chore[gpu]: split plan into unmaterialized / materialized#7175
Merged
Conversation
0ax1
changed the title
Contributor
Author
|
I'll rework how we properly account for and allocate shared memory for the GPU in a follow up. |
0ax1
changed the title
0ax1
changed the title
0ax1
changed the title
0ax1
force-pushed
the
ad/check-max-shared-memory
branch
from
b8093fe to
aa85065
Compare
…dPlan This allows for checking whether the shared memory usage blows past the max before launching the dyn dispatch kernel, and having a separate materialize step we can fine tune that moves buffers to GPU from the host. Signed-off-by: Alexander Droste <alexander.droste@protonmail.com>
0ax1
force-pushed
the
ad/check-max-shared-memory
branch
from
aa85065 to
f1d4355
Compare
Contributor
Author
|
Note the state of this PR is kinda transient and will be reworked as part of: 2cb615e |
a10y
approved these changes
Mar 26, 2026
Contributor
Author
|
@a10y ❤️ |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This allows for checking whether the shared memory usage blows past the max GPU device shared memory before launching the dyn dispatch kernel, as well as having a separate materialize step we can fine tune that moves buffers from the host to the GPU.