Abstract
This chapter discusses the operation of the floating-point unit (FPU). It reviews the basics of FPU operation. The 8087 family includes the floating-point coprocessors, 8087, 80287, and 80387, and the floating-point units in the 486 and Pentium. All these are referred to as the FPU in the chapter, even though this term is technically correct only for the 486 and Pentium. The FPU has a stack architecture. The chapter reviews the instruction for loading and storing data (FLD and FST), performing arithmetic calculations (FADD and FMUL), and controlling program flow (FCOM and FTST). The FPU stack is the register set for floating-point programming. It is helpful to trace the stack when first learning FPU programming and when performing complex operations. The Pentium FPU is much faster than the 486 FPU at basic arithmetic. This improvement is mostly because of better algorithms that reduce instruction cycle times and these gains are automatic. However, additional performance gains of significant magnitude can be realized with proper instruction scheduling and pipeline pairing. The benefits of these techniques are most obvious in loops with many iterations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
