Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

tvm relay backend #79

Merged
merged 25 commits into from
Oct 12, 2023
Merged

tvm relay backend #79

merged 25 commits into from
Oct 12, 2023

Conversation

zrr1999
Copy link
Contributor

@zrr1999 zrr1999 commented Oct 10, 2023

#76 的 tvm.relay.frontend.from_paddle 版本

运行10次耗时对比
paddle 动态图 0.35s
tvm/llvm 不加 tune 0.88s
tvm/llvm 加 auto_scheduler 0.787s
tvm/llvm -mcpu=core-avx2 不加 auto_scheduler 0.52s
tvm/llvm -mcpu=core-avx2 加 auto_scheduler 0.405s

TODO:

  1. 对于不同的后端,cache是共享的,也就是说,如果第一次运行时使用了tvm不加tune的后端,后续即使使用了tvm+tune重新编译,缓存也会被命中,后续改成对不同 compiler 使用不同 cache。
  2. 整理各种临时文件路径

Copy link
Contributor

@jzhang533 jzhang533 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@jzhang533 jzhang533 merged commit 3a76dc7 into PFCCLab:main Oct 12, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants