- It provides a unified style to express graph and kernel for user.
- It provides a unified IR to represent graph and kernel for developer.
- It breaks the boundary between graph and kernel.
- It provides more opportunities to do compile optimization.

Merge pull request !2313 from caifubi/save-profiling-point

Merge pull request !2361 from kisnwang/fix-codex-reviewbot

Merge pull request !2215 from caifubi/support-hccl-profiling

1.Support Broadcast op
2.Support communication op as graph output
3.Optimize Communication op memory alocation
4.support hccl multi-group

Signed-off-by: leonwanghui <leon.wanghui@huawei.com>