* refine toolchain test=develop

* fix wrap compilation error

* fix yolov3 armv8 compilation test=develop

* revert to armv7 as default test=develop

* fix fpga compilation test=develop

* [test=develop]1.fix crash when gpu op scale&elementwise_add input dim size equal 2
2.add gpu op mul

* fix code style test=develop

* enable fast test compilation && push opencl kernels by run.py

* merge cl kernels into so

* restore pre-commit