# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=aarch64 -run-pass=aarch64-prelegalizer-combiner -verify-machineinstrs %s -o - | FileCheck %s
--- |
  target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
  target triple = "arm64-apple-darwin"

  define void @test_memcpy1(i32* nocapture %dst, i32* nocapture readonly %src, i64 %len) local_unnamed_addr #0 {
  entry:
    %0 = bitcast i32* %dst to i8*
    %1 = bitcast i32* %src to i8*
    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 %len, i1 false)
    ret void
  }

  declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1 immarg) #1

  define void @test_memcpy2_const(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #0 {
  entry:
    %0 = bitcast i32* %dst to i8*
    %1 = bitcast i32* %src to i8*
    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 72, i1 false)
    ret void
  }

  define void @test_memcpy2_const_optsize(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #2 {
  entry:
    %0 = bitcast i32* %dst to i8*
    %1 = bitcast i32* %src to i8*
    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 72, i1 false)
    ret void
  }

  define void @test_memcpy2_const_minsize(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #3 {
  entry:
    %0 = bitcast i32* %dst to i8*
    %1 = bitcast i32* %src to i8*
    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 72, i1 false)
    ret void
  }

  define void @test_memcpy3_const_arrays_unaligned(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #0 {
  entry:
    %0 = bitcast i32* %dst to i8*
    %1 = bitcast i32* %src to i8*
    tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 143, i1 false)
    ret void
  }

  attributes #0 = { nounwind ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "frame-pointer"="all" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="cyclone" "target-features"="+aes,+crypto,+fp-armv8,+neon,+sha2,+zcm,+zcz" "unsafe-fp-math"="false" "use-soft-float"="false" }
  attributes #1 = { argmemonly nounwind }
  attributes #2 = { optsize }
  attributes #3 = { minsize }

...
---
name:            test_memcpy1
alignment:       4
tracksRegLiveness: true
registers:
  - { id: 0, class: _ }
  - { id: 1, class: _ }
  - { id: 2, class: _ }
machineFunctionInfo: {}
body:             |
  bb.1.entry:
    liveins: $x0, $x1, $x2

    ; CHECK-LABEL: name: test_memcpy1
    ; CHECK: liveins: $x0, $x1, $x2
    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
    ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $x2
    ; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), [[COPY]](p0), [[COPY1]](p0), [[COPY2]](s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    ; CHECK: RET_ReallyLR
    %0:_(p0) = COPY $x0
    %1:_(p0) = COPY $x1
    %2:_(s64) = COPY $x2
    G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    RET_ReallyLR

...
---
name:            test_memcpy2_const
alignment:       4
tracksRegLiveness: true
registers:
  - { id: 0, class: _ }
  - { id: 1, class: _ }
  - { id: 2, class: _ }
machineFunctionInfo: {}
body:             |
  bb.1.entry:
    liveins: $x0, $x1

    ; CHECK-LABEL: name: test_memcpy2_const
    ; CHECK: liveins: $x0, $x1
    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
    ; CHECK: [[LOAD:%[0-9]+]]:_(s128) = G_LOAD [[COPY1]](p0) :: (load 16 from %ir.1, align 4)
    ; CHECK: G_STORE [[LOAD]](s128), [[COPY]](p0) :: (store 16 into %ir.0, align 4)
    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C]](s64)
    ; CHECK: [[LOAD1:%[0-9]+]]:_(s128) = G_LOAD [[GEP]](p0) :: (load 16 from %ir.1 + 16, align 4)
    ; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C]](s64)
    ; CHECK: G_STORE [[LOAD1]](s128), [[GEP1]](p0) :: (store 16 into %ir.0 + 16, align 4)
    ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
    ; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C1]](s64)
    ; CHECK: [[LOAD2:%[0-9]+]]:_(s128) = G_LOAD [[GEP2]](p0) :: (load 16 from %ir.1 + 32, align 4)
    ; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C1]](s64)
    ; CHECK: G_STORE [[LOAD2]](s128), [[GEP3]](p0) :: (store 16 into %ir.0 + 32, align 4)
    ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
    ; CHECK: [[GEP4:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C2]](s64)
    ; CHECK: [[LOAD3:%[0-9]+]]:_(s128) = G_LOAD [[GEP4]](p0) :: (load 16 from %ir.1 + 48, align 4)
    ; CHECK: [[GEP5:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C2]](s64)
    ; CHECK: G_STORE [[LOAD3]](s128), [[GEP5]](p0) :: (store 16 into %ir.0 + 48, align 4)
    ; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
    ; CHECK: [[GEP6:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C3]](s64)
    ; CHECK: [[LOAD4:%[0-9]+]]:_(s64) = G_LOAD [[GEP6]](p0) :: (load 8 from %ir.1 + 64, align 4)
    ; CHECK: [[GEP7:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
    ; CHECK: G_STORE [[LOAD4]](s64), [[GEP7]](p0) :: (store 8 into %ir.0 + 64, align 4)
    ; CHECK: RET_ReallyLR
    %0:_(p0) = COPY $x0
    %1:_(p0) = COPY $x1
    %2:_(s64) = G_CONSTANT i64 72
    G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    RET_ReallyLR

