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

Use dim_params in dynamic dimension analysis #2620

Merged
merged 6 commits into from
Nov 15, 2023
Merged

Use dim_params in dynamic dimension analysis #2620

merged 6 commits into from
Nov 15, 2023

Conversation

tungld
Copy link
Collaborator

@tungld tungld commented Nov 14, 2023

This patch improves the dynamic dimension analysis by getting the relationship between input and output dimensions via onnx.dim_params attribute.

AlexandreEichenberger
AlexandreEichenberger approved these changes Nov 14, 2023
View reviewed changes
Copy link
Collaborator

@AlexandreEichenberger AlexandreEichenberger left a comment

Choose a reason for hiding this comment

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

LGTM, if you go through one more rebuild, would just add a bit of cements for the build functions as you have now 2, one that is called for normal ops and one for the function params. Lots of useful debug printouts so that helps understand the code too.

Thanks for this great addition, looking forward to see the improvements.

@AlexandreEichenberger
Copy link
Collaborator

@jenkins-droid test this please

@tungld
Copy link
Collaborator Author

tungld commented Nov 15, 2023

if you go through one more rebuild, would just add a bit of cements for the build functions as you have now 2, one that is called for normal ops and one for the function params

Yes, done.

@tungld tungld merged commit 72f2308 into onnx:main Nov 15, 2023
5 checks passed
@jenkins-droid
Copy link
Collaborator

Jenkins Linux amd64 Build #13436 [push] Use dim_params in dynami... started at 03:58

@jenkins-droid
Copy link
Collaborator

Jenkins Linux s390x Build #13463 [push] Use dim_params in dynami... started at 04:58

@jenkins-droid
Copy link
Collaborator

Jenkins Linux ppc64le Build #12457 [push] Use dim_params in dynami... started at 05:07

@jenkins-droid
Copy link
Collaborator

Jenkins Linux ppc64le Build #12457 [push] Use dim_params in dynami... failed after 1 min 49 sec

@jenkins-droid
Copy link
Collaborator

Jenkins Linux amd64 Build #13436 [push] Use dim_params in dynami... passed after 1 hr 11 min

@jenkins-droid
Copy link
Collaborator

Jenkins Linux s390x Build #13463 [push] Use dim_params in dynami... passed after 1 hr 27 min

cjvolzka added a commit to cjvolzka/onnx-mlir that referenced this pull request Nov 15, 2023
@cjvolzka
Merge branch 'main' of github.ibm.com:zosdev/onnx-mlir into update
8180e51 
* 'main' of github.ibm.com:zosdev/onnx-mlir:
  Use dim_params in dynamic dimension analysis (onnx#2620)
  Update rapidcheck to include the fix for missing <cstdint> include (onnx#2623)
  Initial changes for llvm uplift (onnx#2568)
  [build] Add cmake option to enable/disable Java components build (onnx#2613)
  [StableHLO] Lowers PadOp (constant mode) & GatherElements Op to StableHLO (onnx#2602)
  [DialectBuilder] add builder funcrions for ONNXSumOp and ONNXConvOp (onnx#2572)
  Import dim_param for model inputs and outputs (onnx#2616)
  Parse and set --mcpu in onnx-mlir-opt command (onnx#2614)
  Layernorm: convert instance norm and group norm to layer norm. (onnx#2595)
  [NNPA] Use F16 as element type for zTensor (onnx#2611)
  detect LayerNorm in presence of reciprocal and div of 1 (onnx#2609)

# Conflicts:
#	test/mlir/conversion/onnx_to_krnl/NN/Normalization_O3_SIMD_canonicalize.mlir
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@AlexandreEichenberger AlexandreEichenberger AlexandreEichenberger approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@tungld @AlexandreEichenberger @jenkins-droid