; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -S %s | FileCheck %s

define void @test(ptr %p, i64 %a, i8 %b) {
; CHECK-LABEL: define void @test(
; CHECK-SAME: ptr [[P:%.*]], i64 [[A:%.*]], i8 [[B:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH1:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i32 [[TMP0]], 2
; CHECK-NEXT:    [[TMP2:%.*]] = sub i32 [[TMP1]], 1
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 9, [[TMP2]]
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT:    [[TMP4:%.*]] = mul nuw i32 [[TMP3]], 2
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i8> poison, i8 [[B]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i8> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i8> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[A]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP5:%.*]] = shl <vscale x 2 x i64> [[BROADCAST_SPLAT2]], splat (i64 48)
; CHECK-NEXT:    [[TMP6:%.*]] = ashr <vscale x 2 x i64> [[TMP5]], splat (i64 52)
; CHECK-NEXT:    [[TMP7:%.*]] = trunc <vscale x 2 x i64> [[TMP6]] to <vscale x 2 x i32>
; CHECK-NEXT:    [[TMP8:%.*]] = zext <vscale x 2 x i8> [[BROADCAST_SPLAT]] to <vscale x 2 x i32>
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 2 x ptr> poison, ptr [[P]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 2 x ptr> [[BROADCAST_SPLATINSERT3]], <vscale x 2 x ptr> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP9:%.*]] = call <vscale x 2 x i32> @llvm.stepvector.nxv2i32()
; CHECK-NEXT:    [[TMP10:%.*]] = mul <vscale x 2 x i32> [[TMP9]], splat (i32 1)
; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i32> zeroinitializer, [[TMP10]]
; CHECK-NEXT:    br label [[FOR_COND:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[FOR_COND]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i32> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_COND]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i32 [ 9, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[FOR_COND]] ]
; CHECK-NEXT:    [[TMP11:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP11]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <vscale x 2 x i32> [[BROADCAST_SPLATINSERT5]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP20:%.*]] = mul i32 1, [[TMP11]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP20]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT8:%.*]] = shufflevector <vscale x 2 x i32> [[BROADCAST_SPLATINSERT7]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP19:%.*]] = call <vscale x 2 x i32> @llvm.stepvector.nxv2i32()
; CHECK-NEXT:    [[TMP13:%.*]] = icmp ult <vscale x 2 x i32> [[TMP19]], [[BROADCAST_SPLAT6]]
; CHECK-NEXT:    [[TMP14:%.*]] = icmp sge <vscale x 2 x i32> [[VEC_IND]], splat (i32 2)
; CHECK-NEXT:    [[TMP15:%.*]] = select <vscale x 2 x i1> [[TMP13]], <vscale x 2 x i1> [[TMP14]], <vscale x 2 x i1> zeroinitializer
; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP15]], <vscale x 2 x i32> [[TMP7]], <vscale x 2 x i32> [[TMP8]]
; CHECK-NEXT:    [[TMP16:%.*]] = shl <vscale x 2 x i32> [[PREDPHI]], splat (i32 8)
; CHECK-NEXT:    [[TMP17:%.*]] = trunc <vscale x 2 x i32> [[TMP16]] to <vscale x 2 x i8>
; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> [[TMP17]], <vscale x 2 x ptr> align 1 [[BROADCAST_SPLAT4]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP11]])
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP11]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i32 [[AVL]], [[TMP11]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i32> [[VEC_IND]], [[BROADCAST_SPLAT8]]
; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i32 [[INDEX_EVL_NEXT]], 9
; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_COND]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[EXIT1:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_COND1:%.*]]
; CHECK:       for.cond:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH1]] ], [ [[ADD:%.*]], [[FOR_BODY:%.*]] ]
; CHECK-NEXT:    [[ADD]] = add i32 [[IV]], 1
; CHECK-NEXT:    [[CMP_SLT:%.*]] = icmp slt i32 [[IV]], 2
; CHECK-NEXT:    [[SHL:%.*]] = shl i64 [[A]], 48
; CHECK-NEXT:    [[ASHR:%.*]] = ashr i64 [[SHL]], 52
; CHECK-NEXT:    [[TRUNC_I32:%.*]] = trunc i64 [[ASHR]] to i32
; CHECK-NEXT:    br i1 [[CMP_SLT]], label [[COND_FALSE:%.*]], label [[FOR_BODY]]
; CHECK:       cond.false:
; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[B]] to i32
; CHECK-NEXT:    br label [[FOR_BODY]]
; CHECK:       for.body:
; CHECK-NEXT:    [[COND:%.*]] = phi i32 [ [[TRUNC_I32]], [[FOR_COND1]] ], [ [[ZEXT]], [[COND_FALSE]] ]
; CHECK-NEXT:    [[SHL_I32:%.*]] = shl i32 [[COND]], 8
; CHECK-NEXT:    [[TRUNC:%.*]] = trunc i32 [[SHL_I32]] to i8
; CHECK-NEXT:    store i8 [[TRUNC]], ptr [[P]], align 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[IV]], 8
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_COND1]], label [[EXIT1]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %iv = phi i32 [ 0, %entry ], [ %add, %for.body ]
  %add = add i32 %iv, 1
  %cmp.slt = icmp slt i32 %iv, 2
  %shl = shl i64 %a, 48
  %ashr = ashr i64 %shl, 52
  %trunc.i32 = trunc i64 %ashr to i32
  br i1 %cmp.slt, label %cond.false, label %for.body

cond.false:                                       ; preds = %for.cond
  %zext = zext i8 %b to i32
  br label %for.body

for.body:                                         ; preds = %cond.false, %for.cond
  %cond = phi i32 [ %trunc.i32, %for.cond ], [ %zext, %cond.false ]
  %shl.i32 = shl i32 %cond, 8
  %trunc = trunc i32 %shl.i32 to i8
  store i8 %trunc, ptr %p, align 1
  %cmp = icmp slt i32 %iv, 8
  br i1 %cmp, label %for.cond, label %exit

exit:                                             ; preds = %for.body
  ret void
}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]], [[META3:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.isvectorized.tailfoldingstyle", !"evl"}
; CHECK: [[META3]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META3]], [[META1]]}
;.