solve merge conflict

library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp → library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp

 // SPDX-License-Identifier: MIT
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
+#include "ck/ck.hpp"
+#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
+#include "ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp"
+#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
+#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 #include "ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp"
-#include "device_grouped_conv2d_fwd_common.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
 namespace instance {
 
+using BF16 = ck::bhalf_t;
+using F16  = ck::half_t;
+using F32  = float;
+using I8   = int8_t;
+using I32  = int32_t;
+
+using Empty_Tuple = ck::Tuple<>;
+
+template <ck::index_t... Is>
+using S = ck::Sequence<Is...>;
+
+using NHWGC = ck::tensor_layout::convolution::NHWGC;
+using GNHWC = ck::tensor_layout::convolution::GNHWC;
+
+using GKYXC = ck::tensor_layout::convolution::GKYXC;
+
+using NHWGK = ck::tensor_layout::convolution::NHWGK;
+using GNHWK = ck::tensor_layout::convolution::GNHWK;
+
+using PassThrough = ck::tensor_operation::element_wise::PassThrough;
+
+static constexpr auto ConvFwdDefault =
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::Default;
+
+static constexpr auto ConvFwd1x1P0 =
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::Filter1x1Pad0;
+
+static constexpr auto ConvFwd1x1S1P0 =
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::Filter1x1Stride1Pad0;
+
+static constexpr auto ConvFwdOddC =
+    ck::tensor_operation::device::ConvolutionForwardSpecialization::OddC;
+
+static constexpr auto GemmMNKPadding = ck::tensor_operation::device::GemmSpecialization::MNKPadding;
+
 template <typename ALayout,
           typename BLayout,
           typename DsLayout,

library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward.hpp

@@ -151,6 +151,13 @@ void add_device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instances(
                                                               GKYXC,
                                                               Empty_Tuple,
                                                               GNHWK,
+                                                              F16,
+                                                              F16,
+                                                              Empty_Tuple,
+                                                              F16,
+                                                              PassThrough,
+                                                              PassThrough,
+                                                              PassThrough>>>& instances);
 void add_device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f16_instances(
     std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleD<2,
                                                               NHWGC,
@@ -175,6 +182,9 @@ void add_device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instances(
                                                               int8_t,
                                                               Empty_Tuple,
                                                               int8_t,
+                                                              PassThrough,
+                                                              PassThrough,
+                                                              PassThrough>>>& instances);
 void add_device_grouped_conv2d_fwd_dl_nhwgc_gkyxc_nhwgk_f32_instances(
     std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleD<2,
                                                               NHWGC,

library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_f16_instance.cpp

@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-#include "device_grouped_conv2d_fwd_wmma_instance.hpp"
+#include "ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {

library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_wmma_gnhwc_gkyxc_gnhwk_i8_instance.cpp

@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
-#include "device_grouped_conv2d_fwd_wmma_instance.hpp"
+#include "ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv2d_fwd_wmma_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {