| Processors | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1-bit | 4-bit | 8-bit | 12-bit | 16-bit | 18-bit | 24-bit | 31-bit | 32-bit | 36-bit | 48-bit | 60-bit | 64-bit | 128-bit |
| Applications | |||||||||||||
| 8-bit | 16-bit | 32-bit | 64-bit | ||||||||||
| Data sizes | |||||||||||||
| bit nibble octet byte | |||||||||||||
| halfword word dword qword | |||||||||||||
| IEEE floating-point standard | |||||||||||||
| Single precision floating-point format (32-bit) Double precision floating-point format (64-bit) Quadruple precision floating-point format (128-bit) | |||||||||||||
In computing, word is a term for the natural unit of data used by a particular processor design. A word is basically a fixed sized group of bits that are handled as a unit by the instruction set and/or hardware of the processor. The number of bits in a word (the word size, word width, or word length) is an important characteristic of a specific processor design or computer architecture.
The size of a word is reflected in many aspects of a computer's structure and operation; the majority of the registers in a processor are usually word sized and the largest piece of data that can be transferred to and from the working memory in a single operation is a word in many (not all) architectures. The largest possible address size, used to designate a location in memory, is typically a hardware word (in other words, the full-sized natural word of the processor, as opposed to any other definition used).
Modern processors, including embedded systems, usually have a word size of 8, 16, 24, 32 or 64 bits, while modern general purpose computers usually use 32 or 64 bits. Special purpose digital processors, such as DSPs for instance, may use other sizes and many different sizes have been used historically, including 8, 9, 12, 18, 24, 36, 39, 40, 48 and 60 bits. The slab is an example of a system with an earlier word size. Several of the earliest computers (and a few modern as well) used BCD rather than plain binary, typically having a word size of 10 or 12 decimal digits, and some early decimal computers had no fixed word length at all.
The size of a word can sometimes differ from the expected due to backward compatibility with earlier computers. If multiple compatible variations or a family of processors share a common architecture and instruction set but differ in their word sizes, their documentation and software may become notationally complex to accommodate the difference (see Size families below).
Contents |
Depending on how a computer is organized, units of the word size may be used for:
When a computer architecture is designed, the choice of a word size is of substantial importance. There are design considerations which encourage particular bit-group sizes for particular uses (e.g. for addresses), and these considerations point to different sizes for different uses. However, considerations of economy in design strongly push for one size, or a very few sizes related by multiples or fractions (submultiples) to a primary size. That preferred size becomes the word size of the architecture.
Character size is one of the influences on a choice of word size. Before the mid-1960s, characters were most often stored in six bits; this allowed no more than 64 characters, so alphabetics were limited to upper case. Since it is efficient in time and space to have the word size be a multiple of the character size, word sizes in this period were usually multiples of 6 bits (in binary machines). A common choice then was the 36-bit word, which is also a good size for the numeric properties of a floating point format.
After the introduction of the IBM System/360 design which used eight-bit characters and supported lower-case letters, the standard size of a character (or more accurately, a byte) became eight bits. Word sizes thereafter were naturally multiples of eight bits, with 16, 32, and 64 bits being commonly used.
Early machine designs included some that used what is often termed a variable word length. In this type of organization, a numeric operand had no fixed length but rather its end was detected when a character with a special marking was encountered. Such machines often used binary coded decimal for numbers. This class of machines included the IBM 702, IBM 705, IBM 7080, IBM 7010, UNIVAC 1050, IBM 1401, and IBM 1620.
Most of these machines work on one unit of memory at a time and since each instruction or datum is several units long, each instruction takes several cycles just to access memory. These machines are often quite slow because of this. For example, instruction fetches on an IBM 1620 Model I take 8 cycles just to read the 12 digits of the instruction (the Model II reduced this to 6 cycles, or 4 cycles if the instruction did not need both address fields). Instruction execution took a completely variable number of cycles, depending on the size of the operands.
