Reorganize files, Part 1 (#119)

* delete obselete files

* move files

* build

* update cmake

* update cmake

* fix build

* reorg examples

* update cmake for example and test

library/src/tensor_operation_instance/gpu/conv2d_fwd/CMakeLists.txt

+# device_conv2d_fwd_instance
+set(DEVICE_CONV2D_FWD_INSTANCE_SOURCE
+   device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f32_instance.cpp;
+   device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_f16_instance.cpp;
+   device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp;
+   device_conv2d_fwd_xdl_nhwc_kyxc_nhwk_int8_instance.cpp;
+   device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk_f16_instance.cpp;
+)
+add_library(device_conv2d_fwd_instance SHARED ${DEVICE_CONV2D_FWD_INSTANCE_SOURCE}) 
+target_compile_features(device_conv2d_fwd_instance PUBLIC)
+set_target_properties(device_conv2d_fwd_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_conv2d_fwd_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_conv2d_fwd_instance)

library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu/CMakeLists.txt

+# device_conv2d_fwd_bias_relu_instance
+set(DEVICE_CONV2D_FWD_BIAS_RELU_INSTANCE_SOURCE
+   device_conv2d_fwd_xdl_c_shuffle_bias_relu_nhwc_kyxc_nhwk_f16_instance.cpp;
+)
+add_library(device_conv2d_fwd_bias_relu_instance SHARED ${DEVICE_CONV2D_FWD_BIAS_RELU_INSTANCE_SOURCE}) 
+target_compile_features(device_conv2d_fwd_bias_relu_instance PUBLIC)
+set_target_properties(device_conv2d_fwd_bias_relu_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_conv2d_fwd_bias_relu_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_conv2d_fwd_bias_relu_instance)

library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_add/CMakeLists.txt

+# device_conv2d_fwd_bias_relu_add_instance
+set(DEVICE_CONV2D_FWD_BIAS_RELU_ADD_INSTANCE_SOURCE
+   device_conv2d_fwd_xdl_c_shuffle_bias_relu_add_nhwc_kyxc_nhwk_f16_instance.cpp;
+)
+add_library(device_conv2d_fwd_bias_relu_add_instance SHARED ${DEVICE_CONV2D_FWD_BIAS_RELU_ADD_INSTANCE_SOURCE}) 
+target_compile_features(device_conv2d_fwd_bias_relu_add_instance PUBLIC)
+set_target_properties(device_conv2d_fwd_bias_relu_add_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_conv2d_fwd_bias_relu_add_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_conv2d_fwd_bias_relu_add_instance)

library/src/tensor_operation_instance/gpu/conv2d_fwd_bias_relu_atomic_add/CMakeLists.txt

+# device_conv2d_fwd_bias_relu_atomic_add_instance
+set(DEVICE_CONV2D_FWD_BIAS_RELU_ATOMIC_ADD_INSTANCE_SOURCE
+   device_conv2d_fwd_xdl_c_shuffle_bias_relu_atomic_add_nhwc_kyxc_nhwk_f16_instance.cpp;
+)
+
+add_library(device_conv2d_fwd_bias_relu_atomic_add_instance SHARED ${DEVICE_CONV2D_FWD_BIAS_RELU_ATOMIC_ADD_INSTANCE_SOURCE}) 
+target_compile_features(device_conv2d_fwd_bias_relu_atomic_add_instance PUBLIC)
+set_target_properties(device_conv2d_fwd_bias_relu_atomic_add_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_conv2d_fwd_bias_relu_atomic_add_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_conv2d_fwd_bias_relu_atomic_add_instance)

library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt

+# device_gemm_instance
+set(DEVICE_GEMM_INSTANCE_SOURCE
+   device_gemm_xdl_f32_f32_f32_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_f32_f32_f32_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_f32_f32_f32_km_kn_mn_instance.cpp;
+   device_gemm_xdl_f32_f32_f32_km_nk_mn_instance.cpp;
+   device_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_int8_int8_int8_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bf16_bf16_bf16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_f16_f16_f16_km_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_2_stage_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp;
+   device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp;
+   device_gemm_xdl_splitk_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_splitk_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_splitk_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_splitk_f16_f16_f16_km_nk_mn_instance.cpp;
+)
+
+add_library(device_gemm_instance SHARED ${DEVICE_GEMM_INSTANCE_SOURCE}) 
+
+target_compile_features(device_gemm_instance PUBLIC)
+set_target_properties(device_gemm_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_gemm_instance LIBRARY DESTINATION lib)
+
+clang_tidy_check(device_gemm_instance)