[SLP] getVectorCallCosts - don't provide scalar argument data for vector IntrinsicCostAttributes (#124254)

getVectorCallCosts determines the cost of a vector intrinsic, based off
an existing scalar intrinsic call - but we were including the scalar
argument data to the IntrinsicCostAttributes, which meant that not only
was the cost calculation not type-only based, it was making incorrect
assumptions about constant values etc.

This also exposed an issue that x86 relied on fallback calculations for
funnel shift costs - this is great when we have the argument data as
that improves the accuracy of uniform shift amounts etc., but meant that
type-only costs would default to Cost=2 for all custom lowered funnel
shifts, which was far too cheap.

This is the reverse of #124129 where we weren't including argument data
when we could.

Fixes #63980

Author: RKSimon

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -4719,6 +4719,24 @@ X86TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
     if (const auto *Entry = CostTableLookup(X86CostTbl, ISD, MTy))
       if (auto KindCost = Entry->Cost[CostKind])
         return adjustTableCost(Entry->ISD, *KindCost, LT, ICA.getFlags());
+
+    // Without arg data, we need to compute the expanded costs of custom lowered
+    // intrinsics to prevent use of the (very low) default costs.
+    if (ICA.isTypeBasedOnly() &&
+        (IID == Intrinsic::fshl || IID == Intrinsic::fshr)) {
+      Type *CondTy = RetTy->getWithNewBitWidth(1);
+      InstructionCost Cost = 0;
+      Cost += getArithmeticInstrCost(BinaryOperator::Or, RetTy, CostKind);
+      Cost += getArithmeticInstrCost(BinaryOperator::Sub, RetTy, CostKind);
+      Cost += getArithmeticInstrCost(BinaryOperator::Shl, RetTy, CostKind);
+      Cost += getArithmeticInstrCost(BinaryOperator::LShr, RetTy, CostKind);
+      Cost += getArithmeticInstrCost(BinaryOperator::And, RetTy, CostKind);
+      Cost += getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+                                 CmpInst::ICMP_EQ, CostKind);
+      Cost += getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
+                                 CmpInst::ICMP_EQ, CostKind);
+      return Cost;
+    }
   }
 
   return BaseT::getIntrinsicInstrCost(ICA, CostKind);

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -9031,9 +9031,7 @@ getVectorCallCosts(CallInst *CI, FixedVectorType *VecTy,
   FastMathFlags FMF;
   if (auto *FPCI = dyn_cast<FPMathOperator>(CI))
     FMF = FPCI->getFastMathFlags();
-  SmallVector<const Value *> Arguments(CI->args());
-  IntrinsicCostAttributes CostAttrs(ID, VecTy, Arguments, ArgTys, FMF,
-                                    dyn_cast<IntrinsicInst>(CI));
+  IntrinsicCostAttributes CostAttrs(ID, VecTy, ArgTys, FMF);
   auto IntrinsicCost =
     TTI->getIntrinsicInstrCost(CostAttrs, TTI::TCK_RecipThroughput);