[Mlir-commits] [mlir] [mlir][tensor] Extend the logic to generalise tensor.pack (PR #109815)

[Han-Chung Wang]

================
@@ -14,12 +14,13 @@
 namespace mlir {
 namespace tensor {
 
-// Return a PadOp that pads `source` to `type` size where the static
-// sizes are assumed to be greater than the dynamic sizes. If `type` has dynamic
-// dimensions the padding width is set to zero. The op performs "high" padding
-// (i.e. it adds trailing padding values until the desired size is met).
+// Return a PadOp that pads `source` to `type` size. Output sizes (from `type`)
+// are assumed to be static and greater than the potentially dynamic input sizes
+// (from `source). The op performs "high" padding (i.e. it adds trailing padding
+// values until the desired size is met).
 PadOp createPadHighOp(RankedTensorType type, Value source, Value pad,
-                      bool nofold, Location loc, OpBuilder &builder);
+                      bool nofold, Location loc, OpBuilder &builder,
+                      std::optional<Value> dynOutDim = {});
----------------
hanhanW wrote:

We can extend it to multiple dynamic shapes later for sure, but why not we just support it in the patch?

```suggestion
                      std::optional<SmallVector<Value>> dynOutDim = {});
```

https://github.com/llvm/llvm-project/pull/109815