fix clang format

include/ck/utility/filter_tuple.hpp

@@ -22,13 +22,13 @@ struct filter_tuple_by_modulo
 
     // Generate filtered indices for this stride and offset.
     static constexpr int new_size = (std::tuple_size_v<Tuple> + Stride - Offset - 1) / Stride;
-    
+
     template <std::size_t... Is>
     static constexpr auto to_index(std::index_sequence<Is...>)
     {
         return std::index_sequence<(Offset + Is * Stride)...>{};
     }
-    
+
     using filtered_indices = decltype(to_index(std::make_index_sequence<new_size>{}));
 
     // Helper struct to construct the new tuple type from the filtered indices.
@@ -36,12 +36,12 @@ struct filter_tuple_by_modulo
     struct make_filtered_tuple_type_impl;
 
     template <typename T, std::size_t... Is>
-    struct make_filtered_tuple_type_impl<T, std::index_sequence<Is...>> {
+    struct make_filtered_tuple_type_impl<T, std::index_sequence<Is...>>
+    {
         using type = std::tuple<std::tuple_element_t<Is, T>...>;
     };
 
     using type = typename make_filtered_tuple_type_impl<Tuple, filtered_indices>::type;
-
 };
 
 // Filter a tuple with a stride and offset.

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_instance.inc

@@ -31,35 +31,34 @@ void add_device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_instances_s
         instances,
         util::filter_tuple_by_modulo_t<
             device_grouped_conv_fwd_xdl_f16_comp_instances<3,
-                                                            NGCDHW,
-                                                            GKCZYX,
-                                                            Empty_Tuple,
-                                                            NGKDHW,
-                                                            ConvFwdDefault>,
+                                                           NGCDHW,
+                                                           GKCZYX,
+                                                           Empty_Tuple,
+                                                           NGKDHW,
+                                                           ConvFwdDefault>,
             Shards,
             ShardIndex>{});
 
     add_device_operation_instances(
         instances,
-        util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f16_comp_instances<3,
-                                                            NGCDHW,
-                                                            GKCZYX,
-                                                            Empty_Tuple,
-                                                            NGKDHW,
-                                                            ConvFwd1x1P0>,
-            Shards,
-            ShardIndex>{});
+        util::filter_tuple_by_modulo_t<device_grouped_conv_fwd_xdl_f16_comp_instances<3,
+                                                                                      NGCDHW,
+                                                                                      GKCZYX,
+                                                                                      Empty_Tuple,
+                                                                                      NGKDHW,
+                                                                                      ConvFwd1x1P0>,
+                                       Shards,
+                                       ShardIndex>{});
 
     add_device_operation_instances(
         instances,
         util::filter_tuple_by_modulo_t<
             device_grouped_conv_fwd_xdl_f16_comp_instances<3,
-                                                            NGCDHW,
-                                                            GKCZYX,
-                                                            Empty_Tuple,
-                                                            NGKDHW,
-                                                            ConvFwd1x1S1P0>,
+                                                           NGCDHW,
+                                                           GKCZYX,
+                                                           Empty_Tuple,
+                                                           NGKDHW,
+                                                           ConvFwd1x1S1P0>,
             Shards,
             ShardIndex>{});
 }

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_comp_instance.inc

@@ -31,35 +31,34 @@ void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_comp_instances_s
         instances,
         util::filter_tuple_by_modulo_t<
             device_grouped_conv_fwd_xdl_f16_comp_instances<3,
-                                                            NGCDHW,
-                                                            GKCZYX,
-                                                            Empty_Tuple,
-                                                            NGKDHW,
-                                                            ConvFwdDefault>,
+                                                           NGCDHW,
+                                                           GKCZYX,
+                                                           Empty_Tuple,
+                                                           NGKDHW,
+                                                           ConvFwdDefault>,
             Shards,
             ShardIndex>{});
 
