[SystemZTTIImpl] Give correct cost values for vector bswap intrinsics.
Implement getIntrinsicInstrCost() and return costs reflecting that bswap can
be done with a vperm per vector register.
Review: Ulrich Weigand
https://reviews.llvm.org/D54789
llvm-svn: 347445
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
index b25059e..a2b2894 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
@@ -1047,3 +1047,29 @@
// Cost of load/store operations and the permutations needed.
return NumVectorMemOps + NumPermutes;
}
+
+static int getVectorIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy) {
+ if (RetTy->isVectorTy() && ID == Intrinsic::bswap)
+ return getNumVectorRegs(RetTy); // VPERM
+ return -1;
+}
+
+int SystemZTTIImpl::getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
+ ArrayRef<Value *> Args,
+ FastMathFlags FMF, unsigned VF) {
+ int Cost = getVectorIntrinsicInstrCost(ID, RetTy);
+ if (Cost != -1)
+ return Cost;
+ return BaseT::getIntrinsicInstrCost(ID, RetTy, Args, FMF, VF);
+}
+
+int SystemZTTIImpl::getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
+ ArrayRef<Type *> Tys,
+ FastMathFlags FMF,
+ unsigned ScalarizationCostPassed) {
+ int Cost = getVectorIntrinsicInstrCost(ID, RetTy);
+ if (Cost != -1)
+ return Cost;
+ return BaseT::getIntrinsicInstrCost(ID, RetTy, Tys,
+ FMF, ScalarizationCostPassed);
+}
diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
index dd85c4e..e79bee1 100644
--- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
+++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h
@@ -98,6 +98,13 @@
unsigned AddressSpace,
bool UseMaskForCond = false,
bool UseMaskForGaps = false);
+
+ int getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
+ ArrayRef<Value *> Args, FastMathFlags FMF,
+ unsigned VF = 1);
+ int getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
+ ArrayRef<Type *> Tys, FastMathFlags FMF,
+ unsigned ScalarizationCostPassed = UINT_MAX);
/// @}
};