[PATCH] D65197: [LV] Tail-loop Folding

[Michael Kruse via Phabricator via llvm-commits]

Meinersbur added a comment.

Looks fine to me, but see what the other reviewers say.



================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:869-879
+                             PredicatedScalarEvolution &PSE, LoopInfo *LI,
+                             LoopVectorizationLegality *Legal,
                              const TargetTransformInfo &TTI,
                              const TargetLibraryInfo *TLI, DemandedBits *DB,
                              AssumptionCache *AC,
                              OptimizationRemarkEmitter *ORE, const Function *F,
                              const LoopVectorizeHints *Hints,
----------------
[nit] this seems unrelated?


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:7280-7281
 
-  ScalarEpilogueLowering SEL = CM_ScalarEpilogueAllowed;
-  if (Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
-      (F->hasOptSize() ||
-       llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI)))
-    SEL = CM_ScalarEpilogueNotAllowedOptSize;
-
-  LoopVectorizationCostModel CM(SEL, L, PSE, LI, LVL, *TTI, TLI,
-                                DB, AC, ORE, F, &Hints, IAI);
+  LoopVectorizationCostModel CM(SEL, L, PSE, LI, LVL, *TTI, TLI, DB, AC, ORE, F,
+                                &Hints, IAI);
   // Use the planner for outer loop vectorization.
----------------
[nit] formatting-only change?


================
Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:7465-7466
   // Use the cost model.
-  LoopVectorizationCostModel CM(SEL, L, PSE, LI, &LVL, *TTI, TLI,
-                                DB, AC, ORE, F, &Hints, IAI);
+  LoopVectorizationCostModel CM(SEL, L, PSE, LI, &LVL, *TTI, TLI, DB, AC, ORE,
+                                F, &Hints, IAI);
   CM.collectValuesToIgnore();
----------------
[nit] unrelated change?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D65197/new/

https://reviews.llvm.org/D65197