Locks in this case would not fix the issue, as it does not ensure write propagation.
This comment was marked helpful 1 times.
idl
Is it even possible to ensure write propagation using locks? It seems like locks solve a completely different problem...
This comment was marked helpful 0 times.
kayvonf
@idl. Correct. That was a bit of a trick question. You (and @kkz) were not tricked.
This comment was marked helpful 0 times.
Q_Q
I think that some of the mutex libraries out there will issue the correct cache flush instructions, if the underlying architecture doesn't support cache coherence itself and requires explicit cache management.
Locks in this case would not fix the issue, as it does not ensure write propagation.
This comment was marked helpful 1 times.
Is it even possible to ensure write propagation using locks? It seems like locks solve a completely different problem...
This comment was marked helpful 0 times.
@idl. Correct. That was a bit of a trick question. You (and @kkz) were not tricked.
This comment was marked helpful 0 times.
I think that some of the mutex libraries out there will issue the correct cache flush instructions, if the underlying architecture doesn't support cache coherence itself and requires explicit cache management.
This comment was marked helpful 0 times.