Talk:Binary prefix/Archive 2

This is an archive of past discussions about Binary prefix. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page.

Archive 1

Archive 2

Archive 3

Archive 4

Archive 5

We need a template for the little articles

I want to compromise the conciseness and prettiness of this:

Byte unit (SI prefix)
Other:	kilo- \| mega- \| giga- \| tera- \| peta- \| exa- \| zeta-
Related bit unit: Megabit
Related binary prefix unit: Mebibyte

with the info in this:

Decimal prefixes				Binary prefixes edit
SI prefixes powers of ten				Binary prefixes powers of two				IEC std prefixes powers of two
Prefix	Symbol	Multiple		Prefix	Symbol	Multiple		Prefix	Symbol
yotta	Y	10²⁴	≈	yotta	Y	2⁸⁰
zetta	Z	10²¹	≈	zetta	Z	2⁷⁰
exa	E	10¹⁸	≈	exa	E	2⁶⁰	=	exbi	Ei
peta	P	10¹⁵	≈	peta	P	2⁵⁰	=	pebi	Pi
tera	T	10¹²	≈	tera	T	2⁴⁰	=	tebi	Ti
giga	G	10⁹	≈	giga	G	2³⁰	=	gibi	Gi
mega	M	10⁶	≈	mega	M	2²⁰	=	mebi	Mi
kilo	k	10³	≈	kilo	k or K	2¹⁰	=	kibi	Ki
Notes: The SI prefixes have similar values to, but are different from, the corresponding Binary prefixes. The IEC prefixes were proposed to distinguish these meanings. As of 2004, the IEC prefixes have not been widely taken up

and create template that we can put in all the little articles like kilobit and pebibyte so newcomers realize each article has its own info already and stop trying to write the same info into one of the little articles.

I basically just want to make this:

SI, bits	SI, bytes	IEC, bits	IEC, bytes
Kilobit	Kilobyte	Kibibit	Kibibyte
Megabit	Megabyte	Mebibit	Mebibyte
Gigabit	Gigabyte	Gibibit	Gibibyte
Terabit	Terabyte	Tebibit	Tebibyte
Petabit	Petabyte	Pebibit	Pebibyte
Exabit	Exabyte	Exbibit	Exbibyte
Zettabit	Zettabyte	—	—
Yottabit	Yottabyte	—	—

into a prettier navbox with a little more info. Ideas? - Omegatron 17:22, Mar 25, 2005 (UTC)

A little better

Decimal SI prefixes powers of ten				Binary IEC prefixes powers of two
Prefix	Symbol	Multiple		Prefix	Symbol	Multiple
kilo	k	10³	≈	kibi	Ki	2¹⁰
mega	M	10⁶	≈	mebi	Mi	2²⁰
giga	G	10⁹	≈	gibi	Gi	2³⁰
tera	T	10¹²	≈	tebi	Ti	2⁴⁰
peta	P	10¹⁵	≈	pebi	Pi	2⁵⁰
exa	E	10¹⁸	≈	exbi	Ei	2⁶⁰
zetta	Z	10²¹
yotta	Y	10²⁴
These prefixes are often applied to byte and bit.

How about this? Feel free to come up with a better/smaller phrase/sentence to put at the bottom. Variants I thought about: "applied to", "added to", "used with", remove word "prefixes", add word "terms", and so on... What do you think? Also, if we nuke all those dictdef articles we should make sure any interesting info like in petabyte is preserved into the common byte article. Oh and we gotta think of the name for the template. Delicates 19:44, 16 Apr 2005 (UTC)

I like it. — Sebastian 07:11, 2005 Mar 27 (UTC)

Hmm.. That's better, but I wanted to link directly to articles like yottabyte, not yotta

Basically I want this made into a smaller, prettier navbox: - Omegatron 16:40, Mar 27, 2005 (UTC)

SI, bits	SI, bytes	IEC, bits	IEC, bytes
Kilobit	Kilobyte	Kibibit	Kibibyte
Megabit	Megabyte	Mebibit	Mebibyte
Gigabit	Gigabyte	Gibibit	Gibibyte
Terabit	Terabyte	Tebibit	Tebibyte
Petabit	Petabyte	Pebibit	Pebibyte
Exabit	Exabyte	Exbibit	Exbibyte
Zettabit	Zettabyte	—	—
Yottabit	Yottabyte	—	—

