[TTI] Add getCacheLineSize

Summary:
And use it in PPCLoopDataPrefetch.cpp.

@hfinkel, please let me know if your preference would be to preserve the
ppc-loop-prefetch-cache-line option in order to be able to override the
value of TTI::getCacheLineSize for PPC.

Reviewers: hfinkel

Subscribers: hulx2000, mcrosier, mssimpso, hfinkel, llvm-commits

Differential Revision: http://reviews.llvm.org/D16306

llvm-svn: 258419

6 files changed, 29 insertions, 5 deletions

diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index 3913cc3f107..30bda634377 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -416,6 +416,9 @@ public:
   /// \return The width of the largest scalar or vector register type.
   unsigned getRegisterBitWidth(bool Vector) const;
 
+  /// \return The size of a cache line in bytes.
+  unsigned getCacheLineSize() const;
+
   /// \return The maximum interleave factor that any transform should try to
   /// perform for this target. This number depends on the level of parallelism
   /// and the number of execution units in the CPU.
@@ -609,6 +612,7 @@ public:
                             Type *Ty) = 0;
   virtual unsigned getNumberOfRegisters(bool Vector) = 0;
   virtual unsigned getRegisterBitWidth(bool Vector) = 0;
+  virtual unsigned getCacheLineSize() = 0;
   virtual unsigned getMaxInterleaveFactor(unsigned VF) = 0;
   virtual unsigned
   getArithmeticInstrCost(unsigned Opcode, Type *Ty, OperandValueKind Opd1Info,
@@ -775,6 +779,9 @@ public:
   unsigned getRegisterBitWidth(bool Vector) override {
     return Impl.getRegisterBitWidth(Vector);
   }
+  unsigned getCacheLineSize() override {
+    return Impl.getCacheLineSize();
+  }
   unsigned getMaxInterleaveFactor(unsigned VF) override {
     return Impl.getMaxInterleaveFactor(VF);
   }
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
index 43815234051..41bc72ca3ad 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -264,6 +264,8 @@ public:
 
   unsigned getRegisterBitWidth(bool Vector) { return 32; }
 
+  unsigned getCacheLineSize() { return 0; }
+
   unsigned getMaxInterleaveFactor(unsigned VF) { return 1; }
 
   unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty,
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 9c1d3fd4f58..ed7005e5e52 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -215,6 +215,10 @@ unsigned TargetTransformInfo::getRegisterBitWidth(bool Vector) const {
   return TTIImpl->getRegisterBitWidth(Vector);
 }
 
+unsigned TargetTransformInfo::getCacheLineSize() const {
+  return TTIImpl->getCacheLineSize();
+}
+
 unsigned TargetTransformInfo::getMaxInterleaveFactor(unsigned VF) const {
   return TTIImpl->getMaxInterleaveFactor(VF);
 }
diff --git a/llvm/lib/Target/PowerPC/PPCLoopDataPrefetch.cpp b/llvm/lib/Target/PowerPC/PPCLoopDataPrefetch.cpp
index e3a35d5df35..c113ae5f52c 100644
--- a/llvm/lib/Target/PowerPC/PPCLoopDataPrefetch.cpp
+++ b/llvm/lib/Target/PowerPC/PPCLoopDataPrefetch.cpp
@@ -50,10 +50,6 @@ static cl::opt<unsigned>
 PrefDist("ppc-loop-prefetch-distance", cl::Hidden, cl::init(300),
          cl::desc("The loop prefetch distance"));
 
-static cl::opt<unsigned>
-CacheLineSize("ppc-loop-prefetch-cache-line", cl::Hidden, cl::init(64),
-              cl::desc("The loop prefetch cache line size"));
-
 namespace llvm {
   void initializePPCLoopDataPrefetchPass(PassRegistry&);
 }
@@ -110,6 +106,8 @@ bool PPCLoopDataPrefetch::runOnFunction(Function &F) {
   AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
   TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
 
+  assert(TTI->getCacheLineSize() && "Cache line size is not set for target");
+
   bool MadeChange = false;
 
   for (auto I = LI->begin(), IE = LI->end(); I != IE; ++I)
@@ -193,7 +191,7 @@ bool PPCLoopDataPrefetch::runOnLoop(Loop *L) {
         if (const SCEVConstant *ConstPtrDiff =
             dyn_cast<SCEVConstant>(PtrDiff)) {
           int64_t PD = std::abs(ConstPtrDiff->getValue()->getSExtValue());
-          if (PD < (int64_t) CacheLineSize) {
+          if (PD < (int64_t) TTI->getCacheLineSize()) {
             DupPref = true;
             break;
           }
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index cd86dabd5ab..b60c07c3672 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -21,6 +21,12 @@ using namespace llvm;
 static cl::opt<bool> DisablePPCConstHoist("disable-ppc-constant-hoisting",
 cl::desc("disable constant hoisting on PPC"), cl::init(false), cl::Hidden);
 
+// This is currently only used for the data prefetch pass which is only enabled
+// for BG/Q by default.
+static cl::opt<unsigned>
+CacheLineSize("ppc-loop-prefetch-cache-line", cl::Hidden, cl::init(64),
+              cl::desc("The loop prefetch cache line size"));
+
 //===----------------------------------------------------------------------===//
 //
 // PPC cost model.
@@ -230,6 +236,12 @@ unsigned PPCTTIImpl::getRegisterBitWidth(bool Vector) {
 
 }
 
+unsigned PPCTTIImpl::getCacheLineSize() {
+  // This is currently only used for the data prefetch pass which is only
+  // enabled for BG/Q by default.
+  return CacheLineSize;
+}
+
 unsigned PPCTTIImpl::getMaxInterleaveFactor(unsigned VF) {
   unsigned Directive = ST->getDarwinDirective();
   // The 440 has no SIMD support, but floating-point instructions
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
index 04c1b02235f..d216bdfec97 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
@@ -70,6 +70,7 @@ public:
   bool enableInterleavedAccessVectorization();
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector);
+  unsigned getCacheLineSize();
   unsigned getMaxInterleaveFactor(unsigned VF);
   int getArithmeticInstrCost(
       unsigned Opcode, Type *Ty,