Skip to content

Conversation

llvm-beanz
Copy link
Collaborator

This is the start of a proposal for the memory and execution model for HLSL.

This is the start of a proposal for the memory and execution model for
HLSL.
Copy link
Collaborator

@spall spall left a 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.
Copy link
Collaborator

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?

Copy link
Collaborator

@V-FEXrt V-FEXrt left a 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

Copy link
Collaborator

@bogner bogner left a 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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

4 participants