So why cards?

[edward78]

You know the Motherboards with 2 CPU sockets, why not 1 withh a GPU socket (It would have to be Universal of course)? Just sell VRam & they would go in the slots. If it is more complex, tell me.

 

[El_Capitan]

Mostly because the GPU would have to be soldered in. If they made GPU's with pins and IHS's like CPU's, it could be a thing, but no one's done it, yet. I don't see why it couldn't be done.

 

[edward78]

Mostly because the GPU would have to be soldered in. If they made GPU's with pins and IHS's like CPU's, it could be a thing, but no one's done it, yet. I don't see why it couldn't be done.

I always thought so. It would be so nice too. Every home system could be a SFF. Like a NES size case might do it. Well prob. a little bigger. Wsih I had some influence with the right people. My brother in law use to work at a Apple store, but they would just patent it so that is out. I mean, ya we have APUs & iGPUs, but what if you are good with the CPU you have, or can't fiind 1 wuth the GPU you want?

 

[Eulogy]

People already complain about needing a new motherboard to jump CPU generations. Can you imagine having to deal with the complexity of
Intel + nVidia
Intel + AMD
AMD + nVidia (uhh)
AMD + AMD

matrix of boards and compatibility?

 

[LukeTbk]

You know the Motherboards with 2 CPU sockets, why not 1 withh a GPU socket (It would have to be Universal of course)? Just sell VRam & they would go in the slots. If it is more complex, tell me.

memory bandwith is a big one would be my guess, large amd APU could be the limit, 256 bits+ bus of gddr6 bandwith without soldering both the gpu and the memory is probably really hard to do.

With sockets and pins, every one of them become tiny antenna adding noise and with socket-memory slot you add distance has well, with the size/frequency gpu memory bus operate in you would need extreme high quality and size for socket to work.

A simple 5060 gpu has like 4.5 time the memory bandwith than a dual channel ddrt5-6000 9950x, epyc type system can do 5060 bandwith but they cost a lot with massive socket and expensive board versus an entry level gpu not the high end one, something that would support 5080 level would become quickly impraticable.

 

[cpufrost]

Not to mention power delivery. Think MSI Godlike boards are expensive?
A drop in GPU may be cheap but the price of the board itself would be crazy high.
Reminds me of the days of sockets/chipsets that worked on AMD/Intel/Cyrix/WinChip/ and others.

 

[Nobu]

They used to have the graphics on one of the chipsets, nvidia's geforce mobile graphics was pretty badass...for the time.

But GPUs get hella hot, hotter than CPUs (well, used to be), and they need a lot of memory (even still). There's just not enough real estate on most boards to accommodate all that. And if you wanted upgradable vram, that takes more space and adds latency...

 

[edward78]

They used to have the graphics on one of the chipsets, nvidia's geforce mobile graphics was pretty badass...for the time.

But GPUs get hella hot, hotter than CPUs (well, used to be), and they need a lot of memory (even still). There's just not enough real estate on most boards to accommodate all that. And if you wanted upgradable vram, that takes more space and adds latency...

Oh, ok. Would a little slot like te Pentium 2 went in be better for the GPU? The VRam would have slots like the Ram, so that is already good. So Nvidia's Arm will still need a bug fan for the RTX 5090 GPU, right?

 

[Nobu]

If you put it on a card, might as well use PCIe since it's already there, standard, and very fast. And since you have a card, might as well put memory on it.

Yes, most arm solutions solder everything to the board and have a big cooler that covers everything, I would expect a similar solution for nvidia/arm. There are some recent entries with PCIe slots, but they're more like dev boards than something you would really want as a PC/game system.

 

[LukeTbk]

Oh, ok. Would a little slot like te Pentium 2 went in be better for the GPU? The VRam would have slots like the Ram, so that is already good. So Nvidia's Arm will still need a bug fan for the RTX 5090 GPU, right?

Not soldered in vs soldered in is a big difference regardless of the socket format I think.

If an Nvidia arm cpu (or mediatek or Ampere arm cpu) use a 450w-600w 5090 gpu and if you add more power-heat by not having the ram soldered and farther away from the gpu, it will need even more cooling than what we see, the ISA used by the cpu will be irrelevant.

Yes, most arm solutions solder everything to the board and have a big cooler that covers everything, I would expect a similar solution for nvidia/arm.