The memory model of an architecture is strongly influenced by the word size. In particular, the resolution of a memory address, that is, the smallest unit that can be designated by an address, has often been chosen to be the word. In this approach, address values which differ by one designate adjacent memory words. This is natural in machines which deal almost always in word (or multiple-word) units, and has the advantage of allowing instructions to use minimally-sized fields to contain addresses, which can permit a smaller instruction size or a larger variety of instructions.
When byte processing is to be a significant part of the workload, it is usually more advantageous to use the byte, rather than the word, as the unit of address resolution. This allows an arbitrary character within a character string to be addressed straightforwardly. A word can still be addressed, but the address to be used requires a few more bits than the word-resolution alternative. The word size needs to be an integral multiple of the character size in this organization. This addressing approach was used in the IBM 360, and has been the most common approach in machines designed since then.
Different amounts of memory are used to store data values with different degrees of precision. The commonly used sizes are usually a power of two multiple of the unit of address resolution (byte or word). Converting the index of an item in an array into the address of the item then requires only a shift operation rather than a multiplication. In some cases this relationship can also avoid the use of division operations. As a result, most modern computer designs have word sizes (and other operand sizes) that are a power of two times the size of a byte.
As computer designs have grown more complex, the central importance of a single word size to an architecture has decreased. Although more capable hardware can use a wider variety of sizes of data, market forces exert pressure to maintain backward compatibility while extending processor capability. As a result, what might have been the central word size in a fresh design has to coexist as an alternative size to the original word size in a backward compatible design. The original word size remains available in future designs, forming the basis of a size family.
In the mid-1970s, DEC designed the VAX to be a successor of the PDP-11. They used word for a 16-bit quantity, while longword referred to a 32-bit quantity. This was in contrast to earlier machines, where the natural unit of addressing memory would be called a word, while a quantity that is one half a word would be called a halfword. In fitting with this scheme, a VAX quadword is 64 bits.
Another example is the x86 family, of which processors of three different word lengths (16-bit, later 32- and 64-bit) have been released. As software is routinely ported from one word-length to the next, some APIs and documentation define or refer to an older (and thus shorter) word-length than the full word length on the CPU that software may be compiled for. Also, similar to how bytes are used for small numbers in many programs, a shorter word (16 or 32 bits) may be used in contexts where the range of a wider word in not needed (especially where this can save considerable stack space or cache memory space). For example, Microsoft's Windows API maintains the programming language definition of WORD as 16 bits, despite the fact that the API may be used on a 32- or 64-bit x86 processor, where the standard word size would be 32 or 64 bits, respectively. Data structures containing such different sized words refer to them as WORD, DWORD and QWORD respectively. A similar phenomenon has developed in Intel's x86 assembly language – because of the support for various sizes (and backward compatibility) in the instruction set, some instruction mnemonics carry "d" or "q" identifiers denoting "double-", "quad-" or "double-quad-", which are in terms of the architecture's original 16-bit word size.
