[System Model] [TTI] Update cache and prefetch TTI interfaces

Re-apply 9fdfb045ae8b/r365676 with fixes for PPC and Hexagon.  This involved
moving defaults from TargetTransformInfoImplBase to MCSubtargetInfo.

Rework the TTI cache and software prefetching APIs to prepare for the
introduction of a general system model.  Changes include:

- Marking existing interfaces const and/or override as appropriate
- Adding comments
- Adding BasicTTIImpl interfaces that delegate to a subtarget
  implementation
- Moving the default TargetTransformInfoImplBase implementation to a default
  MCSubtarget implementation

Only a handful of targets use these interfaces currently: AArch64, Hexagon, PPC
and SystemZ.  AArch64 already has a custom subtarget implementation, so its
custom TTI implementation is migrated to use the new facilities in BasicTTIImpl
to invoke its custom subtarget implementation.  The custom TTI implementations
continue to exist for the other targets with this change.  They are not moved
over to subtarget-based implementations.

The end goal is to have the default subtarget implementation defer to the system
model defined by the target.  With this change, the default MCSubtargetInfo
implementation essentially returns the defaults TargetTransformInfoImplBase used
to return.  Existing users of TTI defaults will hit the defaults now in
MCSubtargetInfo.  Targets that define their own custom TTI implementations won't
use the BasicTTIImpl implementations that route to the subtarget.

Once system models are in place for the targets that use these interfaces, their
custom TTI implementations can be removed.

Differential Revision: https://reviews.llvm.org/D63614

llvm-svn: 374205

include/llvm/Analysis/TargetTransformInfo.h

@@ -837,18 +837,20 @@ public:
   /// \return The associativity of the cache level, if available.
   llvm::Optional<unsigned> getCacheAssociativity(CacheLevel Level) const;
 
-  /// \return How much before a load we should place the prefetch instruction.
-  /// This is currently measured in number of instructions.
+  /// \return How much before a load we should place the prefetch
+  /// instruction.  This is currently measured in number of
+  /// instructions.
   unsigned getPrefetchDistance() const;
 
-  /// \return Some HW prefetchers can handle accesses up to a certain constant
-  /// stride.  This is the minimum stride in bytes where it makes sense to start
-  /// adding SW prefetches.  The default is 1, i.e. prefetch with any stride.
+  /// \return Some HW prefetchers can handle accesses up to a certain
+  /// constant stride.  This is the minimum stride in bytes where it
+  /// makes sense to start adding SW prefetches.  The default is 1,
+  /// i.e. prefetch with any stride.
   unsigned getMinPrefetchStride() const;
 
-  /// \return The maximum number of iterations to prefetch ahead.  If the
-  /// required number of iterations is more than this number, no prefetching is
-  /// performed.
+  /// \return The maximum number of iterations to prefetch ahead.  If
+  /// the required number of iterations is more than this number, no
+  /// prefetching is performed.
   unsigned getMaxPrefetchIterationsAhead() const;
 
