Integer arithmetic requires much less silicon real estate to implement than calculations on values that had a fractional component. Intel off-loaded the hardware to perform those instructions to a co-processor -- a support chip devoted solely to that task. Computers could be equipped with an 80286, and without an 80287. If the 80287 were present floating point instructions would be off-loaded and executed relatively quickly, by the 80287.
Other chips which were lineal ancestors to the Pentium family of computer chips, the intel 80186 and the intel 80386, had a companion floating point co-processor manufactured to accompany it. Intel was to market an intel 80487. But it was not a separate chip, different from the intel 80486.
- Advanced Micro promotes its power-saving answers to intel 80287 in the UK, Computer Business Review, 1990-08-22. Retrieved on 2008-11-27. mirror
- intel 80287: Technical Specification. Retrieved on 2008-11-27. mirror
- Omar Alvarado, Thomas J. Fellers, Michael W. Davidson. Intel 387 Math Coprocessor, Olympus Micro. Retrieved on 2008-11-27. mirror
- Intel and Floating Point: Updating One of the Industry’s Most Successful Standards, intel. Retrieved on 2008-11-28.