In computer architecture, 32-bit integers, memory addresses, or other data units are those that are 32 bits (4 octets) wide. Also, 32-bit central processing unit (CPU) and arithmetic logic unit (ALU) architectures are those that are based on registers, address buses, or data buses of that size. 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, 32-bit era, 16-bit, 16-bit application, 64-bit