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

define void @trip1_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip1_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP0]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP1]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 1
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 1
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip3_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP15]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST1:%.*]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP16]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 3
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 3
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip5_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP15]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST1:%.*]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP16]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 5
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 5
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip8_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 8, i32 4, i1 true)
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr align 1 [[TMP9:%.*]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP6:%.*]] = shl <vscale x 4 x i8> [[VP_OP_LOAD]], splat (i8 1)
; CHECK-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr align 1 [[TMP12:%.*]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 4 x i8> [[TMP6]], [[VP_OP_LOAD1]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP7]], ptr align 1 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    br label [[MIDDLE_BLOCK:%.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[TMP9]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP15]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP12]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP16]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 8
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 8
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

define void @trip16_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip16_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 16, i32 8, i1 true)
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr align 1 [[TMP1:%.*]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP6:%.*]] = shl <vscale x 8 x i8> [[VP_OP_LOAD]], splat (i8 1)
; CHECK-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr align 1 [[TMP4:%.*]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP11:%.*]] = add <vscale x 8 x i8> [[TMP6]], [[VP_OP_LOAD1]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP11]], ptr align 1 [[TMP4]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    br label [[MIDDLE_BLOCK:%.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP7]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 16
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 16
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}


define void @trip32_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip32_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 32, i32 16, i1 true)
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP1:%.*]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP6:%.*]] = shl <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; CHECK-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP4:%.*]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP11:%.*]] = add <vscale x 16 x i8> [[TMP6]], [[VP_OP_LOAD1]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[TMP11]], ptr align 1 [[TMP4]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    br label [[MIDDLE_BLOCK:%.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP7]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 32
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 32
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

define void @trip24_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip24_i8(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 24, i32 16, i1 true)
; CHECK-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[SRC:%.*]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP6:%.*]] = shl <vscale x 16 x i8> [[VP_OP_LOAD]], splat (i8 1)
; CHECK-NEXT:    [[VP_OP_LOAD1:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[DST:%.*]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 16 x i8> [[TMP6]], [[VP_OP_LOAD1]]
; CHECK-NEXT:    call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> [[TMP7]], ptr align 1 [[DST]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT:    br label [[MIDDLE_BLOCK:%.*]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[FOR_END:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i64 [ 0, [[SCALAR_PH:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT:    [[MUL:%.*]] = shl i8 [[TMP8]], 1
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[MUL]], [[TMP9]]
; CHECK-NEXT:    store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 24
; 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:                                         ; preds = %entry, %for.body
  %i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
  %arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
  %0 = load i8, ptr %arrayidx, align 1
  %mul = shl i8 %0, 1
  %arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
  %1 = load i8, ptr %arrayidx1, align 1
  %add = add i8 %mul, %1
  store i8 %add, ptr %arrayidx1, align 1
  %inc = add nuw nsw i64 %i.08, 1
  %exitcond.not = icmp eq i64 %inc, 24
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}

attributes #0 = { "target-features"="+v,+d" vscale_range(2, 1024) }

; This is a non-power-of-2 low trip count, so we will try to tail-fold this. But
; the reduction is a multiply which is only legal for fixed-length VFs. But
; fixed-length VFs aren't legal for the default tail-folding style
; data-with-evl, so make sure we gracefully fall back to data-without-lane-mask.

define i8 @mul_non_pow_2_low_trip_count(ptr noalias %a) {
; CHECK-LABEL: @mul_non_pow_2_low_trip_count(
; 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 <8 x i8> [ <i8 2, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>, [[VECTOR_PH]] ], [ [[TMP1:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i8>, ptr [[TMP0]], align 1
; CHECK-NEXT:    [[TMP1]] = mul <8 x i8> [[WIDE_LOAD]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 8
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP3:%.*]] = call i8 @llvm.vector.reduce.mul.v8i8(<8 x i8> [[TMP1]])
; CHECK-NEXT:    br label [[SCALAR_PH:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 8, [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[RDX:%.*]] = phi i8 [ [[TMP3]], [[SCALAR_PH]] ], [ [[MUL:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i8, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    [[TMP5:%.*]] = load i8, ptr [[GEP]], align 1
; CHECK-NEXT:    [[MUL]] = mul i8 [[TMP5]], [[RDX]]
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 10
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[MUL_LCSSA:%.*]] = phi i8 [ [[MUL]], [[FOR_BODY]] ]
; CHECK-NEXT:    ret i8 [[MUL_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %rdx = phi i8 [ 2, %entry ], [ %mul, %for.body ]
  %gep = getelementptr i8, ptr %a, i64 %iv
  %0 = load i8, ptr %gep
  %mul = mul i8 %0, %rdx
  %iv.next = add i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 10
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:                                 ; preds = %for.body, %entry
  ret i8 %mul
}