It is more who use and for what they use ARM (apple-nintendo-nvidia, etc...they love coherent memory) than anything inherent, they can look like that, as regular computer board for regular computer has well:

Those nvidia with many gpu rack will also have individual gpu all individually cooled and are not soldered in for yield, ability to swap one that fail later on, the level of thermal expension tolerance needed and so on, they used socket as mentionned in the first message, on a very expensive board, with really giant socket (probably ~4000 pins type for the 1000-1200 watt and amount of signal and that possible because the HBM is direct on the gpu package and not on the motherboard):

And reversly ps5-xbox will create coherent giant soc system using x86 cpus by spending the time and money to make a custom version

 

[edward78]

Isn't this idea mostly what a iGPU/APU already is only not combined with a CPU & using Sys Ram. Why would this be any harder?

 

[LukeTbk]

Isn't this idea mostly what a iGPU/APU already is only not combined with a CPU & using Sys Ram. Why would this be any harder?

It would not be if you do it under those limitation of relatively slow gpu bandwith and relatively low power, that were all the challenge of discrete level GPU in socket would come from.

i.e. we already have gpu in socket that use motherboard ram outhere, those AMD APU, we already have high power socket gpu if the vram is on package (like the picture above), socket is giant and motherboard really not cheap (and it does not use system ram).

 

[edward78]

It would not be if you do it under those limitation of relatively slow gpu bandwith and relatively low power, that were all the challenge of discrete level GPU in socket would come from.

i.e. we already have gpu in socket that use motherboard ram outhere, those AMD APU, we already have high power socket gpu if the vram is on package (like the picture above), socket is giant and motherboard really not cheap (and it does not use system ram).

IGPUs/APUs do use Sys Ram, I said my idea would not. Maybe the wording was confusing in my post above???
Isn't this idea mostly what a iGPU/APU already is only "not" combined with a CPU & using Sys Ram. Why would this be any harder?

 

[Absalom]

Isn't this idea mostly what a iGPU/APU already is only not combined with a CPU & uses Sys Ram. Why would this be any harder?

This. If you're going to do it, do it right, don't half-ass it. Put everything on the same die or same SoC package. Shortest traces, no need for a PCIe bus, etc.

Which sounds nice and all until you recognize the technical hurdles even that brings. Such as the physical size of a 5000 series gpu die dwarfing any CPU die around today. Not to mention the amount of heat all that will produce in such a small space.

The best we can hope for is having both the CPU and GPU relatively close to each other with some dedicated bus between them, much like how consoles are designed. The shorter the traces, the better. Then there's the whole VRAM vs system ram problem. Do you share VRAM as system ram like the PS5? Basically, this problem turns into something consoles have already solved.

Then there's power delivery for all that. Now the motherboard takes on the role of power delivery of the entire system. Falure point becomes a single failure point. If something dies, you basically RMA the entire system.

It would also kill a market segment overnight, because if any of that is soldered in then motherboards now play a completely different role. Less emphasis on horizontal integration and more on vertical integration (i.e. your purchase decision comes down to motherboard + CPU + GPU combination). Going vertical makes things more like Apple hardware. Choices are limited to what configurations are provided at purchase time. Also, good luck getting X and Y companies to agree on what combos "sell". AMD is in a far better position vs getting Nvidia and Intel to agree on things.

I think what's considered "legacy" is what's keeping us tethered to the past. That and the whole "If it ain't broke, don't fix it" mentality.

 

[LukeTbk]

Isn't this idea mostly what a iGPU/APU already is only "not" combined with a CPU & using Sys Ram. Why would this be any harder?

well you had one signal that apu does not have for the board to handle, between cpu and gpu and now the gpu need its own memory controller to talk to its own memory and its own memory slot on the board, way more costly if not harder (which maybe are the same word here, it is all about cost, because there is motherboard with on socket gpu as in the picture I posted, as long as the vram unlike in the op is on gpu package you can have regular gpu-memory speed)

APU/iGPU are low power and low memory bandwiith gpu, those would be possible on a very big and costly motherboard to be as the OP describe (you add a giant socket, whole new rams signals....), but that would be a strange market, way more expensive than an AMD APU, way less performance and not that more swapable than a pci-e GPU and more expensive than those on the initial purchase, what would be the point.

 

[littlegreenmenfromhome]

I'd rather have SXM AIB.

