[LV] PreferPredicateOverEpilog respecting option

[SjoerdMeijer]

Summary

Follow-up of cb47b8783: don't query TTI->preferPredicateOverEpilogue when option -prefer-predicate-over-epilog is set to false, i.e. when we prefer not to predicate the loop.

[samparker]

LGTM

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

 static ScalarEpilogueLowering
 getScalarEpilogueLowering(Function *F, Loop *L, LoopVectorizeHints &Hints,
                           ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI,
                           TargetTransformInfo *TTI, TargetLibraryInfo *TLI,
                           AssumptionCache *AC, LoopInfo *LI,
                           ScalarEvolution *SE, DominatorTree *DT,
                           const LoopAccessInfo *LAI) {
   ScalarEpilogueLowering SEL = CM_ScalarEpilogueAllowed;
+  bool PredicateOptDisabled = PreferPredicateOverEpilog.getNumOccurrences() &&
+                              !PreferPredicateOverEpilog;
+
   if (Hints.getForce() != LoopVectorizeHints::FK_Enabled &&
       (F->hasOptSize() ||
        llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI)))
     SEL = CM_ScalarEpilogueNotAllowedOptSize;
   else if (PreferPredicateOverEpilog ||
            Hints.getPredicate() == LoopVectorizeHints::FK_Enabled ||
            (TTI->preferPredicateOverEpilogue(L, LI, *SE, *AC, TLI, DT, LAI) &&
-            Hints.getPredicate() != LoopVectorizeHints::FK_Disabled))
+            Hints.getPredicate() != LoopVectorizeHints::FK_Disabled &&
+            !PredicateOptDisabled))
     SEL = CM_ScalarEpilogueNotNeededUsePredicate;
 
   return SEL;
 }
 
 // Process the loop in the VPlan-native vectorization path. This path builds
 // VPlan upfront in the vectorization pipeline, which allows to apply
 // VPlan-to-VPlan transformations from the very beginning without modifying the

llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll

 ; RUN:   -enable-arm-maskedldst=true -S < %s | \
 ; RUN:   FileCheck %s -check-prefixes=CHECK,NO-FOLDING
 
 ; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp \
 ; RUN:   -disable-mve-tail-predication=false -loop-vectorize \
 ; RUN:   -enable-arm-maskedldst=true -S < %s | \
 ; RUN:   FileCheck %s -check-prefixes=CHECK,PREFER-FOLDING
 
+; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp \
+; RUN:   -prefer-predicate-over-epilog=false \
+; RUN:   -disable-mve-tail-predication=false -loop-vectorize \
+; RUN:   -enable-arm-maskedldst=true -S < %s | \
+; RUN:   FileCheck %s -check-prefixes=CHECK,NO-FOLDING
+
+; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp \
+; RUN:   -prefer-predicate-over-epilog=true \
+; RUN:   -disable-mve-tail-predication=false -loop-vectorize \
+; RUN:   -enable-arm-maskedldst=true -S < %s | \
+; RUN:   FileCheck %s -check-prefixes=CHECK,FOLDING-OPT
+
 define void @prefer_folding(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C) #0 {
 ; CHECK-LABEL:    prefer_folding(
 ; PREFER-FOLDING: vector.body:
 ; PREFER-FOLDING: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32
 ; PREFER-FOLDING: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32
 ; PREFER-FOLDING: call void @llvm.masked.store.v4i32.p0v4i32
 ; PREFER-FOLDING: br i1 %{{.*}}, label %{{.*}}, label %vector.body
 ;

 }
 
 define void @narrowing_load_not_allowed(i8* noalias nocapture %A, i8* noalias nocapture readonly %B, i16* noalias nocapture readonly %C) #0 {
 ; CHECK-LABEL:        narrowing_load_not_allowed(
 ; PREFER-FOLDING:     vector.body:
 ; PREFER-FOLDING-NOT: llvm.masked.load
 ; PREFER-FOLDING-NOT: llvm.masked.store
 ; PREFER-FOLDING:     br i1 %{{.*}}, label %{{.*}}, label %vector.body
+
+; FOLDING-OPT:        vector.body:
+; FOLDING-OPT         call <8 x i16> @llvm.masked.load.v8i16.p0v8i16
+; FOLDING-OPT         call <8 x i8> @llvm.masked.load.v8i8.p0v8i8
+; FOLDING-OPT         call void @llvm.masked.store.v8i8.p0v8i8
+; FOLDING-OPT:        br i1 %{{.*}}, label %{{.*}}, label %vector.body
 entry:
   br label %for.body
 
 for.cond.cleanup:                                 ; preds = %for.body
   ret void
 
 for.body:                                         ; preds = %for.body, %entry
   %i.012 = phi i32 [ 0, %entry ], [ %add6, %for.body ]