Recent content by Dio

  1. D

    AMD: R8xx Speculation

    Any C++ program needs an operating system for a (normal) end-user to run it, surely?
  2. D

    Analyst: Intel's Larrabee chip needs reality check

    Sure, but back in the 1980s people didn't realise the days of making heavy revisions to the ISA were coming quickly to an end.
  3. D

    Analyst: Intel's Larrabee chip needs reality check

    Dunno. On the MIPS1 & maybe 2, when there was only a 3 or 4 stage pipeline then it's a significant contribution to keeping your pipelines full, and the whole raison d'etre of the MIPS project was to avoid spending money on silicon when you can spend it on software instead. By the time of MIPS...
  4. D

    Analyst: Intel's Larrabee chip needs reality check

    Proper DDBH is basically the ability to say "Next branch if r0 < r1" and then some cycles later take the branch. So you can retire the evaluation of the condition a long time before you take the branch and already know which way you're going. I thought MIPS had this, but I've been reading up...
  5. D

    Voodoo1 capabilities in the last Glide era

    Yeah, that was a lot of my experience as well. Great chip, but the motherboards were absolute bobbins. Then again looking back from today it's hard to believe the crud we used to put up with in MB and memory quality.
  6. D

    Voodoo1 capabilities in the last Glide era

    I reckon UT was earlier than you think - I was working on Unreal with Savage3D and UT with Savage4 (which were up against the Voodoo2 and 3 respectively, and were only around twice the performance of the original).
  7. D

    AMD: R7xx Speculation

    You're not the first and you won't be the last. I try to avoid thinking about that too much :D.
  8. D

    AMD: R7xx Speculation

    Wise words.
  9. D

    AMD: R7xx Speculation

    Remember that most of the time caches in GPUs are there for very different reasons for caches in CPUs. It's more about input/output streaming, latency compensation and bandwidth optimisation. Classic % hit rates just aren't relevant - miss with every access and it will still run at full rate...
  10. D

    AMD: R7xx Speculation

    You think? I disagree. If you look around at a modern game nowadays, the minimum spec is typically a 9700 or 9600, and the entire FX series is nowhere to be seen. But: - it still sold - it took a good six months before the web realised the mud was being slung - the paper press never really...
  11. D

    NVIDIA GT200 Rumours & Speculation Thread

    You're right. Which is why the cost of a chip is set almost entirely by a (relatively simple) function of die area, process type and product maturity. You can derive the formula easily: number of dies on a wafer; the yield, set by the defect rate ; costs of testing and packaging. The...
  12. D

    Monitors/Frame buffers and wasted bandwidth

    That's the typical case in the majority of 3D applications - which is exactly the time at which having the most bandwidth available is useful.
  13. D

    Why is John Carmack so revered?

    Go read his code. Then go read the code of just about everyone else in the industry. And there's his genius. It's compact as hell, does complicated things in what seems like a trivial manner, and a first-time C programmer could read and understand every single line. I'm sure some other...
  14. D

    New ATI Developer Tools

    Yes, that's basically right.
  15. D

    New ATI Developer Tools

    What, no questions on shader architecture yet? I'm disappointed in you guys! :)
Back
Top