[llvm] [LV] Support tail-folded epilogue loops (PR #208764)

[Florian Hahn via llvm-commits]

================
@@ -5401,22 +5414,30 @@ void LoopVectorizationPlanner::plan(ElementCount UserVF, unsigned UserIC) {
       // Collect the instructions (and their associated costs) that will be more
       // profitable to scalarize.
       CM->collectNonVectorizedAndSetWideningDecisions(UserVF);
-      buildVPlans(*VPlan1, UserVF, UserVF);
-      ElementCount EpilogueUserVF = EpilogueVectorizationForceVF;
-      if (EpilogueUserVF.isVector() &&
-          ElementCount::isKnownLT(EpilogueUserVF, UserVF)) {
-        CM->collectNonVectorizedAndSetWideningDecisions(EpilogueUserVF);
-        buildVPlans(*VPlan1, EpilogueUserVF, EpilogueUserVF);
-      }
-      if (!VPlans.empty() && VPlans.front()->getSingleVF() == UserVF) {
-        // For scalar VF, skip VPlan cost check as VPlan cost is designed for
-        // vector VFs only.
-        if (UserVF.isScalar() ||
-            cost(*VPlans.front(), UserVF, /*RU=*/nullptr).isValid()) {
-          LLVM_DEBUG(dbgs() << "LV: Using user VF " << UserVF << ".\n");
-          LLVM_DEBUG(printPlans(dbgs()));
-          return;
+      // Build the main-loop VPlan firstly because if epilogue tail-folding is
+      // enabled, it will be built later, so we keep the epilogue vplans at the
+      // end.
+      buildVPlans(*VPlan1, UserVF, UserVF, *CM);
+
+      // For scalar VF, skip VPlan cost check as VPlan cost is designed for
+      // vector VFs only.
+      if (!VPlans.empty() && (VPlans.front()->getSingleVF() == UserVF) &&
+          (UserVF.isScalar() ||
+           cost(*VPlans.front(), UserVF, /*RU=*/nullptr, *CM).isValid())) {
+        // Plan for epilogue only if we succeeded in building main loop Vplan.
+        // Try to plan for tail-folded epilogue if it's enabled/doable,
----------------
fhahn wrote:

```suggestion
        // Try to build a tail-folded epilogue VPlan. Otherwise build regular plan for the epilogue.
```

https://github.com/llvm/llvm-project/pull/208764