 

[TrailRunner]

Oh, ok. Would a little slot like te Pentium 2 went in be better for the GPU? The VRam would have slots like the Ram, so that is already good. So Nvidia's Arm will still need a bug fan for the RTX 5090 GPU, right?

I think that you're getting somewhere with that packaging idea similar to the Pentium 2.
As mentioned by prior posts, you still can't have discrete RAM for a high-performance video chip, it needs to be soldered or located close to the package. For example, for integrated GPUs similar to how the Apple M processors have packaged memory, and AMD Strix Halo requires soldered ram for technical reasons. GPUs just need some fast memory closer to the GPU than is possible with replaceable RAM.

The necessity for very fast memory (much faster than traditional system ram) is what the Intel engineers encountered when designing the Pentium 2. Before the Pentium 2, system cache was located on the mainboard, and ran at the speed of the front side bus. Intel realized that their Pentium 2 processor would need soldered memory close to the processor, but doing this in the traditional socketed way would limit upgradability. To speed up the memory access of the Pentium 2, Intel packaged the processor together with some very fast cache memory onto the slot-style package. So the downside of the Pentium 2 slot packaging was that you couldn't upgrade only the CPU (as the chip was soldered to the slot-style package), instead the packaging meant that when doing a CPU upgrade you replaced the system cache at the same time (as part of the slot package). The upside is that processors and cache were developing faster concurrently, so when you upgraded the packaged slot processor, you benefited from new faster cache memory as well. So the slot packaging allowed for the benefits of processor upgrades, while also allowing for the benefits of the faster soldered cache memory that the processor required.

So, it could be a good idea to package a GPU and some fast video memory as close as possible, in some sort of slot packaging, similar to the Pentium 2 idea. When the GPU advances occur, and you replace the slot package to perform a GPU upgrade, you would benefit from advances in faster memory at the same time.
Another benefit of some sort of slot packaging, (a card if you want to think of it like that) could be that if the GPU consumes more power than the mainboard could otherwise deliver, you could have some dedicated power cabling in the system deliver additional power to the GPU. You can't do that with a socketed design.
If you think about it, you could even have the flexibility to place the slot package close to the edge of the mainboard so that it could exhaust hot air directly *outside* of the case instead of dumping it into the case itself. An additional benefit of this is that instead of routing the video signal through the slot package and through the mainboard, the system could be designed so you could plug your monitor's cables directly into a video port at the edge of the slot that faces the outside of the PC's case. So that way when DisplayPort/HDMI specifications get updated, you can just upgrade your packaged GPU instead of replacing the whole mainboard.

You could make a vendor-agnostic slot standard so GPUs from Nvidia, AMD, Intel, or any other manufacturer could be used in any mainboard. Since the packaging is for faster video, you could call it Accelerated Graphics Packaging. Or Accelerated Graphics Port. Or AGP.

Just a thought.

 

[zandor]

The way higher end cards are going I kinda wonder if maybe they ought to be more like a PSU. Something you can bolt onto your case to deal with the weight.

 

[THRESHIN]

i think it could easily be done but it would be very limiting. they'd be restricted by socket type (# of pins) and i would think power requirements in particular. every new gen of cards the power requirements can change a lot.

and then imagine we'd have boards that support the newest GPU chip but end user still wants GDDR5 or something...

but we do this with laptops, just soldered. there used to be laptops you could swap out the GPU in the past, would come as a small board. never really took off.

 

[stashinsome]

you know if you think about it, its pretty insane that today's computers are essentially a computer nested inside another computer. Especially since now they have their own dedicated BIOS, RAM, power and cooling. Shit if a crazy smart engineer, figure out a way to solder a hard drive to a GPU could they make it run a kernel on its own?

 

[Nobu]

Yes, and it's been done. Well, maybe not on a gaming GPU, but on hardware like a GPU at least. Pretty sure there are videos on yt.

 

[Tsumi]

you know if you think about it, its pretty insane that today's computers are essentially a computer nested inside another computer. Especially since now they have their own dedicated BIOS, RAM, power and cooling. Shit if a crazy smart engineer, figure out a way to solder a hard drive to a GPU could they make it run a kernel on its own?

It's possible, but it'll become very limited in capability quite fast. CPUs are general processors- they can do everything, but they don't do any one thing particularly fast. GPUs are a subset of dedicated processors- they do very few things but do them very fast. ASICs and NPUs also belong to the dedicated processor group.

