[CK_TILE] Multiple-ABD GEMM example (#2788)

* Multi ABD - initial commit

* Clang-foramt fix

* block gemm, unify the name of CDataType

* Apply chnages to mem-pipeline

* Rollback prefix for DType and Layout

* Gemm Kernel Basic, rename

* WMMA config

* Grouped GEMM

* Clang-format

* Dropout, name

* Review v2

* Move element_wise fn to unnary, remov old ones fn

* clang-format

* Fix issue review

* WP operator adjust to universal gemm

* v2 prepare

* Remove unused comment

* Remove vectorsize

* Rollback

* Adjust pipeline for abd

* Shuffle argument

* CI-fail fix quant

* Fix ag_br pipeline

* Failing tests

* Typo

* Single argument support

include/ck_tile/ops/elementwise/unary_element_wise_operation.hpp

@@ -392,6 +392,23 @@ struct PassThrough
     }
 };
 
+struct AddScale
+{
+    template <typename E, typename... As>
+    CK_TILE_HOST_DEVICE constexpr void operator()(E& a, const As&... as) const
+    {
+        // Start with the base value c
+        float result = ck_tile::type_convert<float>(0.0f);
+
+        // Add by each D parameter using fold expression
+        ((result += ck_tile::type_convert<float>(as)), ...);
+
+        a = ck_tile::type_convert<E>(scale * result);
+    }
+
+    float scale = 1.0;
+};
+
 struct MultiDMultiply
 {
     template <typename E, typename C, typename... Ds>