[llvm] [VPlan] Compute cost of more replicating loads/stores in ::computeCost. (PR #160053)

[Florian Hahn via llvm-commits]

================
@@ -3075,6 +3075,63 @@ bool VPReplicateRecipe::shouldPack() const {
   });
 }
 
+/// Returns true if \p Ptr is a pointer computation for which the legacy cost
+/// model computes a SCEV expression when comping the address cost.
+static bool shouldUseAddressAccessSCEV(VPValue *Ptr) {
+  auto *PtrR = Ptr->getDefiningRecipe();
+  if (!PtrR || !((isa<VPReplicateRecipe>(PtrR) &&
+                  cast<VPReplicateRecipe>(PtrR)->getOpcode() ==
+                      Instruction::GetElementPtr) ||
+                 isa<VPWidenGEPRecipe>(PtrR)))
+    return false;
+
+  // We are looking for a gep with all loop invariant indices except for one
+  // which should be an induction variable.
+  unsigned NumOperands = PtrR->getNumOperands();
+  for (unsigned Idx = 1; Idx < NumOperands; ++Idx) {
+    VPValue *Opd = PtrR->getOperand(Idx);
+    if (!(Opd->isDefinedOutsideLoopRegions()) &&
+        !isa<VPScalarIVStepsRecipe, VPWidenIntOrFpInductionRecipe>(Opd))
+      return false;
+  }
+
+  return true;
+}
+
+/// Returns true of \p V is used as part of the address of another load or
+/// store.
+static bool isUsedByLoadStoreAddress(const VPUser *V) {
+  SmallPtrSet<const VPUser *, 4> Seen;
+  SmallVector<const VPUser *> WorkList = {V};
+
+  while (!WorkList.empty()) {
+    auto *Cur = dyn_cast<VPSingleDefRecipe>(WorkList.pop_back_val());
+    if (!Cur || !Seen.insert(Cur).second)
+      continue;
+
+    for (VPUser *U : Cur->users()) {
+      if (auto *InterleaveR = dyn_cast<VPInterleaveRecipe>(U))
+        if (InterleaveR->getAddr() == Cur)
+          return true;
+      if (auto *RepR = dyn_cast<VPReplicateRecipe>(U)) {
+        if (RepR->getOpcode() == Instruction::Load &&
+            RepR->getOperand(0) == Cur)
+          return true;
+        if (RepR->getOpcode() == Instruction::Store &&
+            RepR->getOperand(1) == Cur)
+          return true;
+      }
+      if (auto *MemR = dyn_cast<VPWidenMemoryRecipe>(U)) {
----------------
fhahn wrote:

I updated the code to check for `VPInterleaveBase`. `VPWidenMemoryRecipe` should include both EVL and non EVL variants.

I don't think we need to handle histogram recipes here, as the address must be an AddRec in the current loop, so should not be able to depend on a load in the loop.

https://github.com/llvm/llvm-project/pull/160053