RFE: Support Ceil or Round operator on DLA
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 13.4k
- Forks
- 2.4k
- Avg merge
- 5d 3h
- Merged PRs (30d)
- 2
Description
Versions:
DRIVE Orin (Automotive)
DRIVE OS 6.0.9.0
TensorRT 8.6.12
Expected DLA SW: 3.14.2
can provide more version info if this is unexpected.
I could use clarification on what "Native" means in the below related issue:
https://github.com/NVIDIA/Deep-Learning-Accelerator-SW/issues/32
command: /usr/src/tensorrt/bin/trtexec --onnx=ceil-example.onnx --useDLACore=0 --int8 --verbose --inputIOFormats=int8:dla_linear --outputIOFormats=int8:dla_linear
example failure: [W] [TRT] node_of_Y: Unary operation: CEIL is not supported on DLA.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the reported failure with trtexec and ceil-example.onnx using the command and DRIVE Orin/DLA settings provided. Review the related DLA issue about “Native” support before defining the scope. Done means the requested Ceil or Round operator is accepted on DLA without the reported unsupported-operation warning.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 30/100