R10000 Design Innovations

  • Floating-point processing done on one chip

  • Ability to process up to four instructions out of order to any two-integer, two-floating-point, one-load/store unit

  • Dynamic register renaming which allows speculative execution of predicted branches using "false" registers which can later be kept or discarded

  • On-chip instruction cache which enables partial decoding of instructions when they are loaded from memory into cache
Hide comments

Comments

  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Publish