; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
; RUN: opt < %s -passes=loop-vectorize,instcombine -enable-histogram-loop-vectorization -force-vector-width=2 -S | FileCheck %s

define void @simple_histogram(ptr noalias %buckets, ptr readonly %indices, i64 %N) {
; CHECK-LABEL: define void @simple_histogram(
; CHECK-SAME: ptr noalias [[BUCKETS:%.*]], ptr readonly [[INDICES:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 2
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[ENTRY:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i64 [[N]], -2
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [4 x i8], ptr [[INDICES]], i64 [[IV]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = zext <2 x i32> [[WIDE_LOAD]] to <2 x i64>
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds nuw [4 x i8], ptr [[BUCKETS]], i64 [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x i64> [[TMP1]], i64 1
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds nuw [4 x i8], ptr [[BUCKETS]], i64 [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x ptr> poison, ptr [[TMP3]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x ptr> [[TMP6]], ptr [[TMP5]], i64 1
; CHECK-NEXT:    call void @llvm.experimental.vector.histogram.add.v2p0.i32(<2 x ptr> [[TMP7]], i32 1, <2 x i1> splat (i1 true))
; CHECK-NEXT:    [[IV_NEXT]] = add nuw i64 [[IV]], 2
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[IV_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY1:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY1:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV1:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT1:%.*]], [[FOR_BODY1]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i8], ptr [[INDICES]], i64 [[IV1]]
; CHECK-NEXT:    [[TMP12:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[IDXPROM1:%.*]] = zext i32 [[TMP12]] to i64
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds nuw [4 x i8], ptr [[BUCKETS]], i64 [[IDXPROM1]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP13]], 1
; CHECK-NEXT:    store i32 [[INC]], ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[IV_NEXT1]] = add nuw nsw i64 [[IV1]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT1]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_EXIT]], label [[FOR_BODY1]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       for.exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %gep.indices = getelementptr inbounds i32, ptr %indices, i64 %iv
  %l.idx = load i32, ptr %gep.indices, align 4
  %idxprom1 = zext i32 %l.idx to i64
  %gep.bucket = getelementptr inbounds i32, ptr %buckets, i64 %idxprom1
  %l.bucket = load i32, ptr %gep.bucket, align 4
  %inc = add nsw i32 %l.bucket, 1
  store i32 %inc, ptr %gep.bucket, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond = icmp eq i64 %iv.next, %N
  br i1 %exitcond, label %for.exit, label %for.body

for.exit:
  ret void
}