There are currently no mainstream general-purpose processors built to operate on 128-bit integers or addresses, though a number of processors do operate on 128-bit data. System/370, made by IBM, could be considered the first rudimentary 128-bit computer as it used 128-bit floating point registers. Most modern CPUs such as the Pentium and PowerPC have 128-bit vector registers used to store several smaller numbers, such as 4 32-bit floating-point numbers. A single instruction can operate on all these values in parallel (SIMD). They are 128-bit processors in the sense that they have 128-bit registers and in some cases a 128-bit ALU, but they do not operate on individual numbers that are 128 binary digits in length.

Uses

128-bit processors may become prevalent when 2⁶⁴ bytes of addressable memory is no longer enough; however, even if Moore's law were to apply to memory size in the years to come, it would still take a long time to exhaust a 64-bit address space. A doubling of memory capacity requires one extra address bit, so if large servers in 2006 can make use of 512 GB of RAM (thus requiring 39-bit addresses), then a 64-bit address space would be sufficient for another 50 years. Most supercomputers comprise many 32-bit processors or 64-bit processors linked together, with instructions being executed simultaneously across those processors.

IPV6 is 128 bits wide. Having a processor that can manipulate a 128 bit integer would be useful, since that way the destination IP address can be stored in a register, much as IPV4 is stored now. See also rfc1924 section 7.

128 bit