summaryrefslogtreecommitdiffstats
path: root/llvm
diff options
context:
space:
mode:
authorSjoerd Meijer <sjoerd.meijer@arm.com>2019-11-14 13:10:44 +0000
committerSjoerd Meijer <sjoerd.meijer@arm.com>2019-11-14 13:10:44 +0000
commitcb47b8783017a76c5f2e4b974cfd6b22c9f1d5ff (patch)
tree4ccb2ed64e2fabb3f8dd682e27121a263ab88a66 /llvm
parent1c247dd028b368875bc36cd2a9ccc7fd90507776 (diff)
downloadbcm5719-llvm-cb47b8783017a76c5f2e4b974cfd6b22c9f1d5ff.tar.gz
bcm5719-llvm-cb47b8783017a76c5f2e4b974cfd6b22c9f1d5ff.zip
[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
Diffstat (limited to 'llvm')
-rw-r--r--llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp2
-rw-r--r--llvm/lib/Transforms/Vectorize/LoopVectorize.cpp6
-rw-r--r--llvm/test/Transforms/LoopVectorize/ARM/prefer-tail-loop-folding.ll15
3 files changed, 11 insertions, 12 deletions
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index f43842be535..109a7506b79 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 f8d3d0b8698..af05683273d 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 d8ada7ae607..fda374189c8 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
OpenPOWER on IntegriCloud