We propose a new form of software transactional memory (STM) designed to support dynamic-sized data structures, and we describe a novel non-blocking implementation. The non-blocking property we consider is obstruction-freedom. Obstruction-freedom is weaker than lock-freedom; as a result, it admits substantially simpler and more efficient implementations. A novel feature of our obstruction-free STM implementation is its use of modular contention managers to ensure progress in practice. We illustrate the utility of our dynamic STM with a straightforward implementation of an obstruction-free red-black tree, thereby demonstrating a sophisticated non-blocking dynamic data structure that would be difficult to implement by other means. We also present the results of simple preliminary performance experiments that demonstrate that an "early release " feature of our STM is useful for reducing contention, and that our STM lends itself to the effective use of modular contention managers.

Non-blocking synchronization has significant advantages over blocking synchronization: however, it has not been used to a significant degree in practice. We designed and implemented a multiprocessor operating system kernel and run-time library for high-performance, reliability and modularity. We used nonblocking synchronization, not because it was an objective in itself, but because it became the approach of choice. It was an attractive approach because of the synergy between other structuring techniques we used to achieve our primary goals and the benefits of non-blocking synchronization. This paper

Abstract. Software Transactional Memory (STM) is a generic synchronization construct that enables automatic conversion of correct sequential objects into correct nonblocking concurrent objects. Recent STM systems, though significantly more practical than their predecessors, display inconsistent performance: differing design decisions cause different systems to perform best in different circumstances, often by dramatic margins. In this paper we consider four dimensions of the STM design space: (i) when concurrent objects are acquired by transactions for modification; (ii) how they are acquired; (iii) what they look like when not acquired; and (iv) the non-blocking semantics for transactions (lock-freedom vs. obstruction-freedom). In this 4-dimensional space we highlight the locations of two leading STM systems: the DSTM of Herlihy et al. and the OSTM of Fraser and Harris. Drawing motivation from the performance of a series of application benchmarks, we then present a new Adaptive STM (ASTM) system that adjusts to the offered workload, allowing it to match the performance of the best known existing system on every tested workload. 1

We present wait-free and lock-free universal constructions that allow operations to access multiple objects atomically. Such constructions provide functionality similar to nested critical sections in conventional, lockbased systems. In such a system, two critical sections might be nested, for example, to swap the contents of two shared buffers. Using our constructions, such a transfer can be done in a wait-free or a lock-free manner. Our universal constructions are based upon multiword synchronization primitives. In the first part of the paper, we present wait-free implementations of such primitives from one-word primitives. These implementations allow processes that access disjoint words to execute in parallel. Previous implementations of multi-word primitives either overly restrict parallelism, or provide only lock-free execution. We also present severa...

1 Introduction Non-blocking synchronization has been of increasing interest recently, largely due to its ability to avoid the ill effects of locking such as convoying, deadlock, priority inversion, contention, and susceptibility to process delays and failures (see, for example,

Mutual exclusion locks remain the de facto mechanism for concurrency control on shared-memory data structures. However, their apparent simplicity is deceptive: it is hard to design scalable locking strategies because locks can harbour problems such as priority inversion, deadlock and convoying. Furthermore, scalable lock-based systems are not readily composable when building compound operations. In looking for solutions to these problems, interest has developed in nonblocking systems which have promised scalability and robustness by eschewing mutual exclusion while still ensuring safety. However, existing techniques for building non-blocking systems are rarely suitable for practical use, imposing substantial storage overheads, serialising non-conflicting operations, or requiring instructions not readily available on today’s CPUs. In this paper we present three APIs which make it easier to develop non-blocking implementations of arbitrary data structures. The first API is a multi-word compare-and-swap operation (MCAS) which atomically updates a set of memory locations. This can be used to advance a data structure from one consistent state to another. The second API is a word-based software transactional memory (WSTM) which can allow sequential code to be re-used more directly than with MCAS and which provides better scalability when locations are being read rather than being

Work on non-blocking data structures has proposed extending processor designs with a compare-and-swap primitive, CAS2, which acts on two arbitrary memory locations. Experience suggested that current operations, typically single-word compare-and-swap (CAS1), are not expressive enough to be used alone in an efficient manner. In this paper we build CAS2 from CAS1 and, in fact, build an arbitrary multi-word compare-and-swap (CASN). Our design requires only the primitives available on contemporary systems, reserves a small and constant amount of space in each word updated (either 0 or 2 bits) and permits nonoverlapping updates to occur concurrently. This provides compelling evidence that current primitives are not only universal in the theoretical sense introduced by Herlihy, but are also universal in their use as foundations for practical algorithms. This provides a straightforward mechanism for deploying many of the interesting non-blocking data structures presented in the literature that have previously required CAS2.

We present lock-free and wait-free universal constructions for implementing large shared objects. Most previous universal constructions require processes to copy the entire object state, which is impractical for large objects. Previous attempts to address this problem require programmers to explicitly fragment large objects into smaller, more manageable pieces, paying particular attention to how suchpieces are copied. In contrast, our constructions are designed to largely shield programmers from this fragmentation. Furthermore, for many objects, our constructions result in lower copying overhead than previous ones. Fragmentation is achieved in our constructions through the use of load-linked, store-conditional, and validate operations on a \large " multi-word shared variable. Before presenting our constructions, we showthat these operations can be e ciently implemented from similar one-word primitives. 1

. This paper concerns software support for non-blocking transactions in shared-memory multiprocessors. We present mechanisms that convert sequential transactions into lock-free or wait-free ones. In contrast to some previous mechanisms, ours support transactions for which the set of memory locations accessed cannot be determined in advance. Our implementations automatically detect and resolve conflicts between concurrent transactions, and allow transactions that do not conflict to execute in parallel. The key to the efficiency of our wait-free implementation lies in using a lock-free (but not wait-free) multi-word compareand -swap (MWCAS) operation. By introducing communication between a high-level helping mechanism and the lock-free MWCAS, we show that an expensive wait-free MWCAS is not necessary to ensure wait-freedom. 1 Introduction The use of locking to coordinate accesses to shared data in multiprocessor applications has a number of associated pitfalls including a lack of concur...

Software Transactional Memory (STM) is a generic nonblocking synchronization construct that enables automatic conversion of correct sequential objects into correct concurrent objects. Because it is nonblocking, STM avoids traditional performance and correctness problems due to thread failure, preemption, page faults, and priority inversion. In this paper we compare and analyze two recent objectbased STM systems, the DSTM of Herlihy et al. and the FSTM of Fraser, both of which support dynamic transactions, in which the set of objects to be modified is not known in advance. We highlight aspects of these systems that lead to performance tradeoffs for various concurrent data structures. More specifically, we consider object ownership acquisition semantics, concurrent object referencing style, the overhead of ordering and bookkeeping, contention management versus helping semantics, and transaction validation. We demonstrate for each system simple benchmarks on which it outperforms the other by a significant margin. This in turn provides us with a preliminary characterization of the applications for which each system is best suited.