; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -stop-after=irtranslator %s -o - | FileCheck %s

define amdgpu_vs void @test_f32_inreg(float inreg %arg0) {
  ; CHECK-LABEL: name: test_f32_inreg
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $sgpr2
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
  ; CHECK-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), 0, 0
  ; CHECK-NEXT:   S_ENDPGM 0
  call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg0, float undef, float undef, float undef, i1 false, i1 false) #0
  ret void
}

define amdgpu_vs void @test_f32(float %arg0) {
  ; CHECK-LABEL: name: test_f32
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $vgpr0
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
  ; CHECK-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), 0, 0
  ; CHECK-NEXT:   S_ENDPGM 0
  call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg0, float undef, float undef, float undef, i1 false, i1 false) #0
  ret void
}

define amdgpu_vs void @test_ptr2_inreg(i32 addrspace(4)* inreg %arg0) {
  ; CHECK-LABEL: name: test_ptr2_inreg
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $sgpr2, $sgpr3
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
  ; CHECK-NEXT:   [[MV:%[0-9]+]]:_(p4) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
  ; CHECK-NEXT:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p4) :: (volatile dereferenceable invariant load (s32) from %ir.arg0, addrspace 4)
  ; CHECK-NEXT:   S_ENDPGM 0
  %tmp0 = load volatile i32, i32 addrspace(4)* %arg0
  ret void
}

define amdgpu_vs void @test_sgpr_alignment0(float inreg %arg0, i32 addrspace(4)* inreg %arg1) {
  ; CHECK-LABEL: name: test_sgpr_alignment0
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $sgpr2, $sgpr3, $sgpr4
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr4
  ; CHECK-NEXT:   [[MV:%[0-9]+]]:_(p4) = G_MERGE_VALUES [[COPY1]](s32), [[COPY2]](s32)
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
  ; CHECK-NEXT:   [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p4) :: (volatile dereferenceable invariant load (s32) from %ir.arg1, addrspace 4)
  ; CHECK-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY]](s32), [[DEF]](s32), [[DEF]](s32), [[DEF]](s32), 0, 0
  ; CHECK-NEXT:   S_ENDPGM 0
  %tmp0 = load volatile i32, i32 addrspace(4)* %arg1
  call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg0, float undef, float undef, float undef, i1 false, i1 false) #0
  ret void
}

define amdgpu_vs void @test_order(float inreg %arg0, float inreg %arg1, float %arg2, float %arg3) {
  ; CHECK-LABEL: name: test_order
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK-NEXT:   liveins: $sgpr2, $sgpr3, $vgpr0, $vgpr1
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr0
  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr1
  ; CHECK-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.exp), 32, 15, [[COPY2]](s32), [[COPY]](s32), [[COPY3]](s32), [[COPY1]](s32), 0, 0
  ; CHECK-NEXT:   S_ENDPGM 0
  call void @llvm.amdgcn.exp.f32(i32 32, i32 15, float %arg2, float %arg0, float %arg3, float %arg1, i1 false, i1 false) #0
  ret void
}

define amdgpu_vs <{ i32, i32 }> @ret_struct(i32 inreg %arg0, i32 inreg %arg1) {
  ; CHECK-LABEL: name: ret_struct
  ; CHECK: bb.1.main_body:
  ; CHECK-NEXT:   liveins: $sgpr2, $sgpr3
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr2
  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr3
  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
  ; CHECK-NEXT:   [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[COPY]](s32)
  ; CHECK-NEXT:   $sgpr0 = COPY [[INT]](s32)
  ; CHECK-NEXT:   [[INT1:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[COPY1]](s32)
  ; CHECK-NEXT:   $sgpr1 = COPY [[INT1]](s32)
  ; CHECK-NEXT:   SI_RETURN_TO_EPILOG implicit $sgpr0, implicit $sgpr1
main_body:
  %tmp0 = insertvalue <{ i32, i32 }> undef, i32 %arg0, 0
  %tmp1 = insertvalue <{ i32, i32 }> %tmp0, i32 %arg1, 1
  ret <{ i32, i32 }> %tmp1
}

define amdgpu_vs i32 @non_void_ret() {
  ; CHECK-LABEL: name: non_void_ret
  ; CHECK: bb.1 (%ir-block.0):
  ; CHECK-NEXT:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
  ; CHECK-NEXT:   [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.readfirstlane), [[C]](s32)
  ; CHECK-NEXT:   $sgpr0 = COPY [[INT]](s32)
  ; CHECK-NEXT:   SI_RETURN_TO_EPILOG implicit $sgpr0
  ret i32 0
}

declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1)  #0

attributes #0 = { nounwind }