| key: b: bits, d: decimal digits, w: word size of architecture, n: variable size | |||||||
|---|---|---|---|---|---|---|---|
| Year | Computer Architecture |
Word Size w |
Integer Sizes |
Floating Point Sizes |
Instruction Sizes |
Unit of Address Resolution |
Char Size |
| 1837 | Babbage Analytical engine |
50 d | w | — | 5 different cards were used for different functions, exact size of cards not known | w | — |
| 1941 | Zuse Z3 | 22 b | — | w | 8 b | w | — |
| 1942 | ABC | 50 b | w | — | — | — | — |
| 1944 | Harvard Mark I | 23 d | w | — | 24 b | — | — |
| 1946 (1948) {1953} |
ENIAC (w/ Panel #16[1]) {w/ Panel #26[2]} |
10 d | w, 2w (w) {w} |
— | — (2d, 4d, 6d, 8d) {2d, 4d, 6d, 8d} |
— — {w} |
— |
| 1951 | UNIVAC I | 12 d | w | — | ½w | w | 1 d |
| 1952 | IAS machine | 40 b | w | — | ½w | w | 5 b |
| 1952 | Fast Universal Digital Computer M-2 | 34 b | w? | w | 34 b = 4 b opcode plus 3× 10b address | 10 b | — |
| 1952 | IBM 701 | 36 b | ½w, w | — | ½w | ½w, w | 6 b |
| 1952 | UNIVAC 60 | n d | 1d, ... 10d | — | — | — | 2d, 3d |
| 1953 | IBM 702 | n d | 0d, ... 511d | — | 5d | d | 1 d |
| 1953 | UNIVAC 120 | n d | 1d, ... 10d | — | — | — | 2d, 3d |
| 1954 (1955) |
IBM 650 (w/IBM 653) |
10 d | w | — (w) |
w | w | 2 d |
| 1954 | IBM 704 | 36 b | w | w | w | w | 6 b |
| 1954 | IBM 705 | n d | 0d, ... 255d | — | 5d | d | 1 d |
| 1954 | IBM NORC | 16 d | w | w, 2w | w | w | — |
| 1956 | IBM 305 | n d | 1d, ... 100d | — | 10d | d | 1 d |
| 1957 | Autonetics Recomp I | 40 b | w, 79 b, 8d, 15d | — | ½w | ½w, w | 5 b |
| 1958 | UNIVAC II | 12 d | w | — | ½w | w | 1 d |
| 1958 | SAGE | 32 b | ½w | — | w | w | 6 b |
| 1958 | Autonetics Recomp II | 40 b | w, 79 b, 8d, 15d | 2w | ½w | ½w, w | 5 b |
| 1959 | IBM 1401 | n d | 1d, ... | — | d, 2d, 4d, 5d, 7d, 8d | d | 1 d |
| 1959 (TBD) |
IBM 1620 | n d | 2d, ... | — (4d, ... 102d) |
12d | d | 2 d |
| 1960 | LARC | 12 d | w, 2w | w, 2w | w | w | 2 d |
| 1960 | CDC 1604 | 48 b | w | w | ½w | w | 6 b |
| 1960 | IBM 1410 | n d | 1d, ... | — | d, 2d, 6d, 7d, 11d, 12d | d | 1 d |
| 1960 | IBM 7070 | 10 d | w | w | w | w, d | 2 d |
| 1960 | PDP-1 | 18 b | w | — | w | w | 6 b |
| 1961 | IBM 7030 (Stretch) |
64 b | 1b, ... 64b, 1d, ... 16d |
w | ½w, w | b, ½w, w | 1 b, ... 8 b |
| 1961 | IBM 7080 | n d | 0d, ... 255d | — | 5d | d | 1 d |
| 1962 | UNIVAC III | 25 b, 6 d | w, 2w, 3w, 4w | — | w | w | 6 b |
| 1962 | Autonetics D-17B Minuteman I Guidance Computer |
27 b | 11 b, 24 b | — | 24 b | w | — |
| 1962 | UNIVAC 1107 | 36 b | 1/6w, ⅓w, ½w, w | w | w | w | 6 b |
| 1962 | IBM 7010 | n d | 1d, ... | — | d, 2d, 6d, 7d, 11d, 12d | d | 1 d |
