; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -mtriple riscv64-linux-gnu -mattr=+zve32f,+f -S 2>%t | FileCheck %s

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

; We can't use scalable vectorization for Zvl32b due to RVVBitsPerBlock being
; 64. Since our vscale value is vlen/RVVBitsPerBlock this makes vscale 0.
; Make sure we fall back to fixed vectorization instead.
define void @vector_add_i16(ptr noalias nocapture %a, i16 %v, i64 %n) {
; CHECK-LABEL: @vector_add_i16(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i16> poison, i16 [[V:%.*]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i16> [[BROADCAST_SPLATINSERT]], <4 x i16> poison, <4 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:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], <4 x i64> [[VEC_IND]]
; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <4 x i16> @llvm.masked.gather.v4i16.v4p0(<4 x ptr> [[TMP0]], i32 2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i16> poison)
; CHECK-NEXT:    [[TMP1:%.*]] = add <4 x i16> [[WIDE_MASKED_GATHER]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    call void @llvm.masked.scatter.v4i16.v4p0(<4 x i16> [[TMP1]], <4 x ptr> [[TMP0]], i32 2, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1020
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1020, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; CHECK-NEXT:    [[ELEM:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
; CHECK-NEXT:    [[ADD:%.*]] = add i16 [[ELEM]], [[V]]
; CHECK-NEXT:    store i16 [[ADD]], ptr [[ARRAYIDX]], align 2
; 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]], !llvm.loop [[LOOP3:![0-9]+]]
; 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 i32, ptr %a, i64 %iv
  %elem = load i16, ptr %arrayidx
  %add = add i16 %elem, %v
  store i16 %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
}