Talk:Control unit

Tomasulo Scoreboard transform article
apologies editing from a hand-hrld unit, [[User:Lkcl] here. useful article describing how Tomasulo is topologically identical to Scoreboards.

https://libre-soc.org/3d_gpu/architecture/tomasulo_transformation/?updated

DESIGN OF CONTROL UNIT
What is "ad-hoc logic"? Should that term if you can be get to get, where it apears in the article, perhaps link to another wikipedia-page (which would be red link (like hear), to begin with, because an article for that term does not exist at the moment. A page for the term "ad-hoc" exists though)?


 * ad-hoc logic litterally means logic developed on the spot. It serves to illustrate the point that the control unit was rarely standardised (the right word has slipped my mind... standardised was the closest I could come). I agree it probably needs a better definition, maybe someone from project computing could do something?
 * 202.89.169.23 01:34, 25 May 2007 (UTC)


 * Hm, maybe hardwired control is the missing phrase? --Abdull 19:48, 5 July 2007 (UTC)

I just redirected something to "hardwired control", I agree that it should be explained first and then on to programmable devices. RE: "ad-hoc" logic: "In the beginning, did ad hoc designs, and then saw patterns repeated, gave names" (http://www.cs.ucsb.edu/~htzheng/teach/cs64s11/pdf/lecture10.pdf), so I guess ad-hoc logic is circuity developed from scratch - random logic - rather than constructed from standard building blocks. Peter Flass (talk) 12:06, 14 September 2012 (UTC)

Merge
Keep. I have seen that a template proposes merging a\but if you dont want to i will ahev to bsay its fine but you still ahve to get to gethardwired control into control unit. I am afraid that it would be inappropriate. The concept of "hardwired" is important of its own, and deserves as a standalone IF THIS IS IN YOUR PROJECT YOU HAVE COPYED OFF WIKIPIDIA article. For example, it is not only used in computing, but also in biology. "Hardwired" is such a "crosscutting-several-sciences" concept, like "bootstrapping" (the latter being used in embryogenesis, language acquisition, computing, and its straightforward generalization exists also in communication and in foundation of mathematics, although the literature does not use this name for that). In summary, I think that hardwired must be kept standalone, should not be merged. Physis (talk) 13:26, 29 August 2008 (UTC)

Agree. They are part of the same topic. Maxudaskin (talk) 14:56, 24 April 2009 (UTC)

Article re-write suggested
I think the article should be completely re-written to first state the historical significance of "hard wired" (eg fixed wiring/wiring loom/unchangeable). Only then should its present meaning be explained to differentiate from programmable/microprogrammable devices.

I agree —Preceding unsigned comment added by 86.140.202.8 (talk) 10:37, 15 August 2009 (UTC)

Citation?
The last paragraph is copypasta from http://www.pcguide.com/ref/cpu/arch/int/compControl-c.html but I don't know how to add references —Preceding unsigned comment added by 220.253.81.204 (talk) 09:44, 10 February 2010 (UTC)

Look out for possible copyright violations in this article
This article has been found to be edited by students of the India Education Program project as part of their (still ongoing) course-work. Unfortunately, many of the edits in this program so far have been identified as plain copy-jobs from books and online resources and therefore had to be reverted. See the India Education Program talk page for details. In order to maintain the WP standards and policies, let's all have a careful eye on this and other related articles to ensure that no material violating copyrights remains in here. --Matthiaspaul (talk) 13:02, 31 October 2011 (UTC)

Merge redux
I propose that this article be merded with Controller_(computing), or at least that a clearer differentiation of content be made. Peter Flass (talk) 00:38, 17 February 2012 (UTC)


 * You are right, that one is mainly a list, and this an article. Merging seems no good. But both can be improved. Tagremover (talk) 20:40, 22 March 2012 (UTC)


 * the problem is that this is a ridiculously (insanely) complex branch of computer science. i am not kidding when i say that it took *five months* talking with Mitch Alsup on comp.arch to understand the 6600 scoreboard and then going from there to learn how to make it precise-capable and multi-issue. expecting the average person to grasp that much information just by reading a "simplified" wikipedia page is too much.  this is a topic that has to be qualified as the same "advanced" level as branches of mathematics and quantum mechanics, i.e. not to be taken lightly.  User:Lkcl

Still too much hand-waving
I did a little retouching, but this article still contains too much "hard-waving" and technobabble that sounds like it's explaining things and really doesn't. I second the call for expert attention. Peter Flass (talk) 16:05, 26 May 2012 (UTC)

Separating control unit from electronic control unit
Trouble started with this edit by a perhaps well-intentioned drive-by IP "expert." Interjecting discussion of automotive control units into this article just muddies the waters and causes confusion. If someone wants to write a generic article or disambiguation including appliance control units, game control units, widget control units, etc., then please create a control unit (disambiguation) page. If you don't think the CPU meaning of the term is primary, please submit a WP:RM to move this article to CPU control unit or control unit (CPU). Thanks, Wbm1058 (talk) 15:45, 1 November 2012 (UTC)
 * IMHO the usage of control unit as "peripheral controller" is primary. Peter Flass (talk) 15:52, 1 November 2012 (UTC)
 * By "peripheral controller", do you mean peripheral DMA controller, peripheral pin controller, or something like the UNIVAC 1050, which "was commonly used as an off-line peripheral controller"? – Wbm1058 (talk) 16:10, 1 November 2012 (UTC)


