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

[DML EP] Re-architect | Partitioning as Transformer #13131

Merged
merged 34 commits into from
Oct 8, 2022

Conversation

sumitsays
Copy link
Contributor

@sumitsays sumitsays commented Sep 28, 2022

Description

Re-architect DML EP to allow ORT L2/L3 transformers. This change includes:

  • During ORT graph partitioning, DML EP will only set the dmlExecutionProvider to all eligible nodes.
  • Moved DML specific operator transformer as L2 transformer
  • Introduced a new DMLGraphFusionTransformer, applicable only for DML EP, which is responsible to
    • partition the graph
    • fuse each partition into a IDMLCompiledOperator
    • register the kernel for each partition

Motivation and Context

  • Why is this change required? What problem does it solve?
    It enables ORT L2/L3 transformers for DML EP, which will increase the perf of Transformer-based models.
  • If it fixes an open issue, please link to the issue here. N/A

@sumitsays sumitsays changed the title User/sumita/dml ep2.0 resume [DML EP] Re-architect | Partitioning as Transformer Sep 28, 2022
@sumitsays sumitsays marked this pull request as ready for review September 28, 2022 03:31
@sumitsays sumitsays requested review from fdwr and jeffbloo September 28, 2022 03:32
@sumitsays sumitsays requested a review from souptc September 28, 2022 21:32
@sumitsays sumitsays force-pushed the user/sumita/DmlEP2.0_Resume branch from 281ab90 to 9ea3c01 Compare September 29, 2022 18:43
@lgtm-com
Copy link

lgtm-com bot commented Oct 5, 2022

This pull request fixes 1 alert when merging dd2100e into 4fc8f71 - view on LGTM.com

fixed alerts:

  • 1 for Potentially uninitialized local variable

@sumitsays sumitsays merged commit e01a851 into main Oct 8, 2022
sumitsays added a commit that referenced this pull request Oct 26, 2022
### Description
DML EP was a special EP w.r.t. capability fusion. It used to fuse a
capability outside the IExecutionProvider::Compile() call. But after
recent re-architecture #13131, it is no longer a special case.



### Motivation and Context
Why is this change required? What problem does it solve?
To make DML EP consistent with the ORT design.
- If it fixes an open issue, please link to the issue here.  N/A

Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
linnealovespie pushed a commit that referenced this pull request Oct 28, 2022
### Description
DML EP was a special EP w.r.t. capability fusion. It used to fuse a
capability outside the IExecutionProvider::Compile() call. But after
recent re-architecture #13131, it is no longer a special case.



### Motivation and Context
Why is this change required? What problem does it solve?
To make DML EP consistent with the ORT design.
- If it fixes an open issue, please link to the issue here.  N/A

Co-authored-by: Sumit Agarwal <sumitagarwal@microsoft.com>
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