Thread Safety #75
Closed
Thread Safety #75
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
added 2 commits
May 20, 2016 17:14
Specify GS_SPINLOCK_X86, GS_SPINLOCK_GCC_ATOMICS or GS_SPINLOCK_PTHREAD_SPINLOCK during build to choose the spinlock implementation Signed-off-by: Guillaume Delbergue <guillaume.delbergue@greensocs.com>
Add request / release exclusive methods These methods use spinlock implementation Signed-off-by: Guillaume Delbergue <guillaume.delbergue@greensocs.com>
| /** | ||
| * Request lock on parameter | ||
| */ | ||
| virtual void request_exclusive() const = 0; |
There was a problem hiding this comment.
I suggest using acquire_exclusive (vs. request_exclusive) for consistency with the tlm_generic_payload's acquire/release.
Closed
|
This is starting to become more involved as we dig into it. This is not deemed critical for our first release so we will shelf it for now and revisit it in the future. Closing the PR without merge (issue #74 will remain open). |
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Outdated suggestions cannot be applied.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 pull request is related to #74 adding a request / release lock in the cci param interface and so the implementation.
The lock is "unique" for all set/get by simplicity.
Some benchmark results :
Test has been done 5 times and the result is an average:
Test :
for(int i = 0; i < 100000000; i++) {
"param" = i;
}
Results on Linux :
unsigned int : 0.198s
cci_param : 12.98s
cci_param thread safe GCC atomics : 13,58 (+ 4,7%)
cci_param thread safe x86 : 14,66 (+ 12,96%)
cci_param thread safe pthread spin lock : 13,68 (+ 13,11%)
On OSX, x86 is faster than GCC atomics and the overhead is +1.4% (pthread spin lock not available)
Untested on Windows