Summarizer

HBM vs Consumer DRAM

Technical discussion of high-bandwidth memory prioritization over general-purpose DRAM, AMD's historical HBM GPUs like Radeon VII and Vega, and why consumer electronics suffer from HBM focus

← Back to The RAM shortage could last years

The aggressive shift in manufacturing priority from consumer DRAM to High Bandwidth Memory (HBM) has created a significant supply crunch, leaving sectors from automotive to mobile computing starved for memory as manufacturers chase lucrative AI contracts. While historical examples like AMD’s Radeon VII demonstrate that HBM was once accessible to mainstream consumers, the technology is now treated as an elite luxury because AI giants are willing to outbid traditional markets regardless of cost. This pivot is viewed by many as a precarious gamble, where lower wafer yields and the looming threat of an "AI bubble" burst could leave memory makers stranded if demand collapses before they can retool for general-purpose electronics. Ultimately, the discussion highlights a growing tension between the technical superiority of HBM for specialized hardware and the economic risk of neglecting the broader consumer ecosystem during a period of extreme market volatility.

29 comments tagged with this topic

View on HN · Topics
Ok so Samsung, SK Hynix and Micron do not have the capacity to meet demand. Also, what little capacity they do have they are allocating to HBM over DRAM. Based on my limited knowledge HBM can not be easily repurposed for consumer electronics. Translation: main street is cooked for the next 3-4 years. It doesn't stop there though. OpenAI is currently mired in a capital crunch. Their last round just about sucked all the dry powder out of the private markets. Folks are now starting to ask difficult questions about their burn rate and revenue. It is increasingly looking like they might not commit to the purchase order they made which kick-started this whole panic over RAM. Soo ... how sure are we that the memory makers themselves are not going to be the ones holding the bag?
View on HN · Topics
The Radeon VII came out in 2019 as a $700 consumer GPU with an 1TB/s HBM2 memory subsystem which is more than any consumer GPU you can get today, including the high-end ones afaik. At that point in time, there was a whole lineup of AMD GPUs with HBM going down into the midrange. If they could make this stuff and sell it to regular people a decade ago for very palatable prices, why do they come up with the idea that this is the technology of the gods, unaffordable by mere mortals?
View on HN · Topics
> why do they come up with the idea that this is the technology of the gods, unaffordable by mere mortals? because the gods want it all and are willing to pay top dollar.
View on HN · Topics
Yes, it's interesting that HBM was invented by a collaboration between AMD and SK Hynix. It seems, HBM is the way to go for GPUs, anyway. The GB202 die that's in the GDDR7 based RTX 5090 and RTX 6000 Pro literally needed to be this big to support the 512bit memory bus. It's probably only getting worse with smaller node sizes. (see https://www.youtube.com/watch?v=rCwgAGG2sZQ&t=65s ). BTW: The 1TB/s is matched by RTX4090 and surpassed by the RTX5090 (1,79 TB/s).
View on HN · Topics
I have been wondering this recently. It was the convention that if you wanted to keep costs down, try to keep the memory bus size down as low as possible. Still remember the awful Radeon 9200 SE - 64bit data bus that strangled an already slow GPU. Heck, I have a phone with a 16bit memory bus for instance. The high(ish) clock rate only makes up the difference slightly. But with general prices on all components going up, it might not be such a big factor any more. HBM migght make sense for higher end products which can free up space for the lower end that will never use the tech.
View on HN · Topics
I was gonna say, I still use an AMD Vega that uses HBM2.
View on HN · Topics
Vega was a card with decent perf/$ for the consumer, but from a pure technical point of view (perf/mm2, perf/BW, perf/W) it was a major failure. Both Vega (and Fiji before it) showed that excess memory BW alone is not sufficient to win.
View on HN · Topics
And the bottleneck at the time was HBM interposers, not actual ram dies.
View on HN · Topics
But wouldn’t you rather hbm prices come down first ? Memory makers will be fine. There is practically infinite demand. Unless you get china style rationing of compute per person world wide. The real issue is everyone wanting to upgrade to hbm, ddr5, and nvme5 at the same time.
View on HN · Topics
What kind of consumer electronics can you build with HBM? That's the startup you should be founding...
View on HN · Topics
AMD has built some consumer GPUs in the recent past with HBM - RX Vega and Radeon VII (although I assume not all "HBM" is created equal).