I think all those dinky little stub articles are nonsense which should be eliminated, most of them wouldn't even be worth a "dictionary" entry. They certainly are not encyclopedic. I could see having an article for each prefix, and linking to that. For the rest, one article on Orders of magnitude for bits and for bytes would be more than sufficient--even that's too much IMHO, this article is enough for both. Gene Nygaard 17:33, 27 Mar 2005 (UTC)

- I agree completely. There is no reason whatever for these quantities to have articles which can never be more than a dictdef. As valid "index entries" they should all redirect here. Dpbsmith (talk) 17:43, 27 Mar 2005 (UTC)

ARGH! That's what I said in the first place! Talk:Binary prefix#Consolidate all the little articles - Omegatron 21:54, Mar 27, 2005 (UTC)

A good idea. Well spotted. Bobblewik (talk) 23:18, 29 Mar 2005 (UTC)

Can we please do this soon? See Petabyte#See also for example. They are just getting bigger. - Omegatron 20:29, Apr 3, 2005 (UTC)

Alright so almost everyone likes the template idea. Do we have one yet? - Omegatron 12:19, May 19, 2005 (UTC)

Vote vote vote!

This vote is over – we decided to create a template that links all the little articles together.

Little articles like pebibit keep getting stuff about other units added to them, get altered so they aren't consistent with the others, etc. by anons who probably don't realize there is an article for each individual prefix and unit, like megabit/mebibit/megabyte/mebibyte.

So what should we do?

Create a template that links them all to each other and put it in every one

Support. I'm sure we can all work together to keep the articles to an acceptable consistency, and a template project, along with other minor changes along the way, would be the best way to maintain them without losing information on each article or making this one too central and overpowering. --Alexwcovington (talk) 04:47, 19 Apr 2005 (UTC)
Support. Good Idea. I want to find Exabyte or Terabyte if i search for it. --Mononoke 09:25, 19 Apr 2005 (UTC)
Support. The template should contain prominent links to Binary prefix, Bit and Byte, and the articles themselves should contain nothing else except a brief definition of the word's meaning(s), and a handful of usage examples. The only exceptions that come to mind are Megabyte and Gigabyte, which have interesting debates about their meanings for floppy and hard disks respectively. – Smyth\^talk 16:39, 20 Apr 2005 (UTC)
Support, and I do believe I owe an apology. I deleted most of the merge templates because I found the discussion on Talk:Kilobyte dated June 2004 and I assumed they all dated that far back...then I found the discussion here. What to do? My rationale:
- Each article removes the need to link munge (i.e., kilobytes per second) since I think it's extremely bad practice
- Each article has its own "What links here" and it'd be much easier to see what links to each unit (instead of one page (which is currently limited to 500 max) for all units)
- Each article would *explicitly* state what each unit means instead of forcing the visitor to hunt down a table
Again, my apologies on the merge template removal! Cburnett 21:45, Apr 20, 2005 (UTC)
You missed all the kibibit/mebibyte merge entries. :-) - Omegatron
Support - This makes sense to me. - Omegatron 22:52, Apr 20, 2005 (UTC)
Support - Sounds good. --Pmsyyz 19:20, 17 August 2005 (UTC)

Merge them all into this article or into byte and bit or something like that

no votes

Merge all but kilo/mega/gigabyte that have significant info on their own

Support. It's A Good Thing™ that someone finally called for a vote on this. With the present scheme we'd surely be swamped with boring micro-maintenance to keep things consistent at all times. --Wernher 05:09, 18 Apr 2005 (UTC)
Support Dpbsmith (talk) 09:57, 18 Apr 2005 (UTC)
kinda support i think it would be a good idea to move the IEC stuff to their corresponding standard prefix pages. there will likely never be more to say about gibli-libbli-bit or whatever silly thing we are calling it than currently is written. i don’t support killing all the articles such as tera which will be growing as time passes on. the template is great and kudos for to the people who wrote this page, its clear and concise. Cavebear42 23:41, 19 May 2005 (UTC)
Support It's too repetive. raylu 04:07, August 17, 2005 (UTC)

Do nothing

no votes

Onward

It's been a month since that poll was last updated, and there seems to be support for the template idea. (Not a consensus, true.) I've adopted the above table into two: one for -byte pages and one for -bit pages.

