[HACKATHON 6th] Refactor phi module structure

[silverling]

PR Category

Environment Adaptation

PR Types

Improvements

Description

以 Linux 平台为例，将 PHI 模块下的 Kernel 实现中的 GPU 算子部分抽离出来，单独编译为 libphi_gpu.so，其余部分编译为 libphi_core.so，从而使 Paddle 可以编译 6 个 CUDA 架构。同时，创建空 libphi.so，将 libphi_core.so 与 libphi_gpu.so 与其链接，使得对用户的代码改动影响最小。

[paddle-bot]

你的PR提交成功，感谢你对开源项目的贡献!
请关注后续CI自动化测试结果，详情请参考Paddle-CI手册。
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

[paddle-ci-bot]

Sorry to inform you that 9dd1a25's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.

[paddle-ci-bot]

Sorry to inform you that 810251c's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}