; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s

; This is a collection of tests whose only purpose is to show changes in the
; default configuration.  Please keep these tests minimal - if you're testing
; functionality of some specific configuration, please place that in a
; separate test file with a hard coded configuration (even if that
; configuration is the current default).

target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
target triple = "riscv64"

define void @vector_add(ptr noalias nocapture %a, i64 %v) {
; CHECK-LABEL: @vector_add(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[V:%.*]], 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:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1024, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP10]])
; CHECK-NEXT:    [[TMP9:%.*]] = add <vscale x 2 x i64> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP9]], ptr align 8 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP10]])
; CHECK-NEXT:    [[TMP8:%.*]] = zext i32 [[TMP10]] to i64
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[TMP8]], [[INDEX]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP8]]
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
  %elem = load i64, ptr %arrayidx
  %add = add i64 %elem, %v
  store i64 %add, ptr %arrayidx
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1024
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret void
}

define i64 @vector_add_reduce(ptr noalias nocapture %a) {
; CHECK-LABEL: @vector_add_reduce(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br 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 <vscale x 2 x i64> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1024, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP8:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP8]])
; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[VEC_PHI]], [[VP_OP_LOAD]]
; CHECK-NEXT:    [[TMP9]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP12]], <vscale x 2 x i64> [[VEC_PHI]], i32 [[TMP8]])
; CHECK-NEXT:    [[TMP13:%.*]] = zext i32 [[TMP8]] to i64
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[TMP13]], [[INDEX]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP13]]
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> [[TMP9]])
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.end:
; CHECK-NEXT:    ret i64 [[TMP11]]
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [0, %entry], [%iv.next, %for.body]
  %sum = phi i64 [0, %entry], [%sum.next, %for.body]
  %arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
  %elem = load i64, ptr %arrayidx
  %iv.next = add nuw nsw i64 %iv, 1
  %sum.next = add i64 %sum, %elem
  %exitcond.not = icmp eq i64 %iv.next, 1024
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret i64 %sum.next
}