-
Couldn't load subscription status.
- Fork 51
[New] Initial draft for memory and execution model #505
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
base: main
Are you sure you want to change the base?
Conversation
This is the start of a proposal for the memory and execution model for HLSL.
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.
You use both warp and wave but don't provide a definition for warp. Not sure if it would be better to choose one term or the other.
| One problem with this model is not having clearly defined memory ordering which | ||
| can impact tangle formation. If a thread is allowed to execute the second `if` | ||
| body before all threads have finished evaluating the condition, tangle formation | ||
| becomes unintuitive. |
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.
is this not just unintuitive but also undefined?
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.
This is a good description of our options! I'm curious on what your thought are towards picking one. Usually, these docs have an inherent preference, but this one is very matter-of-fact and seems to lack a preference
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.
This meets the bar for consideration of the proposal in tree. Please give it a number and update the document header to the newer format before merging.
This is the start of a proposal for the memory and execution model for HLSL.