32-bit

In computer science, 32-bit is an adjective used to describe integers that are at most 32 bits (4 octets) wide, or to describe CPU architectures based on registers, address buses, or data buses of that size.

The term "32-bit" can be used to describe the size of any of the following:

• A data unit.
  • A 4-bit unit (a hexadecimal digit) is called a nibble or nybble.
  • An 8-bit unit is called an octet (or a byte).
• A CPU's registers used to hold memory addresses and other data, as well as the ALU that operates on those registers.
  • Data units of that size are called words.
  • A 32-bit CPU can process 32 bits at a time.
• Memory addresses.
• Data transferred on each read or write of the memory.

32-bit is also a term given to a generation of computers, during which time 32-bit processors were the norm.

The range of integer values that can be stored in 32 bits is 0 through 4294967295, or -2147483648 through 2147483647 using two's complement encoding. Hence, a processor with 32-bit memory addresses can directly access 4GB of byte-addressable memory.

The external address and data buses are often wider than 32 bits but both of these are stored and manipulated internally in the processor as 32-bit quantities. For example, the Pentium Pro processor is a 32-bit machine, but the external address bus is 36 bits wide, and the external data bus is 64 bits wide.

See also: 32-bit application, History of video games (32-bit era), 16-bit, 16-bit application, 64-bit