Reapply "[RISCV][LoopVectorize] Use DataWithEVL as the preferred tail folding style (llvm#148686)"

This reverts commit 25e97fc.

The original commit was reverted due to a crash in llvm-test-suite. The
crash stemmed from a multiply reduction, which isn't supported for
scalable VFs on RISC-V. But for EVL tail folding we only support
scalable VFs, so when -force-tail-folding-style=data-with-evl is
specified we check to see if there's a scalable VF, and fall back to
data-without-lane-mask if there isn't.

This is done in setTailFoldingStyles, but previously we were only
checking if the forced tail folding style was legal, not the style
returned by TTI.

This version fixes this by checking the actual computed tail folding
style and not just the forced one, and adds a test for the crash in
llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll

Author: lukel97

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h

@@ -116,8 +116,8 @@ class RISCVTTIImpl final : public BasicTTIImplBase<RISCVTTIImpl> {
   }
   TailFoldingStyle
   getPreferredTailFoldingStyle(bool IVUpdateMayOverflow) const override {
-    return ST->hasVInstructions() ? TailFoldingStyle::Data
-                                  : TailFoldingStyle::DataWithoutLaneMask;
+    return ST->hasVInstructions() ? TailFoldingStyle::DataWithEVL
+                                  : TailFoldingStyle::None;
   }
   std::optional<unsigned> getMaxVScale() const override;
   std::optional<unsigned> getVScaleForTuning() const override;

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1354,9 +1354,10 @@ class LoopVectorizationCostModel {
       ChosenTailFoldingStyle = {ForceTailFoldingStyle.getValue(),
                                 ForceTailFoldingStyle.getValue()};
 
-    if (ForceTailFoldingStyle != TailFoldingStyle::DataWithEVL)
+    if (ChosenTailFoldingStyle->first != TailFoldingStyle::DataWithEVL &&
+        ChosenTailFoldingStyle->second != TailFoldingStyle::DataWithEVL)
       return;
-    // Override forced styles if needed.
+    // Override EVL styles if needed.
     // FIXME: Investigate opportunity for fixed vector factor.
     bool EVLIsLegal = UserIC <= 1 && IsScalableVF &&
                       TTI.hasActiveVectorLength() && !EnableVPlanNativePath;

llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll

@@ -133,15 +133,15 @@ define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
 ; CHECK-NEXT:    [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 4
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 8)
+; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 8, i32 4, i1 true)
 ; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8:%.*]], i32 0
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP9]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_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:    [[TMP10:%.*]] = shl <vscale x 4 x i8> [[WIDE_MASKED_LOAD]], splat (i8 1)
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[TMP11:%.*]], i32 0
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP12]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_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:    [[TMP13:%.*]] = add <vscale x 4 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i32 0
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP13]], ptr [[TMP14]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT:    call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP13]], ptr align 1 [[TMP14]], <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:%.*]]
@@ -358,3 +358,64 @@ for.end:                                          ; preds = %for.body
 
 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 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:    [[VEC_PHI:%.*]] = phi <16 x i8> [ <i8 2, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>, [[VECTOR_PH]] ], [ [[TMP2:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i64> poison, i64 [[INDEX]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT]], <16 x i64> poison, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[VEC_IV:%.*]] = add <16 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = icmp ule <16 x i64> [[VEC_IV]], splat (i64 9)
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i8, ptr [[TMP0]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <16 x i8> @llvm.masked.load.v16i8.p0(ptr [[TMP1]], i32 1, <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> poison)
+; CHECK-NEXT:    [[TMP2]] = mul <16 x i8> [[WIDE_MASKED_LOAD]], [[VEC_PHI]]
+; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i8> [[TMP2]], <16 x i8> [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[TMP4:%.*]] = call i8 @llvm.vector.reduce.mul.v16i8(<16 x i8> [[TMP3]])
+; CHECK-NEXT:    br label [[FOR_END:%.*]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i8 [ 2, [[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:    [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX]], [[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 [[LOOP8:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    [[MUL_LCSSA:%.*]] = phi i8 [ [[MUL]], [[FOR_BODY]] ], [ [[TMP4]], [[MIDDLE_BLOCK]] ]
+; 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
+}

llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll

@@ -7,29 +7,49 @@ define void @test(ptr %p, i64 %a, i8 %b) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH1:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i8> poison, i8 [[B]], i64 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i8> [[BROADCAST_SPLATINSERT]], <16 x i8> poison, <16 x i32> zeroinitializer
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <16 x i64> poison, i64 [[A]], i64 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT1]], <16 x i64> poison, <16 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = shl <16 x i64> [[BROADCAST_SPLAT2]], splat (i64 48)
-; CHECK-NEXT:    [[TMP1:%.*]] = ashr <16 x i64> [[TMP0]], splat (i64 52)
-; CHECK-NEXT:    [[TMP2:%.*]] = trunc <16 x i64> [[TMP1]] to <16 x i32>
-; CHECK-NEXT:    [[TMP3:%.*]] = zext <16 x i8> [[BROADCAST_SPLAT]] to <16 x i32>
+; 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:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[FOR_COND]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <16 x i32> [ <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_COND]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 9)
-; CHECK-NEXT:    [[TMP4:%.*]] = icmp sge <16 x i32> [[VEC_IND]], splat (i32 2)
-; CHECK-NEXT:    [[TMP5:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i1> [[TMP4]], <16 x i1> zeroinitializer
-; CHECK-NEXT:    [[PREDPHI:%.*]] = select <16 x i1> [[TMP5]], <16 x i32> [[TMP2]], <16 x i32> [[TMP3]]
-; CHECK-NEXT:    [[TMP6:%.*]] = shl <16 x i32> [[PREDPHI]], splat (i32 8)
-; CHECK-NEXT:    [[TMP8:%.*]] = trunc <16 x i32> [[TMP6]] to <16 x i8>
-; CHECK-NEXT:    [[TMP40:%.*]] = extractelement <16 x i8> [[TMP8]], i32 15
-; CHECK-NEXT:    store i8 [[TMP40]], ptr [[P]], align 1
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 16
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <16 x i32> [[VEC_IND]], splat (i32 16)
-; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[FOR_COND]], !llvm.loop [[LOOP0:![0-9]+]]
+; 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:%.*]] = sub i32 9, [[EVL_BASED_IV]]
+; CHECK-NEXT:    [[TMP11:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT:    [[TMP12:%.*]] = mul i32 1, [[TMP11]]
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP12]], 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:    [[TMP13:%.*]] = icmp ule <vscale x 2 x i32> [[VEC_IND]], splat (i32 8)
+; 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:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP4]]
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i32> [[VEC_IND]], [[BROADCAST_SPLAT6]]
+; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; 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:
@@ -52,7 +72,7 @@ define void @test(ptr %p, i64 %a, i8 %b) {
 ; 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 [[LOOP3:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_COND1]], label [[EXIT1]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
@@ -84,8 +104,9 @@ exit:                                             ; preds = %for.body
   ret void
 }
 ;.
-; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]], [[META3:![0-9]+]]}
 ; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
-; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
-; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
+; CHECK: [[META2]] = !{!"llvm.loop.isvectorized.tailfoldingstyle", !"evl"}
+; CHECK: [[META3]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META3]], [[META1]]}
 ;.