论文标题
调整持续数据结构以进行并发和猜测
Adapting Persistent Data Structures for Concurrency and Speculation
论文作者
论文摘要
这项工作统一了从系统和功能编程社区的见解，以便在硬件中有效地实现有关软件的组成推理。它利用了设计目标之间的对应关系，以进行有效的并发数据结构和有效的不可变的持久数据结构，以产生具有低竞争力和有效的快照操作的可变并发树的新颖实现，以支持投机执行模型。它还利用了交通量来表征一个设计空间，以将传统的高性能并发数据结构集成到软件交易记忆（STM）运行时，并扩展了此技术，以产生一种新型算法，以同时执行所谓的“智能合同”（``智能合约''（操纵了blove骨的专业程序）。
This work unifies insights from the systems and functional programming communities, in order to enable compositional reasoning about software which is nonetheless efficiently realizable in hardware. It exploits a correspondence between design goals for efficient concurrent data structures and efficient immutable persistent data structures, to produce novel implementations of mutable concurrent trees with low contention and an efficient snapshot operation to support speculative execution models. It also exploits commutativity to characterize a design space for integrating traditional high-performance concurrent data structures into Software Transactional Memory (STM) runtimes, and extends this technique to yield a novel algorithm for concurrent execution of so-called ``smart contracts'' (specialized programs which manipulate the state of blockchain ledgers).
