[Mlir-commits] [mlir] [mlir][vector] Add vector.transpose with unit-dim to vector.shape_cast pattern (PR #72105)

[Nicolas Vasilache]

================
@@ -336,6 +336,27 @@ class TransposeOpLowering : public OpRewritePattern<vector::TransposeOp> {
       return rewriter.notifyMatchFailure(
           op, "Options specifies lowering to shuffle");
 
+    // Replace:
+    //   vector.transpose %0, [1, 0] : vector<nx1x<eltty>> to
+    //                                 vector<1xnxelty>
+    // with:
+    //   vector.shape_cast %0 : vector<nx1x<eltty>> to vector<1xnxelty>
+    //
+    // Source with leading unit dim (inverse) is also replaced. Unit dim must
+    // be fixed. Non-unit can be scalable.
+    if (resType.getRank() == 2 &&
+        ((resType.getShape().front() == 1 &&
+          !resType.getScalableDims().front()) ||
+         (resType.getShape().back() == 1 &&
+          !resType.getScalableDims().back())) &&
+        transp[0] == 1 && transp[1] == 0) {
----------------
nicolasvasilache wrote:

Can we write this in some high-order form like `transp == {1, 0}` ?

https://github.com/llvm/llvm-project/pull/72105