128-bit
| N-bit processors | |||||
|---|---|---|---|---|---|
| 4-bit | 8-bit | 16-bit | 32-bit | 64-bit | 128-bit |
| N-bit applications | |||||
| 16-bit | 32-bit | 64-bit | |||
| N-bit data sizes | |||||
| 4-bit | 8-bit | 16-bit | 32-bit | 64-bit | 128-bit |
| nibble | byte octet | word | dword | qword | |
| These definitions are current in the x86 world. See linked articles for discussion of the meaning in other architectures. | |||||
In computer science, 128-bit is an adjective used to describe integers, memory addresses or other data units that are at most 128 bits wide, or to describe CPU and ALU architectures based on registers, address buses, or data buses of that size. There are currently, no mainstream processors built to facilitate 128-bit instruction sets and operations, as 128-bit requires a buffer memory size and throughput width, double the size of 64-bit processors, and 128-bit capable processors far exceed practical needs. 64-bit processors today suffice more than enough. System/370, made by IBM is possibly considered the first rudimentary 128-bit computer as it used 128-bit floating point regiters.
128-bit processors may become prevelant when 64-bit processors become 'outdated' in terms of power and arithmetic capability. Most supercomputers are comprised of either many 32-bit processors or 64-bit processors linked together, with instructions being executed simultaneously across those processors. Many servers today or high-end workstations comprise of mostly more than one single CPU. 128-bit processors may be able to dispose of this 'dual-processor' attribute on most computers and provide adaquete processing power without the need of another co-processor, thus reducing power consumption and heat.