...
---
name:            test_memcpy2_const_optsize
alignment:       4
tracksRegLiveness: true
registers:
  - { id: 0, class: _ }
  - { id: 1, class: _ }
  - { id: 2, class: _ }
machineFunctionInfo: {}
body:             |
  bb.1.entry:
    liveins: $x0, $x1

    ; CHECK-LABEL: name: test_memcpy2_const_optsize
    ; CHECK: liveins: $x0, $x1
    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
    ; CHECK: [[LOAD:%[0-9]+]]:_(s128) = G_LOAD [[COPY1]](p0) :: (load 16 from %ir.1, align 4)
    ; CHECK: G_STORE [[LOAD]](s128), [[COPY]](p0) :: (store 16 into %ir.0, align 4)
    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C]](s64)
    ; CHECK: [[LOAD1:%[0-9]+]]:_(s128) = G_LOAD [[GEP]](p0) :: (load 16 from %ir.1 + 16, align 4)
    ; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C]](s64)
    ; CHECK: G_STORE [[LOAD1]](s128), [[GEP1]](p0) :: (store 16 into %ir.0 + 16, align 4)
    ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
    ; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C1]](s64)
    ; CHECK: [[LOAD2:%[0-9]+]]:_(s128) = G_LOAD [[GEP2]](p0) :: (load 16 from %ir.1 + 32, align 4)
    ; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C1]](s64)
    ; CHECK: G_STORE [[LOAD2]](s128), [[GEP3]](p0) :: (store 16 into %ir.0 + 32, align 4)
    ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
    ; CHECK: [[GEP4:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C2]](s64)
    ; CHECK: [[LOAD3:%[0-9]+]]:_(s128) = G_LOAD [[GEP4]](p0) :: (load 16 from %ir.1 + 48, align 4)
    ; CHECK: [[GEP5:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C2]](s64)
    ; CHECK: G_STORE [[LOAD3]](s128), [[GEP5]](p0) :: (store 16 into %ir.0 + 48, align 4)
    ; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
    ; CHECK: [[GEP6:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C3]](s64)
    ; CHECK: [[LOAD4:%[0-9]+]]:_(s64) = G_LOAD [[GEP6]](p0) :: (load 8 from %ir.1 + 64, align 4)
    ; CHECK: [[GEP7:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
    ; CHECK: G_STORE [[LOAD4]](s64), [[GEP7]](p0) :: (store 8 into %ir.0 + 64, align 4)
    ; CHECK: RET_ReallyLR
    %0:_(p0) = COPY $x0
    %1:_(p0) = COPY $x1
    %2:_(s64) = G_CONSTANT i64 72
    G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    RET_ReallyLR

...
---
name:            test_memcpy2_const_minsize
alignment:       4
tracksRegLiveness: true
registers:
  - { id: 0, class: _ }
  - { id: 1, class: _ }
  - { id: 2, class: _ }
machineFunctionInfo: {}
body:             |
  bb.1.entry:
    liveins: $x0, $x1

    ; CHECK-LABEL: name: test_memcpy2_const_minsize
    ; CHECK: liveins: $x0, $x1
    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 72
    ; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), [[COPY]](p0), [[COPY1]](p0), [[C]](s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    ; CHECK: RET_ReallyLR
    %0:_(p0) = COPY $x0
    %1:_(p0) = COPY $x1
    %2:_(s64) = G_CONSTANT i64 72
    G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    RET_ReallyLR

...
---
name:            test_memcpy3_const_arrays_unaligned
alignment:       4
tracksRegLiveness: true
registers:
  - { id: 0, class: _ }
  - { id: 1, class: _ }
  - { id: 2, class: _ }
machineFunctionInfo: {}
body:             |
  bb.1.entry:
    liveins: $x0, $x1

