[RUNTIME][OPENCL] clFinish before releasing memory #2737
Merged
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
tqchen
approved these changes
Mar 7, 2019
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 9, 2019
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 12, 2019
wweic
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Mar 12, 2019
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Outdated suggestions cannot be applied.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 OpenCL specification says that it is safe to call clReleaseMemObject even when the memory object is in use, but some OpenCL platforms violate the specification unfortunately.
https://forums.xilinx.com/t5/SDAccel/clEnqueueWriteBuffer-doesn-t-increase-reference-counts/td-p/932401
https://forums.intel.com/s/question/0D50P0000462rYaSAI/clreleasememobject-just-after-clenqueuetask-causes-segfault
This PR calls clFinish before clReleaseMemObject to make sure that the memory object is not in use. This change doesn't have impact on performance since memory objects are cached by workspace pool of TVM and they are not released at run time usually.
@tqchen @Laurawly @nishi-t please help review this PR.