[Mlir-commits] [mlir] [mlir][Vector] add vector.insert canonicalization pattern for vectors created from ub.poison (PR #142944)

[Yang Bai]

================
@@ -3191,6 +3227,114 @@ class InsertSplatToSplat final : public OpRewritePattern<InsertOp> {
   }
 };
 
+/// Pattern to optimize a chain of constant insertions into a poison vector.
+///
+/// This pattern identifies chains of vector.insert operations that:
+/// 1. Start from an ub.poison operation.
+/// 2. Insert only constant values at static positions.
+/// 3. Completely initialize all elements in the resulting vector.
+/// 4. All intermediate insert operations have only one use.
+///
+/// When these conditions are met, the entire chain can be replaced with a
+/// single arith.constant operation containing a dense elements attribute.
+///
+/// Example transformation:
+///   %poison = ub.poison : vector<2xi32>
+///   %0 = vector.insert %c1, %poison[0] : i32 into vector<2xi32>
+///   %1 = vector.insert %c2, %0[1] : i32 into vector<2xi32>
+/// ->
+///   %result = arith.constant dense<[1, 2]> : vector<2xi32>
+/// TODO: Support the case where only some elements of the poison vector are
+/// set. Currently, MLIR doesn't support partial poison vectors.
+class InsertConstantToPoison final : public OpRewritePattern<InsertOp> {
+public:
+  using OpRewritePattern::OpRewritePattern;
+  LogicalResult matchAndRewrite(InsertOp op,
+                                PatternRewriter &rewriter) const override {
+
+    VectorType destTy = op.getDestVectorType();
+    if (destTy.isScalable())
+      return failure();
+    // Check if the result is used as the dest operand of another vector.insert
+    // Only care about the last op in a chain of insertions.
+    for (Operation *user : op.getResult().getUsers())
+      if (auto insertOp = dyn_cast<InsertOp>(user))
+        if (insertOp.getDest() == op.getResult())
+          return failure();
+
+    InsertOp firstInsertOp;
+    InsertOp previousInsertOp = op;
+    SmallVector<InsertOp> chainInsertOps;
+    SmallVector<Attribute> srcAttrs;
+    while (previousInsertOp) {
+      // Dynamic position is not supported.
+      if (previousInsertOp.hasDynamicPosition())
+        return failure();
+
+      // The inserted content must be constant.
+      chainInsertOps.push_back(previousInsertOp);
+      srcAttrs.push_back(Attribute());
+      matchPattern(previousInsertOp.getValueToStore(),
+                   m_Constant(&srcAttrs.back()));
+      if (!srcAttrs.back())
+        return failure();
+
+      // An insertion at poison index makes the entire chain poisoned.
----------------
yangtetris wrote:

The insert operation’s folder will fold this case into a **ub.poison**, effectively truncating the insert chain’s backward traversal. If the vector is not fully initialized by that point, this pattern will definitively fail. I will add a comment to clarify this behavior in the code.

https://github.com/llvm/llvm-project/pull/142944