[RISCV][TTI] Model the cost of insert/extractelt when the vector split into multiple register group and idx exceed single group. (#118401)

This patch implements the cost when the size of the vector need to split
into multiple groups and the index exceed single vector group.

For extract element, we need to store split vectors to stack and load
the target element.
For insert element, we need to store split vectors to stack and store
the target element and load vectors back.

After this patch, the cost of insert/extract element will close to the
generated assembly.

Author: ElvisWang123

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -1980,6 +1980,34 @@ InstructionCost RISCVTTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
       SlideCost = 1; // With a constant index, we do not need to use addi.
   }
 
+  // When the vector needs to split into multiple register groups and the index
+  // exceeds single vector register group, we need to insert/extract the element
+  // via stack.
+  if (LT.first > 1 &&
+      ((Index == -1U) || (Index >= LT.second.getVectorMinNumElements() &&
+                          LT.second.isScalableVector()))) {
+    Type *ScalarType = Val->getScalarType();
+    Align VecAlign = DL.getPrefTypeAlign(Val);
+    Align SclAlign = DL.getPrefTypeAlign(ScalarType);
+    // Extra addi for unknown index.
+    InstructionCost IdxCost = Index == -1U ? 1 : 0;
+
+    // Store all split vectors into stack and load the target element.
+    if (Opcode == Instruction::ExtractElement)
+      return getMemoryOpCost(Instruction::Store, Val, VecAlign, 0, CostKind) +
+             getMemoryOpCost(Instruction::Load, ScalarType, SclAlign, 0,
+                             CostKind) +
+             IdxCost;
+
+    // Store all split vectors into stack and store the target element and load
+    // vectors back.
+    return getMemoryOpCost(Instruction::Store, Val, VecAlign, 0, CostKind) +
+           getMemoryOpCost(Instruction::Load, Val, VecAlign, 0, CostKind) +
+           getMemoryOpCost(Instruction::Store, ScalarType, SclAlign, 0,
+                           CostKind) +
+           IdxCost;
+  }
+
   // Extract i64 in the target that has XLEN=32 need more instruction.
   if (Val->getScalarType()->isIntegerTy() &&
       ST->getXLen() < Val->getScalarSizeInBits()) {