I remember the Millennium as the first 3D accelerator. It didn't do texturing, but a lot of the games didn't need it yet. It still did gouraud shading.

It does start with the Voodoo, so I got what I came for.

Dystopian future where AI pumps out slop and uses human feedback and comments to correct the output.

>S3 ViRGE

decelerator?

>Matrox G200

because it never got opengl driver? Because it was 2x slower than even Savage3D? Nvidia TNT released a month later offering 2x the speed at lower price

https://www.tomshardware.com/reviews/3d-chips,83-7.html

truly a graphic card that mattered! :)

Kind of funny that a someone making a website about desktop hardware didn't expect anyone to use desktop hardware to look at their site.

Everything is designed for phones now.

Apparently it's a Millenial trait to insist on doing things with a "big screen".

Fixed it, thanks for the feedback

Not only that but a lot of the "defining games" are just games that appeared at about the same time but can be handled by much older GPUs without issues. For me graphics haven't made a real difference since Unreal Engine 4 anyway. It's all about the content these days, not the skin.

does anyone have pointers to similar articles that talk about GPU history?

One example is "No graphics API" by Sebastian Aaltonen shared here 3 months ago, which is a great tour de force of graphics stack innovations through contrasting the history of OpenGL/Vulkan and WebGPU/Metal development: https://news.ycombinator.com/item?id=46293062 Because it requires an in-depth understanding of the shader pipeline, the article touches on significant graphics cards of the era. I'd love to see more about that!

like the PS3? seems like everything is using PC architecture now. it does have RDNA.

My current machine is an i5-3570k with a 1070Ti...

The old CPU is actually more of an issue. I couldn't run Civ 7 because the game (probably the DRM) uses some instructions that aren't implemented on that CPU. Other than that I bet it would run just fine.

I was just about to upgrade before hardware prices went through the roof. Now I'm just holding on until some semblance of sanity returns, hoping every day that the bubble pops and loads of gently loved hardware starts appearing on the secondary market. Also, the way nVidia has been skimping on memory for all but the most outrageously expensive chips has grated on me. I was really hoping they would buck the trend with the 5xxx generation, but nope, and with RAM prices the way they are I have little hope for the 6xxx generation. My current card is close to a decade old and has 8GB of VRAM. I'm not upgrading to a card with 8GB of VRAM, or ever 12GB. That 8GB was crucial in future proofing the original card, none of its 4GB contemporaries are of much use today.

I also have that exact setup sitting around, but am just using my ryzen laptop now.

It is interesting the consumer high you get from buying things. I remember being in a microsoft store like 12 years ago and wanting this Surface laptop. Holding it in my hands but I couldn't afford it. Now I have a Surface Book 3 and it's still cool but not the same experience as it being a flagship/new at the time.

Still there are a lot of laptops I'd like to try when they get cheaper. As far as GPUs I like the Nvidia founder designs, it was a while before I got a 3080 Ti Fe that I ended up having to sell at a loss when I didn't have a job that was sad. I have a 4070 founders now which does struggle on certain games at 1440p but I'm going to use it to run local LLMs.

My truenas scale server still happily running on a i7-3770.

Hey, I could have used that i7-4790k!

I've been running the worst gaming set up I can get away with, which atm is a 3080 10gb, using random DDR3 ram, a budget WD 512gb ssd, and an i5 of the same socket as the i7-4790k that doesn't even support hyperthreading and can't do more than 4 tasks in parallel.

It's absolutely laughable at this point, but I'm unironically looking for a deal on that cpu lmao, it would be a huge upgrade.

its a very honorable mention in my eyes because its more appropriate of the tile of "first independent Graphics unit" than the Geforce 2. (did more than just blast already projected triangles at the screen)

not that it was an awesome product, but certainly it was flexible.

a good (albeit tiny) demo of that is that vquake has the same wobbling water distortion of the software renderer quake but rendered entirely through the gpu. Perhaps with some interpretation this could be called the "caveman discovered fire" of the pixel shading era.

Very interesting culture difference between rendition and 3dfx in their chip design approach..

This sent me down a huge rabbit hole of memories and reading. Thank you! I remember everyone being hyped for that card for their first Pentium / Pro builds at the time but I think a lot of people held off for the Pentium II and a TNT or Rage 128 card that I was hanging around with.

Agreed, those early manufacturers/models that experimented more feels more relevant than the more incremental listings of multiple 2000 3000 and 4000 series NVidia GPU's.

I remember there was a kernel module for the Matrox/MPlayer combination. You get a new device that MPlayer could use. You did get `-vo mga` for the console and `-vo xmga` for X11; you couldn't tell the difference, and both produced high-quality hardware YUV output.

