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.

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

Vecpar implementation #1

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Vecpar implementation #1

wants to merge 4 commits into from

Conversation

georgi-mania
Copy link
Collaborator

@georgi-mania georgi-mania commented Dec 21, 2022 •
edited
Loading

Provide implementations for scenarios

  • run in parallel using vecpar offloading lambda (CUDA and OpenMP)
  • run in parallel using single-source algorithms (CUDA and OpenMP)
  • ability to choose memory resource for GPU (managed-memory AND host-device memory)
  • ability to choose different offloading backend (CUDA vs OpenMP target) -- requires vecpar::map/mmap/map_reduce with 1,2,3 collections
  • scripts for automatic testing (update/adapt existing)
  • BUG - dot kernel fails for 100 repetitions (works for 50); I assume some chunks on memory are not released

@georgi-mania georgi-mania self-assigned this Dec 21, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees

@georgi-mania georgi-mania

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@georgi-mania