Skip to content

[SYCL][PTX] Implements missing atomic builtins #1173

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 1 commit into from
Feb 28, 2020
Merged

[SYCL][PTX] Implements missing atomic builtins #1173

merged 1 commit into from
Feb 28, 2020

Conversation

steffenlarsen
Copy link
Contributor

@steffenlarsen steffenlarsen commented Feb 25, 2020 •
edited
Loading

This PR introduces:

  • Builtins for atomic load and store (int, unsigned int, long, unsigned long, long long, and unsigned long long)
  • Added long, unsigned long, long long, and unsigned long long variants of the following existing builtins:
    • Atomic add
    • Atomic sub
    • Atomic and
    • Atomic or
    • Atomic xor
    • Atomic exhange
    • Atomic compare-and-exchange
    • Atomic max
    • Atomic min

Notice: long is currently used in place of long long due to a problem with the width of long long being defined as 128-bit.

Signed-off-by: Steffen Larsen [email protected]

@steffenlarsen steffenlarsen mentioned this pull request Feb 25, 2020
Closed
@bader bader linked an issue Feb 25, 2020 that may be closed by this pull request
[CUDA] ptxas: unresolved extern function __spirv_AtomicLoad(...) #1111
Closed
@AlexeySachkov AlexeySachkov added the cuda CUDA back-end label Feb 25, 2020
@bader bader self-assigned this Feb 25, 2020
bader
bader approved these changes Feb 27, 2020
View reviewed changes
Copy link
Contributor

@bader bader left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It would be great if we can add more details to about what was added with this PR description (e.g. support for long long and unsigned long long types, atomic load/store built-ins, etc.).

@steffenlarsen
Copy link
Contributor Author

It would be great if we can add more details to about what was added with this PR description (e.g. support for long long and unsigned long long types, atomic load/store built-ins, etc.).

Apologies. I have added a summary of what this PR introduces.

@bader
Copy link
Contributor

bader commented Feb 27, 2020

Thanks!

@bader bader merged commit a540d01 into intel:sycl Feb 28, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bader bader bader approved these changes

Assignees

@bader bader

Labels
cuda CUDA back-end
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[CUDA] ptxas: unresolved extern function __spirv_AtomicLoad(...)
3 participants
@steffenlarsen @bader @AlexeySachkov