Recent content by maddie

  1. M

    Discussion RDNA4 + CDNA3 Architectures Thread

    But you repeat yourself.
  2. M

    Discussion RDNA 5 / UDNA (CDNA Next) speculation

    IC was used effectively even when NVIDIA was also on GDDR6. I don't think cache can reduce the need for "amount of VRAM". It amplifies bandwidth, so allows a smaller bus width. We should remember, the space needed for memory controllers is reduced, so this needs to be factored in the total...
  3. M

    Discussion RDNA 5 / UDNA (CDNA Next) speculation

    True, but almost certainly not abandoning IF caching schemes. GDDR7 alone cannot replace the bandwidth amplification of a large cache.
  4. M

    Discussion RDNA 5 / UDNA (CDNA Next) speculation

    Nah. The bus/CU ratio is the same as RDNA4. They will probably need even better caching schemes to handle the expected improvement in instruction throughput execution rate.
  5. M

    Discussion Leading Edge Foundry Node advances (TSMC, Samsung Foundry, Intel) - [2020 - 2025]

    One nice thing with FELs is the tunable nature of the radiation.
  6. M

    Question Zen 6 Speculation Thread

    How do anyone here determine what is a realistic speed? Historical norms? Physical fundamentals of the node? This is how it has been and thus will always be, AKA faith? Any room for a new approach? These debates remind me of the time when IPC was relatively stagnant following the Haswell...
  7. M

    Question Zen 6 Speculation Thread

    I guess we should be thankful we live in an optimal world.
  8. M

    Discussion RDNA4 + CDNA3 Architectures Thread

    Where did the "busted" 7600 go?
  9. M

    Discussion Nvidia Blackwell in Q1-2025

    Have any noticed this? Heaven help us, we have RTX 5060Ti 16GB widely available at the "false" MSRP. Is the GPU market imploding? Pity those companies that "must" be losing money at present.
  10. M

    Discussion Leading Edge Foundry Node advances (TSMC, Samsung Foundry, Intel) - [2020 - 2025]

    My condolences. As a person older than you, I've seen many friends descend into nostalgic episodes similar to this. It's a one way ticket my friend. :)
  11. M

    Discussion Leading Edge Foundry Node advances (TSMC, Samsung Foundry, Intel) - [2020 - 2025]

    What does this have to do with "How is it viable commercially to take large fixed cost of designing cutting edge stuff and only go for low volume?" Having lots of capital doesn't mean you waste it. That's a fool's behavior, and it's what made Intel throw away accumulated earnings by chasing...
  12. M

    Question Zen 6 Speculation Thread

    Improving this can allow a longer, higher frequency pipeline, without increasing misprediction penalties.
  13. M

    Question Zen 6 Speculation Thread

    Nope, I stated a historical fact. I don't know about future IPC increases, and admit it. Back in the day, when Intel was king, I repeatedly asked if there was some theoretical limit to IPC, and was given the same answer as you do now. "It's hard from here to get significant IPC increases."...
  14. M

    Discussion Leading Edge Foundry Node advances (TSMC, Samsung Foundry, Intel) - [2020 - 2025]

    That is a much bigger psychological problem than most assume, and generally leads to poor outcomes.
  15. M

    Question Zen 6 Speculation Thread

    Maybe you do research in advanced CPU architectures, but unless you do, this is merely your opinion.