[ARM][MVE] Add shuffle costs for LDn and STn instructions. (#145304)

LD2 is represented in IR as deinterleave-shuffle(load), and ST2 as
store(interleave-shuffle). Whilst the shuffle would be expensive in
general for MVE (it does not have zip/uzp instructions), it should be
treated as cheap when part of the LD2/ST2 pattern. This borrows some
code from the AArch64 backed to produce lower costs. (Some of which
still shows as higher than it should - that just shows how broken the
generic shuffle costs are at the moment, they would be lower if
getShuffleCost was called directly as opposed to going through
getInstructionCost).

Author: davemgreen

llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp

@@ -1335,6 +1335,39 @@ InstructionCost ARMTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
 
     if (!Mask.empty()) {
       std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(SrcTy);
+      // Check for LD2/LD4 instructions, which are represented in llvm IR as
+      // deinterleaving-shuffle(load). The shuffle cost could potentially be
+      // free, but we model it with a cost of LT.first so that LD2/LD4 have a
+      // higher cost than just the load.
+      if (Args.size() >= 1 && isa<LoadInst>(Args[0]) &&
+          (LT.second.getScalarSizeInBits() == 8 ||
+           LT.second.getScalarSizeInBits() == 16 ||
+           LT.second.getScalarSizeInBits() == 32) &&
+          LT.second.getSizeInBits() == 128 &&
+          ((TLI->getMaxSupportedInterleaveFactor() >= 2 &&
+            ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, 2)) ||
+           (TLI->getMaxSupportedInterleaveFactor() == 4 &&
+            ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, 4))))
+        return ST->getMVEVectorCostFactor(CostKind) *
+               std::max<InstructionCost>(1, LT.first / 4);
+
+      // Check for ST2/ST4 instructions, which are represented in llvm IR as
+      // store(interleaving-shuffle). The shuffle cost could potentially be
+      // free, but we model it with a cost of LT.first so that ST2/ST4 have a
+      // higher cost than just the store.
+      if (CxtI && CxtI->hasOneUse() && isa<StoreInst>(*CxtI->user_begin()) &&
+          (LT.second.getScalarSizeInBits() == 8 ||
+           LT.second.getScalarSizeInBits() == 16 ||
+           LT.second.getScalarSizeInBits() == 32) &&
+          LT.second.getSizeInBits() == 128 &&
+          ((TLI->getMaxSupportedInterleaveFactor() >= 2 &&
+            ShuffleVectorInst::isInterleaveMask(
+                Mask, 2, SrcTy->getElementCount().getKnownMinValue() * 2)) ||
+           (TLI->getMaxSupportedInterleaveFactor() == 4 &&
+            ShuffleVectorInst::isInterleaveMask(
+                Mask, 4, SrcTy->getElementCount().getKnownMinValue() * 2))))
+        return ST->getMVEVectorCostFactor(CostKind) * LT.first;
+
       if (LT.second.isVector() &&
           Mask.size() <= LT.second.getVectorNumElements() &&
           (isVREVMask(Mask, LT.second, 16) || isVREVMask(Mask, LT.second, 32) ||