tp-multiple-vpst.ll | Explore in Territory

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

define dso_local arm_aapcs_vfpcc i32 @minmaxval4(ptr nocapture readonly %x, ptr nocapture %minp) {
; CHECK-LABEL: minmaxval4:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    push {r7, lr}
; CHECK-NEXT:    vmov.i32 q0, #0x80000000
; CHECK-NEXT:    vmvn.i32 q1, #0x80000000
; CHECK-NEXT:    movs r2, #10
; CHECK-NEXT:    dlstp.32 lr, r2
; CHECK-NEXT:  .LBB0_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q2, [r0], #16
; CHECK-NEXT:    vpt.s32 gt, q2, q0
; CHECK-NEXT:    vmovt q0, q2
; CHECK-NEXT:    vpt.s32 gt, q1, q2
; CHECK-NEXT:    vmovt q1, q2
; CHECK-NEXT:    letp lr, .LBB0_1
; CHECK-NEXT:  @ %bb.2: @ %middle.block
; CHECK-NEXT:    mvn r0, #-2147483648
; CHECK-NEXT:    vminv.s32 r0, q1
; CHECK-NEXT:    str r0, [r1]
; CHECK-NEXT:    mov.w r0, #-2147483648
; CHECK-NEXT:    vmaxv.s32 r0, q0
; CHECK-NEXT:    pop {r7, pc}
entry:
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %entry
  %index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x i32> [ <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>, %entry ], [ %5, %vector.body ]
  %vec.phi29 = phi <4 x i32> [ <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>, %entry ], [ %7, %vector.body ]
  %0 = getelementptr inbounds i32, ptr %x, i32 %index
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 10)
  %1 = bitcast ptr %0 to ptr
  %wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
  %2 = icmp sgt <4 x i32> %wide.masked.load, %vec.phi29
  %3 = icmp slt <4 x i32> %wide.masked.load, %vec.phi
  %4 = and <4 x i1> %active.lane.mask, %3
  %5 = select <4 x i1> %4, <4 x i32> %wide.masked.load, <4 x i32> %vec.phi
  %6 = and <4 x i1> %active.lane.mask, %2
  %7 = select <4 x i1> %6, <4 x i32> %wide.masked.load, <4 x i32> %vec.phi29
  %index.next = add i32 %index, 4
  %8 = icmp eq i32 %index.next, 12
  br i1 %8, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %9 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %7)
  %10 = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %5)
  store i32 %10, ptr %minp, align 4
  ret i32 %9
}

declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32) #1
declare <4 x i32> @llvm.masked.load.v4i32.p0(ptr, i32 immarg, <4 x i1>, <4 x i32>) #2
declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32>) #3
declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32>) #3
llvm/llvm/test/CodeGen/Thumb2/LowOverheadLoops/tp-multiple-vpst.ll
