- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Sirs,
Here is my BKC:
1. OS : ubuntu 22.04
2. Model : My Onnx model : https://www.dropbox.com/s/l8d7qorwv37r04s/bbb3.zip?dl=0
3. GPU : intel ARC pro 60
4. OpenVINO version : 2023.0
Description:
Use OpenVINO 2023.0 Benchmark_app to run my onnx model, GPU will show error message. But CPU can run properly.
Error messages from GPU:
From error messages that can only know cause by dynamic shape . Hope can get more detail information. If possible, please let me know if this model can be executed on a GPU.
Thanks your help.
BR
Jacko
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I did a quick check & I could observe the same thing.
The model can be inferred on CPU but not GPU.
The reason is, currently, dynamic shape support for GPU is a preview feature and has the following limitations:
- It mainly supports NLP models (Natural Language Processing). Not all operations and optimization passes support dynamic shapes. As a result, a given model may crash or experience significant performance drops.
- Due to the dominant runtime overhead on the host device, dynamic shapes may perform worse than static shapes on a discrete GPU.
- Dynamic rank is not supported.
You may refer here for further info.
Cordially,
Iffa
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Iffa,
Thanks your response.
BR
Jacko
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Glad that helps!.
Intel will no longer monitor this thread since this issue has been resolved. If you need any additional information from Intel, please submit a new question.
Cordially,
Iffa

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page