as some reason: some version of trt/cudnn need
-Wl,--whole-archive attribute to fix cuda issue,
target A(CMAKE OBJECT,eg megbrain/megdnn): -Wl,--whole-archive depend on trt/cudnn
target B(SHARED LIBS,eg libmegengine.so) --> A with `PUBLIC` depends
target C(SHARED LIBS,eg _impertive.so) --> B with `PUBLIC` depends,
then ld will force link fatbin section into C, which will be undesired

what`s more, attribute PUBLIC/PRIVATE do not take effect
to OBJECT library(megbrain/megdnn)

what`s more, megengine/megengine_export have to PUBLIC for
mgb/imperative target, as SRC/include depends

so we pull cudalib depend from megbrain/megdnn to
megengine/megengine_export on linux os, to finall
target at windows os, for example lar on windows

GitOrigin-RevId: b278a69e1c

1: fix cmake cross-ios failed caused by df118a87
   build static lib for APPLE define for XCODE third_party framework including require

2: megbrain_test/megdnn_test build when MGE_INFERENCE_ONLY=ON
   now u can build megbrain_test/megdnn_test by:
   EXTRA_CMAKE_ARGS="-DMGE_WITH_TEST=ON" ./scripts/cmake-build/xxx.sh
   example macos-cross-ios build megdnn_test for IOS by
   EXTRA_CMAKE_ARGS="-DMGE_WITH_TEST=ON" ./scripts/cmake-build/cross_build_ios_arm_inference.sh

3: reuse host flatc build when cross build mode
GitOrigin-RevId: 132f4bf893567bdb1d54de506449950513a5841f

Also, upgrade to CMake 3.13.

The commit also contains significant refactors, as otherwise it is not
possible to properly export target `megengine` to
MegEngine-targets.cmake:

1. Optionally use system provided Flatbuffers.
2. Optionally use system provided MKL-DNN (Tested with Debian).
3. Refactor megbrain and megdnn targets into object libraries.
4. Set different path in BUILD_INTERFACE and INSTALL_INTERFACE of
   various target_include_directories.
5. Specify PUBLIC/PRIVATE on various target_link_libraries.

GitOrigin-RevId: df118a879e

GitOrigin-RevId: f0aa7abe85

GitOrigin-RevId: f0c8338beb