[Mlir-commits] [mlir] [mlir][spirv] Use assemblyFormat to define groupNonUniform op assembly (PR #115662)

[Jakub Kuderski]

================
@@ -318,24 +324,14 @@ def SPIRV_GroupNonUniformFAddOp : SPIRV_GroupNonUniformArithmeticOp<"GroupNonUni
 
     <!-- End of AutoGen section -->
 
-    ```
-    scope ::= `"Workgroup"` | `"Subgroup"`
-    operation ::= `"Reduce"` | `"InclusiveScan"` | `"ExclusiveScan"` | ...
-    float-scalar-vector-type ::= float-type |
-                                 `vector<` integer-literal `x` float-type `>`
-    non-uniform-fadd-op ::= ssa-id `=` `spirv.GroupNonUniformFAdd` scope operation
-                            ssa-use ( `cluster_size` `(` ssa_use `)` )?
-                            `:` float-scalar-vector-type
-    ```
-
     #### Example:
 
     ```mlir
     %four = spirv.Constant 4 : i32
     %scalar = ... : f32
     %vector = ... : vector<4xf32>
-    %0 = spirv.GroupNonUniformFAdd "Workgroup" "Reduce" %scalar : f32
-    %1 = spirv.GroupNonUniformFAdd "Subgroup" "ClusteredReduce" %vector cluster_size(%four) : vector<4xf32>
+    %0 = spirv.GroupNonUniformFAdd <Workgroup> <Reduce> %scalar : f32 -> f32
+    %1 = spirv.GroupNonUniformFAdd <Subgroup> <ClusteredReduce> %vector cluster_size(%four) : vector<4xf32>, i32 -> vector<4xf32>
----------------
kuhar wrote:

Nice!

https://github.com/llvm/llvm-project/pull/115662