     add_device_operation_instances(
         instances,
-        util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f16_comp_instances<3,
-                                                            NGCDHW,
-                                                            GKCZYX,
-                                                            Empty_Tuple,
-                                                            NGKDHW,
-                                                            ConvFwd1x1P0>,
-            Shards,
-            ShardIndex>{});
+        util::filter_tuple_by_modulo_t<device_grouped_conv_fwd_xdl_f16_comp_instances<3,
+                                                                                      NGCDHW,
+                                                                                      GKCZYX,
+                                                                                      Empty_Tuple,
+                                                                                      NGKDHW,
+                                                                                      ConvFwd1x1P0>,
+                                       Shards,
+                                       ShardIndex>{});
 
     add_device_operation_instances(
         instances,
         util::filter_tuple_by_modulo_t<
             device_grouped_conv_fwd_xdl_f16_comp_instances<3,
-                                                            NGCDHW,
-                                                            GKCZYX,
-                                                            Empty_Tuple,
-                                                            NGKDHW,
-                                                            ConvFwd1x1S1P0>,
+                                                           NGCDHW,
+                                                           GKCZYX,
+                                                           Empty_Tuple,
+                                                           NGKDHW,
+                                                           ConvFwd1x1S1P0>,
             Shards,
             ShardIndex>{});
 }

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_1of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 0>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_2of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 1>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_3of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 2>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_4of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 3>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_5of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 4>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_6of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 5>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 5>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_7of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 6>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_8of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 7>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances_sharded<8, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_1of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 0>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_2of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 1>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_3of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 2>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_4of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 3>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_5of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 4>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_6of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 5>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 5>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_7of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 6>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_8of8.cpp

@@ -4,7 +4,6 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 7>(
+template void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances_sharded<8, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_10of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 9>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 9>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_1of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_2of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 1>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_3of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 2>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_4of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 3>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_5of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 4>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_6of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_7of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 6>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_8of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 7>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance_9of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 8>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances_sharded<10, 8>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_10of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 9>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 9>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_1of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_2of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 1>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_3of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 2>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_4of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 3>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_5of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 4>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_6of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_7of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 6>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_8of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 7>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance_9of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 8>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances_sharded<10, 8>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc

@@ -27,41 +27,39 @@ template <int Shards, int ShardIndex>
 void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances)
 {
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f16_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwdDefault,
-                                                           Interwave>,
-            Shards,
-            ShardIndex>{});
     add_device_operation_instances(instances,
                                    ck::util::filter_tuple_by_modulo_t<
                                        device_grouped_conv_fwd_xdl_f16_mem_instances<3,
-                                                                                      NGCDHW,
-                                                                                      GKCZYX,
-                                                                                      Empty_Tuple,
-                                                                                      NGKDHW,
-                                                                                      ConvFwd1x1P0,
-                                                                                      Interwave>,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwdDefault,
+                                                                                     Interwave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f16_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1P0,
+                                                                                     Interwave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f16_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1S1P0,
+                                                                                     Interwave>,
                                        Shards,
                                        ShardIndex>{});
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f16_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwd1x1S1P0,
-                                                           Interwave>,
-            Shards,
-            ShardIndex>{});
 }
 
 } // namespace instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_10of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 9>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 9>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_1of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_2of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 1>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_3of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 2>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_4of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 3>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_5of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 4>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_6of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_7of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 6>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_8of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 7>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance_9of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 8>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances_sharded<10, 8>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc

@@ -27,41 +27,39 @@ template <int Shards, int ShardIndex>
 void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances)
 {
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f16_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwdDefault,
-                                                           Intrawave>,
-            Shards,
-            ShardIndex>{});
     add_device_operation_instances(instances,
                                    ck::util::filter_tuple_by_modulo_t<
                                        device_grouped_conv_fwd_xdl_f16_mem_instances<3,
-                                                                                      NGCDHW,
-                                                                                      GKCZYX,
-                                                                                      Empty_Tuple,
-                                                                                      NGKDHW,
-                                                                                      ConvFwd1x1P0,
-                                                                                      Intrawave>,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwdDefault,
+                                                                                     Intrawave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f16_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1P0,
+                                                                                     Intrawave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f16_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1S1P0,
+                                                                                     Intrawave>,
                                        Shards,
                                        ShardIndex>{});
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f16_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwd1x1S1P0,
-                                                           Intrawave>,
-            Shards,
-            ShardIndex>{});
 }
 
