Skip to content
This repository was archived by the owner on Jan 25, 2023. It is now read-only.
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 2 additions & 5 deletions numba/dppl_config.py
Original file line number Diff line number Diff line change
@@ -1,8 +1,5 @@
dppl_present = False

try:
import dpctl
dppl_present = dpctl.has_gpu_queues() and dpctl.has_cpu_queues()
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

OR

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Argh! Yes. You are right.

Copy link
Copy Markdown
Author

@PokhodenkoSA PokhodenkoSA Oct 9, 2020

Choose a reason for hiding this comment

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

I doubt numba.dppl works with CPU devices.
@reazulhoque Can it work when only CPU devices available?

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

The intent of the change is to make sure there is at least some OpenCL device (CPU or GPU) for Numba.dppl to use. We can also use dpctl.has_sycl_platforms() for this check.

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

@PokhodenkoSA it should work with any sycl device.

except:
pass
else:
dppl_present = True
dppl_present = False