Thread

Samsung is expected to more than double output of its HBM4 and HBM4E DRAM

562 points · 458 comments · giuliomagnifico

fooker · 1789929721 · focus · HN ↗
What's the main blocker (other than the current inflated cost) for using HBM instead of DRAM as the primary memory for consumer electronics?
1. nutjob2 · 1789930193 · focus · HN ↗
  Nothing except CPU manufacturer choices. Mac laptops use it and they're consumer products.
  People will have to get used to buying a fixed amount of RAM with their CPU but thats unlikely to be a problem.
  1. fooker · 1789930550 · focus · HN ↗
    Apple's "unified memory" marketing is so strong that even tech literate people seem to have this misconception!
    They have managed to pull this sort of thing off many many times. <a href="https://en.wikipedia.org/wiki/Reality_distortion_field" rel="nofollow">https://en.wikipedia.org/wiki/Reality_distortion_field
    Kon5ole · 1789932776 · focus · HN ↗
    Having unified memory is a real advantage though, it's not a reality distortion.
    davrosthedalek · 1789933697 · focus · HN ↗
    The price is that you essentially glue CPU and GPU together, which limits total compute, from a size and thermal perspective.
    This is really not a limit because of unified memory -- in principle, PCIe GPUs could read/write main memory without the CPU. But it's a limit for /fast/ unified memory, because fast means close.
    So unified memory is great as long as the integrated GPU is strong enough. Then it has two advantages: a) probably faster transfer CPU<->GPU (but that's an implementation choice for the non-unified case b) If you either need a lot of memory for the CPU or the GPU, but not for both at the same time, you pay for memory only once.
    nvme0n1p1 · 1789934004 · focus · HN ↗
    Agreed. That's why it's a good thing all computers made in the past 15 years have unified memory, not just macs.
    <a href="https://x.com/Lina_Hoshino/status/1820947147312820497" rel="nofollow">https://x.com/Lina_Hoshino/status/1820947147312820497
    stymaar · 1789935032 · focus · HN ↗
    Is that Marcan's vtuber persona (Asahi Lina) that changed name since Marcan doesn't work on Asahi Linux anymore?
    Kon5ole · 1789942029 · focus · HN ↗
    In theory perhaps but the benefit is not as relevant with a weak iGPU. In practice all PC's with performance ambitions had a dGPU until Strix Halo and Panther Lake.
    fooker · 1789934759 · focus · HN ↗
    It is a real advantage.
    The reality distortion is that people seem to believe it's HBM, or somehow it gives you extraordinary amounts of vram. Neither are really true.
    jorvi · 1789944284 · focus · HN ↗
    It isn't really, as long as you don't care about power consumption, physical constraints and money. Basically desktops <2025 (and hopefully >2027).
    DDR is optimized for latency and stability at the cost of bandwidth whilst GDDR is optimized for bandwidth at the cost of latency and stability. GDDR is pushed so hard these days that a small percentage of errors is expected and corrected because this is still faster than running it slower but more accurate.
    GDDR7 often has 10-20x the total bandwidth but 3x the latency of DDR5. Graphical workloads want as much bandwidth as possible but care relatively little for latency. Conversely, applications love low latency but don't really see any performance benefit from higher bandwidth.
    So basicallyt you have workloads that are diametrically opposed and running unified memory forces you to compromise.
    Melatonic · 1789979512 · focus · HN ↗
    Is GDDR7 that's ECC then just the super well binned stuff (plus the ECC parts added) ? I've been wondering why we don't see more cards using it as they perform pretty damn well. Take the Nvidia 6000 Pro Blackwell for example. The compute is insanely fast assuming you can fit what you need in 96GB of ECC GDDR7

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.