Computer RAM gets biggest upgrade in 25 years but it may be too little, too late — LPCAMM2 won’t stop Apple, Intel and AMD from integrating memory directly on the CPU::LPCAMM2 is a revolution in RAM, but it faces an uphill struggle
Also, lots of users aren’t gonna want the main system memory on the CPU die. Aside from the fact that it creates a clear path for vendors to artificially inflate prices through pretended scarcity via product segmentation and bundles, it also prevents the end users from upgrading the machines.
I’m pretty sure this even goes against the stated goals of the EU in terms of reduction of e-waste.
I have no doubt that a handful of vendors cooperating could restrict their offer and force the hand of end users, but I don’t think this would be here to stay. Unless it provides such a drastic performance boost (like 2x or more) that it could be enough of an incentive to convince the masses.
Outside of DIY, end users don’t care. See: Apple.
Also, if you have a laptop with LPDDR5, it is soldered. If it has DDR5 or some variant of DDR4, it is likely also soldered as most OEMs did away with DIMM slots.
I don’t like or agree with the practice.
Even people who build their own computers usually buy all the RAM they want at the time that they’re building it.
The biggest difference to them is likely the feeling that they’re losing their ability to upgrade, more than the actual upgrade itself. I still think that feeling is an important factor, though.
Biggest difference is that defective RAM can cost you a lot more imo.
Yes, but statistically it’ll be caught during the return or warranty period, and then RAM failures are extremely rare after that.
Frame.work laptops have non soldered, upgradable DDR5 memory. In fact, you can buy a laptop with no memory and just buy it somewhere else and install it yourself.
Yeah, but it is regular DDR5, which is less power efficient.
I do love Framework, however. They are at the top of my list when I eventually upgrade my laptop.
Hopefully they give us CAMM2 modules with LPDDR5 at that point.
I always think of my old Asus eePc netbook from 2010 that had a special compartment that was accessible from outside without opening up the notebook itself, just so that users would be able to upgrade their RAM. How did times change from “help the user to get what he needs” to “help the user get what we need”. Personally I blame Apple for this tbh.
This is how this looked: http://images.bit-tech.net/content_images/2007/12/add_more_storage_space_to_your_asus_eee_pc/panel.jpg
And the best part: My son is using this netbook now with a light weight linux. I actually switched the RAM 2 month ago. It even plays Minecraft and he draws on it with my drawing tablet.
In the case of LPDDR5, we don’t have removable memory due to tight signaling requirements and the fact that the DIMM slots themselves take up too much space when populated.
LPCAMM2 solves this, so I hope it is widely adopted going forward because LPDDRR5 offers a huge upgrade over previous gen.
But even soldered ram isn’t as bad as in-cpu ram. Soldered ram can be replaced/upgraded by skilled technicians. I don’t think that’s possible at all with in-cpu ram.
Soldered ram can be replaced/upgraded by skilled technicians.
Ok i know it isn’t the point of your comment and i agree with the whole premise but who, i say who is soldering their own ram? I admit that it should be possible but the limited upgradeability imitations not to mention the skill you’d need… I say it puts soldered ram into the same echelon of “not upgradeable”
Can anyone speak to this? Am i wrong about the difficulty and hardware limits?
Exactly. Few people are willing to deal with the adhesive used in Macs and smartphones. Even fewer will deal with solder.
Yeah, I agree.
As for who those few are, well, I wouldn’t myself… probably… but I’d definitely like the option of taking my laptop to someone like Louis Rossmann who can do such work. He’s even shown that sometimes the ram gets destroyed by apples weird circuit designs and if it was just soldered on, the laptop and all your data would actually be salvageable.
Hmm, interesting. Thank you!
Yeah, but at least for now, we can still buy laptops with unsoldered RAM and storage.🤞
Besides, Apple is more of a cult than a tech company, so I am not convinced their customers should be taken as an example of a natural customer’s behavior.
And I agree that most users don’t care, although, this is mostly true in corporate environments, where computers have an expected lifespan of 3 years tops. In that case having the RAM soldered or not does not change anything, as the machine will get spec’ed according to what the company needs, and will get replaced before it ever reaches obsolescence.
For the end users, many still consider keeping a machine 5+ years, and if you check the average “long lasting” (~2k USD) machine from 5 years ago, it is an 8th gen i5 (4 cores, 8 threads) with 8GB of DDR4 and 256GB, or at best 512GB SSDs. Not that those are terrible specs by today’s standard, but the people who spent 2k on a machine back then will probably want to have at least 16G of RAM now. And 1TB SSDs. And if at all possible, more than 8 threads. Heck, I just got a workstation for 550 bucks that has a ryzen 7 with 16 threads…
And that’s where companies like framework come in. I advocate for them as much as possible, along with companies like system76 and purism. If we keep voting with our wallets for such companies, even if the CPUs becomes a SoC entirely, we will still get to have upgradability paths thanks the modularity of their laptops.
