[LV] fold-tail predication should be respected even with assume_safety

assume_safety implies that loads under "if's" can be safely executed
speculatively (unguarded, unmasked). However this assumption holds only for the
original user "if's", not those introduced by the compiler, such as the
fold-tail "if" that guards us from loading beyond the original loop trip-count.
Currently the combination of fold-tail and assume-safety pragmas results in
ignoring the fold-tail predicate that guards the loads, generating unmasked
loads. This patch fixes this behavior.

Differential Revision: https://reviews.llvm.org/D66106

Reviewers: Ayal, hsaito, fhahn
llvm-svn: 368973

2 files changed, 5 insertions, 5 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index 8b311fa8b4c..3ac1234446c 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -869,7 +869,7 @@ bool LoopVectorizationLegality::blockNeedsPredication(BasicBlock *BB) {
 }
 
 bool LoopVectorizationLegality::blockCanBePredicated(
-    BasicBlock *BB, SmallPtrSetImpl<Value *> &SafePtrs) {
+    BasicBlock *BB, SmallPtrSetImpl<Value *> &SafePtrs, bool PreserveGuards) {
   const bool IsAnnotatedParallel = TheLoop->isAnnotatedParallel();
 
   for (Instruction &I : *BB) {
@@ -888,7 +888,7 @@ bool LoopVectorizationLegality::blockCanBePredicated(
         // !llvm.mem.parallel_loop_access implies if-conversion safety.
         // Otherwise, record that the load needs (real or emulated) masking
         // and let the cost model decide.
-        if (!IsAnnotatedParallel)
+        if (!IsAnnotatedParallel || PreserveGuards)
           MaskedOp.insert(LI);
         continue;
       }
@@ -1159,7 +1159,7 @@ bool LoopVectorizationLegality::canVectorize(bool UseVPlanNativePath) {
   return Result;
 }
 
-bool LoopVectorizationLegality::canFoldTailByMasking() {
+bool LoopVectorizationLegality::prepareToFoldTailByMasking() {
 
   LLVM_DEBUG(dbgs() << "LV: checking if tail can be folded by masking.\n");
 
@@ -1202,7 +1202,7 @@ bool LoopVectorizationLegality::canFoldTailByMasking() {
   // Check and mark all blocks for predication, including those that ordinarily
   // do not need predication such as the header block.
   for (BasicBlock *BB : TheLoop->blocks()) {
-    if (!blockCanBePredicated(BB, SafePointers)) {
+    if (!blockCanBePredicated(BB, SafePointers, /* MaskAllLoads= */ true)) {
       reportVectorizationFailure(
           "Cannot fold tail by masking as required",
           "control flow cannot be substituted for a select",
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 20305416079..dac48a1d814 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4853,7 +4853,7 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF() {
   // found modulo the vectorization factor is not zero, try to fold the tail
   // by masking.
   // FIXME: look for a smaller MaxVF that does divide TC rather than masking.
-  if (Legal->canFoldTailByMasking()) {
+  if (Legal->prepareToFoldTailByMasking()) {
     FoldTailByMasking = true;
     return MaxVF;
   }