The first fully programmable gpu being a mips cpu core with bolted on stuff. To bad about the hardware bugs. Was my first accelerator with the creative 3d blaster

G200 Matrox GPUs came integrated with servers for absolute ages,like past 2010's

It didn't start with the Verite, so I didn't get what I came for. :(

Ok? Not bad to be able to throw something like that together with minimal effort. Works nicely enough.

Came here for this ommission. I saved up for a long time to get an 8800 GTX, and I had that card for 5 years before upgrading again.

Here's one anecdotal datapoint:

About a decade ago, I discovered that the HD 530 iGPU included with my budget-oriented i3-6300 CPU was better-performing than the physically-impressive SLI pair of 9800GTs I had been using, at something like 1/10th the power consumption.

(It didn't do PhysX, but nobody cared.)

The 590x was great and lasted me around 5-6 years until I picked up a replacement, but it was really just a rebadged 580.

The 580 is a solid card that was an excellent price/performance value and held a respectable spot in the market for a very long time. Many video games now use is as the entry level bar for playability.

It doesn't hold the same "type" of spot, but it's a workhorse in the same way something like a NVIDIA 1070 was.

I'm still rocking a Z97, i7-4790k and a 980Ti :) I'm still waiting until I need an upgrade. DDR3 is still performing good enough for the games I run.

Pascal is already too late to matter (2016) IMHO.

With the release of D3D9 in 2002, GPUs of different vendors didn't really stand out anymore since they all implemented the same feature set anyway (and that's a good thing).

> massive positive impacts on graphics

I remember the main noticeable difference being ray traced reflections. However that was mostly on immovable objects in extremely simple scenes (office building). Old techniques could've gotten 90% there using cubemaps, screen space reflections, and/or rasterized overlays for dynamic objects like player characters. Or maybe just completely rasterize them, since the scenes are so simple and everything is flat surfaces with right angles anyways. Might've looked better even because you don't get issues with shaders written for a rasterized world on objects that are reflected.

Games that heavily advertise raytracing typically don't use traditional techniques properly at all, making it seem like a bigger graphical jump than it really is. You're not comparing to a real baseline.

Overall that was pretty much the poorest way to advertise the new tech. It's much more impressive in situations where traditional techniques struggle (such as reflections in situations with no right angles or irregular surfaces).

I used my 1080 Ti for about eight years. The successor GPU is in some ways way faster (raytracing, AI features etc.), but in others really quite stagnant considering the huge stretch of time that passed between them. ~10 years for 2-3x performance in GPUs at higher nominal and real price points shows how slow silicon advances have been compared to the 90s and 2000s. The same period from 2000 to 2010 would've seen 1000x performance if not more. The difference between a 1080 Ti and a more expensive RTX 50 card is the RTX can render ideally triple the frames in synthetic benchmarks, double the frames in some rasterizing games (most games won't see gains that high), and do a few relatively tame raytracing tricks at performance which is still not really good. At the same throughput it consumes maybe half the power or a bit less. The difference between a GeForce 2 and e.g a Radeon HD 4k is several planes of existence.

Or the S3 Savage3D, which, while being inferior to the TNT2, pioneered texture compression.

https://en.wikipedia.org/wiki/S3_Texture_Compression

My contributions: Matrox Parhelia for the first card supporting triple-monitors, and ATI All-in-Wonder which did TV out when media centre TVs weren’t really a thing.

For a moment, a Matrox G400 DualHead was THE card to have for a multi-monitor setup.

Recency bias probably, Iirc I think the 3000 and 4000 series did make significant improvements on RTX performance so compared to the 2000 series it's far more useful today.

The G200 mattered to some degree for a long time, because most x86 servers up until a few years ago would ship a G200 implementation or at least something pretending to be a G200 card as part of their BMC for network KVM.

> S3 ViRGE and the Matrox G200

Both were only really famous for how terrible they were though. I think the S3 Virge might even qualify as 3D decelerator ;)

This is an ad from viral marketing company and everyone here is falling for it.

I retired my 5700 XT a few years ago. Wasn't there some kind of hardware problem with it? It kept locking up my Linux kernel.

SGI IMPACT would be another

I had the 6600 GT, insane price-perf ratio, kept it for like 8 years

It was just unjustifiably popular.

It's basically AMD's 1080ti, except they just kept making them lol

I was going the other way, it wasn't obvious enough that it was going to be a horizontal scroll or how to do it. Vertical spacing felt off and the 'defining game' card at the bottom of the video card is nice information but displayed in a distracting manner.

Yes the MX440 deserves to be on this list. More important than the GeForce2 imo.

