Parallel slowdown

From Wikipedia, the free encyclopedia

A diagram of the program runtime (shown in blue) and program speed-up (shown in red) of a real-world program with sub-optimal parallelization. The dashed lines indicate optimal parallelization–linear increase in speedup and linear decrease in program runtime. Note that eventually the runtime actually increases with more processors (and the speed-up likewise decreases). This is parallel slowdown.

Parallel slowdown is a phenomenon in parallel computing where parallelization of a parallel computer program beyond a certain point causes the program to run slower (take more time to run to completion).

Parallel slowdown is typically the result of a communications bottleneck. As more processing nodes are added, each processing node spends progressively more time doing communication than useful processing. At some point, the communications overhead created by adding another processing node surpasses the increased processing power that node provides, and parallel slowdown occurs.

This computer science-related article is a stub. You can help Wikipedia by expanding it.

v • d • e Parallel computing topics

General	High-performance computing

Parallelism	Bit-level parallelism · Instruction level parallelism · Data parallelism · Task parallelism

Theory	Speedup · Amdahl's law · Flynn's taxonomy (SISD • SIMD • MISD • MIMD) · Cost efficiency · Gustafson's law · Karp-Flatt metric · Parallel slowdown

Elements	Process · Thread · Fiber · Parallel Random Access Machine

Coordination	Multiprocessing · Multithreading · Multitasking · Memory coherency · Cache coherency · Barrier · Synchronization · Distributed computing · Grid computing

Programming	Programming model · Implicit parallelism · Explicit parallelism

Hardware	Computer cluster · Beowulf · Symmetric multiprocessing · Non-Uniform Memory Access · Cache only memory architecture · Asymmetric multiprocessing · Simultaneous multithreading · Shared memory · Distributed memory · Massively parallel processing · Superscalar processing · Vector processing · Supercomputer · Stream processing · GPGPU

Software	Distributed shared memory · Application checkpointing · Warewulf

APIs	POSIX Threads · OpenMP · Message Passing Interface (MPI) · Intel Threading Building Blocks

Problems	Embarrassingly parallel · Grand Challenge · Software lockout

Categories: Computer science stubs | Parallel computing

See also ebooksgratis.com: no banners, no cookies, totally FREE.

Parallel slowdown

From Wikipedia, the free encyclopedia

Views

Navigation

Interaction

Search