* optimize GPU conv performance and structure

* add CL macro for test_conv_gpu

* fix build failure

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* update kernel and related files for static quantization in FPGA v2 track

* update

* format CMakeLists

* BugFix: lacking of header file of memset, strlen, stable_sort, n_copy

* Update ARM Linux CPU, GPU build docs for rk3399

* update concat and split kernel and related files in FPGA v2(v3) track

* update

* update

* update kernel and related files in FPGA v2 track

* update

* update

* Fix memory leak if tensor was created outside of global scope

* Fix gemv bugs

* BugFix: fix multi-threadings incorrectness of cpu gemm

* BugFix: fix lack of header file for memset

* BugFix: fix lacking of header file for memset

* FPGA refactor

* disable FPGAKD

* recover misdeleted code segment

* Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode

* Fix code style

* Add fetch API for java, refine android log

* add prepare data and model script, modified corresponding docs:development_android and development_android_GPU

* Add verified multi-threading supported gemv_trans_mx1

* add comments for alloc and free

* optimize reduction progress of gemv_trans_mx1

* add macro for gemv_trans_mx1

* Fix multi-threadings incorrectnesss of armv7 neon gemv_trans_mx1

* add test_gemm_accuracy