-
Notifications
You must be signed in to change notification settings - Fork 532
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
Don't presume pointers are mutually exclusive for device/host. #6128
Open
robertmaynard
wants to merge
2
commits into
rapidsai:branch-24.12
Choose a base branch
from
robertmaynard:bug/device_ptrs_can_be_host_ptrs
base: branch-24.12
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Don't presume pointers are mutually exclusive for device/host. #6128
robertmaynard
wants to merge
2
commits into
rapidsai:branch-24.12
from
robertmaynard:bug/device_ptrs_can_be_host_ptrs
Conversation
This file contains 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
robertmaynard
added
bug
Something isn't working
3 - Ready for Review
Ready for review by team
non-breaking
Non-breaking change
labels
Oct 30, 2024
Here is the results of looking at the cudaPointerGetAttributes of different allocation types. As we can see things like cudaMallocManaged allow the same pointer to be both host and device. ``` cudaPointerGetAttributes attributes integer is_dev_ptr -> 0 is_host_ptr -> 0 cudaPointerGetAttributes attributes std::vector<int> data is_dev_ptr -> 0 is_host_ptr -> 0 cudaPointerGetAttributes attributes malloc ptr is_dev_ptr -> 0 is_host_ptr -> 0 cudaPointerGetAttributes attributes cudaMalloc ptr is_dev_ptr -> 1 is_host_ptr -> 0 cudaPointerGetAttributes attributes cudaMallocManaged cudaMemAttachGlobal ptr is_dev_ptr -> 1 is_host_ptr -> 1 cudaPointerGetAttributes attributes cudaMallocManaged cudaMemAttachHost ptr is_dev_ptr -> 1 is_host_ptr -> 1 cudaPointerGetAttributes attributes cudaMallocHost ptr is_dev_ptr -> 1 is_host_ptr -> 1 ```
robertmaynard
force-pushed
the
bug/device_ptrs_can_be_host_ptrs
branch
from
October 31, 2024 18:30
9d432af
to
5bf3358
Compare
Currently running some more manual validation checks |
robertmaynard
removed
the
5 - DO NOT MERGE
Hold off on merging; see PR for details
label
Nov 1, 2024
dantegd
approved these changes
Nov 4, 2024
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm
wphicks
approved these changes
Nov 5, 2024
/merge |
divyegala
approved these changes
Nov 6, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
3 - Ready for Review
Ready for review by team
bug
Something isn't working
CUDA/C++
non-breaking
Non-breaking change
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.
A pointer can be usable on the device and host at the same time. We can't invert
is_dev_ptr()
to check that something is a host pointer.Here is the results of looking at the cudaPointerGetAttributes of different allocation types. As we can see things like cudaMallocManaged and cudaMallocHost allow the same pointer to be both host and device.