-
Notifications
You must be signed in to change notification settings - Fork 788
[SYCL] Improve memobj creation for devices w/o host unified memory #2761
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
Merged
romanovvlad
merged 10 commits into
intel:sycl
from
sergey-semenov:improvememobjcreation
Nov 18, 2020
Merged
[SYCL] Improve memobj creation for devices w/o host unified memory #2761
romanovvlad
merged 10 commits into
intel:sycl
from
sergey-semenov:improvememobjcreation
Nov 18, 2020
Conversation
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
The aggressive use of USE_HOST_PTR memory object creation option led to significant performance overhead on devices without host unified memory support. Furthermore, any discard access modes were ignored during the allocation leading to unnecessary copy. This patch makes it so that allocations for such devices are made with COPY_HOST_PTR instead, and only if necessitated by the access mode. These allocations are also not linked anymore, since linked allocations rely on USE_HOST_PTR option.
TBD: add tests |
romanovvlad
requested changes
Nov 12, 2020
Note: there's a non-breaking ABI change in the latest version of the PR, a new symbol is added to |
/summary:run |
romanovvlad
reviewed
Nov 17, 2020
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
romanovvlad
approved these changes
Nov 18, 2020
jsji
pushed a commit
that referenced
this pull request
Nov 7, 2024
Signed-off-by: Marcos Maronas <[email protected]> Original commit: KhronosGroup/SPIRV-LLVM-Translator@ee130659c16e2d3
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
The aggressive use of USE_HOST_PTR memory object creation option led to
significant performance overhead on devices without host unified memory
support. Furthermore, any discard access modes were ignored during the
allocation leading to unnecessary copy.
This patch makes it so that allocations for such devices are made with
COPY_HOST_PTR instead, and only if necessitated by the access mode.
These allocations are also not linked anymore, since linked allocations
rely on USE_HOST_PTR option.