No announcement yet.

After ~70% FPS Boost For Zink, The OpenGL-on-Vulkan Code Is ~50% The GL Native Speed

  • Filter
  • Time
  • Show
Clear All
new posts

  • #41
    Hasn't microcode always existed? and microcode or otherwise, processors doing slow ass integer division etc. until a new one does it much better.


    • #42
      Originally posted by mangeek View Post

      I believe this started back in the 1990s with the Pentium Pro/i686. My recollection was that the i586 and below were straight-up CISC processors, but the i686 sort of decoupled things and -emulated- a CISC CPU in microcode while everything really ran on a RISC-ish core with microcode.
      Cyrix 6x86 was good at that little game too while not being i686 compliant at all. (Cyrix 5x86 is a cut down variant of the 6x86 CPU). Might be recognized as i486 level of instructions support even.
      AMD K5 is another one, it suffered delays so it's not much remembered. AMD bought a competitor's design to make the K6 and so they pulled the plug. I'm sure I would have liked playing quake and duke on the K5.


      • #43
        I suspect if it continues to get faster it might actually exceed native performance on some drivers in some applications. At this point, writing the OpenGL driver might become redundant.

        That said, there will always be application specific variations in speed, so I doubt it will ever reach the case of running faster 100% of the time over a highly optimized hardware OpenGL driver, even if it reaches the point of "slightly faster in many cases" which would be enough to stop producing OpenGL drivers for newer cards, or to ditch Compatibility mode support and support for OpenGL versions before OpenGL 3.0 FC (Core Context implied).