Do you think it was entirely AI? Surely some human involved to get this sort of layout..

Dystopian present

Yeah the 560 Ti was insanely popular in my group of friends. In ~2004 there was a good amount of FX 5700s, some people struggling on Geforce 4, and some on the FX 5900 Ultras. Some were updating every two years, some closer to four. When the 560 Ti came out, everyone got it.

The GeForce 4 generation as a whole, while being solid enough cards, were historically not interesting. They were just basic spec bumps over the GeForce 3. No new features or similar. And, critically, the 9700 Pro released the same year as the GeForce 4 and absolutely smoked the living shit out of it.

That will probably be my next GPU.

I'm on a 3060 currently and the changes in the 4xxx and 5xxx just aren't appealing to me. As soon as iGPUs get 3060 performance I'll probably switch. And they aren't far off.

1999? You sure?

I was running a 970ti for the longest time, it was only when I wanted to get into some VR gaming that it was time for an upgrade.

IMO there’s room for something more recent, maybe a Titan or something, to stand in as an avatar for making GPUs as compute accelerators a thing. I know that’s been going on forever, but at some point it went from some niche hacky thing to a primary use-case for the cards.

But yeah this list has a on of incremental bumps on it. Maybe there was some mixing of cards that mattered historically and cards that mattered to the author.

Same. Still play StarCraft2 on a 4790k and AMD R9 Fury X.

The other elephant in the room is the consoles, and even if they're capable of RT they also have to consider the performance capabilities versus visual payoff. As I see it the PC versions of games like Control from studios like Remedy are trailblazers, it's an early implementation (geforce 20 released in 2018, Control was 2019) as the ultra option to shakedown their implementation and start iteration early so future games will benefit, however the baseline is non-RT.

Loads of games from the era roundtripped their textures through lossy S3/DXT compression and then stored them as uncompressed RGB or RGBA.

I know this because I wrote a Unreal Engine texture repacking tool with a "DXT detection" feature so that I wouldn't be responsible for losing DXT compression on a texture which had already paid the price, only to find that this situation was already hyperabundant in the ecosystem.

Many Unreal Engine games of the day could have their size robotically halved just by re-enabling DXT compression in any case where this would cause zero pixel difference. This was at a time before Steam, when game downloads routinely took a day, so I was very excited about this discovery. Unfortunately, the first few developers I emailed all reacted with hostility to an unsolicited tip from what I'm sure they saw as a hacker, so I lost interest in pushing and it went nowhere. Ah well.

The most impressive part of Control's RT (on PC at least) was that it very much applied to (most) dynamic objects - and it features a TON of dynamic destruction.

The "office building" setting meant resticted areas, sure, but it features TONS of reflections - especially transparent reflections (which are practically impossible to decently approximate with screen space techniques).

Oh, and: The Northlight Engine already did more than most other engines at the time to get "90% there" with a ton of hybrid techniques, not least being one of the pioneers regarding realtime software GI.

The big feature of the All-in-Wonder was TV in. You could record, in glorious analog detail that could quickly use up your entire hard drive.

+1 to that, when i first saw unreal tournament with the add-on compressed texture pack was a real WOW moment.

>This is an ad from viral marketing company

they arent a marketing company:

"Dashboards, CRMs, automations. We're a small consulting team that turns your messy spreadsheets into systems that run your business."

I think their point is RTX is not useful.

This was a very sweet video card.

4000 certainly did, the "shader execution reordering" gave an meaningful uplift to tasks that "underutilized warp units due to scattered useful pixels".

it seems to have helped path tracing by a lot.

Yeah it also lacked driver support. But it was for a very brief moment the king of the hill.

I don't like to spend much on hardware, so I bought an 5700XT a few years ago and run a "steam machine" of sorts. Never had any Linux-related problems.

Matrox was really halfhearted with game support. They seemed far more interested in corporate customers, advertising heavily stuff like "VR" conference calls that nobody wants. They were early with multi-monitor support back when monitors were big, heavy, and expensive. I had a G200 that was the last video card I've ever seen where you could expand the VRAM by slotting in a SODIMM. It also had composite out so you could hook it to a TV. I played a lot of games on it up until Return to Castle Wolfenstein, which was almost playable but the low res textures looked real bad and the framerate would precipitously drop at critical times like when a bunch of Nazis rushed into the room and started shooting.

Last time I saw a Matrox chip it was on a server, and somehow they had cut it down even more than the one I had used over a decade earlier. As I recall it couldn't handle a framebuffer larger than 800x600, which was sometimes a problem when people wanted to install and configure Windows Server.

The point is that Nvidia popularized the term, Id guess.

