; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s -check-prefix=CHECK

; Exercise tail folding on RISCV w/scalable vectors.

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, i64 %n) {
; 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:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1025, [[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:    [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP11]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP10]])
; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 2 x i64> [[VP_OP_LOAD]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP7]], ptr align 8 [[TMP11]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP10]])
; CHECK-NEXT:    [[TMP8:%.*]] = zext i32 [[TMP10]] to i64
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP8]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP8]]
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    [[ELEM:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = add i64 [[ELEM]], [[V]]
; CHECK-NEXT:    store i64 [[ADD]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], 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, 1025
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret void
}


; a[b[i]] = v, exercise scatter support
define void @indexed_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i64 %v, i64 %n) {
; CHECK-LABEL: @indexed_store(
; 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:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1025, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], <vscale x 2 x i64> [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    call void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x ptr> align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT:    [[TMP12:%.*]] = zext i32 [[TMP7]] to i64
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP12]]
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[BADDR:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[IV]]
; CHECK-NEXT:    [[AIDX:%.*]] = load i64, ptr [[BADDR]], align 8
; CHECK-NEXT:    [[AADDR:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[AIDX]]
; CHECK-NEXT:    store i64 [[V]], ptr [[AADDR]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], 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 ]
  %baddr = getelementptr inbounds i64, ptr %b, i64 %iv
  %aidx = load i64, ptr %baddr
  %aaddr = getelementptr inbounds i64, ptr %a, i64 %aidx
  store i64 %v, ptr %aaddr
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1025
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret void
}

define i64 @indexed_load(ptr noalias nocapture %a, ptr noalias nocapture %b, i64 %v, i64 %n) {
; CHECK-LABEL: @indexed_load(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 2 x i64> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1025, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], <vscale x 2 x i64> [[WIDE_MASKED_LOAD]]
; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i64> @llvm.vp.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[VEC_PHI]], [[WIDE_MASKED_GATHER]]
; CHECK-NEXT:    [[TMP11]] = 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 [[TMP7]])
; CHECK-NEXT:    [[TMP15:%.*]] = zext i32 [[TMP7]] to i64
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP15]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP15]]
; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> [[TMP11]])
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[SUM:%.*]] = phi i64 [ 0, [[SCALAR_PH]] ], [ [[SUM_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[BADDR:%.*]] = getelementptr inbounds i64, ptr [[B]], i64 [[IV]]
; CHECK-NEXT:    [[AIDX:%.*]] = load i64, ptr [[BADDR]], align 8
; CHECK-NEXT:    [[AADDR:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[AIDX]]
; CHECK-NEXT:    [[ELEM:%.*]] = load i64, ptr [[AADDR]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[SUM_NEXT]] = add i64 [[SUM]], [[ELEM]]
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]]
; CHECK:       for.end:
; CHECK-NEXT:    [[SUM_NEXT_LCSSA:%.*]] = phi i64 [ [[SUM_NEXT]], [[FOR_BODY]] ], [ [[TMP14]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[SUM_NEXT_LCSSA]]
;
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]
  %baddr = getelementptr inbounds i64, ptr %b, i64 %iv
  %aidx = load i64, ptr %baddr
  %aaddr = getelementptr inbounds i64, ptr %a, i64 %aidx
  %elem = load i64, ptr %aaddr
  %iv.next = add nuw nsw i64 %iv, 1
  %sum.next = add i64 %sum, %elem
  %exitcond.not = icmp eq i64 %iv.next, 1025
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret i64 %sum.next
}

define void @splat_int(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-LABEL: @splat_int(
; 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:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1025, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
; CHECK-NEXT:    [[TMP7:%.*]] = zext i32 [[TMP9]] to i64
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP7]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP7]]
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    store i64 [[V]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], 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
  store i64 %v, ptr %arrayidx
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1025
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret void
}

define void @uniform_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i64 %v, i64 %n) {
; CHECK-LABEL: @uniform_store(
; 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:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[AVL:%.*]] = phi i64 [ 1025, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT:    store i64 [[V]], ptr [[B:%.*]], align 8
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT:    [[TMP9:%.*]] = zext i32 [[TMP7]] to i64
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP9]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP9]]
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    store i64 [[V]], ptr [[B]], align 8
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    store i64 [[V]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], 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 ]
  store i64 %v, ptr %b, align 8
  %arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
  store i64 %v, ptr %arrayidx
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1025
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret void
}

define i64 @uniform_load(ptr noalias nocapture %a, ptr noalias nocapture %b, i64 %n) {
; CHECK-LABEL: @uniform_load(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[ENTRY:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1025, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1025, [[N_MOD_VF]]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[B:%.*]], align 8
; 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:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[IV]]
; CHECK-NEXT:    store <vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw i64 [[IV]], [[TMP3]]
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[IV_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1025, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], 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:    [[V1:%.*]] = load i64, ptr [[B]], align 8
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV1]]
; CHECK-NEXT:    store i64 [[V1]], ptr [[ARRAYIDX1]], align 8
; CHECK-NEXT:    [[IV_NEXT1]] = add nuw nsw i64 [[IV1]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT1]], 1025
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY1]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[V_LCSSA:%.*]] = phi i64 [ [[V1]], [[FOR_BODY1]] ], [ [[V]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[V_LCSSA]]
;
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %v = load i64, ptr %b, align 8
  %arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
  store i64 %v, ptr %arrayidx
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1025
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret i64 %v
}


define void @vector_add_trip1024(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-LABEL: @vector_add_trip1024(
; 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:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_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:    [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP11]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP10]])
; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 2 x i64> [[VP_OP_LOAD]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP7]], ptr align 8 [[TMP11]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP10]])
; CHECK-NEXT:    [[TMP8:%.*]] = zext i32 [[TMP10]] to i64
; CHECK-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP8]], [[EVL_BASED_IV]]
; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP8]]
; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    [[ELEM:%.*]] = load i64, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = add i64 [[ELEM]], [[V]]
; CHECK-NEXT:    store i64 [[ADD]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], 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
}