Changed basic cost of store operation on X86

Store operation takes 2 UOps on X86 processors. The exact cost calculation affects several optimization passes including loop unroling.
This change compensates performance degradation caused by https://reviews.llvm.org/D34458 and shows improvements on some benchmarks.

Differential Revision: https://reviews.llvm.org/D35888

llvm-svn: 311285

1 files changed, 15 insertions, 0 deletions

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 2f44d610840..6c73a6875c8 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -2113,6 +2113,21 @@ int X86TTIImpl::getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
   return X86TTIImpl::getIntImmCost(Imm, Ty);
 }
 
+unsigned X86TTIImpl::getUserCost(const User *U,
+                                 ArrayRef<const Value *> Operands) {
+  if (isa<StoreInst>(U)) {
+    Value *Ptr = U->getOperand(1);
+    // Store instruction with index and scale costs 2 Uops.
+    // Check the preceding GEP to identify non-const indices.
+    if (auto GEP = dyn_cast<GetElementPtrInst>(Ptr)) {
+      if (!all_of(GEP->indices(), [](Value *V) { return isa<Constant>(V); }))
+        return TTI::TCC_Basic * 2;
+    }
+    return TTI::TCC_Basic;
+  }
+  return BaseT::getUserCost(U, Operands);
+}
+
 // Return an average cost of Gather / Scatter instruction, maybe improved later
 int X86TTIImpl::getGSVectorCost(unsigned Opcode, Type *SrcVTy, Value *Ptr,
                                 unsigned Alignment, unsigned AddressSpace) {