Floating point processor

A floating point processor or floating point unit was, until recently, an optional processor which allowed a computer to handle floating point numbers in hardware. (Now that CPU chips typically contain extremely large numbers of transistors, floating point is usually supported in them by default.). For a normal integer based CPU with a ALU ( Arithmetic Logic Unit ), Multiply instructions took many CPU cycles, because they had to be handled by repeated adds, ( similar to divides being handled by repeated subtractions ), FPUs could perform these operations in a few CPU cycles.

In early machines, the hardware involved was a complete extra set of printed circuit boards; later on, with the rise of microprocessors, it became an optional chip.

In architectural terms, it might be a co-processor, or on microcoded machines, it might be extra microcode, sometimes along with some additional hardware to speed up some aspects of the computation.

Very recently, GPU ( Graphic Processing Units) have been able to handle floating point operations needed for AI, games, rendering and other math intensive tasks.