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/CMakeLists.txt

+include_directories(BEFORE
+    ${PROJECT_SOURCE_DIR}/include/ck
+    ${PROJECT_SOURCE_DIR}/include/ck/utility
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_description
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor
+    ${PROJECT_SOURCE_DIR}/include/ck/problem_transform
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/device
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/grid
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/block
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/warp
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/thread
+    ${PROJECT_SOURCE_DIR}/include/ck/tensor_operation/gpu/element
+    ${PROJECT_SOURCE_DIR}/library/include/ck/library/host_tensor
+    ${PROJECT_SOURCE_DIR}/library/include/ck/library/tensor_operation_instance
+    ${PROJECT_SOURCE_DIR}/library/include/ck/library/tensor_operation_instance/gpu/reduce
+    ${PROJECT_SOURCE_DIR}/external/include/half
+)
+
+add_subdirectory(gemm)
+add_subdirectory(gemm_bias2d)
+add_subdirectory(gemm_bias_relu)
+add_subdirectory(gemm_bias_relu_add)
+add_subdirectory(batched_gemm)
+add_subdirectory(conv1d_fwd)
+add_subdirectory(conv2d_fwd)
+add_subdirectory(conv2d_fwd_bias_relu)
+add_subdirectory(conv2d_fwd_bias_relu_add)
+add_subdirectory(conv2d_fwd_bias_relu_atomic_add)
+add_subdirectory(conv2d_bwd_data)
+add_subdirectory(reduce)

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

+#device_batched_gemm_instance
+set(DEVICE_BATCHED_GEMM_INSTANCE_SOURCE
+   device_batched_gemm_xdl_f16_f16_f16_gmk_gkn_gmn_instance.cpp;
+   device_batched_gemm_xdl_f16_f16_f16_gmk_gnk_gmn_instance.cpp;
+   device_batched_gemm_xdl_f16_f16_f16_gkm_gkn_gmn_instance.cpp;
+   device_batched_gemm_xdl_f16_f16_f16_gkm_gnk_gmn_instance.cpp;
+)
+
+add_library(device_batched_gemm_instance SHARED ${DEVICE_BATCHED_GEMM_INSTANCE_SOURCE})
+target_compile_features(device_batched_gemm_instance PUBLIC)
+set_target_properties(device_batched_gemm_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_batched_gemm_instance LIBRARY DESTINATION lib)
+
+clang_tidy_check(device_batched_gemm_instance)

library/src/tensor_operation_instance/gpu/conv1d_fwd/CMakeLists.txt

+# device_conv1d_fwd_instance
+set(DEVICE_CONV1D_FWD_INSTANCE_SOURCE
+   device_conv1d_fwd_xdl_nwc_kxc_nwk_f32_instance.cpp;
+)
+
+add_library(device_conv1d_fwd_instance SHARED ${DEVICE_CONV1D_FWD_INSTANCE_SOURCE}) 
+target_compile_features(device_conv1d_fwd_instance PUBLIC)
+set_target_properties(device_conv1d_fwd_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_conv1d_fwd_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_conv1d_fwd_instance)

library/src/tensor_operation_instance/gpu/conv2d_bwd_data/CMakeLists.txt

+# device_conv2d_bwd_data_instance
+set(DEVICE_CONV2D_BWD_DATA_INSTANCE_SOURCE 
+   device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f32_instance.cpp;
+   device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_f16_instance.cpp;
+   device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_bf16_instance.cpp;
+   device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk_int8_instance.cpp;
+) 
+
+add_library(device_conv2d_bwd_data_instance SHARED ${DEVICE_CONV2D_BWD_DATA_INSTANCE_SOURCE})
+target_compile_features(device_conv2d_bwd_data_instance PUBLIC)
+set_target_properties(device_conv2d_bwd_data_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_conv2d_bwd_data_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_conv2d_bwd_data_instance)