A major architectural mistake was that both integer instructions and floating-point instructions used the same register file.

The floating-point instruction could, in turn, combine a floating-point add and multiply in a single instruction.

The R5000 could simultaneously issue an integer and a floating-point instruction.

The latter has three subunits for simple integer, complex integer and floating-point instructions.

The R8010 executed floating-point instructions provided by an instruction queue on the R8000.

The floating-point operate format is used by floating-point instructions.

The E Box executed all instructions, including floating-point instructions through microcode.

The Fbox is responsible for executing floating-point instructions.

All floating-point instructions except for divide have four-cycle latency.

Of course, the addition of floating-point hardware meant the addition of floating-point instructions.