[llvm] [SLP] Account for GEP pointer-chain cost when root scalars feed load/store indices (PR #192726)

[Alexey Bataev via llvm-commits]

================
@@ -19073,6 +19093,41 @@ InstructionCost BoUpSLP::getTreeCost(InstructionCost TreeCost,
 
     ExtractCost += ExtraCost;
   }
+  // Charge the pointer-chain cost difference once for the root entry when
+  // every external use of its scalars is a GEP feeding a single load/store
+  // (see the detection loop above). Vectorizing the root in this pattern
+  // forces lane extracts (or a vector GEP with unknown stride) to drive the
+  // address computation, which is typically more expensive than keeping the
+  // indices scalar in a unit-stride address chain. Add the delta once rather
+  // than per external use.
+  if (AllUsersGEPSWithStoresLoads && !Pointers.empty()) {
+    const TreeEntry &RootEntry = *VectorizableTree.front();
+    const bool AnyRootKeptAsScalar = any_of(RootEntry.Scalars, [&](Value *V) {
+      return ExternalUsesAsOriginalScalar.contains(V);
+    });
+    const Value *CommonBase = nullptr;
+    bool HaveCommonBase = true;
+    for (const Value *P : Pointers) {
+      const Value *Op = cast<GetElementPtrInst>(P)->getPointerOperand();
+      if (!CommonBase)
+        CommonBase = Op;
+      else if (CommonBase != Op) {
+        HaveCommonBase = false;
+        break;
+      }
+    }
+    if (!AnyRootKeptAsScalar && HaveCommonBase) {
+      TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+      auto *VecTy = getWidenedType(UserScalarTy, RootEntry.Scalars.size());
+      InstructionCost ScalarGEPCost = TTI->getPointersChainCost(
+          Pointers, CommonBase, TTI::PointersChainInfo::getUnitStride(),
+          UserScalarTy, CostKind);
+      InstructionCost VectorGEPCost = TTI->getPointersChainCost(
+          Pointers, CommonBase, TTI::PointersChainInfo::getUnknownStride(),
----------------
alexey-bataev wrote:

For a bunch of GEPs to be vectorized. But for scalar GEPs there is no precise estimation for now, so just mimic it as PointersChainInfo::UnitStride

https://github.com/llvm/llvm-project/pull/192726