Merge branch 'develop' into jizhan/reduce_threadwise_multi_d

example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16_comp_bf8_fp8.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 
@@ -78,6 +78,9 @@ using HostConvBwdWeightInstance = ck::tensor_operation::host::ReferenceConvBwdWe
                                                                                      InElementOp,
                                                                                      WeiElementOp,
                                                                                      OutElementOp,
+                                                                                     0,
+                                                                                     0,
+                                                                                     0,
                                                                                      ComputeTypeA,
                                                                                      ComputeTypeB>;