[InlineCost] Don't add the soft float function call cost for the fneg idiom, fsub -0.0, %x

Summary: Fneg can be implemented with an xor rather than a function call so we don't need to add the function call overhead. This was pointed out in D62699

Reviewers: efriedma, cameron.mcinally

Reviewed By: efriedma

Subscribers: javed.absar, eraman, hiraditya, haicheng, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D62747

llvm-svn: 362304

1 files changed, 5 insertions, 2 deletions

diff --git a/llvm/lib/Analysis/InlineCost.cpp b/llvm/lib/Analysis/InlineCost.cpp
index ced30d6..a332a439 100644
--- a/llvm/lib/Analysis/InlineCost.cpp
+++ b/llvm/lib/Analysis/InlineCost.cpp
@@ -35,6 +35,7 @@
 #include "llvm/IR/InstVisitor.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Operator.h"
+#include "llvm/IR/PatternMatch.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 
@@ -1095,9 +1096,11 @@ bool CallAnalyzer::visitBinaryOperator(BinaryOperator &I) {
 
   // If the instruction is floating point, and the target says this operation
   // is expensive, this may eventually become a library call. Treat the cost
-  // as such.
+  // as such. Unless it's fneg which can be implemented with an xor.
+  using namespace llvm::PatternMatch;
   if (I.getType()->isFloatingPointTy() &&
-      TTI.getFPOpCost(I.getType()) == TargetTransformInfo::TCC_Expensive)
+      TTI.getFPOpCost(I.getType()) == TargetTransformInfo::TCC_Expensive &&
+      !match(&I, m_FNeg(m_Value())))
     addCost(InlineConstants::CallPenalty);
 
   return false;