[LV] Disable Scalable VFs when tail folding is enabled b/c of low tripcount.

[sdesmalen]

Summary

The loop vectorizer may decide to use tail folding when the trip-count
is low. When that happens, scalable VFs are no longer a candidate,
since tail folding/predication is not yet supported for scalable vectors.

This can be re-enabled in a future patch.

[kmclaughlin]

This patch LGTM!

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

const SCEV *Rem = SE->getURemExpr(
         SE->getConstant(BackedgeTakenCount->getType(), MaxVFtimesIC));
     if (Rem->isZero()) {
       // Accept MaxFixedVF if we do not have a tail.
       LLVM_DEBUG(dbgs() << "LV: No tail will remain for any chosen VF.\n");
       return MaxFactors;
     }
   }
 
+  // For scalable vectors, don't use tail folding as this is currently not yet
+  // supported. The code is likely to have ended up here if the tripcount is
+  // low, in which case it makes sense not to use scalable vectors.
+  if (MaxFactors.ScalableVF.isVector())
+    MaxFactors.ScalableVF = ElementCount::getScalable(0);
+
   // If we don't know the precise trip count, or if the trip count that we
   // found modulo the vectorization factor is not zero, try to fold the tail
   // by masking.
   // FIXME: look for a smaller MaxVF that does divide TC rather than masking.
   if (Legal->prepareToFoldTailByMasking()) {
     FoldTailByMasking = true;
     return MaxFactors;
   }

llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll

+; RUN: opt -S -loop-vectorize -scalable-vectorization=preferred -prefer-predicate-over-epilogue=predicate-dont-vectorize < %s | FileCheck %s
+
+; CHECK-NOT: vector.body:
+
+target triple = "aarch64-unknown-linux-gnu"
+
+define void @tail_predication(i32 %init, i32* %ptr, i32 %val) #0 {
+entry:
+  br label %while.body
+
+while.body:                                       ; preds = %while.body, %entry
+  %index = phi i32 [ %index.dec, %while.body ], [ %init, %entry ]
+  %gep = getelementptr i32, i32* %ptr, i32 %index
+  store i32 %val, i32* %gep
+  %index.dec = add nsw i32 %index, -1
+  %cmp10 = icmp sgt i32 %index, 0
+  br i1 %cmp10, label %while.body, label %while.end.loopexit
+
+while.end.loopexit:                               ; preds = %while.body
+  ret void
+}
+
+attributes #0 = { "target-features"="+sve" }