This book provides an in-depth overview of underlying principles as well as practical techniques that can be used to design concurrent programs. (Greg Andrews)
This book teaches the fundamental concepts of multithreaded, parallel and distributed computing. Emphasizes how to solve problems, with correctness the primary concern and performance an important, but secondary, concern. (Gregory R. Andrews)
Most uses of synchronization code in multi-threaded applications fall into a small number of high-level “usage patterns”, or what can be called generic synchronization policies (GSPs). This paper illustrates how the use of such GSPs simplify the writing of thread-safe classes. In addition, this paper presents a C++ class library that implements commonly-used GSPs.
Very lightweight stackless threads; give linear code execution for event-driven systems, designed to use little memory; library is pure C, no platform-specific Assembly; usable with or without OS. Open source, BSD-type license.
So far multithreaded file I/O is a under-researched field. Although its simple to measure, there is not much common knowledge about it. The measurements presented here show that multithreading can improve performance of file access directly, as well as indirectly by utilizing available cores to process the data read. (September 28, 2009)
Find out what dangers race conditions in general and C++0x data races in particular pose to concurrent code, as well as the strategies for avoiding them. (September 10, 2009)
This column is about why it's time right now to think about systems with lots of cores. In short: Software is the (only) gating factor; as that gate falls, hardware parallelism is coming more and sooner than many people yet believe. (August 11, 2009)
Explores effective uses of threads by looking at a multi-threaded implementation of the QuickSort algorithm and reports on situations where using threads will not help. (June 18, 2009)
A thread pool hides a lot of details, but to use it effectively some awareness of some things a pool does under the covers is needed to avoid inadvertently hitting performance and correctness pitfalls. (April 13, 2009)
Motivates and illustrate best practices for using threads - techniques that will make concurrent code easier to write correctly and to reason about with confidence. (March 16, 2009)
Sharing requires waiting and overhead, and is a natural enemy of scalability. This article focuses on one important case, namely mutable (writable) shared objects in memory, which are an inherent bottleneck to scalability on multicore systems. (February 13, 2009)
Presents a solution to races and deadlocks based on a well-known deadlock-avoidance protocol and shows how it can be enforced by the compiler. It can be applied to programs in which the number of locks is fixed and known up front. (December 3, 2008)
Shows different ways of how to write a fast, internally synchronized queue, one that callers can use without any explicit external locking or other synchronization, and compares the performance. (December 1, 2008)
The Boost.Thread library, which enables the use of multiple threads of execution with shared data in portable C++ code, has undergone some major changes. (October 24, 2008)
Explains why in the concurrent world, locality is a first-order issue that trumps most other performance considerations. Now locality is no longer just about fitting well into cache and RAM, but to avoid scalability busters by keeping tightly coupled data physically close together and separately used data far, far apart. (May 23, 2008)
What does the future hold for concurrency? What will happen to the tools and techniques around concurrent programming? In part two of our series, concurrency guru Herb Sutter talks about these issues and what developers need to be reading to understand concurrency. (May 8, 2008)
Multi- and many-core chips are entering the mainstream — and one of the first software development authorities to take note was C++ expert Herb Sutter. Thanks to his practical insights, a new generation may grok concurrency sooner than previously thought possible. (March 27, 2008)
Explains how to use lock hierarchies to avoid deadlock by assigning each shared resource a level that corresponds to its architectural layer. (December 11, 2007)
Critical sections are the One True Tool for guaranteeing mutual exclusion on shared variables. Like most tools, these must be applied consistently, and with the intended meanings. (October 10, 2007)
To avoid problems with shared state working with multiple threads, Vinoski recommends a programming language like Erlang rather than C++ or Java. (September, 2007)
Every decade or so there is a major revolution in the way software is developed. But, unlike the object and web revolutions, the concurrency revolution can be seen coming. (September, 2006)
Interprocess communication is an essential component of modern software engineering. Often, lock-free IPC is accomplished via special processor commands. This article propose a communication type that requires only atomic writing of processor word from processor cache into main memory and atomic processor word reading from main memory into the processor register or processor cache. (June 15, 2006)
Argues that for concurrent programming to become mainstream, threads must be discarded as a programming model. Nondeterminism should be judiciously and carefully introduced where needed, and it should be explicit in programs. (May, 2006)
Focuses on the implications of concurrency for software and its consequences for both programming languages and programmers. (Herb Sutter and James Larus) (September, 2005)
