Skip to content

Conversation

CtfGo
Copy link
Contributor

@CtfGo CtfGo commented Dec 22, 2021

PR types

Performance optimization

PR changes

OPs

Describe

collecting input variables that only shape needed of each subgraph that compiled by CINN in build_cinn_pass, and expose them to memory optimization of framework passes by declaringDECLARE_INPLACE_OP_INFERER in cinn_launch op.

@paddle-bot-old
Copy link

Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

@CtfGo CtfGo force-pushed the expose_memory_opt_inside_cinn_launch branch from ea03fe6 to ba4b59a Compare December 29, 2021 12:17
@CtfGo CtfGo changed the title expose memory optmize infos of all ops in each subgraph that compiled by CINN expose input variables that only shape needed in each subgraph that compiled by CINN Dec 29, 2021
Copy link
Contributor

@thisjiang thisjiang left a comment

Choose a reason for hiding this comment

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

Great!

@zhhsplendid zhhsplendid merged commit b4cb358 into PaddlePaddle:develop Jan 17, 2022
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.

3 participants