diff options
author | Anna Thomas <anna@azul.com> | 2017-09-12 16:32:45 +0000 |
---|---|---|
committer | Anna Thomas <anna@azul.com> | 2017-09-12 16:32:45 +0000 |
commit | 269112230203d28dd04beab3ecc09dbab4c75b6e (patch) | |
tree | 5cd916bf9d8d6f6bac11499ba82ce15c1fc95571 /lib/Transforms/Vectorize/LoopVectorize.cpp | |
parent | b24dbf12cd3a3ec11e392be12c195b287b3ed97e (diff) |
[LV] Clamp the VF to the trip count
Summary:
When the MaxVectorSize > ConstantTripCount, we should just clamp the
vectorization factor to be the ConstantTripCount.
This vectorizes loops where the TinyTripCountThreshold >= TripCount < MaxVF.
Earlier we were finding the maximum vector width, which could be greater than
the trip count itself. The Loop vectorizer does all the work for generating a
vectorizable loop, but in the end we would always choose the scalar loop (since
the VF > trip count). This allows us to choose the VF keeping in mind the trip
count if available.
This is a fix on top of rL312472.
Reviewers: Ayal, zvi, hfinkel, dneilson
Reviewed by: Ayal
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37702
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313046 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Transforms/Vectorize/LoopVectorize.cpp')
-rw-r--r-- | lib/Transforms/Vectorize/LoopVectorize.cpp | 19 |
1 files changed, 12 insertions, 7 deletions
diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp index fac76ba643c..5267a2a3f19 100644 --- a/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -1960,7 +1960,7 @@ public: private: /// \return An upper bound for the vectorization factor, larger than zero. /// One is returned if vectorization should best be avoided due to cost. - unsigned computeFeasibleMaxVF(bool OptForSize, unsigned ConstTripCount = 0); + unsigned computeFeasibleMaxVF(bool OptForSize, unsigned ConstTripCount); /// The vectorization cost is a combination of the cost itself and a boolean /// indicating whether any of the contributing operations will actually @@ -6161,8 +6161,9 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) { return None; } + unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop); if (!OptForSize) // Remaining checks deal with scalar loop when OptForSize. - return computeFeasibleMaxVF(OptForSize); + return computeFeasibleMaxVF(OptForSize, TC); if (Legal->getRuntimePointerChecking()->Need) { ORE->emit(createMissedAnalysis("CantVersionLoopWithOptForSize") @@ -6175,7 +6176,6 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) { } // If we optimize the program for size, avoid creating the tail loop. - unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop); DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n'); // If we don't know the precise trip count, don't try to vectorize. @@ -6236,15 +6236,20 @@ LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize, DEBUG(dbgs() << "LV: The Widest register is: " << WidestRegister << " bits.\n"); + assert(MaxVectorSize <= 64 && "Did not expect to pack so many elements" + " into one vector!"); if (MaxVectorSize == 0) { DEBUG(dbgs() << "LV: The target has no vector registers.\n"); MaxVectorSize = 1; } else if (ConstTripCount && ConstTripCount < MaxVectorSize && - isPowerOf2_32(ConstTripCount)) + isPowerOf2_32(ConstTripCount)) { + // We need to clamp the VF to be the ConstTripCount. There is no point in + // choosing a higher viable VF as done in the loop below. + DEBUG(dbgs() << "LV: Clamping the MaxVF to the constant trip count: " + << ConstTripCount << "\n"); MaxVectorSize = ConstTripCount; - - assert(MaxVectorSize <= 64 && "Did not expect to pack so many elements" - " into one vector!"); + return MaxVectorSize; + } unsigned MaxVF = MaxVectorSize; if (MaximizeBandwidth && !OptForSize) { |