Mirror intel/llvm commits #2795
Merged
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
Unified Runtime -> intel/llvm Repo Move NoticeInformationThe source code of Unified Runtime has been moved to intel/llvm under the unified-runtime top-level directory, The code will be mirrored to oneapi-src/unified-runtime and the specification will continue to be hosted at oneapi-src.github.io/unified-runtime. The contribution guide will be updated with new instructions for contributing to Unified Runtime. PR MigrationAll open PRs including this one will be marked with the Should you wish to continue with your PR you will need to migrate it to intel/llvm. If your PR should remain open and not be closed automatically, you can remove the This is an automated comment. |
Enable origin tracking for host/shared/device USM, which can provide the more debug information about the detected uninitialized memory.
When we try to exit the problem when reporting the error, the `exit(1)` could cause hangs in SYCL runtime because it skips some processes before the SYCL shutdown process in atexit stage. The `abort()` is more accurate here because it would stop the whole process right away, and no more SYCL shutdown process with the unstable, early exited program.
Level zero is the only backend that supports 1D fetch. However it was marked as unsupported. This PR fixes that and adds corresponding tests. As with other fetch cases, O0 builds fail on windows for L0 using fetch 1D (see intel/llvm#18919). --------- Signed-off-by: JackAKirk <[email protected]>
Bug1: Leak, when private shadow failed to allocate, the already allocated private base would not be freed. Bug2: Leak, the old private base is never freed. Improve: try to reuse private base just like we try to reuse private shadow. --------- Co-authored-by: Copilot <[email protected]> Co-authored-by: Kenneth Benzie (Benie) <[email protected]>
This commit changes the HIP adapter to select the correct binary for the device when a bundle contains binaries built for multiple AMDGPU architectures. Similarly to other adapaters, the HIP adapter would previously select the first 'amdgcn' binary it came across. This works fine for the common case where the program was compiled for one architecture but may fail otherwise. To aid in this, the SYCL runtime passes some extra information into urDeviceSelectBinary via the pre-existing 'pNext' field of ur_device_binary_t. It does this only for the HIP backend. The HIP adapater then parses this binary information as a clang offload bundle, which conveniently contains specific triple & architecture information for each binary. For this we re-use the code that the offload adapter was using, making it common and fixing a bug in the version matching logic.
urDeviceGetInfo is now able to retrieve the max memory bandwidth. --------- Signed-off-by: Zhang, Winston <[email protected]>
Instead of using a global constructor to initialize the L0 adapter, do it in the first call to `urAdapterGet`. Likewise, instead of de-initing it as a global destructor, do it in the last call to `urAdapterRelease`. As well as not doing L0 initialization where the user is not using L0, it also allows `urAdapterRelease` to be called in a global destructor (e.g. what the SYCL runtime does) without worrying about global destructor order.
github-actions
bot
force-pushed
the
mirror-commits-
branch
from
aa6a556 to
cb4d997
Compare
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.
Automated changes by create-pull-request GitHub action