[Mlir-commits] [mlir] [Mesh] initialize mesh dialect (PR #68007)

[Chengji Yao]

================
@@ -0,0 +1,91 @@
+//===- MeshBase.td - Mesh Dialect --------------------------*- tablegen -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_DIALECT_MESH_IR_MESHBASE_TD
+#define MLIR_DIALECT_MESH_IR_MESHBASE_TD
+
+include "mlir/IR/OpBase.td"
+include "mlir/IR/AttrTypeBase.td"
+include "mlir/IR/BuiltinTypeInterfaces.td"
+
+//===----------------------------------------------------------------------===//
+// Mesh Dialect
+//===----------------------------------------------------------------------===//
+
+def Mesh_Dialect : Dialect {
+  let name = "mesh";
+  let cppNamespace = "::mlir::mesh";
+
+  let description = [{
+    The `mesh` dialect contains a set of attributes, operations, interfaces that
+    are useful for representing sharding and communication on device mesh
+    cluster.
+  }];
+
+  let dependentDialects = [
+    "arith::ArithDialect"
+  ];
+
+  let useDefaultAttributePrinterParser = 1;
+  let hasConstantMaterializer = 1;
+}
+
+//===----------------------------------------------------------------------===//
+// Mesh Attribute
+//===----------------------------------------------------------------------===//
+
+def MeshSharding : AttrDef<Mesh_Dialect, "MeshSharding"> {
+  let mnemonic = "shard";
+
+  let parameters = (ins
+    OptionalParameter<"::mlir::SymbolRefAttr">:$cluster,
+    ArrayRefParameter<"::mlir::DenseI64ArrayAttr">:$axes
+  );
+
+  let summary = "Attribute that extends tensor type to distributed tensor type.";
+
+  let description = [{
+    The mesh.shard attribute contains two attribute in it:
+    1. `cluster`: this attribute is a SymbolRefAttr that refers to the mesh
+    cluster where the distributed tensor is placed.
+
+    2. `axes`: is an array composed of int64_t sub-arrays. The outer array's
+    maximum size is the `rank` of the related tensor plus one. For the i-th
+    sub-array, if its value is [x, y]:
+    - When i < `rank`, it indicates that the tensor's i-th dimension is sharded
+    along the x and y axes of the device mesh.
+    - When i == `rank`, it signifies that the tensor represents a partial sum
+    along the x and y axes. More partial types could be introduced if needed, 
+    e.g. partial-max, partial-min and even partial-generic.
----------------
yaochengji wrote:

Updated. Your suggestion is quite better :)

BTW, the `ASMPrinter` encounters some issuses with printing 8-bit integers, it's fixed in this PR.

https://github.com/llvm/llvm-project/pull/68007