; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 5
; RUN: opt < %s -scalable-vectorization=on -force-target-supports-scalable-vectors=true -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=2  -S | FileCheck %s

define void @test1(ptr noalias nocapture %a, ptr noalias nocapture readonly %b) {
; CHECK-LABEL: define void @test1(
; CHECK-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias readonly captures(none) [[B:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1600, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1600, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1600, [[N_MOD_VF]]
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP8:%.*]] = mul nuw i64 [[TMP7]], 2
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds float, ptr [[TMP6]], i64 [[TMP8]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x float>, ptr [[TMP6]], align 4
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 2 x float>, ptr [[TMP9]], align 4
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <vscale x 2 x float> [[WIDE_LOAD]], i32 0
; CHECK-NEXT:    [[FCMP1:%.*]] = fcmp ogt float [[TMP10]], 1.000000e+02
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <vscale x 2 x float> [[WIDE_LOAD1]], i32 0
; CHECK-NEXT:    [[FCMP2:%.*]] = fcmp ogt float [[TMP12]], 1.000000e+02
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[FCMP1]])
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[FCMP2]])
; CHECK-NEXT:    [[TMP14:%.*]] = fadd <vscale x 2 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
; CHECK-NEXT:    [[TMP15:%.*]] = fadd <vscale x 2 x float> [[WIDE_LOAD1]], splat (float 1.000000e+00)
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP17:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP18:%.*]] = mul nuw i64 [[TMP17]], 2
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds float, ptr [[TMP16]], i64 [[TMP18]]
; CHECK-NEXT:    store <vscale x 2 x float> [[TMP14]], ptr [[TMP16]], align 4
; CHECK-NEXT:    store <vscale x 2 x float> [[TMP15]], ptr [[TMP19]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP20]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1600, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[FOR_END:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx = getelementptr inbounds float, ptr %b, i64 %indvars.iv
  %0 = load float, ptr %arrayidx, align 4
  %cmp1 = fcmp ogt float %0, 1.000000e+02
  tail call void @llvm.assume(i1 %cmp1)
  %add = fadd float %0, 1.000000e+00
  %arrayidx5 = getelementptr inbounds float, ptr %a, i64 %indvars.iv
  store float %add, ptr %arrayidx5, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv, 1599
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0

for.end:                                          ; preds = %for.body
  ret void
}

declare void @llvm.assume(i1) #0

attributes #0 = { nounwind willreturn }

%struct.data = type { ptr, ptr }

define void @test2(ptr %a, ptr noalias %b) {
; CHECK-LABEL: define void @test2(
; CHECK-SAME: ptr [[A:%.*]], ptr noalias [[B:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[PTRINT1:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[PTRINT1]], 0
; CHECK-NEXT:    [[PTRINT2:%.*]] = ptrtoint ptr [[B]] to i64
; CHECK-NEXT:    [[MASKCOND4:%.*]] = icmp eq i64 [[PTRINT2]], 0
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1600, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP7:%.*]] = mul nuw i64 [[TMP6]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1600, [[TMP7]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1600, [[N_MOD_VF]]
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND]])
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP12:%.*]] = mul nuw i64 [[TMP11]], 2
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds float, ptr [[TMP10]], i64 [[TMP12]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x float>, ptr [[TMP10]], align 4
; CHECK-NEXT:    [[WIDE_LOAD3:%.*]] = load <vscale x 2 x float>, ptr [[TMP13]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = fadd <vscale x 2 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
; CHECK-NEXT:    [[TMP15:%.*]] = fadd <vscale x 2 x float> [[WIDE_LOAD3]], splat (float 1.000000e+00)
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND4]])
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[MASKCOND4]])
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP17:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP18:%.*]] = mul nuw i64 [[TMP17]], 2
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds float, ptr [[TMP16]], i64 [[TMP18]]
; CHECK-NEXT:    store <vscale x 2 x float> [[TMP14]], ptr [[TMP16]], align 4
; CHECK-NEXT:    store <vscale x 2 x float> [[TMP15]], ptr [[TMP19]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP7]]
; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP20]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1600, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[FOR_END:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  %ptrint1 = ptrtoint ptr %a to i64
  %maskcond = icmp eq i64 %ptrint1, 0
  %ptrint2 = ptrtoint ptr %b to i64
  %maskcond4 = icmp eq i64 %ptrint2, 0
  br label %for.body