Table for pebibit, petabit, etc articles:

Decimal names powers of ten				Binary names powers of two
Name	Symbol	Multiple		Name	Symbol	Multiple
kilobit	kb	10³	≈	kibibit	Kib	2¹⁰
megabit	Mb	10⁶	≈	mebibit	Mib	2²⁰
gigabit	Gb	10⁹	≈	gibibit	Gib	2³⁰
terabit	Tb	10¹²	≈	tebibit	Tib	2⁴⁰
petabit	Pb	10¹⁵	≈	pebibit	Pib	2⁵⁰
exabit	Eb	10¹⁸	≈	exbibit	Eib	2⁶⁰
zettabit	Zb	10²¹
yottabit	Yb	10²⁴

Table for petabyte, pebibyte, etc articles:

Decimal names powers of ten				Binary names powers of two
Name	Symbol	Multiple		Name	Symbol	Multiple
kilobyte	kB	10³	≈	kibibyte	KiB	2¹⁰
megabyte	MB	10⁶	≈	mebibyte	MiB	2²⁰
gigabyte	GB	10⁹	≈	gibibyte	GiB	2³⁰
terabyte	TB	10¹²	≈	tebibyte	TiB	2⁴⁰
petabyte	PB	10¹⁵	≈	pebibyte	PiB	2⁵⁰
exabyte	EB	10¹⁸	≈	exbibyte	EiB	2⁶⁰
zettabyte	ZB	10²¹
yottabyte	YB	10²⁴

I suggest that at the bottom of each -bibyte pages we have a see also with links to: the corresponding decimal-prefixed version, the corresponding -bibit, the binary prefix article, and the orders of magnitude (data) article. Similarly for the -bibit and decimal-prefixed pages.

I'll wait for a couple days for comments. If there are no objections, I'll turn the above into real templates and go about changing all the relevant pages. One-dimensional Tangent (Talk) 19:44, 19 May 2005 (UTC)

Looks good to me. Just one minor point: there is no sense in linking each -bit article to the corresponding -byte, as the two have no connection.

I also suggest that the table headers link to the primary articles, as follows:

Multiples of bytes
Decimal prefixes				Binary prefixes
Name	Symbol	Multiple		Name	Symbol	Multiple
kilobyte	kB	10³	≈	kibibyte	KiB	2¹⁰
megabyte	MB	10⁶	≈	mebibyte	MiB	2²⁰
gigabyte	GB	10⁹	≈	gibibyte	GiB	2³⁰
terabyte	TB	10¹²	≈	tebibyte	TiB	2⁴⁰
petabyte	PB	10¹⁵	≈	pebibyte	PiB	2⁵⁰
exabyte	EB	10¹⁸	≈	exbibyte	EiB	2⁶⁰
zettabyte	ZB	10²¹
yottabyte	YB	10²⁴

And of course, there should be a third template for the bare prefixes, as in #A little better above.

– Smyth\^talk 21:19, 19 May 2005 (UTC)

Looks good! I don't think enough people care about this for it to reach a true consensus in the next millenium. I say we just be bold and add it.

I agree that kilobit should link to kilobyte and vice versa.

Where would the third template go, Smyth? - Omegatron 21:27, May 19, 2005 (UTC)

I agree that we won't get a consensus; the reason for the delay was to gather any input others might care to offer. I like the title on Smyth's version, but I'm not sure whether to label the two columns "prefixes", since they show the prefixed words rather than just the prefix. ("Prefixed" perhaps? But that sounds as though something were about to be broken.) One-dimensional Tangent (Talk) 22:08, 19 May 2005 (UTC)

Created Template:Quantities of bytes and Template:Quantities of bits. My schedule just changed, so I'm going to start changing pages now. One-dimensional Tangent (Talk) 22:16, 19 May 2005 (UTC)

We can always change the titles. I'm just glad we finally got around to doing this.

By the way, "standard" capitalization is the first word capitals and then the rest lowercase, so it's "See also", not "See Also". It's absurdly pedantic of me to even bring it up, though. :-) - Omegatron 22:59, May 19, 2005 (UTC)

Ah. Now I know. Well, I don't feel like changing that now that I'm done, but I'll keep it in mind for future articles. Thanks for pointing that out. :) One-dimensional Tangent (Talk) 23:05, 19 May 2005 (UTC)

Uh oh. Do we need to do the same thing with megabit per second, kibibit per second, etc.? I see everyone is misspelling "mebibit" as "mibibit". - Omegatron 23:49, May 23, 2005 (UTC)

See an analogous discussion at Wikipedia:Votes for deletion/Myriametre. Uncle G 11:10, 2005 May 24 (UTC)

I made another one for the bit rates:

Bit rates (data-rate units)
Name	Symbol	Multiple
bit per second	bit/s	1	1
Metric prefixes (SI)
kilobit per second	kbit/s	10³	1000¹
megabit per second	Mbit/s	10⁶	1000²
gigabit per second	Gbit/s	10⁹	1000³
terabit per second	Tbit/s	10¹²	1000⁴
Binary prefixes (IEC 80000-13)
kibibit per second	Kibit/s	2¹⁰	1024¹
mebibit per second	Mibit/s	2²⁰	1024²
gibibit per second	Gibit/s	2³⁰	1024³
tebibit per second	Tibit/s	2⁴⁰	1024⁴

Byte rates don't deserve their own articles at this point, and are just merged into bit rates. I would like if someone could double check them all. I fixed a lot of errors, but missed a few I'm sure.