   /// \return The maximum interleave factor that any transform should try to
@@ -1250,12 +1252,26 @@ public:
   virtual unsigned getMinimumVF(unsigned ElemWidth) const = 0;
   virtual bool shouldConsiderAddressTypePromotion(
       const Instruction &I, bool &AllowPromotionWithoutCommonHeader) = 0;
-  virtual unsigned getCacheLineSize() = 0;
-  virtual llvm::Optional<unsigned> getCacheSize(CacheLevel Level) = 0;
-  virtual llvm::Optional<unsigned> getCacheAssociativity(CacheLevel Level) = 0;
-  virtual unsigned getPrefetchDistance() = 0;
-  virtual unsigned getMinPrefetchStride() = 0;
-  virtual unsigned getMaxPrefetchIterationsAhead() = 0;
+  virtual unsigned getCacheLineSize() const = 0;
+  virtual llvm::Optional<unsigned> getCacheSize(CacheLevel Level) const = 0;
+  virtual llvm::Optional<unsigned> getCacheAssociativity(CacheLevel Level) const = 0;
+
+  /// \return How much before a load we should place the prefetch
+  /// instruction.  This is currently measured in number of
+  /// instructions.
+  virtual unsigned getPrefetchDistance() const = 0;
+
+  /// \return Some HW prefetchers can handle accesses up to a certain
+  /// constant stride.  This is the minimum stride in bytes where it
+  /// makes sense to start adding SW prefetches.  The default is 1,
+  /// i.e. prefetch with any stride.
+  virtual unsigned getMinPrefetchStride() const = 0;
+
+  /// \return The maximum number of iterations to prefetch ahead.  If
+  /// the required number of iterations is more than this number, no
+  /// prefetching is performed.
+  virtual unsigned getMaxPrefetchIterationsAhead() const = 0;
+
   virtual unsigned getMaxInterleaveFactor(unsigned VF) = 0;
   virtual unsigned
   getArithmeticInstrCost(unsigned Opcode, Type *Ty, OperandValueKind Opd1Info,
@@ -1606,22 +1622,36 @@ public:
     return Impl.shouldConsiderAddressTypePromotion(
         I, AllowPromotionWithoutCommonHeader);
   }
-  unsigned getCacheLineSize() override {
+  unsigned getCacheLineSize() const override {
     return Impl.getCacheLineSize();
   }
-  llvm::Optional<unsigned> getCacheSize(CacheLevel Level) override {
+  llvm::Optional<unsigned> getCacheSize(CacheLevel Level) const override {
     return Impl.getCacheSize(Level);
   }
-  llvm::Optional<unsigned> getCacheAssociativity(CacheLevel Level) override {
+  llvm::Optional<unsigned> getCacheAssociativity(CacheLevel Level) const override {
     return Impl.getCacheAssociativity(Level);
   }
-  unsigned getPrefetchDistance() override { return Impl.getPrefetchDistance(); }
-  unsigned getMinPrefetchStride() override {
+
+  /// Return the preferred prefetch distance in terms of instructions.
+  ///
+  unsigned getPrefetchDistance() const override {
+    return Impl.getPrefetchDistance();
+  }
+
+  /// Return the minimum stride necessary to trigger software
+  /// prefetching.
+  ///
+  unsigned getMinPrefetchStride() const override {
     return Impl.getMinPrefetchStride();
   }
-  unsigned getMaxPrefetchIterationsAhead() override {
+
+  /// Return the maximum prefetch distance in terms of loop
+  /// iterations.
+  ///
+  unsigned getMaxPrefetchIterationsAhead() const override {
     return Impl.getMaxPrefetchIterationsAhead();
   }
+
   unsigned getMaxInterleaveFactor(unsigned VF) override {
     return Impl.getMaxInterleaveFactor(VF);
   }

include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -371,37 +371,6 @@ public:
     return false;
   }
 
-  unsigned getCacheLineSize() { return 0; }
-
-  llvm::Optional<unsigned> getCacheSize(TargetTransformInfo::CacheLevel Level) {
-    switch (Level) {
-    case TargetTransformInfo::CacheLevel::L1D:
-      LLVM_FALLTHROUGH;
-    case TargetTransformInfo::CacheLevel::L2D:
-      return llvm::Optional<unsigned>();
-    }
-
-    llvm_unreachable("Unknown TargetTransformInfo::CacheLevel");
-  }
-
-  llvm::Optional<unsigned> getCacheAssociativity(
-    TargetTransformInfo::CacheLevel Level) {
-    switch (Level) {
-    case TargetTransformInfo::CacheLevel::L1D:
-      LLVM_FALLTHROUGH;
-    case TargetTransformInfo::CacheLevel::L2D:
-      return llvm::Optional<unsigned>();
-    }
-
-    llvm_unreachable("Unknown TargetTransformInfo::CacheLevel");
-  }
-
-  unsigned getPrefetchDistance() { return 0; }
-
-  unsigned getMinPrefetchStride() { return 1; }
-
-  unsigned getMaxPrefetchIterationsAhead() { return UINT_MAX; }
-
   unsigned getMaxInterleaveFactor(unsigned VF) { return 1; }
 
   unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty,

include/llvm/CodeGen/BasicTTIImpl.h

@@ -514,6 +514,34 @@ public:
     return BaseT::getInstructionLatency(I);
   }
 
+  virtual Optional<unsigned>
+  getCacheSize(TargetTransformInfo::CacheLevel Level) const {
+    return Optional<unsigned>(
+      getST()->getCacheSize(static_cast<unsigned>(Level)));
+  }
+
+  virtual Optional<unsigned>
+  getCacheAssociativity(TargetTransformInfo::CacheLevel Level) const {
+    return Optional<unsigned>(
+      getST()->getCacheAssociativity(static_cast<unsigned>(Level)));
+  }
+
+  virtual unsigned getCacheLineSize() const {
+    return getST()->getCacheLineSize();
+  }
+
+  virtual unsigned getPrefetchDistance() const {
+    return getST()->getPrefetchDistance();
+  }
+
+  virtual unsigned getMinPrefetchStride() const {
+    return getST()->getMinPrefetchStride();
+  }
+
+  virtual unsigned getMaxPrefetchIterationsAhead() const {
+    return getST()->getMaxPrefetchIterationsAhead();
+  }
+
   /// @}
 
