[LV] Add TTI::shouldMaximizeVectorBandwidth to allow enabling it per target

The default implementation returns false and keeps the current behavior.

Differential Revision: https://reviews.llvm.org/D44735

llvm-svn: 328632

4 files changed, 20 insertions, 1 deletions

diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index efa08a6e7a1..72d640a20cb 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -670,6 +670,14 @@ public:
   /// \return The width of the smallest vector register type.
   unsigned getMinVectorRegisterBitWidth() const;
 
+  /// \return True if the vectorization factor should be chosen to
+  /// make the vector of the smallest element type match the size of a
+  /// vector register. For wider element types, this could result in
+  /// creating vectors that span multiple vector registers.
+  /// If false, the vectorization factor will be chosen based on the
+  /// size of the widest element type.
+  bool shouldMaximizeVectorBandwidth(bool OptSize) const;
+
   /// \return True if it should be considered for address type promotion.
   /// \p AllowPromotionWithoutCommonHeader Set true if promoting \p I is
   /// profitable without finding other extensions fed by the same input.
@@ -1062,6 +1070,7 @@ public:
   virtual unsigned getNumberOfRegisters(bool Vector) = 0;
   virtual unsigned getRegisterBitWidth(bool Vector) const = 0;
   virtual unsigned getMinVectorRegisterBitWidth() = 0;
+  virtual bool shouldMaximizeVectorBandwidth(bool OptSize) const = 0;
   virtual bool shouldConsiderAddressTypePromotion(
       const Instruction &I, bool &AllowPromotionWithoutCommonHeader) = 0;
   virtual unsigned getCacheLineSize() = 0;
@@ -1357,6 +1366,9 @@ public:
   unsigned getMinVectorRegisterBitWidth() override {
     return Impl.getMinVectorRegisterBitWidth();
   }
+  bool shouldMaximizeVectorBandwidth(bool OptSize) const override {
+    return Impl.shouldMaximizeVectorBandwidth(OptSize);
+  }
   bool shouldConsiderAddressTypePromotion(
       const Instruction &I, bool &AllowPromotionWithoutCommonHeader) override {
     return Impl.shouldConsiderAddressTypePromotion(
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
index 80b2182a067..e549ca24ba1 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -349,6 +349,8 @@ public:
 
   unsigned getMinVectorRegisterBitWidth() { return 128; }
 
+  bool shouldMaximizeVectorBandwidth(bool OptSize) const { return false; }
+
   bool
   shouldConsiderAddressTypePromotion(const Instruction &I,
                                      bool &AllowPromotionWithoutCommonHeader) {
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index a78ec9a5a89..673e55559c5 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -338,6 +338,10 @@ unsigned TargetTransformInfo::getMinVectorRegisterBitWidth() const {
   return TTIImpl->getMinVectorRegisterBitWidth();
 }
 
+bool TargetTransformInfo::shouldMaximizeVectorBandwidth(bool OptSize) const {
+  return TTIImpl->shouldMaximizeVectorBandwidth(OptSize);
+}
+
 bool TargetTransformInfo::shouldConsiderAddressTypePromotion(
     const Instruction &I, bool &AllowPromotionWithoutCommonHeader) const {
   return TTIImpl->shouldConsiderAddressTypePromotion(
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index ba07ebe1e51..a80c7f94e8d 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -6139,7 +6139,8 @@ LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize,
   }
 
   unsigned MaxVF = MaxVectorSize;
-  if (MaximizeBandwidth && !OptForSize) {
+  if (TTI.shouldMaximizeVectorBandwidth(OptForSize) ||
+      (MaximizeBandwidth && !OptForSize)) {
     // Collect all viable vectorization factors larger than the default MaxVF
     // (i.e. MaxVectorSize).
     SmallVector<unsigned, 8> VFs;