; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc < %s -mtriple=riscv64 -mattr=+v | FileCheck %s
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n32:64-S128"
target triple = "riscv64-unknown-linux-gnu"

define i32 @_ZN4Mesh12rezone_countESt6vectorIiSaIiEERiS3_(<vscale x 4 x i32> %wide.load, <vscale x 4 x i1> %0, <vscale x 4 x i1> %1, <vscale x 4 x i1> %2, <vscale x 4 x i1> %3) #0 {
; CHECK-LABEL: _ZN4Mesh12rezone_countESt6vectorIiSaIiEERiS3_:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
; CHECK-NEXT:    vmv1r.v v8, v0
; CHECK-NEXT:    li a0, 0
; CHECK-NEXT:    vmv.v.i v10, 0
; CHECK-NEXT:    vmv.v.i v12, 0
; CHECK-NEXT:    vmv.v.i v14, 0
; CHECK-NEXT:  .LBB0_1: # %vector.body
; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vsetvli a1, zero, e32, m2, ta, mu
; CHECK-NEXT:    vmv1r.v v0, v8
; CHECK-NEXT:    slli a0, a0, 2
; CHECK-NEXT:    vmv2r.v v16, v10
; CHECK-NEXT:    vle32.v v16, (a0), v0.t
; CHECK-NEXT:    vand.vi v16, v16, 1
; CHECK-NEXT:    vmsne.vi v9, v16, 0
; CHECK-NEXT:    vmand.mm v0, v8, v9
; CHECK-NEXT:    vmerge.vim v12, v12, -1, v0
; CHECK-NEXT:    vmv1r.v v0, v8
; CHECK-NEXT:    vor.vi v14, v14, 1, v0.t
; CHECK-NEXT:    li a0, 1
; CHECK-NEXT:    j .LBB0_1
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i64 [ 0, %entry ], [ 1, %vector.body ]
  %vec.phi = phi <vscale x 4 x i32> [ zeroinitializer, %entry ], [ %predphi88, %vector.body ]
  %vec.phi81 = phi <vscale x 4 x i32> [ zeroinitializer, %entry ], [ %predphi93, %vector.body ]
  %wide.load1 = load <vscale x 4 x i32>, ptr null, align 4
  %4 = icmp slt <vscale x 4 x i32> %wide.load, zeroinitializer
  %5 = icmp sgt <vscale x 4 x i32> %wide.load, zeroinitializer
  %wide.masked.load82 = tail call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr null, i32 1, <vscale x 4 x i1> zeroinitializer, <vscale x 4 x i32> zeroinitializer)
  %6 = icmp eq <vscale x 4 x i32> zeroinitializer, zeroinitializer
  %7 = getelementptr i32, ptr null, i64 %index
  %wide.masked.load83 = tail call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr %7, i32 1, <vscale x 4 x i1> %0, <vscale x 4 x i32> zeroinitializer)
  %8 = select <vscale x 4 x i1> %0, <vscale x 4 x i1> %0, <vscale x 4 x i1> zeroinitializer
  %9 = trunc <vscale x 4 x i32> %wide.masked.load83 to <vscale x 4 x i1>
  %narrow = select <vscale x 4 x i1> %0, <vscale x 4 x i1> %9, <vscale x 4 x i1> zeroinitializer
  %10 = sext <vscale x 4 x i1> %narrow to <vscale x 4 x i32>
  %predphi88 = or <vscale x 4 x i32> %vec.phi, %10
  %11 = zext <vscale x 4 x i1> %0 to <vscale x 4 x i32>
  %predphi93 = or <vscale x 4 x i32> %vec.phi81, %11
  %index.next = add i64 0, 1
  br i1 false, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %12 = tail call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %vec.phi)
  %13 = tail call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %vec.phi81)
  ret i32 %13
}

; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: read)
declare <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr captures(none), i32 immarg, <vscale x 4 x i1>, <vscale x 4 x i32>) #1

; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
declare i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32>) #2

; uselistorder directives
uselistorder ptr @llvm.masked.load.nxv4i32.p0, { 1, 0 }
uselistorder ptr @llvm.vector.reduce.add.nxv4i32, { 1, 0 }

attributes #0 = { "target-features"="+v" }
attributes #1 = { nocallback nofree nosync nounwind willreturn memory(argmem: read) }
attributes #2 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }