[llvm] [VPlan] Explicitly replicate VPInstructions by VF. (PR #155102)

[via llvm-commits]

================
@@ -3377,34 +3377,40 @@ void VPlanTransforms::materializeBuildVectors(VPlan &Plan) {
       vp_depth_first_shallow(Plan.getEntry()));
   auto VPBBsInsideLoopRegion = VPBlockUtils::blocksOnly<VPBasicBlock>(
       vp_depth_first_shallow(LoopRegion->getEntry()));
-  // Materialize Build(Struct)Vector for all replicating VPReplicateRecipes,
-  // excluding ones in replicate regions. Those are not materialized explicitly
-  // yet. Those vector users are still handled in VPReplicateRegion::execute(),
-  // via shouldPack().
+  // Materialize Build(Struct)Vector for all replicating VPReplicateRecipes and
+  // VPInstructions, excluding ones in replicate regions. Those are not
+  // materialized explicitly yet. Those vector users are still handled in
+  // VPReplicateRegion::execute(), via shouldPack().
   // TODO: materialize build vectors for replicating recipes in replicating
   // regions.
   // TODO: materialize build vectors for VPInstructions.
   for (VPBasicBlock *VPBB :
        concat<VPBasicBlock *>(VPBBsOutsideLoopRegion, VPBBsInsideLoopRegion)) {
     for (VPRecipeBase &R : make_early_inc_range(*VPBB)) {
-      auto *RepR = dyn_cast<VPReplicateRecipe>(&R);
-      auto UsesVectorOrInsideReplicateRegion = [RepR, LoopRegion](VPUser *U) {
+      auto *DefR = dyn_cast<VPRecipeWithIRFlags>(&R);
+      if (!DefR || !isa<VPReplicateRecipe, VPInstruction>(DefR))
+        continue;
+      auto UsesVectorOrInsideReplicateRegion = [DefR, LoopRegion](VPUser *U) {
         VPRegionBlock *ParentRegion =
             cast<VPRecipeBase>(U)->getParent()->getParent();
-        return !U->usesScalars(RepR) || ParentRegion != LoopRegion;
+        return !U->usesScalars(DefR) || ParentRegion != LoopRegion;
       };
-      if (!RepR || RepR->isSingleScalar() ||
-          none_of(RepR->users(), UsesVectorOrInsideReplicateRegion))
+      if ((isa<VPReplicateRecipe>(DefR) &&
+           cast<VPReplicateRecipe>(DefR)->isSingleScalar()) ||
+          (isa<VPInstruction>(DefR) &&
+           !cast<VPInstruction>(DefR)->doesGeneratePerAllLanes()) ||
+          vputils::onlyFirstLaneUsed(DefR) ||
----------------
ayalz wrote:

so should the `onlyFirstLaneUsed(DefR)` be placed under the `isa<VPInstruction>(DefR) &&`?

https://github.com/llvm/llvm-project/pull/155102