Nvidia called the Geforce 256 the first ever GPU.

Even current Dell servers less than a year old ship with G200 graphics. If it works, why change it? A 1998 ASIC can be put in the corner of a modern chipset for pennies or less.

And the 4 MX versions were GeForce 2 MX based IIRC. 3 was expensive.

The MX440 allowed players that were playing games on id Tech 3 to finally play at high frame rates. I remember this card being all the rage back then in pro gaming circles for this reason.

The MX440 is a nearly 25 year old GPU, it performed somewhere between a Geforce 2 and GeForce 3 ti 200.

It was a good budget option those decades ago.

Still using my RX 5700 XT. The amdgpu driver had a major issue resuming from suspend a few months ago[0], but other than that, I'm not aware of (nor have I experienced) any stability issues. Maybe you had a bad card.

0: https://gitlab.freedesktop.org/drm/amd/-/issues/4531

My 1080ti is still working away in my kid's PC. If you connect a 1080p monitor, it will still hit 60fps in mostly everything.

The only thing that holds this card back now is a handful of titles that will not run unless ray-tracing support present on card - Indiana Jones and The Great Circle springs to mind etc.

I am very likely going to get a decade of use out of it across three different builds, one of the best technology investments I've ever made.

The article blew a huge opportunity to showcase the great diversity of “Pioneering Era” 3D accelerators (they weren’t called GPUs until later). But instead they just pretended it was always NVIDIA vs ATI, and threw in a few Voodoos.

Well. The 5090ti is significantly faster than a 1080ti. It has 92b vs 12b transistors. That's the 10 years difference you mention. 10 years before the 1080ti we had the 8800 ultra with 600m transistors. So yeah you are a bit right. But stacked transistors in the future might become reality and enable transistor increase again.

Like virtualized NICs pretending to be an NE2000? That's interesting, do you know why they'd use a G200 and not something like an older ATI chip?

The only thing the ViRGE was good for was passing through to a Voodoo2

Or the RealityEngine, but really any SGI - that's kind of where modern 3D computer graphics began.

What are they advertising? Nvidia graphics cards?

They were probably forced to update when they dropped older busses. Without a PCI or AGP bus on there they have to find something that can hang off of a PCIe lane.

But it WAS ultra popular with OEMs. If you had embedded video there was a huge chance that was it.

Sure. I picked IMPACT for having hardware textures. An interesting list would contain the first examples of processors that had things we still have today, like geometry processors. It would also contain evolutionary dead ends that tried to do things differently, like the Rendition Vérité.

Probably started out as a real G200 chip which might’ve been the cheapest and easiest to integrate in the 2000s? Or it had the needed I/O features to support KVM (since this would’ve involved reading the framebuffer from the BMC side), or matrox was amenable to adding that.

And they say that Nvidia coined the phrase GPU - but I recall that Sony did it earlier... not that it really matters.

Drivers, probably.

A 5090 is more than twice as expensive as a 1080 Ti in real MSRP terms and way more than that in actual real terms, since the 1080 Ti was available for some time below MSRP, while the 5090 realistically never was and usually goes for 50-100% above MSRP. So I don't think these can be compared. Basically a similar story with the 5080, it's significantly more expensive in real terms (and about ~2x in nominal terms).

The 5070 Ti would be the same spot.

If you compare these - the RTX 50 card has a bit higher TDP (which it will usually not reach due to clock limits), is a roughly 100mm² smaller die with around 4x the transistors and about 3x the compute (since much more of the chip is disabled compared to the 1080 Ti's chip). It has 5 GB more memory (11->16) and a lot more bandwidth.

It really is an impressive bit of hardware. I finally pulled it out of my last system a year ago, but it was definitely holding its own up until that point.

Ikonas 3000

The ATi Rage 128 was used in everything short of toasters for a long time too. I assume that the drivers are part of what made it obsolete.

It was only 3dfx and NVIDIA (since the TNT) that mattered in the 1990s though. All the other 3D accelerators were only barely better than software rasterization, if at all.

Seeing Quake II run butter smooth on a Riva TNT at 1024x768 for the first time was like witnessing the second coming of Christ ;)

Yes. They are likely also advertising for themselves with how viral their ads are. The article is featured on their website.

I remember having a ton of servers with cut down Mach64 chips. They were so bad that you would get horizontal lines flickering across the screen while text was scrolling in an 80x25 text console. I don't know why server manufacturers go to so much effort to make the console as terrible as possible. Are they nostalgic for the 8 bit ISA graphics from the original 5150? They seem offended at the idea that someone might hook a crash cart directly up to their precious hardware.

Rendition's VQuake was actually pretty good, more than barely better than software rasterization.