    ; CHECK-LABEL: name: test_memcpy3_const_arrays_unaligned
    ; CHECK: liveins: $x0, $x1
    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
    ; CHECK: [[LOAD:%[0-9]+]]:_(s128) = G_LOAD [[COPY1]](p0) :: (load 16 from %ir.1, align 4)
    ; CHECK: G_STORE [[LOAD]](s128), [[COPY]](p0) :: (store 16 into %ir.0, align 4)
    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
    ; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C]](s64)
    ; CHECK: [[LOAD1:%[0-9]+]]:_(s128) = G_LOAD [[GEP]](p0) :: (load 16 from %ir.1 + 16, align 4)
    ; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C]](s64)
    ; CHECK: G_STORE [[LOAD1]](s128), [[GEP1]](p0) :: (store 16 into %ir.0 + 16, align 4)
    ; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
    ; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C1]](s64)
    ; CHECK: [[LOAD2:%[0-9]+]]:_(s128) = G_LOAD [[GEP2]](p0) :: (load 16 from %ir.1 + 32, align 4)
    ; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C1]](s64)
    ; CHECK: G_STORE [[LOAD2]](s128), [[GEP3]](p0) :: (store 16 into %ir.0 + 32, align 4)
    ; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
    ; CHECK: [[GEP4:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C2]](s64)
    ; CHECK: [[LOAD3:%[0-9]+]]:_(s128) = G_LOAD [[GEP4]](p0) :: (load 16 from %ir.1 + 48, align 4)
    ; CHECK: [[GEP5:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C2]](s64)
    ; CHECK: G_STORE [[LOAD3]](s128), [[GEP5]](p0) :: (store 16 into %ir.0 + 48, align 4)
    ; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
    ; CHECK: [[GEP6:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C3]](s64)
    ; CHECK: [[LOAD4:%[0-9]+]]:_(s128) = G_LOAD [[GEP6]](p0) :: (load 16 from %ir.1 + 64, align 4)
    ; CHECK: [[GEP7:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
    ; CHECK: G_STORE [[LOAD4]](s128), [[GEP7]](p0) :: (store 16 into %ir.0 + 64, align 4)
    ; CHECK: [[C4:%[0-9]+]]:_(s64) = G_CONSTANT i64 80
    ; CHECK: [[GEP8:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C4]](s64)
    ; CHECK: [[LOAD5:%[0-9]+]]:_(s128) = G_LOAD [[GEP8]](p0) :: (load 16 from %ir.1 + 80, align 4)
    ; CHECK: [[GEP9:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C4]](s64)
    ; CHECK: G_STORE [[LOAD5]](s128), [[GEP9]](p0) :: (store 16 into %ir.0 + 80, align 4)
    ; CHECK: [[C5:%[0-9]+]]:_(s64) = G_CONSTANT i64 96
    ; CHECK: [[GEP10:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C5]](s64)
    ; CHECK: [[LOAD6:%[0-9]+]]:_(s128) = G_LOAD [[GEP10]](p0) :: (load 16 from %ir.1 + 96, align 4)
    ; CHECK: [[GEP11:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C5]](s64)
    ; CHECK: G_STORE [[LOAD6]](s128), [[GEP11]](p0) :: (store 16 into %ir.0 + 96, align 4)
    ; CHECK: [[C6:%[0-9]+]]:_(s64) = G_CONSTANT i64 112
    ; CHECK: [[GEP12:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C6]](s64)
    ; CHECK: [[LOAD7:%[0-9]+]]:_(s128) = G_LOAD [[GEP12]](p0) :: (load 16 from %ir.1 + 112, align 4)
    ; CHECK: [[GEP13:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C6]](s64)
    ; CHECK: G_STORE [[LOAD7]](s128), [[GEP13]](p0) :: (store 16 into %ir.0 + 112, align 4)
    ; CHECK: [[C7:%[0-9]+]]:_(s64) = G_CONSTANT i64 127
    ; CHECK: [[GEP14:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C7]](s64)
    ; CHECK: [[LOAD8:%[0-9]+]]:_(s128) = G_LOAD [[GEP14]](p0) :: (load 16 from %ir.1 + 127, align 4)
    ; CHECK: [[GEP15:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C7]](s64)
    ; CHECK: G_STORE [[LOAD8]](s128), [[GEP15]](p0) :: (store 16 into %ir.0 + 127, align 4)
    ; CHECK: RET_ReallyLR
    %0:_(p0) = COPY $x0
    %1:_(p0) = COPY $x1
    %2:_(s64) = G_CONSTANT i64 143
    G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
    RET_ReallyLR

...