Edit: as expected, religious people got offended about me calling out their religion, thus proving my point. 🥲
Edit 2: don’t get me wrong, I’m not denying that Apple has a good tech stack (as a BSD lover, that would be silly), and that the Lemmy audience is likely aware of that too. But it is also abundantly clear that the overwhelming majority of the Apple customers have absolutely zero idea what makes their “must have” tech stand out, and are merely in for the cult part. If Apple would stop making sense technologically, it wouldn’t make the slightest difference to them.
The iPhone I’m currently on right now feels more like a piece of tech then a religious symbol but how would I know?
On CPU RAM does provide much faster performance. That’s the reason they are going that route.
It’s part of the reason why RAM was always placed close to the CPU on the motherboard anyway. The farther they are apart, the more time and energy is used to transfer data and instructions between them.
Right, it s a physics issue, not greed. I mean, they’re going to make a margin off of it for sure but that’s not the sole reason to do this.
Greed might not be the main driving force, but it’s absolutely there too. I predict on-cpu ram costing more than it should in the future due to lack of competition. (yes I know there aren’t that many manufacturers of the actual chips even today when the consumers can choose from many brands of ram sticks)
I’m imagining a world with desktops and laptops that have On-CPU-RAM and On-Motherboard-RAM with the traditionally slotted RAM acting as a swap for the On-CPU-RAM.
I mean, isn’t that in principle how old swaps traditionally work? They take up some space on your slower disk drive to “swap” data from RAM onto when out of RAM. On-Motherboard-RAM, since it’s slower than On-CPU-RAM, could achieve the same purpose, meaning limited On-CPU-RAM wouldn’t be as impactful.
Which makes a lot of sense as RAM speed is the one big bottleneck.
People who really care about computers buy handmade artisanal transistors.
I know you’re kidding, but: http://www.homebrewcpu.com/
wasnt there a guy who made his own GPU too?
Here is an alternative Piped link(s):
https://www.piped.video/watch?v=-vHwZhWoWkk
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I’m open-source; check me out at GitHub.
On CPU is definitely superior for performance, and what I’m not seeing people consider here is a future where you have On-CPU-RAM and On-Motherboard-RAM. CPU RAM for intense CPU functions, and traditionally seated RAM to be more like a modern “swap” I suppose, but instead of using the slower disks for swap, you’re just using slower RAM.
I could especially see this in Enterprise level hardware. I’m just saying, don’t throw the baby out with the bathwater. Por Que No Los Dos?
I know, I know, you can’t expect corporations to do squat to benefit the consumer, but one can hope.
Yeah, there is no way they’re gonna put 1TB of RAM on a CPU die anytime soon.
Does that mean that consumer hardware will include expandable RAM though? I feel like for the average person, that option still has a very high chance of disappearing on a lot of machines.
Oh yeah, a very high chance of disappearing. The unfortunate reality is probably 80% of people never upgrade their laptops or desktops. Building and maintaining your own PC has become more en vogue in recent years, but the vast majority of average consumers just don’t take part in the practice. Thus, it will not be prioritized by the industry. Why spend money on making your machines upgrade-able if the majority of users don’t ever take advantage of the feature?
I don’t like why it will happen, but I understand the economics of it.
Bro, it’s way higher than 80%.
I think most people don’t know the difference between “on-die” and “on-package”. This may be what they mean: https://beebom.com/intel-meteor-lake-cpu-on-chip-ram/
both techniques will obviously need to coexist for some time. they dont have logistics on large memory near the processor,. quite yet, so there is still a place for ram.
I’d argue that they do have the logistics down pretty well at this point as HBM3E can squeeze 144Gb onto a package.
That makes it sound like they’ll probably use software locks on one die to restrict RAM.
Downloadmoreram.com could become a reality!
Almost a zero percent chance that will happen as HBM is a stack of DRAM dies, capacity can be reduced by omitting additional dies. If the DRAM were directly integrated into the CPU’s die then maybe we could see software locks however historically that would be accomplished by physically laser cutting the traces (unless you are AMD and forget to with the K10.5)
deleted by creator
We already have memory wafers glued to our CPU wafers in the form of L3 cache. It’s lower latency, higher throughput, up to a few hundred MiB in bigger models and can potentially be used without external RAM sticks (but I’ve not heard of using that feature outside of BIOS firmware early boot – that’s probably the only change we’ll see). Sometimes it’s DRAM, sometimes it’s SRAM, its size varies quite a bit.
Wouldn’t RAM on die mean lower wafer yield?
This is about RAM on the package not RAM on the die. It honestly makes no sense why we don’t have CPUs and RAM soldered to the motherboard right next to the CPU package. I love being able to change the stuff myself, but any reasonable repair shop could be doing that for you and we can have much higher performance than we currently have. It’s not like there’s really many viable options anyways. AMD has what four good CPUs intel has like two, and there’s two good ram ICS.
Why would you think soldering would increase performance vs socketed at all much less provide “much higher performance”
If soldered was the only option ans 6 skud was enough for everyone everyone would have to buy very expensive hardware to increase one spec instead of smart people getting to mix match and upgrade.