   /// \name Vector TTI Implementations

include/llvm/MC/MCSubtargetInfo.h

@@ -223,6 +223,50 @@ public:
   }
 
   virtual unsigned getHwMode() const { return 0; }
+
+  /// Return the cache size in bytes for the given level of cache.
+  /// Level is zero-based, so a value of zero means the first level of
+  /// cache.
+  ///
+  virtual Optional<unsigned> getCacheSize(unsigned Level) const;
+
+  /// Return the cache associatvity for the given level of cache.
+  /// Level is zero-based, so a value of zero means the first level of
+  /// cache.
+  ///
+  virtual Optional<unsigned> getCacheAssociativity(unsigned Level) const;
+
+  /// Return the target cache line size in bytes at a given level.
+  ///
+  virtual Optional<unsigned> getCacheLineSize(unsigned Level) const;
+
+  /// Return the target cache line size in bytes.  By default, return
+  /// the line size for the bottom-most level of cache.  This provides
+  /// a more convenient interface for the common case where all cache
+  /// levels have the same line size.  Return zero if there is no
+  /// cache model.
+  ///
+  virtual unsigned getCacheLineSize() const {
+    Optional<unsigned> Size = getCacheLineSize(0);
+    if (Size)
+      return *Size;
+
+    return 0;
+  }
+
+  /// Return the preferred prefetch distance in terms of instructions.
+  ///
+  virtual unsigned getPrefetchDistance() const;
+
+  /// Return the maximum prefetch distance in terms of loop
+  /// iterations.
+  ///
+  virtual unsigned getMaxPrefetchIterationsAhead() const;
+
+  /// Return the minimum stride necessary to trigger software
+  /// prefetching.
+  ///
+  virtual unsigned getMinPrefetchStride() const;
 };
 
 } // end namespace llvm

lib/Analysis/TargetTransformInfo.cpp

@@ -40,6 +40,34 @@ namespace {
 struct NoTTIImpl : TargetTransformInfoImplCRTPBase<NoTTIImpl> {
   explicit NoTTIImpl(const DataLayout &DL)
       : TargetTransformInfoImplCRTPBase<NoTTIImpl>(DL) {}
+
+  unsigned getCacheLineSize() const { return 0; }
+
+  llvm::Optional<unsigned> getCacheSize(TargetTransformInfo::CacheLevel Level) const {
+    switch (Level) {
+    case TargetTransformInfo::CacheLevel::L1D:
+      LLVM_FALLTHROUGH;
+    case TargetTransformInfo::CacheLevel::L2D:
+      return llvm::Optional<unsigned>();
+    }
+    llvm_unreachable("Unknown TargetTransformInfo::CacheLevel");
+  }
+
+  llvm::Optional<unsigned> getCacheAssociativity(
+    TargetTransformInfo::CacheLevel Level) const {
+    switch (Level) {
+    case TargetTransformInfo::CacheLevel::L1D:
+      LLVM_FALLTHROUGH;
+    case TargetTransformInfo::CacheLevel::L2D:
+      return llvm::Optional<unsigned>();
+    }
+
+    llvm_unreachable("Unknown TargetTransformInfo::CacheLevel");
+  }
+
+  unsigned getPrefetchDistance() const { return 0; }
+  unsigned getMinPrefetchStride() const { return 1; }
+  unsigned getMaxPrefetchIterationsAhead() const { return UINT_MAX; }
 };
 }
 

lib/MC/MCSubtargetInfo.cpp

@@ -315,3 +315,28 @@ void MCSubtargetInfo::initInstrItins(InstrItineraryData &InstrItins) const {
   InstrItins = InstrItineraryData(getSchedModel(), Stages, OperandCycles,
                                   ForwardingPaths);
 }
+
+Optional<unsigned> MCSubtargetInfo::getCacheSize(unsigned Level) const {
+  return Optional<unsigned>();
+}
+
+Optional<unsigned>
+MCSubtargetInfo::getCacheAssociativity(unsigned Level) const {
+  return Optional<unsigned>();
+}
+
+Optional<unsigned> MCSubtargetInfo::getCacheLineSize(unsigned Level) const {
+  return Optional<unsigned>();
+}
+
+unsigned MCSubtargetInfo::getPrefetchDistance() const {
+  return 0;
+}
+
+unsigned MCSubtargetInfo::getMaxPrefetchIterationsAhead() const {
+  return UINT_MAX;
+}
+
+unsigned MCSubtargetInfo::getMinPrefetchStride() const {
+  return 1;
+}

lib/Target/AArch64/AArch64Subtarget.h

@@ -353,10 +353,10 @@ public:
   unsigned getVectorInsertExtractBaseCost() const {
     return VectorInsertExtractBaseCost;
   }
-  unsigned getCacheLineSize() const { return CacheLineSize; }
-  unsigned getPrefetchDistance() const { return PrefetchDistance; }
-  unsigned getMinPrefetchStride() const { return MinPrefetchStride; }
-  unsigned getMaxPrefetchIterationsAhead() const {
+  unsigned getCacheLineSize() const override { return CacheLineSize; }
+  unsigned getPrefetchDistance() const override { return PrefetchDistance; }
+  unsigned getMinPrefetchStride() const override { return MinPrefetchStride; }
+  unsigned getMaxPrefetchIterationsAhead() const override {
     return MaxPrefetchIterationsAhead;
   }
   unsigned getPrefFunctionLogAlignment() const {

lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -892,22 +892,6 @@ bool AArch64TTIImpl::shouldConsiderAddressTypePromotion(
   return Considerable;
 }
 
-unsigned AArch64TTIImpl::getCacheLineSize() {
-  return ST->getCacheLineSize();
-}
-
-unsigned AArch64TTIImpl::getPrefetchDistance() {
-  return ST->getPrefetchDistance();
-}
-
-unsigned AArch64TTIImpl::getMinPrefetchStride() {
-  return ST->getMinPrefetchStride();
-}
-
-unsigned AArch64TTIImpl::getMaxPrefetchIterationsAhead() {
-  return ST->getMaxPrefetchIterationsAhead();
-}
-
 bool AArch64TTIImpl::useReductionIntrinsic(unsigned Opcode, Type *Ty,
                                            TTI::ReductionFlags Flags) const {
   assert(isa<VectorType>(Ty) && "Expected Ty to be a vector type");

lib/Target/AArch64/AArch64TargetTransformInfo.h

@@ -156,14 +156,6 @@ public:
   shouldConsiderAddressTypePromotion(const Instruction &I,
                                      bool &AllowPromotionWithoutCommonHeader);
 
-  unsigned getCacheLineSize();
-
-  unsigned getPrefetchDistance();
-
-  unsigned getMinPrefetchStride();
-
-  unsigned getMaxPrefetchIterationsAhead();
-
   bool shouldExpandReduction(const IntrinsicInst *II) const {
     return false;
   }

lib/Target/Hexagon/HexagonTargetTransformInfo.h

@@ -68,8 +68,8 @@ public:
   bool shouldFavorPostInc() const;
 
   // L1 cache prefetch.
-  unsigned getPrefetchDistance() const;
-  unsigned getCacheLineSize() const;
+  unsigned getPrefetchDistance() const override;
+  unsigned getCacheLineSize() const override;
 
   /// @}
 

lib/Target/PowerPC/PPCTargetTransformInfo.cpp

@@ -613,7 +613,7 @@ unsigned PPCTTIImpl::getRegisterBitWidth(bool Vector) const {
 
 }
 
-unsigned PPCTTIImpl::getCacheLineSize() {
+unsigned PPCTTIImpl::getCacheLineSize() const {
   // Check first if the user specified a custom line size.
   if (CacheLineSize.getNumOccurrences() > 0)
     return CacheLineSize;
@@ -628,7 +628,7 @@ unsigned PPCTTIImpl::getCacheLineSize() {
   return 64;
 }
 
-unsigned PPCTTIImpl::getPrefetchDistance() {
+unsigned PPCTTIImpl::getPrefetchDistance() const {
   // This seems like a reasonable default for the BG/Q (this pass is enabled, by
   // default, only on the BG/Q).
   return 300;

lib/Target/PowerPC/PPCTargetTransformInfo.h

@@ -74,8 +74,8 @@ public:
   bool enableInterleavedAccessVectorization();
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector) const;
-  unsigned getCacheLineSize();
-  unsigned getPrefetchDistance();
+  unsigned getCacheLineSize() const override;
+  unsigned getPrefetchDistance() const override;
   unsigned getMaxInterleaveFactor(unsigned VF);
   int vectorCostAdjustment(int Cost, unsigned Opcode, Type *Ty1, Type *Ty2);
   int getArithmeticInstrCost(

lib/Target/SystemZ/SystemZTargetTransformInfo.h

@@ -59,9 +59,9 @@ public:
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector) const;
 
-  unsigned getCacheLineSize() { return 256; }
-  unsigned getPrefetchDistance() { return 2000; }
-  unsigned getMinPrefetchStride() { return 2048; }
+  unsigned getCacheLineSize() const override { return 256; }
+  unsigned getPrefetchDistance() const override { return 2000; }
+  unsigned getMinPrefetchStride() const override { return 2048; }
 
   bool hasDivRemOp(Type *DataType, bool IsSigned);
   bool prefersVectorizedAddressing() { return false; }