Contested accesses occur when data written by one thread is read by another thread on a different core. Examples of contested accesses include synchronizations such as locks, true data sharing such as modified locked variables, and false sharing. Contested accesses metric is a ratio of the number of contested accesses to all demand loads and stores. This metrics only accounts for contested accesses between two cores on the same tile.
There is a high number of contested accesses to cachelines modified by another core. Consider either using techniques suggested for other long latency load events (for example, LLC Miss) or reducing the contested accesses. To reduce contested accesses, first identify the cause. If it is synchronization, try increasing synchronization granularity. If it is true data sharing, consider data privatization and reduction. If it is false data sharing, restructure the data to place contested variables in distinct cachelines. This may increase the working set due to padding, but false sharing can always be avoided.