From 774f8fde01bcd7786544820cce84a4d08fb945fa Mon Sep 17 00:00:00 2001
From: Wojciech Laskowski <wojciech.laskowski@streamhpc.com>
Date: Fri, 5 Dec 2025 09:08:02 +0000
Subject: [PATCH] removed unnecessary source file

---
 .../gpu/grouped_conv3d_fwd/CMakeLists.txt     |  1 -
 ...ev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.cpp | 63 -------------------
 ...lev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.in | 10 +++
 3 files changed, 10 insertions(+), 64 deletions(-)
 delete mode 100644 library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.cpp

diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
index e9271dc52b..676a5ba18a 100644
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
@@ -76,7 +76,6 @@ set(GROUPED_CONV3D_FWD
    wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_f16_16x16_instance.cpp
    wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
    wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_f16_16x16_instance.cpp
-   wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.cpp
 
    wmma/merged_groups/device_grouped_conv3d_fwd_wmma_cshufflev3_merged_groups_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
    wmma/merged_groups/device_grouped_conv3d_fwd_wmma_cshufflev3_merged_groups_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.cpp b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.cpp
deleted file mode 100644
index 1d13c9a1fd..0000000000
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.cpp
+++ /dev/null
@@ -1,63 +0,0 @@
-// SPDX-License-Identifier: MIT
-// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-#include "ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_instance.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-void add_device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instances(
-    std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
-                                                                NGCDHW,
-                                                                GKCZYX,
-                                                                Empty_Tuple,
-                                                                NGKDHW,
-                                                                BF16,
-                                                                BF16,
-                                                                Empty_Tuple,
-                                                                BF16,
-                                                                PassThrough,
-                                                                PassThrough,
-                                                                PassThrough>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_grouped_conv_fwd_wmma_cshufflev3_bf16_ngchw_instances<3,
-                                                                     NGCDHW,
-                                                                     GKCZYX,
-                                                                     Empty_Tuple,
-                                                                     NGKDHW,
-                                                                     ConvFwdDefault>{});
-
-    add_device_operation_instances(
-        instances,
-        device_grouped_conv_fwd_wmma_cshufflev3_bf16_ngchw_instances<3,
-                                                                     NGCDHW,
-                                                                     GKCZYX,
-                                                                     Empty_Tuple,
-                                                                     NGKDHW,
-                                                                     ConvFwd1x1P0>{});
-    add_device_operation_instances(
-        instances,
-        device_grouped_conv_fwd_wmma_cshufflev3_bf16_ngchw_instances<3,
-                                                                     NGCDHW,
-                                                                     GKCZYX,
-                                                                     Empty_Tuple,
-                                                                     NGKDHW,
-                                                                     ConvFwd1x1S1P0>{});
-    add_device_operation_instances(
-        instances,
-        device_grouped_conv_fwd_wmma_cshufflev3_bf16_ngchw_instances<3,
-                                                                     NGCDHW,
-                                                                     GKCZYX,
-                                                                     Empty_Tuple,
-                                                                     NGKDHW,
-                                                                     ConvFwdOddC>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.in b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.in
index 8dc3ee2245..4f55ce8d4a 100644
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.in
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/wmma/device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_instance.in
@@ -56,6 +56,16 @@ void add_device_grouped_conv3d_fwd_wmma_cshufflev3_ngcdhw_gkczyx_ngkdhw_bf16_ins
                                                                                   ConvFwd1x1S1P0>,
                                        Shards,
                                        ShardIndex>{});
+    add_device_operation_instances(
+        instances,
+        util::filter_tuple_by_modulo_t<device_grouped_conv_fwd_wmma_cshufflev3_bf16_ngchw_instances<3,
+                                                                                  NGCDHW,
+                                                                                  GKCZYX,
+                                                                                  Empty_Tuple,
+                                                                                  NGKDHW,
+                                                                                  ConvFwdOddC>,
+                                       Shards,
+                                       ShardIndex>{});
 }
 
 } // namespace ck::tensor_operation::device::instance