From 899f7d2b00a59f284fdb8915b63813705ce66148 Mon Sep 17 00:00:00 2001 From: Matt Arsenault Date: Mon, 16 Sep 2013 22:43:16 +0000 Subject: MemCpyOptimizer: Use max legal int size instead of pointer size If there are no legal integers, assume 1 byte. This makes more sense than using the pointer size as a guess for the maximum GPR width. It is conceivable to want to use some 64-bit pointers on a target where 64-bit integers aren't legal. llvm-svn: 190817 --- llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp') diff --git a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp index 8f61ffd84bf..9912d3dafed 100644 --- a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp +++ b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp @@ -170,14 +170,17 @@ bool MemsetRange::isProfitableToUseMemset(const DataLayout &TD) const { // pessimize the llvm optimizer. // // Since we don't have perfect knowledge here, make some assumptions: assume - // the maximum GPR width is the same size as the pointer size and assume that - // this width can be stored. If so, check to see whether we will end up - // actually reducing the number of stores used. + // the maximum GPR width is the same size as the largest legal integer + // size. If so, check to see whether we will end up actually reducing the + // number of stores used. unsigned Bytes = unsigned(End-Start); - unsigned NumPointerStores = Bytes/TD.getPointerSize(); + unsigned MaxIntSize = TD.getLargestLegalIntTypeSize(); + if (MaxIntSize == 0) + MaxIntSize = 1; + unsigned NumPointerStores = Bytes / MaxIntSize; // Assume the remaining bytes if any are done a byte at a time. - unsigned NumByteStores = Bytes - NumPointerStores*TD.getPointerSize(); + unsigned NumByteStores = Bytes - NumPointerStores * MaxIntSize; // If we will reduce the # stores (according to this heuristic), do the // transformation. This encourages merging 4 x i8 -> i32 and 2 x i16 -> i32 -- cgit v1.2.3