[llvm] [VPlan] First step towards VPlan cost modeling. (PR #67934)

via llvm-commits llvm-commits at lists.llvm.org
Wed May 8 13:02:41 PDT 2024


================
@@ -361,6 +364,9 @@ class LoopVectorizationPlanner {
   /// Return the best VPlan for \p VF.
   VPlan &getBestPlanFor(ElementCount VF) const;
 
+  /// Return the most profitable plan.
----------------
ayalz wrote:

nit: every plan contains its VF range; reduce the range of the best plan to a single value, instead of passing it alongside? Method should be const?

https://github.com/llvm/llvm-project/pull/67934


More information about the llvm-commits mailing list