Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add arch flags for Intel GPU Ponte Vecchio #4932

Merged
merged 4 commits into from
Apr 7, 2022
Merged

Add arch flags for Intel GPU Ponte Vecchio #4932

merged 4 commits into from
Apr 7, 2022

Conversation

masterleinad
Copy link
Contributor

Among others, announcements for this GPU to be used in Aurora can be found at https://www.intel.com/content/www/us/en/newsroom/news/intel-technology-roadmaps-milestones.html.

dalg24
dalg24 reviewed Apr 4, 2022
View reviewed changes
Copy link
Member

@dalg24 dalg24 left a comment

Choose a reason for hiding this comment

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

What about the GNU makefiles?

dalg24
dalg24 reviewed Apr 4, 2022
View reviewed changes
Copy link
Member

@dalg24 dalg24 left a comment

Choose a reason for hiding this comment

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

add to the [gnu_]generate_makefile.bash scripts

dalg24
dalg24 reviewed Apr 5, 2022
View reviewed changes
Copy link
Member

@dalg24 dalg24 left a comment

Choose a reason for hiding this comment

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

No -D__STRICT_ANSI__ with the GNU makefiles?

@masterleinad
Copy link
Contributor Author

No -D__STRICT_ANSI__ with the GNU makefiles?

That's for OpenMPTarget which doesn't have support for Intel architectures in Makefiles yet. I would prefer to do that in a separate pull request.

@masterleinad
Copy link
Contributor Author

I decided to also push the changes to add OpenMPTarget Intel GPU architectures flags to Makefile.kokkos. I'm happy to discuss the approach separately and remove the last commit here, though.

dalg24
dalg24 approved these changes Apr 5, 2022
View reviewed changes
Makefile.kokkos
tmp := $(call kokkos_append_header,"$H""define KOKKOS_ARCH_INTEL_XEHP")
KOKKOS_INTERNAL_SYCL_ARCH_FLAG := -fsycl-targets=spir64_gen-unknown-unknown-sycldevice -Xsycl-target-backend "-device xehp"
endif
KOKKOS_INTERNAL_LC_BACKEND := sycl
Copy link
Member

Choose a reason for hiding this comment

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

What does "LC" stand for?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

lowercase

@masterleinad
Copy link
Contributor Author

Only CUDA-9.2-NVCC is failing in default_exec.overlap_mdrange_policy which is clearly unrelated.
`

@dalg24 dalg24 merged commit 87d5c45 into kokkos:develop Apr 7, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dalg24 dalg24 dalg24 approved these changes

@crtrott crtrott crtrott approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@masterleinad @dalg24 @crtrott