The socket has big reductions in ram and pcie signal integrity. If you don’t plan to change the CPU and motherboard separately soldering it would save money and the store could do it for you when you order both together.
Because it’s true. Soldering the memory right next to the CPU allows us to run the memory at a lower voltage and faster clock rate, while getting lower latency too. The LPDDR4/5X are designed based around these improvements. GPUs have been doing this forever too for the same reasons. It’s a huge upgrade in every way except upgradability, which is effectively eliminated.
I’d like to see non-synthetic benchmarks showing real world performance increase in otherwise as close as possible to identical systems
Can it not just be socketed next to the CPU?
We seem to socket CPUs just fine.
On an ATX motherboard maybe, but there would be no space on a laptop or ITX board.
I get that this was primarily created to benefit laptops, but would it provide any advantage for desktops?
Yes, the laws of physics require that on-die RAM is markedly faster.
I get that, but is this on-die? It says that it is modular, so I interpreted that to mean that it was not on-die.
3d vcache would like to say hi
I already use a processor with integrated graphics
I know it’s standard for graphics to be integrated into a motherboard. Is that what you’re referring to? Because I’ve never heard of on-CPU graphics.
What?
Cpus have had integrated graphics for years… My 11 year old cpu has awful graphics that I try to turn off usually.
what sort of a rock did you crawl out of /s
Kiryu after getting out of prison mf up there💀
And has been doing it for years with the Ryzen G series chips. They have built in Radeon graphics chips. Not as powerful as a discrete GPU, but enough for a lot of people.
Question: modern systems can mount hundreds of GB or even terabytes of RAM, right? At this point, why not mount non-volatile storage as RAM? Performance should increase since data wouldn’t have to be loaded.
What you’re describing is the holy grail of computer memory technology. If we had nonvolatile memory as fast as RAM, we would absolutely be using it instead. Unfortunately even the fastest SSD today would be a significant drop in speed from modern RAM.
Would it be faster than loading gigabytes of data from an SSD over NVMe into RAM?
RAM is basically the scratch space for the CPU. It doesn’t just contain data loaded from the SSD, it contains the running state of the OS and all applications and is constantly being read from and written to by the CPU. As it is, RAM is already a lot slower than the CPU. Replacing RAM with a standard NVMe SSD would slow a PC down to an unusable crawl.
I’m familiar with what RAM is for.
The idea I’m getting at is, back in the day computer software especially video games came on ROM cartridges, which were little more than a plastic shell around a small circuit board that had a ROM chip or two, maybe a battery backed RAM chip to save game progress if you’re Nintendo. This ROM was attached to the same data bus on the CPU as the system’s built-in RAM, which meant the CPU could read from it just like RAM. This meant that cartridge-based systems didn’t need as much total RAM, because instructions, graphics, audio etc. were read directly from ROM, and it didn’t have to load instructions or graphics into memory before executing/displaying them. So no loading screens.
Modern computer SSDs are attached via SATA or at best the PCIe bus, and the CPU has to interact with a controller on the device to get data loaded into memory before it can be executed. Could you attach some non-volatile storage on the same bus with the RAM. Like, the average ATX motherboard has 4 RAM slots, right? Could you mount two sticks of RAM and two sticks of non-volatile storage that exists in the memory address space?
The simple answer your entire query is the fact that PCIe is not the bottleneck. The bus that connects your storage to the CPU is faster than any storage we have these days (ignore sata it doesn’t count). There is no innovation to be had with your suggestion, just complexity.
Now, there is something related to your suggestion. Graphics cards are exploring / have explored having storage communicate with them directly because of the latency in loading assets into the CPU then sending them to the GPU. This is where progress is being made on optimizing communication between storage and host.
deleted by creator
If you’re only loading data to access it once, then yes, but it almost never is the case - some specific programs might do it, but OS definitely caches pretty much everything it can in RAM for subsequent access - Linux, for example, fills unused RAM with cache
From the perspective of a computer engineer SSDs are painfully slow. Waiting for data on disk is slow enough that it is typically done by asking the OS for the data and having the OS schedule another process onto the CPU while it waits. RAM is also slow although not nearly as slow. Ideally you want your data in the L1 cache which is fast enough to minimally stall the CPU. The L2 and L3 caches are slower but larger and more likely to have the data you want. If the caches are empty and you have to read RAM your CPU will either do a lot of speculative execution or more likely stall.
Speculative execution on CPUs is a desperate attempt to deal with the fact that all memory access is slow by just continuing through the code as if you know what is in memory. If the speculative execution is wrong a lot of work gets thrown out (hopefully nothing unsound happens) and the delay is more noticable.
Bluntly an SSD only system would probably be an order of magnitude slower. I’m also not sure switching to a new process (or even thread) to load from SSD would be viable without RAM as it would likely invalidate a lot of cache triggering more loads.
Essentially we do. If you run out of RAM, you get pages from disk. You would know this if you ever used Windows ME.
This is the future of PC, but with soldered RAM: https://en.m.wikipedia.org/wiki/Slot_1
