- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi, I'm running the offloading collection analysis, capturing also estimated data transfer with reuse using the command:
advisor --collect=offload --data-transfer=full --project-dir ./advisor_results -- ./source.o
and is suggesting me all the function from my code that could get benefit from GPU offloading.
Is there a way to perform the same analysis, since I'm interested in estimated data transfer with reuse to the GPU and the evaluation of FLOPs, but only for a specific loop/function? I've tried adding
--select=source.cpp:34
to that command but does not run the analysis only on that loop. Thanks in advance.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Thank you for posting in Intel Community.
The issue may be because that particular loop is not offloading on gpu or that loop is running for negligible time.
In order to debug the issue from our end, could you please share the OS details and the Advisor version you are using?
Also share the exact command you used and reproducer code so that we can try out the same form our end.
Thanks
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
We have not heard back from you. Could you please give us an update?
Thanks
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
We have not heard back from you. This thread will no longer be monitored by Intel. If you need further assistance, please post a new question.
Thanks

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