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/gemm_bias_relu/CMakeLists.txt

+# device_gemm_bias_relu_instance
+set(DEVICE_GEMM_BIAS_RELU_INSTANCE_SOURCE
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_f16_f16_f16_km_nk_mn_instance.cpp;
+)
+
+add_library(device_gemm_bias_relu_instance SHARED ${DEVICE_GEMM_BIAS_RELU_INSTANCE_SOURCE}) 
+target_compile_features(device_gemm_bias_relu_instance PUBLIC)
+set_target_properties(device_gemm_bias_relu_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_gemm_bias_relu_instance LIBRARY DESTINATION lib)
+
+clang_tidy_check(device_gemm_bias_relu_instance)

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

+# device_gemm_bias_relu_add_instance
+set(DEVICE_GEMM_BIAS_RELU_ADD_INSTANCE_SOURCE
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_mk_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_mk_nk_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_km_kn_mn_instance.cpp;
+   device_gemm_xdl_c_shuffle_bias_relu_add_f16_f16_f16_km_nk_mn_instance.cpp;
+)
+
+add_library(device_gemm_bias_relu_add_instance SHARED ${DEVICE_GEMM_BIAS_RELU_ADD_INSTANCE_SOURCE}) 
+target_compile_features(device_gemm_bias_relu_add_instance PUBLIC)
+set_target_properties(device_gemm_bias_relu_add_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_gemm_bias_relu_add_instance LIBRARY DESTINATION lib)
+
+clang_tidy_check(device_gemm_bias_relu_add_instance)

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

+# device_reduce_instance
+set(DEVICE_REDUCE_INSTANCE_SOURCE
+   device_reduce_instance_blockwise_f16_f16_f16.cpp;
+   device_reduce_instance_blockwise_f16_f32_f16.cpp;
+   device_reduce_instance_blockwise_f32_f32_f32.cpp;
+   device_reduce_instance_blockwise_f32_f64_f32.cpp;
+   device_reduce_instance_blockwise_f64_f64_f64.cpp;
+   device_reduce_instance_threadwise_f16_f16_f16.cpp;
+   device_reduce_instance_threadwise_f16_f32_f16.cpp;
+   device_reduce_instance_threadwise_f32_f32_f32.cpp;
+   device_reduce_instance_threadwise_f32_f64_f32.cpp;
+   device_reduce_instance_threadwise_f64_f64_f64.cpp;
+   device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp;
+   device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp;
+   device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp;
+   device_reduce_instance_blockwise_second_call_f64_f64_f32.cpp;
+   device_reduce_instance_blockwise_second_call_f64_f64_f64.cpp;
+   device_reduce_instance_multiblock_atomic_add_f16_f32_f32.cpp;
+   device_reduce_instance_multiblock_atomic_add_f32_f32_f32.cpp;
+   device_reduce_instance_multiblock_atomic_add_f32_f64_f32.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f16_f16_f16.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f16_f32_f16.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f32_f32_f32.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f32_f64_f32.cpp;
+   device_reduce_instance_multiblock_partial_reduce_f64_f64_f64.cpp;
+)
+
+add_library(device_reduce_instance SHARED ${DEVICE_REDUCE_INSTANCE_SOURCE}) 
+target_compile_features(device_reduce_instance PUBLIC)
+set_target_properties(device_reduce_instance PROPERTIES POSITION_INDEPENDENT_CODE ON)
+install(TARGETS device_reduce_instance LIBRARY DESTINATION lib) 
+
+clang_tidy_check(device_reduce_instance)