48-bit computing
 | This articleneeds additional citations forverification.(August 2007) |
| Computer architecture bit widths |
|---|
| Bit |
| Application |
| Binary floating-pointprecision |
| Decimal floating-pointprecision |
Incomputer architecture,48-bitintegerscan represent 281,474,976,710,656 (248or 2.814749767×1014) discrete values. This allows anunsignedbinary integer range of 0 through 281,474,976,710,655 (248− 1) or asignedtwo's complementrange of −140,737,488,355,328 (−247) through 140,737,488,355,327 (247− 1). A 48-bitmemory addresscan directly address every byte of 256terabytesof storage. 48-bit can refer to any otherdataunit that consumes 48bits(6octets) in width. Examples include 48-bitCPUandALUarchitecturesthat are based onregisters,address buses,ordata busesof that size.
Word size[edit]
Computers with 48-bitwordsinclude theAN/FSQ-32,CDC1604/upper-3000 series,BESM-6,FerrantiAtlas,PhilcoTRANSAC S-2000andBurroughs large systems.[a][b]
The HoneywellDATAmatic 1000, H-800, theMANIAC II, theMANIAC III, theBrookhaven National LaboratoryMerlin,[1] thePhilco CXPQ, theFerranti Orion, theTelefunken Rechner TR 440, theICT 1301, and many other early transistor-based and vacuum tube computers[2] used 48-bit words.
Addressing[edit]
TheIBM System/38,and theIBM AS/400in itsCISCvariants, use 48-bit addresses.
The address size used inlogical block addressingwas increased to 48 bits with the introduction ofATA-6.TheExt4file system physically limits the file block count to 48 bits.
The minimal implementation of thex86-64architecture provides 48-bit addressing encoded into 64 bits; future versions of the architecture can expand this without breaking properly written applications.
The media access control address (MAC address) of anetwork interface controlleruses a 48-bit address space.
Images[edit]
In digital images, 48 bits per pixel, or 16 bits per each color channel (red, green and blue), is used for accurate processing. For the human eye, it is almost impossible to see any difference between such an image and a 24-bit image,[citation needed]but the existence of more shades of each of the three primary colors (65,536 as opposed to 256) means that more operations can be performed on the image without risk of noticeablebandingorposterization.