Misplaced Pages

Concurrent ML

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.
This article may need to be rewritten to comply with Misplaced Pages's quality standards. You can help. The talk page may contain suggestions. (October 2017)
Programming language
Concurrent ML
ParadigmsMulti-paradigm: functional, imperative, modular, concurrent
FamilyML: Standard ML
First appeared1991; 33 years ago (1991)
Websitecml.cs.uchicago.edu
Major implementations
SML/NJ, MLton, Manticore
Influenced by
ML, Standard ML

Concurrent ML (CML) is a multi-paradigm, general-purpose, high-level, functional programming language. It is a dialect of the programming language ML which is a concurrent extension of the Standard ML language, characterized by its ability to allow creating composable communication abstractions that are first-class rather than built into the language. The design of CML and its primitive operations have been adopted in several other programming languages, such as GNU Guile, Racket, and Manticore.

Concepts

Many programming languages that support concurrency offer communication channels that allow the exchange of values between processes or threads running concurrently in a system. Communications established between processes may follow a specific protocol, requiring the programmer to write functions to establish the required pattern of communication. Meanwhile, a communicating system often requires establishing multiple channels, such as to multiple servers, and then choosing between the available channels when new data is available. This can be accomplished using polling, such as with the select operation on Unix systems.

Combining both application-specific protocols and multi-party communication may be complicated due to the need to introduce polling and checking for blocking within a pre-existing protocol. Concurrent ML solves this problem by reducing this coupling of programming concepts by introducing synchronizable events. Events are a first-class abstraction that can be used with a synchronization operation (called sync in CML and Racket) in order to potentially block and then produce some value resulting from communication (for example, data transmitted on a channel).

In CML, events can be combined or manipulated using a number of primitive operations. Each primitive operation constructs a new event rather than modifying the event in-place, allowing for the construction of compound events that represent the desired communication pattern. For example, CML allows the programmer to combine several sub-events in order to create a compound event that can then make a non-deterministic choice of one of the sub-events. Another primitive creates a new event that will modify the value resulting from synchronization to the original event. These events embody patterns of communication that, in a non-CML language, would typically be handled using a polling loop or function with handlers for each kind of event.

Hello world

Here is a "Hello, World!" program that prints to the system console. It spawns one thread with a channel for strings, and another thread which prints a string received on the channel. It uses Standard ML of New Jersey (SML/NJ) and CML. (On non linux-x86 platforms, the heap name will differ; the line with "cml_test.x86-linux" may need changing to something different.)

cml_test.cm
Library
    structure Hello
is
    $cml/basis.cm
    $cml/cml.cm
    cml_test.sml
cml_test.sml
structure Hello = struct
    open CML
    fun hello () = let
        val c : string chan = channel ()
        in
            spawn (fn () => TextIO.print (recv c));
            send (c, "Hello, world!\n");
            exit ()
        end
    fun main (_, argv) =
        RunCML.doit (fn () => ignore (spawn hello), NONE)
end
bash
$ ml-build cml_test.cm Hello.main
Standard ML of New Jersey v110.60 
$ heap2exec cml_test.x86-linux cml_test
$ ./cml_test
Hello, world!

External links

References

  1. Reppy, John H. (June 1991). CML: a Higher-Order Concurrent Language. PLDI.
  2. "What is Standard ML of New Jersey?". Retrieved April 5, 2021.
  3. "ConcurrentMLImplementation". Retrieved April 5, 2021.
  4. ^ Fluet, Matthew; Bergstrom, Lars; Ford, Nic; Rainey, Mike; Reppy, John; Shaw, Adam; Xiao, Yingqi (May 2009). "Programming in Manticore, a Heterogenous Parallel Functional Language" (PDF). Retrieved July 11, 2018.
  5. Wingo, Andy (June 29, 2017). "A New Concurrent ML". Retrieved July 11, 2018.
  6. Flatt, Matthew; Findler, Robert Bruce (2004). "Kill-safe synchronization abstractions". Proceedings of the ACM SIGPLAN 2004 conference on Programming language design and implementation. Vol. 39. pp. 47–58. doi:10.1145/996841.996849. ISBN 1581138075. S2CID 5547460.
  7. Reppy, John H. (1993). "Concurrent ML: Design, application and semantics". Functional Programming, Concurrency, Simulation and Automated Reasoning. Lecture Notes in Computer Science. Vol. 693. pp. 165–198. CiteSeerX 10.1.1.50.7965. doi:10.1007/3-540-56883-2_10. ISBN 978-3-540-56883-4.
ML programming
Software
Implementations,
dialects
Caml
Standard ML
Dependent ML
Programming tools
  • Alt-Ergo°
  • Astrée
  • Camlp4°
  • FFTW°
  • Frama-C°
  • Haxe°
  • Marionnet°
  • MTASC°
  • Poplog°
  • Semgrep°
  • SLAM project
  • Theorem provers,
    proof assistants
    Community
    Designers
  • Lennart Augustsson (Lazy ML)
  • Damien Doligez (OCaml)
  • Gérard Huet (Caml)
  • Xavier Leroy (Caml, OCaml)
  • Robin Milner (ML)
  • Don Sannella (Extended ML)
  • Don Syme (F#)
  • Italics = discontinued
  • ° = Open-source software
    Book Category:Family:ML Category:Family:OCaml Category:Software:OCaml
  • Categories: