[ARM][MVE] Tail-predication: use unsigned SCEV ranges for tripcount

[SjoerdMeijer]

Summary

Tripcount expressions have a positive range, so use unsigned scev ranges for it.

[SjoerdMeijer]

test case clean up.

[samparker]

Cheers!

llvm/lib/Target/ARM/MVETailPredication.cpp

bool MVETailPredication::IsSafeActiveMask(IntrinsicInst *ActiveLaneMask,
   // Because of a lack of context, it is difficult to get a useful bounds on
   // this expression. But since ElementCount uses the same variables as the
   // TripCount (TC), for which we can find meaningful value ranges, we use that
   // instead and assert that:
   //
   //     upperbound(TC) <= UINT_MAX - VectorWidth
   //
   unsigned SizeInBits = TripCount->getType()->getScalarSizeInBits();
-  auto Diff = APInt(SizeInBits, ~0) - APInt(SizeInBits, VectorWidth);
-  uint64_t MaxMinusVW = Diff.getZExtValue();
-  // FIXME: since ranges can be negative we work with signed ranges here, but
-  // we shouldn't extract the zext'ed values for them.
-  uint64_t UpperboundTC = SE->getSignedRange(TC).getUpper().getZExtValue();
+  auto MaxMinusVW = APInt(SizeInBits, ~0) - APInt(SizeInBits, VectorWidth);
+  APInt UpperboundTC = SE->getUnsignedRangeMax(TC);
 
-  if (UpperboundTC > MaxMinusVW && !ForceTailPredication) {
+  if (UpperboundTC.ugt(MaxMinusVW) && !ForceTailPredication) {
     LLVM_DEBUG(dbgs() << "ARM TP: Overflow possible in tripcount rounding:\n";
                dbgs() << "upperbound(TC) <= UINT_MAX - VectorWidth\n";
                dbgs() << UpperboundTC << " <= " << MaxMinusVW << " == false\n";);
     return false;
   }
 
   // 2.2) Make sure overflow doesn't happen in final expression:
   //  (((ElementCount + (VectorWidth - 1)) / VectorWidth) - TripCount,
bool MVETailPredication::IsSafeActiveMask(IntrinsicInst *ActiveLaneMask,
 
   // Tmp = ElementCount + (VW-1)
   auto *ECPlusVWMinus1 = SE->getAddExpr(EC,
       SE->getSCEV(ConstantInt::get(TripCount->getType(), VectorWidth - 1)));
   // Ceil = ElementCount + (VW-1) / VW
   auto *Ceil = SE->getUDivExpr(ECPlusVWMinus1,
       SE->getSCEV(ConstantInt::get(TripCount->getType(), VectorWidth)));
 
-  ConstantRange RangeCeil = SE->getSignedRange(Ceil) ;
-  ConstantRange RangeTC = SE->getSignedRange(TC) ;
+  ConstantRange RangeCeil = SE->getUnsignedRange(Ceil) ;
+  ConstantRange RangeTC = SE->getUnsignedRange(TC) ;
   if (!RangeTC.isSingleElement()) {
     auto ZeroRange =
         ConstantRange(APInt(TripCount->getType()->getScalarSizeInBits(), 0));
     RangeTC = RangeTC.unionWith(ZeroRange);
   }
   if (!RangeTC.contains(RangeCeil) && !ForceTailPredication) {
     LLVM_DEBUG(dbgs() << "ARM TP: Overflow possible in sub\n");
     return false;