* add CPU_ARCH info, improve the performance of GEMM1*1s1

* improve the performance of gemm1*1s1_conv_add and gemm1*1s1_conv_add_bn_relu

* improve the performance of slidingwindow_bn_relu,slidingwindow_add,slidingwindow_add_bn_relu,gemm1*1s1_bn_relu,gemm1*1s1_add_relu

1.update CPUContext to probe CPU info 2.improve the performance of SlidingwindowConv3x3s1 and SlidingwindowConv3x3s2 (#1655)

* format CMakeLists

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

* Update ARM Linux CPU, GPU build docs for rk3399

* 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

* 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