NVIDIA / NVIDIA/TensorRT

RFE: Support Ceil or Round operator on DLA

Open
#4,486 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Module:Embedded triaged
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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.