StackThreads/MP : Integrating Futures into Calling Standards

StackThreads/MP：将 Future 集成到调用标准中

• 批准号: 08408008
• 负责人: YONEZAWA Akinori
• 金额: $ 22.14万
• 依托单位: The University of Tokyo
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (A)
• 财政年份: 1996
• 资助国家: 日本
• 起止时间: 1996 至 1998
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-08408008/
• 关键词: concurrent programming language; concurrent objects; synchronous channels; type systems; deadlock; partial evaluation; multithread; distributed GC; 並列プログラミング

An implementation scheme of fine-grain multithreading that needs no changes to current calling standards for sequential languages and modest extensions to sequential compilers is implemented. Like previous similar systems, it performs an asynchronous call as if it were an ordinary procedure call, and detaches the callee from the caller when the callee suspends or either of them migrates to another processor. Unlike previous similar systems, it detaches and connects arbitrary frames generated by off-the-shelf sequential compilers obeying calling standards. As a consequence, it requires neither a frontend preprocessor nor a native code generator that has a builtin notion of parallelism. The system practically works with unmodified GNU C compiler (GCC). Desirable extensions to sequential compilers for guaranteeing portability and correctness of the scheme are clarified and claimed modest. Experiments indicate that sequential performance is not sacrificed for practical applications and both sequential and parallel performance are comparable to Cilk, whose current implementation requires a fairly sophisticated preprocessor to C. These results show that efficient asynchronous calls (i.e., future calls) can be integrated into current calling standard with a very small impact both on sequential performance and compiler engineering.

在不改变现有顺序语言调用标准和对顺序编译器进行适当扩展的前提下，实现了一种细粒度多线程的实现方案。像以前的类似系统一样，它执行异步调用，就像它是一个普通的过程调用一样，并且当被调用者挂起或其中一个迁移到另一个处理器时，将被调用者从调用者分离。与以前的类似系统不同，它分离和连接由遵循调用标准的现成顺序编译器生成的任意帧。因此，它既不需要前端预处理器，也不需要具有内置并行概念的本机代码生成器。该系统实际上与未修改的GNU C编译器（GCC）一起工作。为了保证该方案的可移植性和正确性，对顺序编译器进行了必要的扩展。实验表明，在实际应用中，顺序性能并没有被牺牲，顺序和并行性能都可以与Cilk相媲美，Cilk目前的实现需要相当复杂的C预处理器。这些结果表明，有效的异步调用（即，未来的调用）可以被集成到当前的调用标准中，对顺序性能和编译器工程都具有非常小的影响。

项目成果

外山純生: "明示的なタスク配置指定が可能な遅延タスク生成に基づく動的不可分散方法"情報処理学会プログラミング研究会論文誌. 40. (1999)

Sumio Toyama：“基于具有显式任务放置规范的延迟任务生成的动态非分布方法”日本信息处理学会编程研究组杂志 40。（1999）

Kenjiro Taura: "Fine-grain Multithreading with Minimal Compiler Support --- A cost Effective Approach to Implementing Efficient Multithreading Languages"Proceedings of the 1997 ACM SIGPLAN Conference on Programming Language Design and Implementation. 320-

Kenjiro Taura：“具有最少编译器支持的细粒度多线程 --- 实现高效多线程语言的成本有效方法”1997 年 ACM SIGPLAN 编程语言设计和实现会议记录。

山本泰宇, 田浦健次朗, 米澤明憲: "分散メモリ並列計算機上おけるreference couut GCとmark and Sweep GCの比較" 並列分散協調システムに関する合同ワークショップ予稿集(SWOPP). (1997)

Yasuo Yamamoto、Kenjiro Taura、Akinori Yonezawa：“分布式内存并行计算机上的参考 couout GC 与标记和扫描 GC 的比较”并行分布式协作系统联合研讨会 (SWOPP) 论文集 (1997)。

Kenjiro Taura: "StackThreads MP : Integrating Futures into Calling Standards"Proceedings of ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming (PPoPP). (1999)

Kenjiro Taura：“StackThreads MP：将 Future 集成到调用标准中”ACM SIGPLAN 原理研讨会论文集

増原英彦: "Reasoningを容易にする並列自己反映言語のメタオブジェクトの設計" コンピュータソフトウェア. 15(4). 62-66 (1998)

Hidehiko Masuhara：“并行自反射语言的元对象设计以促进推理”计算机软件 15(4)。