Hacker News

The author clearly wasn't implying that these were 1GB chips. They just wanted to show a graph scaled per unit of memory. It could just as well have been per byte, and the graph would've been identical but the values on the left would be changed by a factor of a billion.

You could argue that you'd rather see a "price per typical-sized RAM chip as sold at the time". That would also be a perfectly valid thing to graph (though a bit more subjective), but it doesn't invalidate this one. Since per byte (or GB or whatever you want to say) has continued downward all this time, it makes the recent spike all the more notable.

(I'm not sure it's right to label vacuum tubes and core memory as "DRAM" though.)

> adjusting those 1960-1980 prices for inflation would make the graph a lot taller.

It won't though. One dollar in 1960 is just about ten dollars today. The graph is already in logarithmic scale so it won't make much difference.

I wouldn't go so far as to say "nobody". Electric Boat had 2 GB memory in one of its systems at that time, with the hardware capacity to increase to 4 GB. It sounded insane at the time, but it absolutely existed, and thereby seems reasonable to include it in any research of historical pricing.

I once held in my hand the main part of a ferrite core memory module from the early 70s. It was kilobytes at best.

I also recall looking at recommended requirements for Dungeon Keeper 2 - 266MHz CPU, 64MB RAM and thinking "that's absurd - no such device exists!". I was a kid back then, so what did I know?

Later on in college a friend showed us his absolute monster of a laptop with a whopping 8GB of RAM - he could spin up several VMs on one device! Groundbreaking on a (nominally) portable device.

So yeah, safe to say the notion of gigabytes of RAM anywhere close to a regular person belongs firmly to the 21st century.

Yes, you really need "dollars per amount of RAM you need for standard computing tasks." Windows 11 requires a bare minimum of 4 GB of RAM, Window 10 only needed 1 GB.

The graph wouldn't be a lot taller because it's using a logarithmic scale

Back then was it 1000KB or 1024KB?

The Cray-2 had 2GB of RAM in 1985.

Also maybe you want price per average program footprint size...

IIRC the Cray 2 was offered in a 1GB configuration by the mid 80s.

There’s been a sharp divergence in memory requirements. Talk to developers and they think that 32GB is the bare minimum these days, with 64GB or more preferred. They’ll point to Electron and Chrome tabs and everything else.

Then you sit down with an average computer user on their 8GB RAM MacBook Neo and they’re in love with how fast and smooth it is, even with their chrome tabs and the company Slack up and Spotify in the background.

I still have an older 8GB machine to kick around with on the go when I don’t want to haul the expensive laptop. It’s fine, even for a lot of development.

I think it would be better if one has the discipline to just use older machines and play older games and only visit certain websites that can be visited on older version of browsers. A second-hand 16GB laptop can go a long way.

But yeah that probably sucks from time to time, especially for young people.

Memory prices per GB were cheaper in 2012.

It’s possible we’ll see a huge price drop on the near term but SSD + Cache + GPU’s seems to have changed the equation where RAM speed is considered more important than size. And from a pure architecture standpoint it makes sense.

> while the upfront cost to scale up production is huge, prices are now high enough to justify it even if demand is expected to drop abruptly later on.

Given the nature of the industry and how critical the product is I think it would make more sense for governments to bankroll fab construction in a way that the public takes on the risk of consumer prices falling below a certain level within some limited timeframe. Mildly subsidized chip production seems like a much better downside than the current sky high prices.

The dataset about memory prices now has a memory preservation problem. Very meta.

Memory semis are a classical example of a cyclical industry: simulaneous capacity investments -> overproduction -> price crash -> ...

This cycle is the first one than truly breaks the trend. It seems that the industry NEVER needed thus nuch memory for this long.

Also, given the history, producers are afraid to overivest, and newer players from china are lagging behind for now.

Cyclical industries are very common.

Can you blame Moore's Law ending? The graph at https://en.wikipedia.org/wiki/Moore's_law looks steady up to the 2020s.

1979 to 2009 in the OP graph has a pretty steady drop from 10^7 to 10^1 USD/GB: 6 OOMs in 30 years. Then till before the recent spike it was around 1 OOM in 15 years: 1/3 the rate of progress on a log scale.

When it comes to CPU progress we blame the end of Dennard scaling several years before the knee in this memory curve. I'd guess the story of memory is similar in also hitting technical difficulties, but I don't know.

Moore's law didn't end in any broad sense and certainly not that far back. It's a tiring piece of misinformation that just won't die.