 } // namespace instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_10of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 9>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 9>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_1of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_2of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 1>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_3of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 2>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_4of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 3>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_5of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 4>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_6of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_7of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 6>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_8of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 7>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance_9of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 8>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances_sharded<10, 8>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc

@@ -27,41 +27,39 @@ template <int Shards, int ShardIndex>
 void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances)
 {
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f32_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwdDefault,
-                                                           Interwave>,
-            Shards,
-            ShardIndex>{});
     add_device_operation_instances(instances,
                                    ck::util::filter_tuple_by_modulo_t<
                                        device_grouped_conv_fwd_xdl_f32_mem_instances<3,
-                                                                                      NGCDHW,
-                                                                                      GKCZYX,
-                                                                                      Empty_Tuple,
-                                                                                      NGKDHW,
-                                                                                      ConvFwd1x1P0,
-                                                                                      Interwave>,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwdDefault,
+                                                                                     Interwave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f32_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1P0,
+                                                                                     Interwave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f32_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1S1P0,
+                                                                                     Interwave>,
                                        Shards,
                                        ShardIndex>{});
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f32_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwd1x1S1P0,
-                                                           Interwave>,
-            Shards,
-            ShardIndex>{});
 }
 
 } // namespace instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_10of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 9>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 9>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_1of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_2of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 1>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_3of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 2>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_4of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 3>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_5of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 4>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_6of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_7of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 6>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_8of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 7>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance_9of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 8>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances_sharded<10, 8>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc

@@ -27,41 +27,39 @@ template <int Shards, int ShardIndex>
 void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances)
 {
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f32_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwdDefault,
-                                                           Intrawave>,
-            Shards,
-            ShardIndex>{});
     add_device_operation_instances(instances,
                                    ck::util::filter_tuple_by_modulo_t<
                                        device_grouped_conv_fwd_xdl_f32_mem_instances<3,
-                                                                                      NGCDHW,
-                                                                                      GKCZYX,
-                                                                                      Empty_Tuple,
-                                                                                      NGKDHW,
-                                                                                      ConvFwd1x1P0,
-                                                                                      Intrawave>,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwdDefault,
+                                                                                     Intrawave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f32_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1P0,
+                                                                                     Intrawave>,
+                                       Shards,
+                                       ShardIndex>{});
+    add_device_operation_instances(instances,
+                                   ck::util::filter_tuple_by_modulo_t<
+                                       device_grouped_conv_fwd_xdl_f32_mem_instances<3,
+                                                                                     NGCDHW,
+                                                                                     GKCZYX,
+                                                                                     Empty_Tuple,
+                                                                                     NGKDHW,
+                                                                                     ConvFwd1x1S1P0,
+                                                                                     Intrawave>,
                                        Shards,
                                        ShardIndex>{});
-    add_device_operation_instances(
-        instances,
-        ck::util::filter_tuple_by_modulo_t<
-            device_grouped_conv_fwd_xdl_f32_mem_instances<3,
-                                                           NGCDHW,
-                                                           GKCZYX,
-                                                           Empty_Tuple,
-                                                           NGKDHW,
-                                                           ConvFwd1x1S1P0,
-                                                           Intrawave>,
-            Shards,
-            ShardIndex>{});
 }
 
 } // namespace instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_10of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 9>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 9>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_1of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_2of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 1>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 1>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_3of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 2>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 2>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_4of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 3>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 3>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_5of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 4>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 4>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_6of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 0>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 0>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_7of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 6>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 6>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_8of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 7>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 7>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance

library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance_9of10.cpp

@@ -4,7 +4,7 @@
 #include "device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc"
 
 namespace ck::tensor_operation::device::instance {
-template
-void add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 8>(
+template void
+add_device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances_sharded<10, 8>(
     device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instances& instances);
 } // namespace ck::tensor_operation::device::instance