Talk:Multiple instruction, single data

This article is rated Stub-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects:

Computing This article is within the scope of WikiProject Computing, a collaborative effort to improve the coverage of computers, computing, and information technology on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.ComputingWikipedia:WikiProject ComputingTemplate:WikiProject ComputingComputing ??? This article has not yet received a rating on the project's importance scale. This article has been automatically rated by a bot or other tool as Stub-class because it uses a stub template. Please ensure the assessment is correct before removing the |auto= parameter.

after inserting a hint on fault-tolerant microarchitectures, i noticed the corresponding paragraph was removed only recently, with the following motivation:

• 'redundant computation is a form of sisd'. this may apply, e.g. if multiple processors are deployed for that purpose. it is not true in general. redundant computation can be well applied in one and the same microarchitecture.
• 'it contradicts the above paragraph'. i believe juliano refers to instructions being 'different' ones. they are different, the same instruction, but different instances. the same applies to sisd above.

any more objections? if not, i'd suggest to rather restore revision id 64861772.

Does Pipelinig systems really come under this category. As the term says "Single Data", In Pipelinig the functional units are effectively processing different data? — Preceding unsigned comment added by 80.57.57.112 (talk) 17:21, 1 July 2011 (UTC)Reply

Micron's Automata Processor may be an outstanding example of a MISD architecture. --94.36.200.39 (talk) 01:01, 29 December 2015 (UTC)Reply

Internally the pipeline is essentially sequential, so it can not be classified as MISD. Even the machinery to implement hyperthreading does not fall under the MISD classification. Besides this, the phrase using the term 'purists' is clearly out of context, unless there was a real debate to be presented. The only thing in this perspective seems to be the opinion of the writer. — Preceding unsigned comment added by 187.58.253.2 (talk) 00:18, 22 April 2013 (UTC)Reply

Why is this even in here. It clouds the entire discussion and makes it read like the author themselves that wrote the research paper are trying to get more noticed. There is already a Wikipedia page for systolic arrays. Just mention it is one type of MISD and refer to existing page instead of repeating it again. Keep information localized so that it can be proof read, verified, and discussed instead of spreading the topic among many different Wikipedia pages. This page would be clouded with so many discussions of MISD types it would be ridiculous to read. Wikipedia itself would be a bag of over information if this kind of approach was done. — Preceding unsigned comment added by 2601:646:8100:9540:E1AD:ECE3:5446:640D (talk) 01:33, 16 February 2020 (UTC)Reply

I agree.

Adding to what was already stated, the systolic array page has four paragraphs under classification controversy that very closely mirror those hereby present.

Moreover, these paragraphs in the systolic array page do not have the same references they have here, rather, they have none.

Furthermore, I think that a mention of Duncan's taxonomy, that attempts to fix the aforementioned controversy, should also be included.

As already suggested, I too propose to move everything under systolic array and keep here only the mention of systolic arrays as a textbook example (even if flawed) of MISD.

EMJzero (talk) 17:25, 10 July 2025 (UTC)Reply