llvm/test/Transforms/LoopVectorize/ARM/tail-fold-multiple-icmps.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve -tail-predication=enabled -passes=loop-vectorize %s -S -o - | FileCheck %s

target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"

define arm_aapcs_vfpcc i32 @minmaxval4(ptr nocapture readonly %x, ptr nocapture %minp, i32 %N) {
; CHECK-LABEL: @minmaxval4(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP26_NOT:%.*]] = icmp eq i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP26_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = and i32 [[N]], 3
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ splat (i32 2147483647), [[VECTOR_PH]] ], [ [[TMP2:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI1:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), [[VECTOR_PH]] ], [ [[TMP1:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[WIDE_LOAD]], <4 x i32> [[VEC_PHI1]])
; CHECK-NEXT:    [[TMP2]] = call <4 x i32> @llvm.smin.v4i32(<4 x i32> [[WIDE_LOAD]], <4 x i32> [[VEC_PHI]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP4:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[TMP2]])
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP1]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP4]], [[MIDDLE_BLOCK]] ], [ 2147483647, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX2:%.*]] = phi i32 [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ -2147483648, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    [[COND_LCSSA:%.*]] = phi i32 [ [[COND:%.*]], [[FOR_BODY]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    [[COND9_LCSSA:%.*]] = phi i32 [ [[COND9:%.*]], [[FOR_BODY]] ], [ [[TMP4]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[MAX_0_LCSSA:%.*]] = phi i32 [ -2147483648, [[ENTRY:%.*]] ], [ [[COND_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; CHECK-NEXT:    [[MIN_0_LCSSA:%.*]] = phi i32 [ 2147483647, [[ENTRY]] ], [ [[COND9_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; CHECK-NEXT:    store i32 [[MIN_0_LCSSA]], ptr [[MINP:%.*]], align 4
; CHECK-NEXT:    ret i32 [[MAX_0_LCSSA]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_029:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[MIN_028:%.*]] = phi i32 [ [[COND9]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[MAX_027:%.*]] = phi i32 [ [[COND]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX2]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[X]], i32 [[I_029]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[COND]] = call i32 @llvm.smax.i32(i32 [[TMP6]], i32 [[MAX_027]])
; CHECK-NEXT:    [[COND9]] = call i32 @llvm.smin.i32(i32 [[TMP6]], i32 [[MIN_028]])
; CHECK-NEXT:    [[INC]] = add nuw i32 [[I_029]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
;
entry:
  %cmp26.not = icmp eq i32 %N, 0
  br i1 %cmp26.not, label %for.cond.cleanup, label %for.body

for.cond.cleanup:
  %max.0.lcssa = phi i32 [ -2147483648, %entry ], [ %cond, %for.body ]
  %min.0.lcssa = phi i32 [ 2147483647, %entry ], [ %cond9, %for.body ]
  store i32 %min.0.lcssa, ptr %minp, align 4
  ret i32 %max.0.lcssa

for.body:
  %i.029 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %min.028 = phi i32 [ %cond9, %for.body ], [ 2147483647, %entry ]
  %max.027 = phi i32 [ %cond, %for.body ], [ -2147483648, %entry ]
  %arrayidx = getelementptr inbounds i32, ptr %x, i32 %i.029
  %0 = load i32, ptr %arrayidx, align 4
  %cond = call i32 @llvm.smax(i32 %0, i32 %max.027)
  %cond9 = call i32 @llvm.smin(i32 %0, i32 %min.028)
  %inc = add nuw i32 %i.029, 1
  %exitcond.not = icmp eq i32 %inc, %N
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}