Efficient rollback and retry of conflicted speculative threads with hardware support

摘要

A method for rolling back speculative threads in symmetric-multiprocessing (SMP) environments is disclosed. In one embodiment, such a method includes detecting an aborted thread at runtime and determining whether the aborted thread is an oldest aborted thread. In the event the aborted thread is the oldest aborted thread, the method sets a high-priority request for allocation to an absolute thread number associated with the oldest aborted thread. The method further detects that the high-priority request is set and, in response, clears the high-priority request and sets an allocation token to the absolute thread number associated with the oldest aborted thread, thereby allowing the oldest aborted thread to retry a work unit associated with the absolute thread number. A corresponding apparatus and computer program product are also disclosed.

主权项

1. A method for efficiently rolling back and retrying conflicted speculative threads in symmetric-multiprocessing (SMP) environments, the method comprising:
detecting an aborted thread at runtime; determining whether the aborted thread is an oldest aborted thread; in the event the aborted thread is the oldest aborted thread, setting a high-priority request for allocation to an absolute thread number assigned to the oldest aborted thread; detecting that the high-priority request is set; and in response to detecting that the high-priority request is set, clearing the high-priority request and setting an allocation token to the absolute thread number of the oldest aborted thread, thereby allowing the oldest aborted thread to retry a work unit associated with its absolute thread number.