| 1962 | IBM 7094 | 36 b | w | w, 2w | w | w | 6 b |
| 1963 | Gemini Guidance Computer | 39 b | 26 b | — | 13 b | 13 b, 26 b | — |
| 1963 (1966) |
Apollo Guidance Computer | 15 b | w | — | w, 2w | w | — |
| 1963 | Saturn Launch Vehicle Digital Computer | 26 b | w | — | 13 b | w | — |
| 1964 | CDC 6600 | 60 b | w | w | ¼w, ½w | w | 6 b |
| 1964 | Autonetics D-37C Minuteman II Guidance Computer |
27 b | 11 b, 24 b | — | 24 b | w | 4 b, 5 b |
| 1965 | IBM 360 | 32 b | ½w, w, 1d, ... 16d |
w, 2w | ½w, w, 1½w | 8 b | 8 b |
| 1965 | UNIVAC 1108 | 36 b | 1/6w, ¼w, ⅓w, ½w, w, 2w | w, 2w | w | w | 6 b, 9 b |
| 1965 | PDP-8 | 12 b | w | — | w | w | 8 b |
| 1970 | PDP-11 | 16 b | w | 2w, 4w | w, 2w, 3w | 8 b | 8 b |
| 1971 | Intel 4004 | 4 b | w, d | — | 2w, 4w | w | — |
| 1972 | Intel 8008 | 8 b | w, 2d | — | w, 2w, 3w | w | 8 b |
| 1972 | Calcomp 900 | 9 b | w | — | w, 2w | w | 8 b |
| 1974 | Intel 8080 | 8 b | w, 2w, 2d | — | w, 2w, 3w | w | 8 b |
| 1975 | ILLIAC IV | 64 b | w | w, ½w | w | w | — |
| 1975 | Motorola 6800 | 8 b | w, 2d | — | w, 2w, 3w | w | 8 b |
| 1975 | MOS Tech. 6501 MOS Tech. 6502 |
8 b | w, 2d | — | w, 2w, 3w | w | 8 b |
| 1976 | Cray-1 | 64 b | 24 b, w | w | ¼w, ½w | w | 8 b |
| 1976 | Zilog Z80 | 8 b | w, 2w, 2d | — | w, 2w, 3w, 4w, 5w | w | 8 b |
| 1978 (1980) |
Intel 8086 (w/Intel 8087) |
16 b | ½w, w, 2d (w, 2w, 4w) |
— (2w, 4w, 5w, 17d) |
½w, w, ... 7w | 8 b | 8 b |
| 1978 | VAX-11/780 | 32 b | ¼w, ½w, w, 1d, ... 31d, 1b, ... 32b | w, 2w | ¼w, ... 14¼w | 8 b | 8 b |
| 1979 | Motorola 68000 | 32 b | ¼w, ½w, w, 2d | — | ½w, w, ... 7½w | 8 b | 8 b |
| 1982 (1983) |
Motorola 68020 (w/Motorola 68881) |
32 b | ¼w, ½w, w, 2d | — (w, 2w, 2½w) |
½w, w, ... 7½w | 8 b | 8 b |
| 1985 | Intel 80386 | 32 b | ½w, w, 2d w, 2w, 4w |
2w, 4w, 5w, 17d | ½w, w, ... 7w | 8 b | 8 b |
| 1985 | ARM1 | 32 b | w | — | w | 8 b | 8 b |
| 1985 | MIPS | 32 b | ¼w, ½w, w | w, 2w | w | 8 b | 8 b |
| 1989 | Motorola 68040 | 32 b | ¼w, ½w, w, 2d | w, 2w, 2½w | ½w, w, ... 7½w | 8 b | 8 b |
| 1991 | Alpha | 64 b | ¼w, ½w, w | w, 2w | ½w | 8 b | 8 b |
| 1991 | Cray C90 | 64 b | 32 b, w | w | ¼w, ½w, 48b | w | 8 b |
| 1991 | PowerPC | 32–64 b | ¼w, ½w, w | w, 2w | w | 8 b | 8 b |
| 2000 | IA-64 | 64 b | 8 b, ¼w, ½w, w | ½w, w | 41 b | 8 b | 8 b |
| 2002 | XScale | 32 b | w | w, 2w | ½w, w | 8 b | 8 b |
| Year | Computer Architecture |
Word Size w |
Integer Sizes |
Floating Point Sizes |
Instruction Sizes |
Unit of Address Resolution |
Char Size |
| key: b: bits, d: decimal digits, w: word size of architecture, n: variable size | |||||||
|
|||||||||||||||||||||||