-
Notifications
You must be signed in to change notification settings - Fork 797
[SYCL] Add double to bfloat16 conversion in imf libdevice #8403
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.
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
Conversation
Hi, @xtian-github @zettai-reido @akolesov-intel |
/verify with intel/llvm-test-suite#1608 |
Hi, @xtian-github @zettai-reido @akolesov-intel |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks correct.
But I would like to avoid type punning through union as it was problematic in the past
with exactly IGC compiler we targeting.
Also,
but it is a matter of code style and might not be accepted in this header,
long constants read better annotated with '.
0x3ff0'0000'0000'0000
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
Thanks for addressing comments.
Hi, @intel/dpcpp-tools-reviewers |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sycl-post-link
part LGTM
Failing HIP test was disabled in intel/llvm-test-suite#1625
Seems to be unrelated. Could be caused by recent test changes done in intel/llvm-test-suite#1618. Tagging @maksimsab for awareness |
Add double to bfloat16 utils to imf libdevice, the corresponding test is in: intel/llvm-test-suite#1608