 

[FrgMstr]

Power delivery changes greatly between GPU models. Theoretically you can solder those down, but what's the point? Will all up being APUs sooner or later anyway, so it will happen one day.

 

[are closed]

I have a feeling we are on last iterations of physical consumer personal computers. Anything else that is coming in the near future, will be based off cloud servers and basic device with capability to stream display data back and forth. Like a smart TV or a cellphone connected to data center and AI. (Dedicated "at home" anything, will be obsolete)

 

[tordogs]

And welcome to the forums.

 

[Sycraft]

Mostly because it would be more limiting without any real gain. The good thing about PCIe cards, the whole reason they exist, is that they make it easy to cheaply add capabilities to a system. You can build a board as big or as small as you want, with whatever additional support hardware it needs, more power connectors, etc. And it is all standard. Expansion boards are a good way of doing things when you have the space, which we do in desktops. You'd have to have a real compelling reason to not want to keep them on boards.

It's possible, but it'll become very limited in capability quite fast. CPUs are general processors- they can do everything, but they don't do any one thing particularly fast. GPUs are a subset of dedicated processors- they do very few things but do them very fast. ASICs and NPUs also belong to the dedicated processor group.

Slight correction in that ASICs aren't really dedicated processors, they go further and are often fixed function devices. A network switch ASIC, particularly an unmanaged one, is a good example: It does nothing but forward ethernet frames. It has no ability to be programmed at all. It isn't Turing complete, you can't use it to execute arbitrary code. That's the AS part of ASIC: Application Specific. Now I'll grant you sometimes things that get called ASICs are full Turing complete devices but many are not and in the strict sense of the word they shouldn't be. They are devices designed to do one thing only.

 

[djstarfox]

A dedicated graphics slot was called AGP. It's dead and gone for good reason.

 

[LukeTbk]

I have a feeling we are on last iterations of physical consumer personal computers. Anything else that is coming in the near future, will be based off cloud servers and basic device with capability to stream display data back and forth. Like a smart TV or a cellphone connected to data center and AI. (Dedicated "at home" anything, will be obsolete)

I extremelly doubt Apple last personal computers would have been M5 or the upcoming M6, as long people buy them someone will make them (we could members this message board start a company that make and sell them if not one else do at a very good margin if that ever the case)

 

[are closed]

Perhaps you are right, but Adobe went the way of the cloud and not many people were all too happy about it either, but they haven't reversed course.

I mist certainly hope everything will go back to normal and we will all forget the woes we are experiencing at the present time.

Thank you.

 

[DanNeely]

They used to have the graphics on one of the chipsets, nvidia's geforce mobile graphics was pretty badass...for the time.

But GPUs get hella hot, hotter than CPUs (well, used to be), and they need a lot of memory (even still). There's just not enough real estate on most boards to accommodate all that. And if you wanted upgradable vram, that takes more space and adds latency...

IGP graphics are the modern equivalent of chipset ones. They share the same big limit in ram bandwidth; but probably have more thermal headroom since chipsets never had more than tiny heatsinks and fans which are dwarfed by even the smallest and crappiest of OEM CPU coolers.

 

[LukeTbk]

Perhaps you are right, but Adobe went the way of the cloud and not many people were all too happy about it either, but they haven't reversed course.

It still run on your local computer (photoshop, lightroom, after effect and premier at least), adobe are not paying all that compute, they even putting local AI inference more and more, they push cloud subs (like microsoft windows do) with cloud service like easy to share files and so on, library of assets, etc..., but the program itself still run on personal computers for the most part.

 

[HockeyJon]

Not to mention power delivery. Think MSI Godlike boards are expensive?
A drop in GPU may be cheap but the price of the board itself would be crazy high.
Reminds me of the days of sockets/chipsets that worked on AMD/Intel/Cyrix/WinChip/ and others.

This was the first thing that came to mind for me. Imagine trying to design an AM5 board with a VRM for a sub-200W CPU, and then having to accommodate the prospect of a 600W RTX 5090 into it? But maybe the user doesn't want that and then you just have a massive VRM they have to pay for just sitting there for no good reason.

You CAN do this, but there are benefits to modularity and letting the customer decide what GPU they'd like to slot in, rather than charging everyone for the prospect they go super high end. Plus you can design the GPU so the VRAM chips are closer, as well as keep the entire motherboard formfactor more compact since you don't have to widen it in order to accommodate the GPU and all relevant components. A slot in GPU is effectively a 3D addition in another plane, so you don't have to make the X-Y plane bigger when the GPU has to occupy the Z plane. And then you have to make space for GPU cooling.

