[llvm] [LV] Create block in mask up-front if needed. (PR #76635)

[via llvm-commits]

================
@@ -8659,23 +8663,28 @@ LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range) {
   bool HasNUW = Style == TailFoldingStyle::None;
   addCanonicalIVRecipes(*Plan, Legal->getWidestInductionType(), HasNUW, DL);
 
-  // Proactively create header mask. Masks for other blocks are created on
-  // demand.
-  RecipeBuilder.createHeaderMask(*Plan);
-
   // Scan the body of the loop in a topological order to visit each basic block
   // after having visited its predecessor basic blocks.
   LoopBlocksDFS DFS(OrigLoop);
   DFS.perform(LI);
 
   VPBasicBlock *VPBB = HeaderVPBB;
+  bool NeedsMasks = CM.foldTailByMasking() ||
+                    any_of(OrigLoop->blocks(), [this](BasicBlock *BB) {
+                      return Legal->blockNeedsPredication(BB);
+                    });
   for (BasicBlock *BB : make_range(DFS.beginRPO(), DFS.endRPO())) {
     // Relevant instructions from basic block BB will be grouped into VPRecipe
     // ingredients and fill a new VPBasicBlock.
     if (VPBB != HeaderVPBB)
       VPBB->setName(BB->getName());
     Builder.setInsertPoint(VPBB);
 
+    if (VPBB == HeaderVPBB)
+      RecipeBuilder.createHeaderMask(*Plan);
----------------
ayalz wrote:

nit: this retains the previous behavior of always creating a mask for HeaderVPBB, proactively. But we can refrain from doing so if !NeedsMasks.

https://github.com/llvm/llvm-project/pull/76635