; 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 -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:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds float, ptr [[TMP0]], i32 2
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <2 x float>, ptr [[TMP7]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = fcmp ogt <2 x float> [[WIDE_LOAD]], splat (float 1.000000e+02)
; CHECK-NEXT:    [[TMP2:%.*]] = fcmp ogt <2 x float> [[WIDE_LOAD1]], splat (float 1.000000e+02)
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x i1> [[TMP1]], i32 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[TMP3]])
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x i1> [[TMP1]], i32 1
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[TMP4]])
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[TMP5]])
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
; CHECK-NEXT:    tail call void @llvm.assume(i1 [[TMP6]])
; CHECK-NEXT:    [[TMP8:%.*]] = fadd <2 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
; CHECK-NEXT:    [[TMP9:%.*]] = fadd <2 x float> [[WIDE_LOAD1]], splat (float 1.000000e+00)
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds float, ptr [[TMP10]], i32 2
; CHECK-NEXT:    store <2 x float> [[TMP8]], ptr [[TMP10]], align 4
; CHECK-NEXT:    store <2 x float> [[TMP9]], ptr [[TMP11]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1600
; CHECK-NEXT:    br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br [[FOR_END:label %.*]]
; 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

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

declare void @llvm.assume(i1) #0

attributes #0 = { nounwind willreturn }

define void @test2(ptr noalias %a, ptr noalias %b) {
; CHECK-LABEL: define void @test2(
; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[PTRINT:%.*]] = ptrtoint ptr [[A]] to i64
; CHECK-NEXT:    [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
; CHECK-NEXT:    [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
; CHECK-NEXT:    [[PTRINT2:%.*]] = ptrtoint ptr [[B]] to i64
; CHECK-NEXT:    [[MASKEDPTR3:%.*]] = and i64 [[PTRINT2]], 31
; CHECK-NEXT:    [[MASKCOND4:%.*]] = icmp eq i64 [[MASKEDPTR3]], 0
; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; 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:    [[TMP3:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, ptr [[TMP3]], i32 2
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP3]], align 4
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <2 x float>, ptr [[TMP4]], align 4
; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x float> [[WIDE_LOAD]], splat (float 1.000000e+00)
; CHECK-NEXT:    [[TMP6:%.*]] = fadd <2 x float> [[WIDE_LOAD1]], 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:    [[TMP7:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, ptr [[TMP7]], i32 2
; CHECK-NEXT:    store <2 x float> [[TMP5]], ptr [[TMP7]], align 4
; CHECK-NEXT:    store <2 x float> [[TMP6]], ptr [[TMP8]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1600
; CHECK-NEXT:    br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br [[FOR_END:label %.*]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  %ptrint = ptrtoint ptr %a to i64
  %maskedptr = and i64 %ptrint, 31
  %maskcond = icmp eq i64 %maskedptr, 0
  %ptrint2 = ptrtoint ptr %b to i64
  %maskedptr3 = and i64 %ptrint2, 31
  %maskcond4 = icmp eq i64 %maskedptr3, 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
  %2 = load float, ptr %arrayidx, align 4
  %add = fadd float %2, 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

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, i32 %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:%.*]], i32 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[CMP15:%.*]] = icmp eq i32 [[N]], 0
; CHECK-NEXT:    br i1 [[CMP15]], [[FOR_COND_CLEANUP:label %.*]], label %[[FOR_BODY_PREHEADER:.*]]
; CHECK:       [[FOR_BODY_PREHEADER]]:
; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[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:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 0, i64 1>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[STEP_ADD:%.*]] = add <2 x i64> [[VEC_IND]], splat (i64 2)
; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult <2 x i64> [[VEC_IND]], splat (i64 495616)
; CHECK-NEXT:    [[TMP2:%.*]] = icmp ult <2 x i64> [[STEP_ADD]], splat (i64 495616)
; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP1]], <2 x float> splat (float 2.300000e+01), <2 x float> splat (float 4.200000e+01)
; CHECK-NEXT:    [[PREDPHI1:%.*]] = select <2 x i1> [[TMP2]], <2 x float> splat (float 2.300000e+01), <2 x float> splat (float 4.200000e+01)
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, ptr [[TMP3]], i32 2
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x float>, ptr [[TMP3]], align 4
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <2 x float>, ptr [[TMP4]], align 4
; CHECK-NEXT:    [[TMP5:%.*]] = fmul <2 x float> [[PREDPHI]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP6:%.*]] = fmul <2 x float> [[PREDPHI1]], [[WIDE_LOAD2]]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, ptr [[TMP7]], i32 2
; CHECK-NEXT:    store <2 x float> [[TMP5]], ptr [[TMP7]], align 4
; CHECK-NEXT:    store <2 x float> [[TMP6]], ptr [[TMP8]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[STEP_ADD]], splat (i64 2)
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[FOR_COND_CLEANUP_LOOPEXIT:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  %cmp15 = icmp eq i32 %n, 0
  br i1 %cmp15, label %for.cond.cleanup, label %for.body.preheader

for.body.preheader:                               ; preds = %entry
  %0 = zext i32 %n to i64
  br label %for.body

for.cond.cleanup.loopexit:                        ; preds = %if.end5
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %if.end5
  %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %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
  %1 = load float, ptr %arrayidx, align 4
  %mul = fmul float %x.0, %1
  %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, %0
  br i1 %cmp, label %for.cond.cleanup.loopexit, label %for.body
}