Single program, multiple data

In <a href="/facts/Computing/Kghtm9fX">computing</a>, single program, multiple data (SPMD) is a term that has been used to refer to computational models for exploiting <a href="/facts/Parallel_computing/nQzcpzQt">parallelism</a> whereby multiple processors cooperate in the execution of a program in order to obtain results faster.
The term SPMD was introduced in 1983 and was used to denote two different computational models:

<ol><li>by Michel Auguin (University of Nice Sophia-Antipolis) and François Larbey (Thomson/Sintra), as a “fork-and-join” and data-parallel approach where the parallel tasks (“single program”) are split-up and run simultaneously in lockstep on multiple SIMD processors with different inputs, and</li>
<li>by Frederica Darema (IBM), where “all (processors) <a href="/facts/Process_(computing)/Vcq7EnUV">processes</a>  begin executing the same program... but through synchronization directives ... self-schedule themselves  to execute different instructions and act on different data” and enabling MIMD parallelization of a given program, and is a more general approach than <a href="/facts/Data_parallelism/SkYoL91S">data-parallel</a> and more efficient than the fork-and-join for parallel execution on general purpose multiprocessors.</li></ol>
The (IBM) SPMD is the most common style of parallel programming and can be considered a subcategory of MIMD in that it refers to MIMD execution of a given (“single”) program. It is also a prerequisite for research concepts such as <a href="/facts/Active_message/mPdGezTI">active messages</a> and <a href="/facts/Distributed_shared_memory/IboHJvt6">distributed shared memory</a>.

Single program, multiple data open-in-new

Single program, multiple data