[llvm] cb47b87 - [LV] PreferPredicateOverEpilog respecting predicate loop hint

[Sjoerd Meijer via llvm-commits]

Author: Sjoerd Meijer
Date: 2019-11-14T13:10:44Z
New Revision: cb47b8783017a76c5f2e4b974cfd6b22c9f1d5ff

URL: https://github.com/llvm/llvm-project/commit/cb47b8783017a76c5f2e4b974cfd6b22c9f1d5ff
DIFF: https://github.com/llvm/llvm-project/commit/cb47b8783017a76c5f2e4b974cfd6b22c9f1d5ff.diff

LOG: [LV] PreferPredicateOverEpilog respecting predicate loop hint

The vectoriser queries TTI->preferPredicateOverEpilogue to determine if
tail-folding is preferred for a loop, but it was not respecting loop hint
'predicate' that can disable this, which has now been added. This showed that
we were incorrectly initialising loop hint 'vectorize.predicate.enable' with 0
(i.e. FK_Disabled) but this should have been FK_Undefined, which has been
fixed.

Differential Revision: https://reviews.llvm.org/D70125

Added: 
    

Modified: 
    llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
    llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index f43842be5357..109a7506b79f 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -72,7 +72,7 @@ LoopVectorizeHints::LoopVectorizeHints(const Loop *L,
       Interleave("interleave.count", InterleaveOnlyWhenForced, HK_UNROLL),
       Force("vectorize.enable", FK_Undefined, HK_FORCE),
       IsVectorized("isvectorized", 0, HK_ISVECTORIZED),
-      Predicate("vectorize.predicate.enable", 0, HK_PREDICATE), TheLoop(L),
+      Predicate("vectorize.predicate.enable", FK_Undefined, HK_PREDICATE), TheLoop(L),
       ORE(ORE) {
   // Populate values with existing loop metadata.
   getHintsFromMetadata();

diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index f8d3d0b8698b..af05683273d1 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7433,8 +7433,10 @@ getScalarEpilogueLowering(Function *F, Loop *L, LoopVectorizeHints &Hints,
       (F->hasOptSize() ||
        llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI)))
     SEL = CM_ScalarEpilogueNotAllowedOptSize;
-  else if (PreferPredicateOverEpilog || Hints.getPredicate() ||
-           TTI->preferPredicateOverEpilogue(L, LI, *SE, *AC, TLI, DT, LAI))
+  else if (PreferPredicateOverEpilog ||
+           Hints.getPredicate() == LoopVectorizeHints::FK_Enabled ||
+           (TTI->preferPredicateOverEpilogue(L, LI, *SE, *AC, TLI, DT, LAI) &&
+            Hints.getPredicate() != LoopVectorizeHints::FK_Disabled))
     SEL = CM_ScalarEpilogueNotNeededUsePredicate;
 
   return SEL;

diff  --git a/llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll b/llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll
index d8ada7ae607b..fda374189c86 100644
--- a/llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll
@@ -323,15 +323,12 @@ for.end:
 }
 
 define void @pragma_vect_predicate_disable(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C) #0 {
-; CHECK-LABEL: pragma_vect_predicate_disable(
-;
-; FIXME:
-; respect loop hint predicate.enable = false, and don't tail-fold here:
-;
-; 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
+; CHECK-LABEL:        pragma_vect_predicate_disable(
+; PREFER-FOLDING:     vector.body:
+; PREFER-FOLDING-NOT: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32
+; PREFER-FOLDING-NOT: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32
+; PREFER-FOLDING-NOT: call void @llvm.masked.store.v4i32.p0v4i32
+; PREFER-FOLDING:     br i1 %{{.*}}, label %{{.*}}, label %vector.body
 entry:
   br label %for.body