[DO NOT MERGE] Use only CUDA devices with a supported architecture #299
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
|
Second attempt at #286, mostly to check if we can find a working set of CUDA build rules for this use case. |
|
The present CUDA rules do not allow to have .cu files both in a shared library and in a plugin. |
|
Just to note (in case it was not intentional) that now there are implementations of |
|
Sorry about that, I'll clean it up. |
For each available CUDA device, check if its architecture is supported running a simple kernel. This allows to restrict using only the supported devices - at configuration time, in the SwitchProducerCUDA, via the cudaIsEnabled test; - at run time, in the CUDAService and its clients; - when running tests, via exitSansCUDADevices. Includes Matti's fix for the sizes of stream and event caches (cms-sw#289).
fwyzard
force-pushed
the
Patatrack_use_only_supported_devices
branch
from
2be0bc1
to
8deb1d9
Compare
|
The logic here cmssw/HeterogeneousCore/CUDACore/interface/CUDAESProduct.h Lines 32 to 35 in 586c0c0 needs to be updated as well. |
fwyzard
changed the base branch from
CMSSW_10_5_X_Patatrack
to
CMSSW_11_1_X_Patatrack
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Outdated suggestions cannot be applied.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.
For each available CUDA device, check if its architecture is supported running a simple kernel.
This allows to restrict using only the supported devices
Includes Matti's fix for the sizes of stream and event caches (#289).