[CostModel][X86] getShuffleCost - use processShuffleMasks to split SK_PermuteTwoSrc shuffles to legal types (#120599)

processShuffleMasks can now correctly handle 2 src shuffles, so we can use the existing SK_PermuteSingleSrc splitting cost logic to handle SK_PermuteTwoSrc as well and correctly recognise the number of active subvectors per legalised shuffle.

Author: RKSimon

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -1698,7 +1698,8 @@ InstructionCost X86TTIImpl::getShuffleCost(
   // We are going to permute multiple sources and the result will be in multiple
   // destinations. Providing an accurate cost only for splits where the element
   // type remains the same.
-  if (Kind == TTI::SK_PermuteSingleSrc && LT.first != 1) {
+  if ((Kind == TTI::SK_PermuteSingleSrc || Kind == TTI::SK_PermuteTwoSrc) &&
+      LT.first != 1) {
     MVT LegalVT = LT.second;
     if (LegalVT.isVector() &&
         LegalVT.getVectorElementType().getSizeInBits() ==
@@ -1784,14 +1785,6 @@ InstructionCost X86TTIImpl::getShuffleCost(
     return BaseT::getShuffleCost(Kind, BaseTp, Mask, CostKind, Index, SubTp);
   }
 
-  // For 2-input shuffles, we must account for splitting the 2 inputs into many.
-  if (Kind == TTI::SK_PermuteTwoSrc && !IsInLaneShuffle && LT.first != 1) {
-    // We assume that source and destination have the same vector type.
-    InstructionCost NumOfDests = LT.first;
-    InstructionCost NumOfShufflesPerDest = LT.first * 2 - 1;
-    LT.first = NumOfDests * NumOfShufflesPerDest;
-  }
-
   static const CostTblEntry AVX512VBMIShuffleTbl[] = {
       {TTI::SK_Reverse, MVT::v64i8, 1}, // vpermb
       {TTI::SK_Reverse, MVT::v32i8, 1}, // vpermb