[SYCL][CUDA] Enable cuda_piEnqueueEventsWaitWithBarrier #3932
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
Enable cuda_piEnqueueEventsWaitWithBarrier using cuda_piEnqueueEventsWait implementation and redirect cuda_piEnqueueEventsWait to cuda_piEnqueueEventsWaitWithBarrier until it can be implemented properly after multiple streams are supported properly after an Event class refactor. Signed-off-by: Alexander Johnston <alexander@codeplay.com>
|
@tfzhu, there's no space on cuda machine. |
This was referenced Jul 30, 2021
npmiller
added a commit
to npmiller/llvm-test-suite
that referenced
this pull request
Nov 16, 2021
These are passing with CUDA, as far as I can tell this feature was implemented as part of intel/llvm#3932. `enqueue_barrier.cpp` had to be tweaked to accept a triple as that is required when using the CUDA plugin. Note that this feature is missing from the hip plugin which is why these are still unsupported for hip.
vladimirlaz
pushed a commit
to intel/llvm-test-suite
that referenced
this pull request
Nov 17, 2021
These are passing with CUDA, as far as I can tell this feature was implemented as part of intel/llvm#3932. `enqueue_barrier.cpp` had to be tweaked to accept a triple as that is required when using the CUDA plugin. Note that this feature is missing from the hip plugin which is why these are still unsupported for hip.
npmiller
added a commit
to npmiller/llvm
that referenced
this pull request
Nov 17, 2021
This patch enables piEnqueueEventsWaitWithBarrier for the HIP plugin, it brings it to the same level as the CUDA plugin, see intel#3932. This fixes the `llvm-test-suite`, `SYCL/Basic/submit_barrier.cpp`, `SYCL/Basic/enqueue_barrier.cpp` and `SYCL/Basic/barrier_order.cpp` tests for the HIP plugin.
bader
pushed a commit
that referenced
this pull request
Jan 10, 2022
This patch enables piEnqueueEventsWaitWithBarrier for the HIP plugin, it brings it to the same level as the CUDA plugin, see #3932. This fixes the `llvm-test-suite`, `SYCL/Basic/submit_barrier.cpp`, `SYCL/Basic/enqueue_barrier.cpp` and `SYCL/Basic/barrier_order.cpp` tests for the HIP plugin.
aelovikov-intel
pushed a commit
to aelovikov-intel/llvm
that referenced
this pull request
Mar 27, 2023
These are passing with CUDA, as far as I can tell this feature was implemented as part of intel#3932. `enqueue_barrier.cpp` had to be tweaked to accept a triple as that is required when using the CUDA plugin. Note that this feature is missing from the hip plugin which is why these are still unsupported for hip.
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.
This enables cuda_piEnqueueEventsWaitWithBarrier by moving the implementation of cuda_piEnqueueEventsWait and redirecting cuda_piEnqueueEventsWait to cuda_piEnqueueEventsWaitWithBarrier.
cuda_piEnqueueEventsWait will need refactored at a later time to not use the barrier version. This requires refactoring to the pi_cuda Event class which is beyond the scope of this PR.