-
Notifications
You must be signed in to change notification settings - Fork 202
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
Simplify rmm::exec_policy
and refactor Thrust support
#647
Simplify rmm::exec_policy
and refactor Thrust support
#647
Conversation
Please update the changelog in order to start CI tests. View the gpuCI docs here. |
rmm::exec_policy
and refactor Thrust support
We should not merge this until corresponding PRs for cuDF and cuSpatial are merged, and this is tested with cuML and cuGraph. Update: determined that this PR is non-breaking for cuML and cuGraph, which have not been updated to use |
Updates libcudf to use the new, simplified `rmm::exec_policy` and include the new refactored headers `rmm/exec_policy.hpp` and `rmm/device_vector.hpp` The new `exec_policy` can be passed directly to Thrust, no longer any need to call `rmm::exec_policy(stream)->on(stream)`. Depends on rapidsai/rmm#647
Updates libcudf to use the new, simplified rmm::exec_policy and include the new refactored headers rmm/exec_policy.hpp and rmm/device_vector.hpp The new exec_policy can be passed directly to Thrust, no longer any need to call rmm::exec_policy(stream)->on(stream). Depends on rapidsai/rmm#647 Authors: - Mark Harris <mharris@nvidia.com> Approvers: - Paul Taylor - Christopher Harris URL: #331
Closes #620.
This PR improves
rmm::exec_policy
so you can now just passrmm::exec_policy(stream)
rather thanrmm::exec_policy(stream)->on(stream)
. Also refactors thermm::device_vector
alias into its own header, and the newrmm::exec_policy
into its own header. The oldthrust_rmm_allocator.h
still exists for backwards compatibility. We should probably deprecate it and the oldexec_policy
.#620 describes the motivation for this PR very well.