[LoopDataPrefetch] Add TTI to limit the number of iterations to prefetch ahead

Summary:
It can hurt performance to prefetch ahead too much.  Be conservative for
now and don't prefetch ahead more than 3 iterations on Cyclone.

Reviewers: hfinkel

Subscribers: llvm-commits, mzolotukhin

Differential Revision: http://reviews.llvm.org/D17949

llvm-svn: 263772

2 files changed, 15 insertions, 0 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index aee298998f3..2b3fae958f4 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -31,6 +31,13 @@ static cl::opt<unsigned> CycloneMinPrefetchStride(
     cl::desc("Min stride to add prefetches for Cyclone"),
     cl::init(2048), cl::Hidden);
 
+// Be conservative for now and don't prefetch ahead too much since the loop
+// may terminate early.
+static cl::opt<unsigned> CycloneMaxPrefetchIterationsAhead(
+    "cyclone-max-prefetch-iters-ahead",
+    cl::desc("Max number of iterations to prefetch ahead on Cyclone"),
+    cl::init(3), cl::Hidden);
+
 /// \brief Calculate the cost of materializing a 64-bit value. This helper
 /// method might only calculate a fraction of a larger immediate. Therefore it
 /// is valid to return a cost of ZERO.
@@ -602,3 +609,9 @@ unsigned AArch64TTIImpl::getMinPrefetchStride() {
     return CycloneMinPrefetchStride;
   return BaseT::getMinPrefetchStride();
 }
+
+unsigned AArch64TTIImpl::getMaxPrefetchIterationsAhead() {
+  if (ST->isCyclone())
+    return CycloneMaxPrefetchIterationsAhead;
+  return BaseT::getMaxPrefetchIterationsAhead();
+}
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index a54db00e7d3..93a84b7a992 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -133,6 +133,8 @@ public:
   unsigned getPrefetchDistance();
 
   unsigned getMinPrefetchStride();
+
+  unsigned getMaxPrefetchIterationsAhead();
   /// @}
 };