %12.sub1, %2, implicit-def dead $vcc, implicit killed $vcc, implicit $exec
    %6 = FLAT_LOAD_DWORD %13, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %ir.gep34)
    undef %10.sub0 = V_ADD_CO_U32_e32 16, %9.sub0, implicit-def $vcc, implicit $exec
    %10.sub1 = V_ADDC_U32_e32 %9.sub1, %2, implicit-def dead $vcc, implicit killed $vcc, implicit $exec
    FLAT_STORE_DWORD %9, %5, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %ir.gep2)
    FLAT_STORE_DWORD %10, %6, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %ir.gep4)
    S_ENDPGM 0

...