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.

Sign up for GitHub

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

Jump to bottom

Support for block floating point (bfp16) #437

Open
newling opened this issue Jun 17, 2024 · 1 comment
Open

Support for block floating point (bfp16) #437

newling opened this issue Jun 17, 2024 · 1 comment

Comments

@newling
Copy link
Contributor

newling commented Jun 17, 2024

There are 2 kinds of bfp16 number formats which AIE2p supports (as announced at computex 2024..). They are exponent:mantissa ratios of 1:8 and 1:16.

We need to support this at multiple levels.

In IREE:

  • CPU emulation (will we be able to run with llvm-cpu backend?)
  • storage formats
  • etc.

In iree-amd-aie:

  • exponent and mantissa now separate tensors to be tiled, and moved through DMAs separately.

In peano:

  • general support

In numpy and C++:

  • You wish!

Realistically we might not get all of this for quite a long time, so ideas on prioritization are welcome here. Please feel free to modify this task
@newling newling mentioned this issue Jul 25, 2024
Open
@newling
Copy link
Contributor Author

newling commented Oct 3, 2024

@yzhang93 was working on this, probably a duplicate issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@newling