; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -tail-predication=enabled -mtriple=thumbv8.1m.main -mattr=+mve,+mve.fp %s -o - | FileCheck %s

target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m-arm-none-eabi"

; Tests that LSR will not interfere with the VCTP intrinsic,
; and that this loop will correctly become tail-predicated.

define arm_aapcs_vfpcc float @vctpi32(float* %0, i32 %1) {
; CHECK-LABEL: vctpi32:
; CHECK:       @ %bb.0:
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    mvn r3, #31
; CHECK-NEXT:    vmov.32 q2[0], r0
; CHECK-NEXT:    movs r4, #0
; CHECK-NEXT:    subs r2, r1, #1
; CHECK-NEXT:    vadd.i32 q2, q2, r3
; CHECK-NEXT:    vidup.u32 q1, r4, #8
; CHECK-NEXT:    vmov r0, s8
; CHECK-NEXT:    vadd.i32 q1, q1, r0
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    dlstp.32 lr, r2
; CHECK-NEXT:  .LBB0_1: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q2, [q1, #32]!
; CHECK-NEXT:    vadd.f32 q0, q0, q2
; CHECK-NEXT:    letp lr, .LBB0_1
; CHECK-NEXT:  @ %bb.2:
; CHECK-NEXT:    bl vecAddAcrossF32Mve
; CHECK-NEXT:    vmov s0, r0
; CHECK-NEXT:    vcvt.f32.s32 s0, s0
; CHECK-NEXT:    vabs.f32 s0, s0
; CHECK-NEXT:    pop {r4, pc}
  %3 = tail call { <4 x i32>, i32 } @llvm.arm.mve.vidup.v4i32(i32 0, i32 8)
  %4 = extractvalue { <4 x i32>, i32 } %3, 0
  %5 = add nsw i32 %1, -1
  %6 = ptrtoint float* %0 to i32
  %7 = insertelement <4 x i32> undef, i32 %6, i32 0
  %8 = add <4 x i32> %7, <i32 -32, i32 undef, i32 undef, i32 undef>
  %9 = shufflevector <4 x i32> %8, <4 x i32> undef, <4 x i32> zeroinitializer
  %10 = add <4 x i32> %4, %9
  br label %11

11:
  %12 = phi i32 [ %5, %2 ], [ %20, %11 ]
  %13 = phi <4 x float> [ zeroinitializer, %2 ], [ %19, %11 ]
  %14 = phi <4 x i32> [ %10, %2 ], [ %17, %11 ]
  %15 = tail call <4 x i1> @llvm.arm.mve.vctp32(i32 %12)
  %16 = tail call { <4 x float>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v4f32.v4i32.v4i1(<4 x i32> %14, i32 32, <4 x i1> %15)
  %17 = extractvalue { <4 x float>, <4 x i32> } %16, 1
  %18 = extractvalue { <4 x float>, <4 x i32> } %16, 0
  %19 = tail call <4 x float> @llvm.arm.mve.add.predicated.v4f32.v4i1(<4 x float> %13, <4 x float> %18, <4 x i1> %15, <4 x float> %13)
  %20 = add nsw i32 %12, -4
  %21 = icmp sgt i32 %12, 4
  br i1 %21, label %11, label %22

22:
  %23 = tail call arm_aapcs_vfpcc i32 bitcast (i32 (...)* @vecAddAcrossF32Mve to i32 (<4 x float>)*)(<4 x float> %19)
  %24 = sitofp i32 %23 to float
  %25 = tail call float @llvm.fabs.f32(float %24)
  ret float %25
}

declare { <4 x i32>, i32 } @llvm.arm.mve.vidup.v4i32(i32, i32)
declare <4 x i1> @llvm.arm.mve.vctp32(i32)
declare { <4 x float>, <4 x i32> } @llvm.arm.mve.vldr.gather.base.wb.predicated.v4f32.v4i32.v4i1(<4 x i32>, i32, <4 x i1>)
declare <4 x float> @llvm.arm.mve.add.predicated.v4f32.v4i1(<4 x float>, <4 x float>, <4 x i1>, <4 x float>)
declare arm_aapcs_vfpcc i32 @vecAddAcrossF32Mve(...)
declare float @llvm.fabs.f32(float)