摘要:
The design of nonblocking linked data structures using single-location synchronization primitives such as compare-and-swap (CAS) is a complex affair that often requires severe restrictions on the way pointers are used. One way to address this problem is to provide stronger synchronization operations, for example, ones that atomically modify one memory location while simultaneously verifying the contents of others. We provide a simple and highly efficient nonblocking implementation of such an operation: an atomic k-word-compare single-swap operation (KCSS). Our implementation is obstruction-free. As a result, it is highly efficient in the uncontended case and relies on contention management mechanisms in the contended cases. It allows linked data structure manipulation without the complexity and restrictions of other solutions. Additionally, as a building block of some implementations of our techniques, we have developed the first nonblocking software implementation of load-linked/store-conditional that does not severely restrict word size.
摘要:
From among a plurality of threads accessing a shared data object, one thread acquires a “master” status to arbitrate among the requests of competing threads during a given session of data access to the shared data object. During the session, the master thread resolves any conflicts resulting from attempts to access or modify the shared data object by other threads, and only the master thread may apply modifications to the shared data object during the session. Meanwhile, during the session, non-master threads may perform non-blocking read operations on the shared data object. During a subsequent session, a different thread may acquire master status.
摘要:
The design of nonblocking linked data structures using single-location synchronization primitives such as compare-and-swap (CAS) is a complex affair that often requires severe restrictions on the way pointers are used. One way to address this problem is to provide stronger synchronization operations, for example, ones that atomically modify one memory location while simultaneously verifying the contents of others. We provide a simple and highly efficient nonblocking implementation of such an operation: an atomic k-word-compare single-swap operation (KCSS). Our implementation is obstruction-free. As a result, it is highly efficient in the uncontended case and relies on contention management mechanisms in the contended cases. It allows linked data structure manipulation without the complexity and restrictions of other solutions. Additionally, as a building block of some implementations of our techniques, we have developed the first nonblocking software implementation of load-linked/store-conditional that does not severely restrict word size.
摘要:
In general, in one aspect, the invention relates to a method of establishing a queue-based lock including inserting a first qnode into a local queue, where the first qnode is associated with a first thread, splicing the local queue into the global queue, obtaining a lock for the first thread when the first qnode is at the head of the global queue, and executing a critical section of the first thread after obtaining the lock.
摘要:
The design of nonblocking linked data structures using single-location synchronization primitives such as compare-and-swap (CAS) is a complex affair that often requires severe restrictions on the way pointers are used. One way to address this problem is to provide stronger synchronization operations, for example, ones that atomically modify one memory location while simultaneously verifying the contents of others. We provide a simple and highly efficient nonblocking implementation of such an operation: an atomic k-word-compare single-swap operation (KCSS). Our implementation is obstruction-free. As a result, it is highly efficient in the uncontended case and relies on contention management mechanisms in the contended cases. It allows linked data structure manipulation without the complexity and restrictions of other solutions. Additionally, as a building block of some implementations of our techniques, we have developed the first nonblocking software implementation of load-linked/store-conditional that does not severely restrict word size.
摘要:
Methods and apparatus provide a lock resizer for resizing of a lock array of a lock-based concurrent hash table. The lock resizer provides a data structure with memory locations which is apportioned into buckets that contain a plurality of the memory locations. It is understood that the data structure can dynamically add new memory locations. The lock resizer further provides a location lock for each distinct memory location and a bucket lock for each distinct bucket. A resizing flag can reference a thread to indicate whether or not the thread is resizing the amount of locks. Upon detection of the existence of a policy condition, the lock resizer resizes the amount of location locks and/or bucket locks in order to create new location locks and new bucket locks, thereby ensuring that as new memory locations are added, all buckets can contain up to a fixed number of memory locations.
摘要:
Apparatus, methods, and computer program products are disclosed for performing a wait-free search of a concurrent, lock-free skiplist to determine existence of a sought-after key.
摘要:
Concurrent cuckoo hashing is performed on a hash table that includes a number of locations; each may hold a value. A plurality of processes may concurrently execute on the table; each process includes a sequence of operations, which are divided into a number of phases. Each phase corresponds to one operation in the sequence. An overflow buffer is provided for each location in the table. Each overflow buffer may hold a value displaced from its corresponding location in the table. A plurality of sequences of operations is concurrently executed. Each phase in a sequence executes by acquiring one or two locks on two locations in the table; a lock acts on a location and its overflow buffer. An operation of a phase is then executed. If, on conclusion of the phase execution, any overflow buffer holds a value, the execution is repeated until all overflow buffers are empty.
摘要:
A system for controlling contention between conflicting transactions in a transactional memory system. During operation, the system receives a request to access a cache line and then determines if the cache line is already in use by an existing transaction in a cache state that is incompatible with the request. If so, the system determines if the request is from a processor which is in a polite mode. If this is true, the system denies the request to access the cache line and continues executing the existing transaction.
摘要:
A multiple-location read, single-location write operation is implemented using transient blocking synchronization support. The multiple-location read, single-location write operation involves first acquiring transient ownership of a memory location to be modified and then acquiring transient ownership of at least one other memory location, the contents of which are read and used to modify the memory location first acquired.