48-bit computing: Difference between revisions

Revision as of 05:56, 14 July 2021

Latest revision as of 17:31, 29 January 2024

(7 intermediate revisions by 6 users not shown)

Line 1:

{{UnreferencedMore references|date=August 2007}}

{{Computer architecture bit widths}}

In [[computer architecture]], '''48-bit''' [[integer (computer science)|integer]]s can represent 281,474,976,710,656 (2⁴⁸ or 2.814749767×10¹⁴) discrete values. This allows an [[Unsigned integer|unsigned]] binary integer range of 0 through 281,474,976,710,655 (2⁴⁸ − 1) or a [[Signed number representations|signed]] [[two's complement]] range of -140−140,737,488,355,328 (-2−2⁴⁷) through 140,737,488,355,327 (2⁴⁷ − 1). A 48-bit [[memory address]] can directly address every byte of 256 [[Terabyte|terabytesterabyte]]s of storage. 48-bit can refer to any other [[Data (computing)|data]] unit that consumes 48 [[bit]]s (6 [[octet (computing)|octets]]) in width. Examples include 48-bit [[Central processing unit|CPU]] and [[Arithmetic logic unit|ALU]] [[computer architecture|architecture]]s are those that are based on [[processor register|register]]s, [[address bus]]es, or [[Bus (computing)|data bus]]es of that size.

{{short description|discrete values integer in computer architecture}}

In [[computer architecture]], '''48-bit''' [[integer (computer science)|integer]]s can represent 281,474,976,710,656 (2⁴⁸ or 2.814749767×10¹⁴) discrete values. This allows an [[Unsigned integer|unsigned]] binary integer range of 0 through 281,474,976,710,655 (2⁴⁸ − 1) or a [[Signed number representations|signed]] [[two's complement]] range of -140,737,488,355,328 (-2⁴⁷) through 140,737,488,355,327 (2⁴⁷ − 1). A 48-bit [[memory address]] can directly address every byte of 256 [[Terabyte|terabytes]] of storage. 48-bit can refer to any other [[Data (computing)|data]] unit that consumes 48 [[bit]]s (6 [[octet (computing)|octets]]) in width. Examples include 48-bit [[Central processing unit|CPU]] and [[Arithmetic logic unit|ALU]] [[computer architecture|architecture]]s are those that are based on [[processor register|register]]s, [[address bus]]es, or [[Bus (computing)|data bus]]es of that size.

==Word size==

Computers with 48-bit [[Word (data type)|words]] include the [[AN/FSQ-32]], [[Control Data Corporation|CDC]] 1604/[[CDC 3000|upper-3000 series]], [[BESM#BESM-6|BESM-6]], [[Ferranti]] [[Atlas (computer)|Atlas]], [[Philco]] [[Philco Transac S-2000|TRANSAC S-2000]] and [[Burroughs large systems]].{{efn|The B5000, B5500 and B5700 took 3 bits in control words and numeric data for use as a tag; alphanumeric data and instruction syllables were stored in the full 48 bits and had no tags.}}{{efn|The B5900-B8xxx additionally had a 3- or 4-bit type tag.}}

The Honeywell [[DATAmatic 1000]],

[[Honeywell 800|H-800]],

the [[MANIAC II]],

the [[MANIAC III]],

the [[Brookhaven National Laboratory]] Merlin,<ref>

[http://ed-thelen.org/comp-hist/BRL61-m.html#MERLIN "MERLIN"].

</ref>

the [[Philco computers#CXPQ|Philco CXPQ]],

the [[Ferranti Orion]],

the [[Telefunken Rechner TR 440]],

the [[ICT 1301]],

and many other early transistor-based and vacuum tube computers<ref>

[https://retrocomputingforum.com/t/in-search-of-48-bit-computers/898 "In search of 48 bit computers"].

</ref>

used 48-bit words.

==Addressing==

The [[IBM System/38]], and the [[IBM AS/400]] in its [[complex instruction set computer|CISC]] variants, use 48-bit addresses.

The address size used in [[logical block addressing]] was increased to 48 bits with the introduction of [[AT Attachment#ATA standards versions, transfer rates, and features|ATA-6]]. The [[Ext4]] file system physically limits the file block count to 48 bits.

Line 22 ⟶ 37:

==Notes==

{{Notelist}}

==References==

{{Reflist}}

{{CPU technologies}}