Progress has consistently become more difficult (ie more expensive) but has generally kept up. The scaling of a couple specific technologies noticably slowed down a few years back but that's not the general case.

The node names aren't representative of the reality.

Drawing a line backward from today's high water mark only goes back to 2018.

2010 prices were significantly higher.

The chart is also not inflation adjusted, which would bring the equivalent date forward even further.

Nowhere near a 16 year regression.

Nominal. The inflation-adjusted price today is 2/3 of what it was then.

sure but you also need more gb these days for various tasks so it's not 1:1

I wonder if developers will start trying to do more with less in certain areas

>it also enables software that was not possible before

Which is not always a good thing.

DRAM hit a barrier at 10 nm a few years ago[0], so 16 nm is actually even closer to state-of-the-art. E.g. Micron newest node (1-γ) is their sixth at 10 nm [1] and their first EUV-based node.

The problem is that DRAM is fundamentally based on storing charge in a capacitor and how much charge a capacitor can store is a result of the geometry of the capacitor. So either someone will have to figure out a way to make the same size capacitor take up less space on the RAM chip (this is what broke the previous 20 nm barrier) or someone will have to invent a practical way of making RAM with less than 1 capacitor per bit.

0: https://semiengineering.com/dram-scaling-challenges-grow/

1: https://www.techpowerup.com/333111/micron-announces-shipment...

what makes you think China RAM makers will sell their chips at the old memory prices and not just 10% below the current market price

Yeah but now apps will have to start shaving off memory and maybe going native again. So it'll end up okay.

Except you didn't when you consider the prices aren't adjusted for inflation.

The truly absurd part is that datacenters are barely being built and those that are built can't be turned on because they don't have enough power. Satya Nadella admitted recently that they have warehouses full of unused hardware because they a) can't get datacenters built and b) don't have enough power i.e. this whole RAM scandal is a bloody joke. If OpenAI goes bust (their financials are a huge mess and lots of red flags - they might not even survive to IPO!) and then what will happen to all those "inked" deals to buy all that RAM?

This post had me wracking my brain asking, "Did any of Gibson's books have someone get mugged for some hot RAM?"

Edit: Actually Johnny Mnemonic had 325MB in his head and he had the whole Yakuza out to kill him.

If you care about only capacity and cost yes, but not if you care about performance.

If it were possible, it would have been done already. The issue is the capacitors are already tiny, and barely can prevent a single bit decaying before refresh.

Which manufacturers quickly thereafter put to an end:

https://en.wikipedia.org/wiki/DRAM_price_fixing_scandal

Only if you're buying DDR3 now, DDR4 and DDR5 are both more expensive than the 2017 peak.

We're paying more now than we paid in the late 2010s, but less than we paid in the early 2010s.

But relative usefulness is entirely subjective, making it a meaningless unit. Depending on your use case you may need 256 GB or 0.5 GB.

The audience who would benefit from hypothetical $/usefulness would be people who don’t know what memory is and don’t know what’s inside of their computers, or what it does. This is a fine audience to be in and to serve, but obviously not the audience of that website and not HN.

If you think that audience is under served for memory market statistics, I encourage you to make such a website and serve that audience.

For people on HN, who do you know what memory is, $/GB is a fine metric.

> The unit needs to be tied to the relative usefulness for its time.

That requires baking in assumptions, and makes the data less general.

You can go from $/gb to $/usefulness fairly trivially by adding assumptions, but you can't go the other way.

A useful task isn't a fixed thing though. Everything the 2012 computer did you can still do today with the same amount of ram we had back then.

Gas is priced in $/gal, not dollars per mile or hour of lawn mowing or whatever. The resource and the use are completely different concepts and the resource owner/producer cares not of the buyers purpose for it.

The line would look the exact same if you switched it to price per PB. Only the labels on the y-axis would change.

Going up is worse though because software has gradually got less and less memory efficient.

So, it’s on a logarithmic scale

Let f(t) be the price of RAM per GB from 1960 to 2026. Let F(t) be the price of RAM per byte in the same period.

At every point in time t, f(t) is the price per 1 GB of RAM which is 1GB/1B times the price per byte of RAM.

Because 1GB/1B is non-zero, it follows that f(t)=1GB/1B F(t).

It also follows that ratios are preserved, ie

f(t1)/f(t2)= 1GB/1B F(t1)/F(t2)

As long as f(t2) is non-zero, which in this context is never the case.

Visually, the two graphs are the same except scale is different.

Likely your expectations are mismatched because this is just data and not an analysis.