TagBoxArray on GPU #1258
Merged
TagBoxArray on GPU #1258
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
WeiqunZhang
force-pushed
the
tagbox_gpu
branch
9 times, most recently
from
9f33e26
to
22e5729
Compare
TagBoxArray functions can now run on GPU now. We no longer rely on unified memory for TagBoxArray functions.
WeiqunZhang
force-pushed
the
tagbox_gpu
branch
from
22e5729
to
45426f8
Compare
atmyers
approved these changes
Aug 17, 2020
WeiqunZhang
added a commit
to WeiqunZhang/amrex
that referenced
this pull request
Aug 18, 2020
In AMReX-Codes#1258, TagBoxArray::numtags was removed. However, IAMR still needs it. So a new function, hasTags, is added for IAMR.
drummerdoc
pushed a commit
that referenced
this pull request
Aug 18, 2020
In #1258, TagBoxArray::numtags was removed. However, IAMR still needs it. So a new function, hasTags, is added for IAMR.
dwillcox
pushed a commit
to dwillcox/amrex
that referenced
this pull request
Oct 3, 2020
# Summary TagBoxArray functions can now run on GPU now. We no longer rely on unified memory for TagBoxArray functions. ## Additional background ## Checklist The proposed changes: - [ ] fix a bug or incorrect behavior in AMReX - [x] add new capabilities to AMReX - [ ] changes answers in the test suite to more than roundoff level - [ ] are likely to significantly affect the results of downstream AMReX users - [ ] are described in the proposed changes to the AMReX documentation, if appropriate
dwillcox
pushed a commit
to dwillcox/amrex
that referenced
this pull request
Oct 3, 2020
In AMReX-Codes#1258, TagBoxArray::numtags was removed. However, IAMR still needs it. So a new function, hasTags, is added for IAMR.
WeiqunZhang
added a commit
to WeiqunZhang/amrex
that referenced
this pull request
Apr 19, 2021
Add a CPU version of TagBox::buffer. @MSABuschman reported in AMReX-Codes#1951 that TagBox::buffer has been very slow since commit AMReX-Codes#1258 if the error buffer size is large. The function was rewritten in AMReX-Codes#1258 to do the work on GPU. In this PR, the old version is reintroduced for CPU. Note that the current implementation is expected to have poor performance on GPU if it has a very large error buffer. It's still not clear how we should implement this function for GPU if a large error buffer is used.
5 tasks
WeiqunZhang
added a commit
to WeiqunZhang/amrex
that referenced
this pull request
Apr 19, 2021
Add a CPU version of TagBox::buffer. @MSABuschman reported in AMReX-Codes#1951 that TagBox::buffer has been very slow since commit AMReX-Codes#1258 if the error buffer size is large. The function was rewritten in AMReX-Codes#1258 to do the work on GPU. In this PR, the old version is reintroduced for CPU. Note that the current implementation is expected to have poor performance on GPU if it has a very large error buffer. It's still not clear how we should implement this function for GPU if a large error buffer is used.
WeiqunZhang
added a commit
to WeiqunZhang/amrex
that referenced
this pull request
Apr 19, 2021
Add a CPU version of TagBox::buffer. @MSABuschman reported in AMReX-Codes#1951 that TagBox::buffer has been very slow since commit AMReX-Codes#1258 if the error buffer size is large. The function was rewritten in AMReX-Codes#1258 to do the work on GPU. In this PR, the old version is reintroduced for CPU. Note that the current implementation is expected to have poor performance on GPU if it has a very large error buffer. It's still not clear how we should implement this function for GPU if a large error buffer is used.
WeiqunZhang
added a commit
that referenced
this pull request
Apr 19, 2021
Add a CPU version of TagBox::buffer. @MSABuschman reported in #1951 that TagBox::buffer has been very slow since commit #1258 if the error buffer size is large. The function was rewritten in #1258 to do the work on GPU. In this PR, the old version is reintroduced for CPU. Note that the current implementation is expected to have poor performance on GPU if it has a very large error buffer. It's still not clear how we should implement this function for GPU if a large error buffer is used.
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.
Summary
TagBoxArray functions can now run on GPU now. We no longer rely on unified memory for TagBoxArray functions.
Additional background
Checklist
The proposed changes: