From e62f7c72c533b29aaabe01dfa2a39c81388f1931 Mon Sep 17 00:00:00 2001 From: illsilin Date: Fri, 30 May 2025 13:38:43 -0700 Subject: [PATCH] fix clang format --- include/ck/utility/filter_tuple.hpp | 8 +-- ...ndhwgc_gkzyxc_ndhwgk_f16_comp_instance.inc | 37 ++++++------ ...ngcdhw_gkczyx_ngkdhw_f16_comp_instance.inc | 37 ++++++------ ...gcdhw_gkczyx_ngkdhw_bf16_instance_1of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_2of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_3of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_4of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_5of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_6of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_7of8.cpp | 3 +- ...gcdhw_gkczyx_ngkdhw_bf16_instance_8of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_1of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_2of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_3of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_4of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_5of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_6of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_7of8.cpp | 3 +- ...ngcdhw_gkczyx_ngkdhw_f16_instance_8of8.cpp | 3 +- ..._ngkdhw_bf16_mem_inter_instance_10of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_1of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_2of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_3of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_4of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_5of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_6of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_7of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_8of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_inter_instance_9of10.cpp | 4 +- ..._ngkdhw_bf16_mem_intra_instance_10of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_1of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_2of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_3of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_4of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_5of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_6of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_7of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_8of10.cpp | 4 +- ...x_ngkdhw_bf16_mem_intra_instance_9of10.cpp | 4 +- ...w_gkczyx_ngkdhw_f16_mem_inter_instance.inc | 58 +++++++++---------- ...x_ngkdhw_f16_mem_inter_instance_10of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_1of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_2of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_3of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_4of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_5of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_6of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_7of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_8of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_inter_instance_9of10.cpp | 4 +- ...w_gkczyx_ngkdhw_f16_mem_intra_instance.inc | 58 +++++++++---------- ...x_ngkdhw_f16_mem_intra_instance_10of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_1of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_2of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_3of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_4of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_5of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_6of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_7of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_8of10.cpp | 4 +- ...yx_ngkdhw_f16_mem_intra_instance_9of10.cpp | 4 +- ...w_gkczyx_ngkdhw_f32_mem_inter_instance.inc | 58 +++++++++---------- ...x_ngkdhw_f32_mem_inter_instance_10of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_1of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_2of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_3of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_4of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_5of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_6of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_7of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_8of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_inter_instance_9of10.cpp | 4 +- ...w_gkczyx_ngkdhw_f32_mem_intra_instance.inc | 58 +++++++++---------- ...x_ngkdhw_f32_mem_intra_instance_10of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_1of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_2of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_3of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_4of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_5of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_6of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_7of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_8of10.cpp | 4 +- ...yx_ngkdhw_f32_mem_intra_instance_9of10.cpp | 4 +- 83 files changed, 288 insertions(+), 314 deletions(-) diff --git a/include/ck/utility/filter_tuple.hpp b/include/ck/utility/filter_tuple.hpp index 84026841fc..c2e378b879 100644 --- a/include/ck/utility/filter_tuple.hpp +++ b/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 + Stride - Offset - 1) / Stride; - + template static constexpr auto to_index(std::index_sequence) { return std::index_sequence<(Offset + Is * Stride)...>{}; } - + using filtered_indices = decltype(to_index(std::make_index_sequence{})); // 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 - struct make_filtered_tuple_type_impl> { + struct make_filtered_tuple_type_impl> + { using type = std::tuple...>; }; using type = typename make_filtered_tuple_type_impl::type; - }; // Filter a tuple with a stride and offset. diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_instance.inc b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_instance.inc index 7fab30ec05..ad2c974041 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ndhwgc_gkzyxc_ndhwgk_f16_comp_instance.inc +++ b/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, + 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>{}); } diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_comp_instance.inc b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_comp_instance.inc index 80d4bc7431..ada196f4d2 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/comp/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_comp_instance.inc +++ b/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, + 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>{}); } diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_1of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_1of8.cpp index af97f91a0f..493b9e9dc5 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_1of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_2of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_2of8.cpp index 619cb9f30e..4d7df88562 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_2of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_3of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_3of8.cpp index e444cc6b9e..29ed41426b 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_3of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_4of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_4of8.cpp index aae5e24b09..d9ecf9d74e 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_4of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_5of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_5of8.cpp index 74cb9651f5..10fb27ddbb 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_5of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_6of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_6of8.cpp index 34b2f17fa2..13310da86b 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_6of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_7of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_7of8.cpp index a7f55a1a51..4cb19330a1 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_7of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_8of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_8of8.cpp index 7dded232da..cfef11f708 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_bf16_instance_8of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_1of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_1of8.cpp index 6bff2efd88..da2f3dc1fa 