3.3.2.Work-item Load/Store Consistency
Memory operations within a single work-item to the same address are fully consistent and ordered. As a
consequence, a load executed after a store by the same work-item will never receive stale data, so no
fence operations are needed for single work-item consistency. Memory operations (loads / stores) at
different addresses, however, could be re-ordered by the implementation.
http://developer.amd.com/wordpress/media/2012/10/hsa10.pdf
Work-item Load/Store Consistency