Skip to content

Conversation

@anthony-linaro
Copy link

Currently, this is only in the form of the reference implementations, as the other ARM implementations require ACL, or SVE512 (which is not widely implemented yet outside of a few select/recent CPUs).

ACL is not an option due to not working on Windows.

This also (sort of) cherry picks the following upstream PRs:
uxlfoundation/oneDNN#1557
uxlfoundation/oneDNN#1648
uxlfoundation/oneDNN#1654

Only the relevant sections of these have been pulled in.

This works on both Linux (gcc) and Windows (MSVC).

Tested on a Volterra (Windows Dev Kit 2023) machine with Windows 11/Debian WSL, a Thinkpad X13s with Windows 11/Ubuntu WSL, and a Raspberry Pi 4 with Raspbian.

Follow-up PR to OIDN to be made shortly after this one with further detail.

Marking as draft until discussion on other PR resolved.

Currently, this is only in the form of the reference implementations,
as the other ARM implementations require ACL, or SVE512 (which is not
widely implemented yet outside of a few select/recent CPUs).

ACL is not an option due to not working on Windows.

This also (sort of) cherry picks the following upstream PRs:
uxlfoundation/oneDNN#1557
uxlfoundation/oneDNN#1648
uxlfoundation/oneDNN#1654

Only the relevant sections of these have been pulled in.

This works on both Linux (gcc) and Windows (MSVC)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant