Try using clEnqueueMigrateMemObjects#21121
Closed
jenshannoschwalm wants to merge 3 commits into
Closed
Conversation
jenshannoschwalm
added
wip
Collaborator
Author
|
Also tested on rocm, that might be a bit slower but otherwise no problems ... |
Contributor
|
Works for me on my Radeon 780M iGPU w/ 10 GB of GTT mem using ROCm 7.2.1. On this branch: With current master: |
Collaborator
Author
About what i find here. Let's see if it would help on DGX Spark... |
- dt_clEnqueueMigrateMemObjects - dt_clEnqueueFillBuffer - dt_clEnqueueFillImage all are safe for OpenCL 1.2 API so no special treatment is required.
Also a first try it ...
jenshannoschwalm
force-pushed
the
try_migration
branch
from
c467a10 to
ca07029
Compare
Collaborator
Author
|
Closing as this is not the way to go for now |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See #21069
dt_opencl_copy_device_to_host()as that was the reported bottlenecka) no critical performance drops
b) no reported errors
c) no instabilities