 * Start with the general summary article on computer. It has a Control unit section which says an alternate name for control unit is central controller and clearly is about the CPU component, and points to another main article, CPU design, which says that a control unit is "logic which controls the datapaths."  It seems to me that control unit primarily means central, not peripheral controller, and controller primarily means peripheral, not central controller—see Controller (computing), which is really not much of an "article", perhaps it's a broad-concept article (WP:CONCEPTDAB). – Wbm1058 (talk) 17:53, 1 November 2012 (UTC)


 * That's the reason I haven't gone near this article lately - there's too much of a difference in terminology. For someone with a mainframe background a "control unit" is a piece of gear, often a separate box, that interfaces between a channel and a device, only occasionally called a "controller."  Controller (computing) touches on some of this, plus a lot of other stuff.  I added the "standalone device" part there myself.  It seems there are just lots and lots of things that can be named by "controller" or "control unit" - that's why I like the idea of renaming this article to something like CPU control unit so that the other "control units" can have separate articles. Peter Flass (talk) 18:44, 1 November 2012 (UTC)


 * Hi, just noticed and read your comment over at Talk:Controller (computing). As a student, I had hands-on experience with the Programma 101 and IBM 1620. But then the closest I got to a mainframe was the window where punched cards were dropped off or later, a CRT terminal or PC running terminal software.  I suppose your perspective depends on whether you had up-close-and-personal experience with the mainframe hardware.  From the earliest days, the Von Neumann architecture used the term control unit for the CPU component.  Perhaps back in the day just that CPU component was housed in a separate box with wires running from it to the box containing the processing unit.  Then they merged the two units into a single box called the central processing unit, but even though the control(ler) unit was no longer in a separate physical unit, the term control unit stuck.  I suppose at one time it was easy to distinguish between the central processing unit (without any concern for what components were inside it) and apparently still-separate "control units" for peripherals.  But, as these also gradually shrunk to the point of becoming single chips, or even one of many functions of a single chip, perhaps the name changed to controller to disambiguate it from the CPU unit.  I'm fine with mentioning in articles about peripheral controllers that they are or were sometimes called control units, but I don't think we should have article titles or links calling them control units, as that can only cause confusion.  I'm open to the possibility of renaming this article, and it may come to that, but first I'd like to try to make it work with the current title.  Next step is creating Control unit (disambiguation), we need that. – Wbm1058 (talk) 21:21, 1 November 2012 (UTC)
 * Perhaps you are familiar with the IBM 2821 Control Unit. I note that its article doesn't really say whether its a control unit or controller. Control Unit is capitalized because that is the proper name for the device (well, I assume that it is, if the article title is correct).  But there's no law that says that a device given the proper name Control Unit can't be described as a controller, if that is actually what it is.  See List of IBM products.  Many of these are actually named or described controller. – Wbm1058 (talk) 00:45, 2 November 2012 (UTC)

Reasonable choice
Looks like a reasonable reorganization. The disambiguation page needs a little cleanup, but that can be worked on. Peter Flass (talk) 11:01, 2 November 2012 (UTC)
 * Thanks. And reasonable DAB cleanup, too. Wbm1058 (talk) 16:25, 2 November 2012 (UTC)

Still unsourced, still needs rewrite to be comprehensible to layman
The most recent set of edits added a lot of unsourced info about the control unit's function. I know nothing about control units, so it is impossible for me to verify or refute the new edits. Almost every sentence in this article warrants a "citation needed" tag. I hope someone with a bit more expertise can fix this entry, because it is currently a hot mess. Aroundthewayboy (talk) 22:23, 25 July 2014 (UTC)

External links modified
Hello fellow Wikipedians,

I have just modified 1 one external link on Control unit. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:
 * Corrected formatting/usage for http://qss.stanford.edu/~godfrey/vonNeumann/vnedvac.pdf

When you have finished reviewing my changes, please set the checked parameter below to true or failed to let others know (documentation at ).

Cheers.—cyberbot II  Talk to my owner :Online 22:41, 31 March 2016 (UTC)

2019 Rewrite
I found the text to be vague, incomplete and repetitive. I tried to preserve the nonrepetitive parts of the text as found. I separated the discussion to describe a control unit for the three major types of microarchitectures, then added sections for stall-reduction, low power and I/O. I tried to cite examples. I'm definitely hoping for feedback and corrective edits. I've noticed that as an article becomes less vague, reviewers are more able to correct its facts. Best wishes. Ray Van De Walker (talk) 00:09, 27 December 2019 (UTC)

Chemistry and physics
Chemistry note and physics note 105.112.154.118 (talk) 18:35, 16 February 2022 (UTC)

India Education Program course assignment
This article was the subject of an educational assignment at Department of Electronics and Telecommunication, College of Engineering, Pune, India supported by Wikipedia Ambassadors through the India Education Program&#32;during the 2011 Q3 term.&#32;Further details are available on the course page.

The above message was substituted from by PrimeBOT (talk) on 20:00, 1 February 2023 (UTC)