Skip to content
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

DeepCopy HBWSpace / HostSpace #548

Closed
hcedwar opened this issue Nov 21, 2016 · 3 comments
Closed

DeepCopy HBWSpace / HostSpace #548

hcedwar opened this issue Nov 21, 2016 · 3 comments
Assignees
Labels
Enhancement Improve existing capability; will potentially require voting
Milestone

Comments

@hcedwar
Copy link
Contributor

hcedwar commented Nov 21, 2016

DeepCopy between HBWSpace and HostSpace, for example
https://github.com/kokkos/kokkos/blob/master/core/src/Kokkos_HBWSpace.hpp#L250
would perform better if the memcpy were performed by multiple threads, for example on a KNL architecture.

@hcedwar hcedwar added the Enhancement Improve existing capability; will potentially require voting label Nov 21, 2016
@hcedwar hcedwar added this to the Backlog milestone Nov 21, 2016
@ibaned ibaned closed this as completed Mar 14, 2018
@olivier-snl
Copy link

Does this mean Kokkos is doing multi-threaded copies now, or that users are expected to always do enough work in their kernels to amortize the copies?

@ibaned
Copy link
Contributor

ibaned commented Mar 14, 2018

@crtrott does the latest deep_copy actually run a kernel?

@ibaned ibaned reopened this Mar 14, 2018
@ibaned ibaned self-assigned this Mar 14, 2018
@ibaned ibaned modified the milestones: Backlog, 2018 June Mar 14, 2018
@crtrott
Copy link
Member

crtrott commented May 31, 2018

Yeah this is fixed.

@crtrott crtrott assigned crtrott and unassigned ibaned May 31, 2018
@crtrott crtrott closed this as completed Nov 5, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Enhancement Improve existing capability; will potentially require voting
Projects
None yet
Development

No branches or pull requests

4 participants