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_1of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_2of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_2of8.cpp index cf8c3ed814..5d551833c0 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_2of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_3of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_3of8.cpp index 39a1393a3b..715cbf6beb 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_3of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_4of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_4of8.cpp index c1bfa72274..cf2a9f4023 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_4of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_5of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_5of8.cpp index 6522201ec2..085b2904d6 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_5of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_6of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_6of8.cpp index 5843387c61..18b1e0c6d9 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_6of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_7of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_7of8.cpp index 1df19b270e..b95f1d1229 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_7of8.cpp +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_8of8.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_8of8.cpp index c6a1a8c9fb..afe3e5d19f 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_instance_8of8.cpp +++ b/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 diff --git a/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 b/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 index 5a261f2b82..e90c2b1f4a 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 994ea90b5f..d853b74ead 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 5953a7274f..471b26ac2a 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index cb70072c4f..e98f9c4b96 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 8b8b20fb99..5fe302c550 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index f3942a9828..f1ddae003b 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 994ea90b5f..d853b74ead 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 13155a1ffd..1f19d2e867 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 74739193d0..e2bd53db8b 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index d091a162dc..97646aac28 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 9596734b47..ddd2e29ba6 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index a1a6e7f7ce..36cb6f5a8d 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 99a8b626a1..3c442a55eb 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 52c1cfe021..7621bae57f 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index c574f9a575..ef34ef3764 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index dbb08be1c7..3c4ce1728b 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index a1a6e7f7ce..36cb6f5a8d 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index a1b700373b..c0c044ff8c 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 7dddc1563b..7a865d852f 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 4388ee76eb..f2aa266ab9 100644 --- a/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 +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc index 0cabb5c8b5..2f825e23ff 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_inter_instance.inc +++ b/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 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 diff --git a/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 b/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 index d9680adbd3..a10cda251c 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 241e3bcfda..2fcb6ef68d 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 7ec8e64e09..1060f7f926 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 72dc779ffc..227e61dccd 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 597b21c317..83a4cf6733 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 438926b103..3a72d02151 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 241e3bcfda..2fcb6ef68d 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index e4d6f0c1ac..192870304d 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 6529731c1e..5e036804f3 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 2f4820b500..65064fd3d6 100644 --- a/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 +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc index 56f349ae43..5e3be12648 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f16_mem_intra_instance.inc +++ b/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 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 diff --git a/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 b/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 index 009e4e8e79..64097cb377 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 389ffeb8af..5313544e5e 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 19fd779309..da9ce0c570 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 278cdeda4f..866eaa54c6 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index e3d3f9beab..8ccf402fac 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 5e65dbeeb9..66969676d6 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 389ffeb8af..5313544e5e 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 6d775b7940..cddc15d357 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index dfea75b22a..b245aeb2ca 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index a0865b43df..80ac4fcb78 100644 --- a/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 +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc index 99d1679a15..20ac9acf32 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_inter_instance.inc +++ b/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 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 diff --git a/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 b/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 index 3000988ca6..677405b307 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index c94d413325..9a072a4fe5 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 18d0546524..5205292188 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 3e47891460..16ccde7c80 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 81a21c2ca8..68513b1982 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index ca731e18f2..12347eaa50 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index c94d413325..9a072a4fe5 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 3861d02485..e29f6d0c7e 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 54094d0730..b64cd1ff40 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 77aae247f6..840055eeb7 100644 --- a/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 +++ b/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 diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc index 264b5e096e..77c3c221c8 100644 --- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/xdl/mem/device_grouped_conv3d_fwd_xdl_ngcdhw_gkczyx_ngkdhw_f32_mem_intra_instance.inc +++ b/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 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 diff --git a/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 b/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 index b24f34acc1..df88797237 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index a8af40bb8b..8a8e1ba632 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 2b5e35bd54..babd81713c 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index e71052b25e..49f5d54d2c 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 68d3bfb300..28cb24acd4 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 6b346a7bda..95044ffb8e 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index a8af40bb8b..8a8e1ba632 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index b7b397f8fc..d2c20c91c9 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 114f8c5513..85ed83485f 100644 --- a/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 +++ b/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 diff --git a/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 b/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 index 67cf8e29e5..238ec708d1 100644 --- a/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 +++ b/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