-
Notifications
You must be signed in to change notification settings - Fork 38
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
Add CTS for scratch register reading. #89
base: master
Are you sure you want to change the base?
Conversation
} | ||
} | ||
|
||
TEST_F( |
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.
Query why cant we use the same test case which @bmyates mentioned in our sync?
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.
Then we might need to modify the kernel too. Kernel is not allocating any local memory as such.
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.
Any difficulty in modifing the kernel? I hope scratch is forced using IGC_OPTs, so maybe with these options kernel modification might not be required
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.
yes please try to use the same test. The kernel should not need to allocate any local memory. Local memory is for SLM - scratch is different. The compiler will determine if scratch is needed or not based on register usage.
Try to use same kernel. If scratch isnt allocated then we can try to use IGC opt. If we still are not getting any spills I can give some suggestions to modify kernel
4697059
to
79e34c0
Compare
No description provided.