For the record, it's mebibit (Mib) and mebibyte (MiB), not mibibyte or MeB. Everyone gets those mixed up. - Omegatron 23:11, Jun 19, 2005 (UTC)

decimal prefixes wrong?

Discussion moved from Talk:Gigabyte since it's much more appropriate here. I didn't actually move the whole conversation, since I don't want to overstep anything. - Omegatron 01:15, May 28, 2005 (UTC)

I am aware of the errors which people who are pushing the GiB notation (which has not been accepted in widespread use) have put all over the wikipedia. the article on binary prefix is well written for the most part and uses the unpopular titles for the sake of clarity in discussion. there are some claims in there which should be verified such as the ones you have made in the previous comment. please feel free to come forward with proof that those are the accepted uses in those fields (perhaps from IEEE or such) and we can go about citing sources. I have not changed them to the correct uses because i have not done the same. the abstract (such as this article) are easy enough to back up and that is why i edit it. to state what constitutes common use would take more reseach (which i dont currently have time to do) Cavebear42 17:20, 23 May 2005 (UTC)

That's a very good idea. I'll start collecting references. - Omegatron 17:56, May 23, 2005 (UTC)

And so you did, and a fine job i might add. I added 2 lines below and noted them as mine so as not to confuse the remainder of this work done by Omegatron. I think we are settled in data rate issues pretty firmly as being the standad SI interptitations of the units. What I said in Talk:Gigabyte, however, is still true. the original and (from a computer's standpoint) accurate definitions are still very much the standard definition. We can not abandon all that computers are built on and pretend like transistors have 10 fingers. The mebibyte notation has not gained widespread use and we can not pretend as though it has. The standard rule for such things on the wiki is to use the most common usage as used in the world. Also, the manual of style tells us "For units of measure use SI units, unless there are compelling historical or pragmatic reasons not to do so" and i feel that this is definatly both historical and pragmatic. I am willing join IEEE in conceeding this common usage in the name of clarity and, for lack of other options from IEEE or SI, use the unpopular IEC titles. In order to set a standard to be uniformly implemented across the wiki, I would like to suggest that we create a boilerplate of some sort to explain that we use the less popular titles directing inquisitive readers to this article. I would also like to see us create a rule in the Manual of Style in order to guide editors. I don't know what it takes to create such rules, but I think that this might be a wise move. perhaps it's time to move this discussion (once again) to Wikipedia talk:Manual of Style? Cavebear42 23:36, 31 May 2005 (UTC)

Actually, I think standards trump common usage. See aluminium. The Manual of Style says "For units of measure use SI units, unless there are compelling historical or pragmatic reasons not to do so". So whether their commonness is a "compelling historical reason" to use them or whether these recommendations even count as standards is debatable.

"What I said in Talk:Gigabyte, however, is still true. the original and (from a computer's standpoint) accurate definitions are still very much the standard definition. We can not abandon all that computers are built on and pretend like transistors have 10 fingers."

My biased POV: So the physicists should have their own definition of the mega- prefix so that quoting the speed of light is the more convenient whole number 3 instead of 2.99792458? Or the chemists will come up with their own version of the standard prefixes so that Avogadro's number starts with 6 instead of 6.0221415? The whole point of the SI prefixes is to maintain a consistent set of multipliers so that the various disciplines mesh well together. Laziness on the part of computer engineers shouldn't inconvenience everyone else. - Omegatron 13:29, Jun 1, 2005 (UTC)

