* reduce .so size. test=develop

* compile all targets when LITE_ON_TINY_PUBLISH=OFF

* unordered_map is more convenient when key is customized class

* test=develop

lite cuda support exec multi-stream

[LITE][ALL] Refine NPU and XPU passes, fix the pass matching based on the bound targets and excluded targets (#2477)

* checkout if passes match targets and kernels, test=develop

* add pass_utils, test=develop

* fix lite/core/mir/pass_registry.h, test=develop

* improve code styles, test=develop

* fix spell error, test=develop

* make passes related to the device type, test=develop

* improve tips, test=develop