[VPlan] Simplify ExplicitVectorLength(%AVL) -> %AVL when AVL <= VF (#167647)

[`llvm.experimental.get.vector.length`](https://llvm.org/docs/LangRef.html#id2399)
has the property that if the AVL (%cnt) is less than or equal to VF
(%max_lanes) then the return value is just AVL.

This patch uses SCEV to simplify this in optimizeForVFAndUF, and adds
`ExplicitVectorLength` to
`VPInstruction::opcodeMayReadOrWriteFromMemory` so it gets removed once
dead.

1 files changed, 30 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index e8fea6851dae..7fe40c3e0490 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1843,6 +1843,35 @@ static bool simplifyBranchConditionForVFAndUF(VPlan &Plan, ElementCount BestVF,
   return true;
 }
 
+/// From the definition of llvm.experimental.get.vector.length,
+/// VPInstruction::ExplicitVectorLength(%AVL) = %AVL when %AVL <= VF.
+static bool simplifyKnownEVL(VPlan &Plan, ElementCount VF,
+                             PredicatedScalarEvolution &PSE) {
+  for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
+           vp_depth_first_deep(Plan.getEntry()))) {
+    for (VPRecipeBase &R : *VPBB) {
+      VPValue *AVL;
+      if (!match(&R, m_EVL(m_VPValue(AVL))))
+        continue;
+
+      ScalarEvolution &SE = *PSE.getSE();
+      const SCEV *AVLSCEV = vputils::getSCEVExprForVPValue(AVL, SE);
+      if (isa<SCEVCouldNotCompute>(AVLSCEV))
+        continue;
+      const SCEV *VFSCEV = SE.getElementCount(AVLSCEV->getType(), VF);
+      if (!SE.isKnownPredicate(CmpInst::ICMP_ULE, AVLSCEV, VFSCEV))
+        continue;
+
+      VPValue *Trunc = VPBuilder(&R).createScalarZExtOrTrunc(
+          AVL, Type::getInt32Ty(Plan.getContext()), AVLSCEV->getType(),
+          R.getDebugLoc());
+      R.getVPSingleValue()->replaceAllUsesWith(Trunc);
+      return true;
+    }
+  }
+  return false;
+}
+
 void VPlanTransforms::optimizeForVFAndUF(VPlan &Plan, ElementCount BestVF,
                                          unsigned BestUF,
                                          PredicatedScalarEvolution &PSE) {
@@ -1852,6 +1881,7 @@ void VPlanTransforms::optimizeForVFAndUF(VPlan &Plan, ElementCount BestVF,
   bool MadeChange = tryToReplaceALMWithWideALM(Plan, BestVF, BestUF);
   MadeChange |= simplifyBranchConditionForVFAndUF(Plan, BestVF, BestUF, PSE);
   MadeChange |= optimizeVectorInductionWidthForTCAndVFUF(Plan, BestVF, BestUF);
+  MadeChange |= simplifyKnownEVL(Plan, BestVF, PSE);
 
   if (MadeChange) {
     Plan.setVF(BestVF);