Merge branch 'develop' into standalone-layernorm

library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_batched_gemm_reduce_xdl_cshuffle.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_gemm_instance {
+namespace instance {
 
 using F16              = ck::half_t;
 using F32              = float;
@@ -74,7 +74,7 @@ void add_device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn
         device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gkn_gmn_instances{});
 }
 
-} // namespace device_gemm_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_batched_gemm_reduce_xdl_cshuffle.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_gemm_instance {
+namespace instance {
 
 using F16              = ck::half_t;
 using F32              = float;
@@ -74,7 +74,7 @@ void add_device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn
         device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gkm_gnk_gmn_instances{});
 }
 
-} // namespace device_gemm_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_batched_gemm_reduce_xdl_cshuffle.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_gemm_instance {
+namespace instance {
 
 using F16              = ck::half_t;
 using F32              = float;
@@ -74,7 +74,7 @@ void add_device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn
         device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gkn_gmn_instances{});
 }
 
-} // namespace device_gemm_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/batched_gemm_reduce/device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_batched_gemm_reduce_xdl_cshuffle.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_gemm_instance {
+namespace instance {
 
 using F16              = ck::half_t;
 using F32              = float;
@@ -71,7 +71,7 @@ void add_device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn
         device_batched_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_gmk_gnk_gmn_instances{});
 }
 
-} // namespace device_gemm_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv1d_fwd/device_conv1d_fwd_xdl_nwc_kxc_nwk_bf16_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv1d_fwd_instance {
+namespace instance {
 
 using F32  = float;
 using BF16 = bhalf_t;
@@ -109,7 +109,7 @@ void add_device_conv1d_fwd_xdl_nwc_kxc_nwk_bf16_instances(
                                    device_conv1d_fwd_xdl_nwc_kxc_nwk_1x1_s1_p0_bf16_instances{});
 }
 
-} // namespace device_conv1d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv1d_fwd/device_conv1d_fwd_xdl_nwc_kxc_nwk_f16_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv1d_fwd_instance {
+namespace instance {
 
 using F16 = ck::half_t;
 using F32 = float;
@@ -109,7 +109,7 @@ void add_device_conv1d_fwd_xdl_nwc_kxc_nwk_f16_instances(
                                    device_conv1d_fwd_xdl_nwc_kxc_nwk_1x1_s1_p0_f16_instances{});
 }
 
-} // namespace device_conv1d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv1d_fwd/device_conv1d_fwd_xdl_nwc_kxc_nwk_f32_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv1d_fwd_instance {
+namespace instance {
 
 using F32 = float;
 
@@ -112,7 +112,7 @@ void add_device_conv1d_fwd_xdl_nwc_kxc_nwk_f32_instances(
                                    device_conv1d_fwd_xdl_nwc_kxc_nwk_1x1_s1_p0_f32_instances{});
 }
 
-} // namespace device_conv1d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv1d_fwd/device_conv1d_fwd_xdl_nwc_kxc_nwk_int8_instance.cpp

@@ -8,12 +8,12 @@
 #include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
 #include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv1d_fwd_instance {
+namespace instance {
 
 using F32 = float;
 
@@ -111,7 +111,7 @@ void add_device_conv1d_fwd_xdl_nwc_kxc_nwk_int8_instances(
                                    device_conv1d_fwd_xdl_nwc_kxc_nwk_1x1_s1_p0_int8_instances{});
 }
 
-} // namespace device_conv1d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_bwd_data_instance {
+namespace instance {
 
 using BF16 = ck::bhalf_t;
 using F32  = float;
@@ -82,7 +82,7 @@ void add_device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instances(
         instances, device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_bf16_instances{});
 }
 
-} // namespace device_conv2d_bwd_data_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_bwd_data_instance {
+namespace instance {
 
 using F16 = ck::half_t;
 using F32 = float;
@@ -84,7 +84,7 @@ void add_device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instances(
         instances, device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_f16_instances{});
 }
 
-} // namespace device_conv2d_bwd_data_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_bwd_data_instance {
+namespace instance {
 
 using F32 = float;
 
@@ -81,7 +81,7 @@ void add_device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instances(
         instances, device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_f32_instances{});
 }
 
-} // namespace device_conv2d_bwd_data_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_bwd_data_instance {
+namespace instance {
 
 using DataType = int8_t;
 using AccType  = int32_t;
@@ -82,7 +82,7 @@ void add_device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instances(
         instances, device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_int8_instances{});
 }
 
-} // namespace device_conv2d_bwd_data_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_bwd_weight_instance {
+namespace instance {
 
 using F16 = ck::half_t;
 using F32 = float;
@@ -52,7 +52,7 @@ void add_device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f16_instances(
                                    device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f16_instances{});
 }
 
-} // namespace device_conv2d_bwd_weight_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f32_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_bwd_weight_instance {
+namespace instance {
 
 using F32 = float;
 
@@ -51,7 +51,7 @@ void add_device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f32_instances(
                                    device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f32_instances{});
 }
 
-} // namespace device_conv2d_bwd_weight_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_fwd_instance {
+namespace instance {
 
 using F16 = ck::half_t;
 using F32 = float;
@@ -143,7 +143,7 @@ void add_device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instances(
         instances, device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_odd_c_f16_instances{});
 }
 
-} // namespace device_conv2d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_fwd_instance {
+namespace instance {
 
 using BF16 = ck::bhalf_t;
 using F32  = float;
@@ -109,7 +109,7 @@ void add_device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instances(
                                    device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_bf16_instances{});
 }
 
-} // namespace device_conv2d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_fwd_instance {
+namespace instance {
 
 using F16 = ck::half_t;
 using F32 = float;
@@ -108,7 +108,7 @@ void add_device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instances(
                                    device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_f16_instances{});
 }
 
-} // namespace device_conv2d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_fwd_instance {
+namespace instance {
 
 using F32 = float;
 
@@ -107,7 +107,7 @@ void add_device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instances(
                                    device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_f32_instances{});
 }
 
-} // namespace device_conv2d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_fwd_instance {
+namespace instance {
 
 using F32 = float;
 
@@ -108,7 +108,7 @@ void add_device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instances(
                                    device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_int8_instances{});
 }
 
-} // namespace device_conv2d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck

library/src/tensor_operation_instance/gpu/conv2d_fwd/device_convnd_2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp

@@ -7,12 +7,12 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "ck/tensor_operation/gpu/device/device_convnd_fwd_xdl_nhwc_kyxc_nhwk.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
-#include "ck/library/tensor_operation_instance/device_operation_instance.hpp"
+#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
 
 namespace ck {
 namespace tensor_operation {
 namespace device {
-namespace device_conv2d_fwd_instance {
+namespace instance {
 
 using BF16 = ck::bhalf_t;
 using F32  = float;
@@ -112,7 +112,7 @@ void add_device_convnd_2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instances(
                                    device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_1x1_s1_p0_bf16_instances{});
 }
 
-} // namespace device_conv2d_fwd_instance
+} // namespace instance
 } // namespace device
 } // namespace tensor_operation
 } // namespace ck