-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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
[AMD] Add buffer support #4716
base: main
Are you sure you want to change the base?
[AMD] Add buffer support #4716
Conversation
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.
just putting a blocker on this as some pieces will need a bit more discussions. Lei had mentioned those to me so it's not a surprise but haven't had a chance to discuss it with Phil and the rest of the team yet
Do we have some data on the performance impact of this feature? Considering the cost in extra compilations and maintenance it would be good to have this information |
After having a quick chat with @ptillet one problem is that the specialization will apply to all backends even the ones that can't take advantage of that. |
Absolutely fine, I put it here exactly to have discussions while we get on with #4638 |
fbeb3a6
to
b426ce4
Compare
- The getPtrAlignment needs to run on a tensor - getPtrAlignment returns the alignment in terms of number of elements. We need to multiply by 8 to get the bytes - I renamed alignment to alignmentBytes to be clear on what we are computing
b426ce4
to
6dafa47
Compare
6dafa47
to
8894638
Compare
This PR is building on top of #4638 to finally add support for buffer operations. For now we will focus on buffer load/store, but in the future we might add more. What this PR is doing:
tt.non_negative
) and the size of the memory buffers passed (tt.within_2gb
)tt.within_2gb
propertyAMDGCN_USE_BUFFER_OPS
. In this way we can enable the feature gradually and check for possible performance/correctness issues.