llvm/test/Transforms/LoopVectorize/RISCV/safe-dep-distance.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -riscv-v-vector-bits-min=-1 -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s

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

; Dependence distance between read and write is greater than the trip
; count of the loop.  Thus, values written are never read for any
; valid vectorization of the loop.
define void @test(ptr %p) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 200, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 200, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 200, [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP8]], align 32
; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 200
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[TMP10]], i32 0
; CHECK-NEXT:    store <vscale x 2 x i64> [[WIDE_LOAD]], ptr [[TMP11]], align 32
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 200
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 200
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Dependence distance is less than trip count, thus we must prove that
; chosen VF guaranteed to be less than dependence distance.
define void @test_may_clobber(ptr %p) {
; CHECK-LABEL: @test_may_clobber(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], 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:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[TMP1]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP2]], align 32
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 100
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[TMP4]], i32 0
; CHECK-NEXT:    store <4 x i64> [[WIDE_LOAD]], ptr [[TMP5]], align 32
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 200
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 200, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 100
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 100
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Trviailly no overlap due to maximum possible value of VLEN and LMUL
define void @trivial_due_max_vscale(ptr %p) {
; CHECK-LABEL: @trivial_due_max_vscale(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 200, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 200, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 200, [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP8]], align 32
; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 8192
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[TMP10]], i32 0
; CHECK-NEXT:    store <vscale x 2 x i64> [[WIDE_LOAD]], ptr [[TMP11]], align 32
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 8192
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 8192
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

; Dependence distance could be violated via LMUL>=2 or interleaving
define void @no_high_lmul_or_interleave(ptr %p) {
; CHECK-LABEL: @no_high_lmul_or_interleave(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 200, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 200, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 200, [[N_MOD_VF]]
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP7]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP8]], align 32
; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 1024
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i64, ptr [[P]], i64 [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[TMP10]], i32 0
; CHECK-NEXT:    store <vscale x 2 x i64> [[WIDE_LOAD]], ptr [[TMP11]], align 32
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 200, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[A1:%.*]] = getelementptr i64, ptr [[P]], i64 [[IV]]
; CHECK-NEXT:    [[V:%.*]] = load i64, ptr [[A1]], align 32
; CHECK-NEXT:    [[OFFSET:%.*]] = add i64 [[IV]], 1024
; CHECK-NEXT:    [[A2:%.*]] = getelementptr i64, ptr [[P]], i64 [[OFFSET]]
; CHECK-NEXT:    store i64 [[V]], ptr [[A2]], align 32
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i64 [[IV]], 199
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [0, %entry], [%iv.next, %loop]
  %a1 = getelementptr i64, ptr %p, i64 %iv
  %v = load i64, ptr %a1, align 32
  %offset = add i64 %iv, 1024
  %a2 = getelementptr i64, ptr %p, i64 %offset
  store i64 %v, ptr %a2, align 32
  %iv.next = add i64 %iv, 1
  %cmp = icmp ne i64 %iv, 199
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}

@a = external global [10 x [12 x i16]]

; Test case for https://github.com/llvm/llvm-project/issues/134696.
define void @safe_load_store_distance_not_pow_of_2(i64 %N) {
; CHECK-LABEL: @safe_load_store_distance_not_pow_of_2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[UMIN:%.*]] = call i64 @llvm.umin.i64(i64 [[N:%.*]], i64 1)
; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 [[N]], [[UMIN]]
; CHECK-NEXT:    [[TMP1:%.*]] = udiv i64 [[TMP0]], 3
; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[UMIN]], [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[TMP2]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ule i64 [[TMP3]], 8
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP3]], 8
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP4]], i64 8, i64 [[N_MOD_VF]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP3]], [[TMP5]]
; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[N_VEC]], 3
; 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 <8 x i64> [ <i64 0, i64 3, i64 6, i64 9, i64 12, i64 15, i64 18, i64 21>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr [10 x [12 x i16]], ptr @a, i64 0, i64 8, <8 x i64> [[VEC_IND]]
; CHECK-NEXT:    call void @llvm.masked.scatter.v8i16.v8p0(<8 x i16> zeroinitializer, <8 x ptr> [[TMP7]], i32 2, <8 x i1> splat (i1 true))
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <8 x i64> [[VEC_IND]], splat (i64 24)
; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[TMP6]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr [10 x [12 x i16]], ptr @a, i64 0, i64 0, i64 [[IV]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i16, ptr [[GEP]], align 2
; CHECK-NEXT:    [[GEP_OFF:%.*]] = getelementptr [10 x [12 x i16]], ptr @a, i64 0, i64 8, i64 [[IV]]
; CHECK-NEXT:    store i16 0, ptr [[GEP_OFF]], align 2
; CHECK-NEXT:    [[IV_NEXT]] = add nsw i64 [[IV]], 3
; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i64 [[IV]], [[N]]
; CHECK-NEXT:    br i1 [[CMP]], label [[LOOP]], label [[EXIT:%.*]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %gep = getelementptr [10 x [12 x i16]], ptr @a, i64 0, i64 0, i64 %iv
  %1 = load i16, ptr %gep, align 2
  %gep.off = getelementptr [10 x [12 x i16]], ptr @a, i64 0, i64 8, i64 %iv
  store i16 0, ptr %gep.off, align 2
  %iv.next = add nsw i64 %iv, 3
  %cmp = icmp ult i64 %iv, %N
  br i1 %cmp, label %loop, label %exit

exit:
  ret void
}