An int64 i containing 8 bytes of flags that are 0-1 can be converted to an int8 bitmask with i*0x0102040810204080>>56. Neat trick for atomic-free garbage-collector card table traversal.
-
-
yeah my question was going to be about cache line contention - on multicore and even moreso multi-socket
-
These shared memory updates will be slow (hundreds of cycles) if there’s high write-contention. We can reduce write-contention by reading first and skipping the writing if it would be changed, which is a common case for garbage collector card marking.
End of conversation
New conversation -
-
-
Oh that, ok :)... probably I get now what you are writinghttps://stackoverflow.com/questions/19154607/how-actually-card-table-and-writer-barrier-works …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Do different cores writing bytes to the same cache line not contend for write access to the cache line just the same?
-
Perhaps he has pinned the threads to the same core.
- 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.