Parallel computing
Last updated
Parallelism has become the dominant paradigm in computer architecture due to physical constraints that ended frequency scaling as the main performance driver.[1][2]
Quick Facts
- Field
- Computer science
- Key forms
- Bit-level
- instruction-level
- data
- and task parallelism
Facts from the source article.
Key facts and history
Frequency scaling drove computer performance improvements from the mid-1980s until 2004, but increasing power consumption led Intel to cancel its Tejas and Jayhawk processors in May 2004.[3][2] By 2023 some processors had over one hundred cores, following Moore's law prediction that core counts would double every 18–24 months.[4] An operating system can run different tasks in parallel on available cores, but serial programs must be restructured to take full advantage of multi-core architectures.[5] Amdahl's law calculates the maximum potential speedup of a system and shows that increasing processors yields diminishing returns beyond a certain point.[6][7]
Parallel computing can incur significant overhead from inter-process communication and synchronization, which may be two or more orders of magnitude higher than single-thread processing.[8] Software was traditionally written for serial computation, where only one instruction may execute at a time.[9]
What the cited sources add
Krauss's "Thread Safety for Performance" states that using threads to distribute computing across processors yields best results when thread safety is a priority.[10]
References
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: S.V. Adve et al. (November 2008). "Parallel Computing Research at Illinois: The UPCRC Agenda" (PDF). Parallel@Illinois, University of Illinois at Urbana-Champai; Asanovic et al. Old [conventional wisdom]: Power is free, but transistors are expensive. New [conventional wisdom] is [that] power is expensive, but transistors; Asanovic, Krste et al. (December 18, 2006). "The Landscape of Parallel Computing Research: A View from Berkeley" (PDF). University of California, Berkeley. Tech (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Flynn, "Intel Halts Development Of 2 New Microprocessors", New York Times, 8 May 2004 (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Hennessy, "Computer architecture / a quantitative approach.", International Thomson, 2002, p. 43; Rabaey, "Digital integrated circuits : a design perspective", Prentice-Hall, 1996, p. 235 (we also read that source) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Thomas Rauber, "Parallel Programming: for Multicore and Cluster Systems", Springer Science & Business Media, 2013, p. 2 (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Thomas Rauber, "Parallel Programming: for Multicore and Cluster Systems", Springer Science & Business Media, 2013, p. 3 (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Bakos, "Embedded Systems", Morgan Kaufmann, 2016-01-01, p. 49–103 (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: "The Art of Multiprocessor Programming, Revised Reprint", Morgan Kaufmann, 22 May 2012; Vajda, "Programming Many-Core Chips", Springer, 10 June 2011 (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Silberschatz, "Operating System Concepts", Wiley, 29 July 2008; "Computer Organization and Design MIPS Edition: The Hardware/Software Interface (The Morgan Kaufmann Series in Computer Architecture and Design)", Morgan Kaufmann, 2013; "Parallel Programming: Techniques and Applications Using Networked Workstations and Parallel Computers", Pearson, 2005 (original not read by us) en.wikipedia.org
- Wikipedia, "Parallel computing" (CC BY-SA 4.0), which cites: Barney, Blaise, "Introduction to Parallel Computing", Lawrence Livermore National Laboratory (we also read that source) en.wikipedia.org
- Krauss, "Thread Safety for Performance", Develop for Performance, 2018. facts only, no text reused. developforperformance.com
Each numbered sentence above was checked against the source it cites before publication. Sentences citing Wikipedia adapt text from the English Wikipedia article Parallel computing (contributors), used under CC BY-SA 4.0; this entry is available under the same licence. Other sources were used for facts only; no text or images are copied from them.
More in Computing & Software
Sources
Compiled from Wikipedia and the sources listed below. Text from Wikipedia is available under CC BY-SA 4.0; this entry is adapted from it.
- Wikipedia: Parallel computing (CC BY-SA 4.0).
Spotted an error? Know more?
Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced
