[llvm] [LV][POC] Use umin to avoid second-to-last iteration problems with EVL (PR #143434)

[Mel Chen via llvm-commits]

================
@@ -2273,55 +2270,34 @@ bool VPlanTransforms::tryAddExplicitVectorLength(
   // The transform updates all users of inductions to work based on EVL, instead
   // of the VF directly. At the moment, widened inductions cannot be updated, so
   // bail out if the plan contains any.
-  bool ContainsWidenInductions = any_of(
-      Header->phis(),
-      IsaPred<VPWidenIntOrFpInductionRecipe, VPWidenPointerInductionRecipe>);
-  if (ContainsWidenInductions)
-    return false;
 
   auto *CanonicalIVPHI = Plan.getCanonicalIV();
-  VPValue *StartV = CanonicalIVPHI->getStartValue();
 
-  // Create the ExplicitVectorLengthPhi recipe in the main loop.
-  auto *EVLPhi = new VPEVLBasedIVPHIRecipe(StartV, DebugLoc());
-  EVLPhi->insertAfter(CanonicalIVPHI);
   VPBuilder Builder(Header, Header->getFirstNonPhi());
   // Compute original TC - IV as the AVL (application vector length).
   VPValue *AVL = Builder.createNaryOp(
-      Instruction::Sub, {Plan.getTripCount(), EVLPhi}, DebugLoc(), "avl");
+      Instruction::Sub, {Plan.getTripCount(), CanonicalIVPHI}, DebugLoc(), "avl");
   if (MaxSafeElements) {
     // Support for MaxSafeDist for correct loop emission.
     VPValue *AVLSafe = Plan.getOrAddLiveIn(
         ConstantInt::get(CanonicalIVPHI->getScalarType(), *MaxSafeElements));
     VPValue *Cmp = Builder.createICmp(ICmpInst::ICMP_ULT, AVL, AVLSafe);
     AVL = Builder.createSelect(Cmp, AVL, AVLSafe, DebugLoc(), "safe_avl");
   }
-  auto *VPEVL = Builder.createNaryOp(VPInstruction::ExplicitVectorLength, AVL,
-                                     DebugLoc());
 
-  auto *CanonicalIVIncrement =
-      cast<VPInstruction>(CanonicalIVPHI->getBackedgeValue());
-  Builder.setInsertPoint(CanonicalIVIncrement);
-  VPSingleDefRecipe *OpVPEVL = VPEVL;
-  if (unsigned IVSize = CanonicalIVPHI->getScalarType()->getScalarSizeInBits();
-      IVSize != 32) {
-    OpVPEVL = Builder.createScalarCast(
-        IVSize < 32 ? Instruction::Trunc : Instruction::ZExt, OpVPEVL,
-        CanonicalIVPHI->getScalarType(), CanonicalIVIncrement->getDebugLoc());
-  }
-  auto *NextEVLIV = Builder.createOverflowingOp(
-      Instruction::Add, {OpVPEVL, EVLPhi},
-      {CanonicalIVIncrement->hasNoUnsignedWrap(),
-       CanonicalIVIncrement->hasNoSignedWrap()},
-      CanonicalIVIncrement->getDebugLoc(), "index.evl.next");
-  EVLPhi->addOperand(NextEVLIV);
+  // This is just a umin pattern
+  VPValue &VFxUF = Plan.getVFxUF();
+  VPValue *Cmp = Builder.createICmp(ICmpInst::ICMP_ULT, AVL, &VFxUF);
----------------
Mel-Chen wrote:

I think it's because VPBuilder currently doesn't provide a way to create min/max intrinsics, and VPInstruction doesn't have a recipe for min/max yet either.

https://github.com/llvm/llvm-project/pull/143434