View on HN · Topics
Isn't their APU also capable of doing HBM? There was an Intel AMD hybrid chip that used unified a while back too.
View on HN · Topics
That was not unified. It was just on same package. Functionally it was like if you had a dedicated gpu.
View on HN · Topics
My vega 56 still has 400gb/s of memory which is still insane for how old the card is.
View on HN · Topics
AMD's Hawaii architecture had 320GB/s on a 512b GDDR5 bus in 2013. The Fiji XT architecture after it had 512GB/S on a 4096b HBM bus in 2015. The Vega architecture did have 400GB/s or so in 2017, which was a bit of a downgrade.
View on HN · Topics
Anything where there's _at worst_ solder and traces between the compute and the memory. That's why you see it on GPUs (and Apple hardware). DRAMs advantage is modularity. At least as I understand it.
View on HN · Topics
HBM is just normal DDR RAM that's been packaged with (much) wider-than-usual data buses. That's where the high bandwidth comes from, not from high clock rates or any other innovation or improvement in core specifications. Very few applications other than GPUs need HBM.
View on HN · Topics
They can just switch back to normal DRAM if HBM demand drops, you ain't getting it cheap just coz AI flops
View on HN · Topics
> Based on my limited knowledge HBM can not be easily repurposed for consumer electronics. Translation: main street is cooked for the next 3-4 years. It's worse. HBM have lower yields so they are essentially making less GB per wafer too
View on HN · Topics
And how is that a problem and more importantly how's that a problem of Average Joe? Capitalists did their gamble things. If they fail in that gamble what forbids them to sell the regular RAM they made for AI bubbleists to the regular consumers? Besides HBM it's just the regular chips which are exactly the same for the consumer/server market, why it would be any different?
View on HN · Topics
There's actually plenty of demand for LPDDR even in the AI datacenter, because HBM is quite wasteful of area for any given memory capacity.
View on HN · Topics
Wafer area?
View on HN · Topics
Yes, HBM requires more wafer area for the TSVs and maybe some other features.
View on HN · Topics
not all DRAM capacity can switch to HBM quickly. That lag is where volatility comes from
View on HN · Topics
It's not going to last until 2028, it'll last until 'min(AI_bubble_burst, 2028)', which I expect will be a lot smaller than just '2028'. So the real question is, how long will it take to retool for non-HBM, and will there be a fire sale as they scramble to recover? Which also explains why production is falling behind demand, companies aren't going to sink billions into creating product for a market that could dry up overnight.
View on HN · Topics
It’s not merely a “gaming vs data center“. There’s so many other places DRAM and NVM are needed - mobile, automotive, other consumer electronics,… the current situation is that _all_ of that is deprived of the memory that it needs. And much of this is critical to the real economy.
View on HN · Topics
Why are you only talking about gamers? Apple, the most cautious planners in the whole industry have straight up cancelled their 512gb RAM Mac Studio. Don’t ask; they won’t sell you one. Everybody’s getting pinched, not just the gamers.
View on HN · Topics
I've read that the chip manufacturers are looking into high bandwidth flash for on package storage of ai models. That would solve some of the cost issue, flash is significantly cheaper than dram.
View on HN · Topics
This is simple extrapolation from current demand, nothing more. And that's a borderline silly analysis because it assumes the AI bubble won't burst. The great misadventure in the Persian Gulf probably accelerates that because we're almost certainly going to be facing a recession. Another thing I've been thinking about is what happens when the next generation of NVidia chips comes out? I suspect NVidia is going to delay this to milk the current demand but at some point you'll be able to buy something that's better than the H100 or B200 or whatever the current state-of-the-art for half the price. And what's that going to do to the trillions in AI DC investment? I'm interested when the next bump in DRAM chip density is coming. That's going to change things although it seems like much of production has moved from consumer DRAM chips to HBM chips. So maybe that won't help at all. I do think that companies will start seeing little ot no return from billions spent on AI and that's going to be aproblem. I also think that the hudnreds of billions of capital expenditure of OpenAI is going to come crashing down as there just isn't any even theoretical future revenue that can pay for all that.