 

[Armenius]

Would still need auxiliary power delivery, dedicated cooling, and more beefier dedicated power phases on the motherboard. It's going to need to be a SOC-like design, with memory on the interposer because sharing system RAM would be a bad idea. If you get rid of PCI-E expansion slots to make room, it could work, but it sounds pretty impractical to me.

 

[mullet]

The GPU's are getting the point to where we just dump CPU's all together and have the GPU run everything.

or

Have to 2 micro atx motherboards in a PC, one for CPU and one for GPU. with a 4000watt PSU!!!!!!!!!!!

 

[cpufrost]

Cloud gaming may solve the platform dependency problem but not everyone has a sub 5ms FTTP internet feed to make the experience good.

 

[sethk]

When I first read the title of this topic, I thought this would be about a similar idea I have had for a while but probably in the exact opposite direction. Rather than thinking we should squeeze GpUs into a socket that is fighting for horizontal layout space on a motherboard, I was thinking it just needs to completely uncoupled from the motherboard like intels “sandwich” NUC design, asus’ laptop eGPUs or older home PCs where a lot of peripherals were external boxes that just stacked. And this should be the norm, or a widely supported niche.

This would let GPU makers go all out on efficient cooling solutions, power delivery and aesthetics not constrained by current card restrictions- something that was essentially designed to be 1 slot, internal and bleeding heat into your already hot pc case. While this is technically possible with EGPUs and riser cables (thunderbolt is still a hack with an efficiency and speed cost) it is not the norm and there isn’t any real easily available and compelling offerings on high end gpus designed to be external at competitive prices and designs.

Imagine if Asus and MSIs top offerings were truly optimized external GPUs with their standalone cooling and cool visual aesthetics. No need to worry about cables disconnecting and frying your gpu, PSU spec (maybe they could take a standard atx psu as an option) and most importantly case size and cooling. It would free up pc builds like SFF or crazy non traditional pc to still be ridiculously powerful without having to worry about internal card placement. You could also much more easily stack multiple high end GPUs (if they were available lol). You could swap or share gpus more consistently with laptops. You could get a 5090 with better cooling, speed, noise and power characteristics than current minivan sized monstrosities.
Or maybe this would lead to a mini fridge sized “GPU” that is wildly more powerful, like a GB300 class GPU. Many benefits since cards are inherently a serious design limitation that standalone designs could fix.

 

[Tsumi]

When I first read the title of this topic, I thought this would be about a similar idea I have had for a while but probably in the exact opposite direction. Rather than thinking we should squeeze GpUs into a socket that is fighting for horizontal layout space on a motherboard, I was thinking it just needs to completely uncoupled from the motherboard like intels “sandwich” NUC design, asus’ laptop eGPUs or older home PCs where a lot of peripherals were external boxes that just stacked. And this should be the norm, or a widely supported niche.

This would let GPU makers go all out on efficient cooling solutions, power delivery and aesthetics not constrained by current card restrictions- something that was essentially designed to be 1 slot, internal and bleeding heat into your already hot pc case. While this is technically possible with EGPUs and riser cables (thunderbolt is still a hack with an efficiency and speed cost) it is not the norm and there isn’t any real easily available and compelling offerings on high end gpus designed to be external at competitive prices and designs.

Imagine if Asus and MSIs top offerings were truly optimized external GPUs with their standalone cooling and cool visual aesthetics. No need to worry about cables disconnecting and frying your gpu, PSU spec (maybe they could take a standard atx psu as an option) and most importantly case size and cooling. It would free up pc builds like SFF or crazy non traditional pc to still be ridiculously powerful without having to worry about internal card placement. You could also much more easily stack multiple high end GPUs (if they were available lol). You could swap or share gpus more consistently with laptops. You could get a 5090 with better cooling, speed, noise and power characteristics than current minivan sized monstrosities.
Or maybe this would lead to a mini fridge sized “GPU” that is wildly more powerful, like a GB300 class GPU. Many benefits since cards are inherently a serious design limitation that standalone designs could fix.

Oculink might do what you're looking for. There are boards that can do two 8x Oculinks for a 16x card, but I only found PCI-E 4.0 at the moment.

The problem with external cabling is maintaining signal integrity and latency. The faster the link, the harder this is.