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

Enable Global Intermediate Buffers #325

Merged
merged 5 commits into from
Sep 2, 2020
Merged

Conversation

rdspring1
Copy link
Collaborator

@rdspring1 rdspring1 commented Aug 26, 2020

  • When the user designates a intermediate TensorView with the Global memory type, the fuser will pass the intermediate value as an argument to the kernel via global memory.
  • Enable support for the default schedule.

@rdspring1 rdspring1 changed the title [WIP] Enable Global Intermediate Buffers Enable Global Intermediate Buffers Aug 26, 2020
@rdspring1
Copy link
Collaborator Author

I made changes so that local memory is the default type and the memory type matches between the TensorView and its corresponding allocate node.

@csarofeen
Copy link
Owner

Could you also add/check there are couple things:
In addOutput/Input in fusion add a check to make sure they're in global memory
In the function to change memory type of a TV make sure we don't change a TV registered as input/output to anything besides global

torch/csrc/jit/codegen/cuda/fusion.cpp Outdated Show resolved Hide resolved
torch/csrc/jit/codegen/cuda/fusion.cpp Outdated Show resolved Hide resolved
@rdspring1 rdspring1 merged commit 4ec6d5a into 20_8_18_devel Sep 2, 2020
@csarofeen csarofeen deleted the rds_global_intermediate branch June 9, 2021 13:49
jjsjann123 pushed a commit that referenced this pull request Jun 8, 2022
…ytorch#78276)

Fixes #325
**Summary**: Currently, the pytorchbot only allows for rebasing to the master branch. These modifications add functionality for rebasing to the 'viable/strict' branch of pytorch/pytorch by adding a flag to the comment.
**Test Plan:** tested manually on personal fork ([#1](swang392#1)), and included a test case in test_tryrebase.py that checks if rebasing to viable/strict branch was successful.
Pull Request resolved: pytorch#78276
Approved by: https://github.com/clee2000, https://github.com/janeyx99
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