[Mlir-commits] [mlir] [mlir][mesh] Handling changed halo region sizes during spmdization (PR #114238)

[Chengji Yao]

================
@@ -196,16 +197,18 @@ def Mesh_ShardingOp : Mesh_Op<"sharding", [
     e.g. the first sharded dimension gets [1,2] halos and the seconds gets [2,3] halos.
     `?` indicates dynamic halo sizes.
     
-    6. [Optional] Sizes of sharded dimensions of each shard.
-    `sharded_dims_sizes`is provided as a flattened 1d array of i64s: for each device of the
-    device-mesh one value for each sharded tensor dimension.
+    6. [Optional] Offsets for each shard and sharded tensor dimension.
+    `sharded_dims_offsets` is provided as a flattened 1d array of i64s:
----------------
yaochengji wrote:

Why is it a flattened 1d array?

In my understanding, the offsets in each dimension is a strictly increasing array. I feel it might be more straightforward to organize it as a 2d array.

BTW, I think we'd better add some code to check whether it's a strictly increasing array or not.

https://github.com/llvm/llvm-project/pull/114238