Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2695,8 +2695,11 @@
     if (C->isZero())
       return;
 
+  // FIXME: FoldTailByMasking no longer implies OptForSize, this should be
+  // checking CM_ScalarEpilogueNotAllowedOptSize
   assert(!Cost->foldTailByMasking() &&
          "Cannot SCEV check stride or overflow when folding tail");
+
   // Create a new block containing the stride check.
   BB->setName("vector.scevcheck");
   auto *NewBB = BB->splitBasicBlock(BB->getTerminator(), "vector.ph");
@@ -2729,7 +2732,6 @@
   if (!MemRuntimeCheck)
     return;
 
-  assert(!Cost->foldTailByMasking() && "Cannot check memory when folding tail");
   // Create a new block containing the memory check.
   BB->setName("vector.memcheck");
   auto *NewBB = BB->splitBasicBlock(BB->getTerminator(), "vector.ph");
Index: llvm/test/Transforms/LoopVectorize/X86/tail-folding-memcheck.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopVectorize/X86/tail-folding-memcheck.ll
@@ -0,0 +1,38 @@
+; RUN: opt < %s  -loop-vectorize -mcpu=core-avx2 -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define dso_local void @_Z1GPiS_S_(i32* nocapture %A, i32* nocapture readonly %B, i32* nocapture readonly %C) local_unnamed_addr #0 {
+; CHECK-LABEL: @_Z1GPiS_S_
+; CHECK: vector.memcheck:
+; CHECK: vector.body:
+; CHECK: @llvm.masked.load.v8i32.p0v8i32
+; CHECK: @llvm.masked.load.v8i32.p0v8i32
+; CHECK: @llvm.masked.store.v8i32.p0v8i32
+; CHECK: br i1 %12, label %middle.block, label %vector.body
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
+  %1 = load i32, i32* %arrayidx2, align 4
+  %add = add nsw i32 %1, %0
+  %arrayidx4 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
+  store i32 %add, i32* %arrayidx4, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 430
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body, !llvm.loop !6
+}
+
+attributes #0 = { nofree norecurse nounwind uwtable }
+
+!6 = distinct !{!6, !7, !8}
+!7 = !{!"llvm.loop.vectorize.predicate.enable", i1 true}
+!8 = !{!"llvm.loop.vectorize.enable", i1 true}