for.body:                                         ; preds = %for.body, %entry
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  tail call void @llvm.assume(i1 %maskcond)
  %arrayidx = getelementptr inbounds float, ptr %a, i64 %indvars.iv
  %0 = load float, ptr %arrayidx, align 4
  %add = fadd float %0, 1.000000e+00
  tail call void @llvm.assume(i1 %maskcond4)
  %arrayidx5 = getelementptr inbounds float, ptr %b, i64 %indvars.iv
  store float %add, ptr %arrayidx5, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv, 1599
  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0

for.end:                                          ; preds = %for.body
  ret void
}

; Test case for PR43620. Make sure we can vectorize with predication in presence
; of assume calls. For now, check that we drop all assumes in predicated blocks
; in the vector body.
define void @predicated_assume(ptr noalias nocapture readonly %a, ptr noalias nocapture %b, i64 %n) {
; Check that the vector.body does not contain any assumes.
; CHECK-LABEL: define void @predicated_assume(
; CHECK-SAME: ptr noalias readonly captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 2
; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP6]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP7:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
; CHECK-NEXT:    [[TMP8:%.*]] = mul <vscale x 2 x i64> [[TMP7]], splat (i64 1)
; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP8]]
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP5]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[STEP_ADD:%.*]] = add <vscale x 2 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP9:%.*]] = icmp ult <vscale x 2 x i64> [[VEC_IND]], splat (i64 495616)
; CHECK-NEXT:    [[TMP10:%.*]] = icmp ult <vscale x 2 x i64> [[STEP_ADD]], splat (i64 495616)
; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP9]], <vscale x 2 x float> splat (float 2.300000e+01), <vscale x 2 x float> splat (float 4.200000e+01)
; CHECK-NEXT:    [[PREDPHI1:%.*]] = select <vscale x 2 x i1> [[TMP10]], <vscale x 2 x float> splat (float 2.300000e+01), <vscale x 2 x float> splat (float 4.200000e+01)
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP13:%.*]] = mul nuw i64 [[TMP12]], 2
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[TMP11]], i64 [[TMP13]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x float>, ptr [[TMP11]], align 4
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 2 x float>, ptr [[TMP14]], align 4
; CHECK-NEXT:    [[TMP15:%.*]] = fmul <vscale x 2 x float> [[PREDPHI]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP16:%.*]] = fmul <vscale x 2 x float> [[PREDPHI1]], [[WIDE_LOAD2]]
; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP19:%.*]] = mul nuw i64 [[TMP18]], 2
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i64 [[TMP19]]
; CHECK-NEXT:    store <vscale x 2 x float> [[TMP15]], ptr [[TMP17]], align 4
; CHECK-NEXT:    store <vscale x 2 x float> [[TMP16]], ptr [[TMP20]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[STEP_ADD]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP21]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[FOR_COND_CLEANUP:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %for.body

for.body:                                         ; preds = %for.body.preheader, %if.end5
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end5 ]
  %cmp1 = icmp ult i64 %indvars.iv, 495616
  br i1 %cmp1, label %if.end5, label %if.else

if.else:                                          ; preds = %for.body
  %cmp2 = icmp ult i64 %indvars.iv, 991232
  tail call void @llvm.assume(i1 %cmp2)
  br label %if.end5

if.end5:                                          ; preds = %for.body, %if.else
  %x.0 = phi float [ 4.200000e+01, %if.else ], [ 2.300000e+01, %for.body ]
  %arrayidx = getelementptr inbounds float, ptr %a, i64 %indvars.iv
  %0 = load float, ptr %arrayidx, align 4
  %mul = fmul float %x.0, %0
  %arrayidx7 = getelementptr inbounds float, ptr %b, i64 %indvars.iv
  store float %mul, ptr %arrayidx7, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %cmp = icmp eq i64 %indvars.iv.next, %n
  br i1 %cmp, label %for.cond.cleanup, label %for.body, !llvm.loop !0

for.cond.cleanup:                                 ; preds = %if.end5, %entry
  ret void
}

!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}