[llvm] [SLP]Initial support for copyable elements (non-schedulable only) (PR #140279)

[Simon Pilgrim via llvm-commits]

================
@@ -9761,13 +9891,99 @@ bool BoUpSLP::canBuildSplitNode(ArrayRef<Value *> VL,
 }
 
 namespace {
-/// Class accepts incoming list of values and generates the list of values
-/// for scheduling and list of operands for the new nodes.
+/// Class accepts incoming list of values, checks if it is able to model
+/// "copyable" values as compatible operations, and generates the list of values
+/// for scheduling and list of operands doe the new nodes.
 class InstructionsCompatibilityAnalysis {
   DominatorTree &DT;
   const DataLayout &DL;
   const TargetTransformInfo &TTI;
   const TargetLibraryInfo &TLI;
+  unsigned MainOpcode = 0;
+  Instruction *MainOp = nullptr;
+
+  /// Identifies the best candidate value, which represents main opcode
+  /// operation.
+  /// Currently the best candidate is the Add instruction with the parent
+  /// block with the highest DFS incoming number (block, that dominates other).
+  void findAndSetMainInstruction(ArrayRef<Value *> VL) {
+    BasicBlock *Parent = nullptr;
+    // Checks if the instruction has supported opcode.
+    auto IsSupportedOpcode = [](Instruction *I) {
+      return I && I->getOpcode() == Instruction::Add;
+    };
+    SmallDenseSet<Value *, 8> Operands;
+    for (Value *V : VL) {
+      auto *I = dyn_cast<Instruction>(V);
+      if (!I)
+        continue;
+      if (!DT.isReachableFromEntry(I->getParent()))
+        continue;
+      if (!MainOp) {
+        MainOp = I;
+        Parent = I->getParent();
+        Operands.insert(I->op_begin(), I->op_end());
+        continue;
+      }
+      if (Parent == I->getParent()) {
+        if (!IsSupportedOpcode(MainOp))
+          MainOp = I;
+        if (MainOp->getOpcode() == I->getOpcode() &&
+            doesNotNeedToBeScheduled(MainOp) && !doesNotNeedToBeScheduled(I))
+          MainOp = I;
+        Operands.insert(I->op_begin(), I->op_end());
+        continue;
+      }
+      auto *NodeA = DT.getNode(Parent);
+      auto *NodeB = DT.getNode(I->getParent());
+      assert(NodeA && "Should only process reachable instructions");
+      assert(NodeB && "Should only process reachable instructions");
+      assert((NodeA == NodeB) ==
+                 (NodeA->getDFSNumIn() == NodeB->getDFSNumIn()) &&
+             "Different nodes should have different DFS numbers");
+      if (NodeA->getDFSNumIn() < NodeB->getDFSNumIn()) {
+        MainOp = I;
+        Parent = I->getParent();
+        Operands.clear();
+        Operands.insert(I->op_begin(), I->op_end());
+      }
+    }
+    if (!IsSupportedOpcode(MainOp) || Operands.contains(MainOp)) {
+      MainOp = nullptr;
+      return;
+    }
+    MainOpcode = MainOp->getOpcode();
+  }
+
+  /// Returns the idempotent value for the \p MainOp with the detected \p
+  /// MainOpcode. For Add, returns 0. For Or, it should choose between false and
+  /// the operand itself, since V or V == V.
+  Value *selectBestIdempotentValue() const {
+    switch (MainOpcode) {
+    case Instruction::Add:
+      return ConstantInt::getNullValue(MainOp->getType());
----------------
RKSimon wrote:

ConstantExpr::getBinOpIdentity is the best I've found so far

https://github.com/llvm/llvm-project/pull/140279