; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; Check remark analysis runs successfully.
; TODO: Remove this test when we fully migrate to VPlan-based cost model.
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -prefer-inloop-reductions -pass-remarks-analysis=loop-vectorize -S | FileCheck %s

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"

define i32 @reduction_sum(ptr noalias nocapture %A, ptr noalias nocapture %B) {
; CHECK-LABEL: define i32 @reduction_sum(
; CHECK-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias 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:    [[VEC_PHI:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP2]], align 4
; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[TMP4]] = add i32 [[TMP3]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 256, %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP4]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT:    br label %[[BODY:.*]]
; CHECK:       [[BODY]]:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], %[[BODY]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; CHECK-NEXT:    [[SUM_TMP:%.*]] = phi i32 [ [[SUM:%.*]], %[[BODY]] ], [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ]
; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[LOAD0:%.*]] = load i32, ptr [[GEP0]], align 4
; CHECK-NEXT:    [[SUM]] = add i32 [[SUM_TMP]], [[LOAD0]]
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 256
; CHECK-NEXT:    br i1 [[EXITCOND]], label %[[EXIT]], label %[[BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ [[SUM]], %[[BODY]] ], [ [[TMP4]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  br label %body

body:                                           ; preds = %entry, %body
  %indvars.iv = phi i64 [ %indvars.iv.next, %body ], [ 0, %entry ]
  %sum.tmp = phi i32 [ %sum, %body ], [ 0, %entry ]
  %gep0 = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
  %load0 = load i32, ptr %gep0, align 4
  %sum = add i32 %sum.tmp, %load0
  %indvars.iv.next = add i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, 256
  br i1 %exitcond, label %exit, label %body

exit:                                      ; preds = %body
  %sum.0.lcssa = phi i32 [ %sum, %body ]
  ret i32 %sum.0.lcssa
}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
;.