Just my 2c since I've been wondering whether to edit this article on the same lines. When measuring bits (or clock cycles), the most common usage appears to be powers of 10 ie. SI. The confusion appears to arise when talking about bytes, whether these should be powers of 10 or powers of 2. Operating systems such as Windows and Linux measure bytes in powers of 2, as do RAM manufacturers. The odd man out seems to be makers of secondary storage devices such as hard disks and USB drives who insist on bytes measured in powers of 10. As far as the manual of style goes, I'd recommend bits are always SI, bytes are always powers of 2. --kudz75 01:04, 1 Jun 2005 (UTC)

hmmm, where to start? clock cycles would be true. they have very little to do with computers as that it's a measure of time. the measure of time existed before computers and stands independently of computing components. the same would be true for computing terms which done requre computing components such as the gigaflop. these are not derived from a binary system comming out of a transistor or similer device. the case of data rates is interesting. a bit is either 1 or 0 and in that sense, its binary. however data rates dont care about what the data is, they care how much is moved. if you move 100 bits in 1 second, it doesnt matter what those bits were and therefore si units work fine. data storage is where the tables turn. if i have 1 bit of memory, i can store 2 values (0, 1). if i have 2 bits, i can store 4 values (00, 01, 10 , 11). if i have 3 i can store 8 values (000, 001, 010, 011, 100, 101, 110, 111). it is easy to see that this is a 2^x case where x is the number of bits you have. the fact that we break them into bytes and then count them from there is a historical norm, it was once thought that 8 bits could represent any nessicery number/chariter and therefore was the largest nessicery size for data storage.

as time progressed, we started to make larger devices and used the kilobyte (historical usage) to be 10 bytes of data. this would, of course, store 2¹⁰ different bytes, not 10² differnt bytes. in hindsight, we should ahve found something other to call it than the kilobyte. back then calling it the kibibyte would have us currently not talking about it. the fact that we were already grouping into 8 bits at that time is the reason this is a bytes discussion. you see, if we never went to the 8 bit theory, we would have declared the kilobit (historical useage) to be 2¹⁰ bits. this is why it would be a bad idea to keep the powers of 2 called this confusing tytle in bytes and just not bits (which is what we are pretty much doing now). now, hard drive manufacturers can claim whatever reason they want for using powers of 10 and not powers of 2 but the fact remains that the people who make the drives know the difference and that a drive with ~74 GiB of data has a giant 80GB written on the box. if one drive wrote 74 and another wrote 80 at the same price, you can guess which would sell better. in any case, we count in powers of 10 because we ahve 10 fingers, computers count in powers of 2 because they have 2 states. the confution here came when we chose not to give a new name to this new way of counting. I did not make this decition personally, but it was made and saying that it shouldnt have been doesnt change history. the best we can do a tthis point is figure out how to correct it.Cavebear42 18:05, 1 Jun 2005 (UTC)

IEC prefixes are *not* unpopular. They are gaining widespread use in newly developed applications. The OSes is the main inertia that is holding them back. You are mistaken about the lack of "other options" from IEEE and SI, because both have accepted IEC prefixes years ago. IEEE has published a standard with IEC prefixes, this standard has also been accepted by ANSI which re-released it, and at BIPM it has been decided to insert pointer to IEC prefixes in the upcoming new international SI edition, while American localisation of the current SI edition by NIST has referred to IEC prefixes all along. I have been tracking these issues for years now on my IEC prefixes and symbols for binary multiples page with links to all relevant documents and software applications that use them. Delicates 21:04, 3 Jun 2005 (UTC)

perhaps you and i define "popular" diffently, i mean that not only your adverage consumer has never hear of it, i mean that your adverage person who works with electronics and computers on a day to day basis also has never hear of it. that it has been referenced in a document somewhere does not make it popular. I see no point in pointing the finger at OS'es or anything/anyone else. there is a prudent reason why the historical definitions were used. last i heard SI did not have a unit to measure data storage. perhaps they will soon but i havent see that shown. IEEE asked people to not use KB to mean 1024, they did not ask people to use KiB to mean 1024. this is why i said that it was not accepted as their standard. when i get some more time on my hands, ill read your page, it sounds like an interesting thing to track. Cavebear42 21:20, 3 Jun 2005 (UTC)

IEEE Std 1541-2002, IEEE Trial-Use Standard for prefixes for Binary Multiples is a two-year trial standard that would have ended in 2004. Can't find what happened next. - Omegatron 19:36, Jun 6, 2005 (UTC)

It has been accepted into full-use on March 19. Delicates 21:50, 6 Jun 2005 (UTC)

I completely oppose pervasive use of "KiB" instead of "KB" to mean 1024 bytes. This is terrible, terrible. No one but the geekiest nerds knows what this means (this is not a pejorative claim). Is this being discussed anywhere else? --Locarno 18:59, 2 June 2006 (UTC)

Is this being discussed anywhere else?

Standards committees everywhere?

Atlant 19:08, 2 June 2006 (UTC)

No one but the geekiest nerds know what "KB" means, either. — Omegatron 20:05, 2 June 2006 (UTC)