Have Graphics Card Reached The Technological Brickwall ?

[ScottMC7000]

I've been using computers since 1981, and funnily enough my first was a ZX81, and a 16K ram expansion, that ominous brick of extra power you wondered why you needed. In just a few years, this tech will be 40 years old, yet that time in my memory in using one, is as still fresh as it was a few weeks ago. Buying a computer, a branded custom built one like an Amiga where you could boost it's performance with addon cards whilst drooling over the pictures of bar charts in Amiga Format magazine with the little jet fighter's vapor trail to show the performance comparisons between them...

Looking back now, it's like I see history repeating itself. What was largely proclaimed and boasted back then has pretty much become irrelevant, and obsolete. The technology and whilst it still may work today, has become pretty much history. It's all somewhat of an illusion of what you think is new and cutting edge today but won't be in reality when you look back. I think what will be remembered today in the future is, where development of graphics cards and the materials to produce them, just was barely good enough, or the fabrication process of them was really inefficient... hence the high number of RMA's for what are proclaimed as high end graphic cards...

My general view on all this is that, there is a limit... and we have reach it with the current technology, we already have... and this is one of the reasons for high mark up of prices of graphic cards being sold today.

I guess, I'll have to look out for a 2000 Watt PSU, in the future so I can run this old tech card with 3 GPU's on it... because technology didn't advance in the way it may have should have...

I remember the days of 1999, where there was all this excitement for bio nano computers, real living organisms being able to run and process calculations. It was all quite bazaar back then, but it was a prediction of what we may have been using now...

 

[Grim5]

In 1981 they also thought we’d have flying cars powered on nuclear engines by now.

The brick wall you mention is not isolated it can be applied to all component engineering so it encompasses just about every electronic device sold.

Improvements in relative, it’s all relative to what you had before barring no generation leaping new inventions

Cars only get slightly faster each year without those flying machines we were expected to have - and they to are starting to run closer to the boundaries set by physics, just like processors design for gpus and cpus

 

[bigmike20vt]

Not so sure . Anyone remember the 8800gtx generation and subsequent 9800gtx?

Things were much like now with no pressure from AMD Nvidia took their foot off the gas.

Or perhaps on a more positive note in other ways current gen reminds me of gtx480 (Fermi)

When it launched it was expensive, ran hot and was not as fast as many hoped, however it really did not take long before the architecture was refined slightly and it did end up being the start of a series of excellent NV GPUs.
(I saw a vid recently about using a Fermi on modern games and time has shown what a monster of a card it actually was considering it is over 9 years old now!)

I am hoping the next gen of NV cards at 7nm will see a significant upgrade esp the rtx cores.

Whether Navi will get AMD back in the sharp end I am not so sure but I think it will be a profitable Mid/above Mid range GPU to get them back in the game and then maybe the gen after (with Intel hopefully in the mix too) maybe we will have 3 big companies keeping each other honest.

 

[gpuerrilla]

I dont subscribe to it being an AMD fault. Its greedy corporations placing money first before advancements. Whilst you think nVidia have taken their foot off the gas, they still horlicksed the raytracing rollout and like said earlier have made little advancement from the Pascal phase in comparison and just regurgitate more cards for micro price points. Commanding so much money for the latest range is ringing the deathknell of dedicated GPUs for regular consumers and I am not surprised people are turning to consoles for instant gaming with reasonable graphics for the price of a mid tier card.

 

[LePhuronn]

Brick wall? Not even remotely.

For all of the woes regarding Nvidia's implementation of RTX tech, we have the first step towards real time ray tracing at home and AI-supported image improvement algorithms. The technology itself is only just getting started and in the coming years we're going to see some significant jumps in capability, just like when the Amiga landed and the first PC graphics accelerators. I think we're actually entering a new period of "wow".

As far as actual products go, we're just in one of those periods of stagnation where vendor A feels no pressure from competitor B so are capitalising on their market position to prioritise revenue rather than push technology. It's not the first time, it will happen again, and it certainly won't last.

 

[Nasher]

In 1981 they also thought we’d have flying cars powered on nuclear engines by now.

Well technically we could make them, but it wouldn't exactly be safe

 

[Gregster]

Like you, I have been gaming since around 1981 on a Spectrum and a c64. I remember writing games out of the magazines and then having to go back through with a fine tooth comb to find my mistakes when it didn't work. I feel the leaps we have made since then are amazing and going from sprite based games to movie quality games is huge. Technology is advancing all the time and I embrace it.

Amiga games was my favourite gaming time though but that was probably down to Xcopy and bulletin boards and my age but I still enjoy gaming now and playing on a Pimax 5K+ is jaw dropping.

 

[phrases]

I would have thought its the cpu now that is the blocker.

 

[SupraWez]

Like you, I have been gaming since around 1981 on a Spectrum and a c64. I remember writing games out of the magazines and then having to go back through with a fine tooth comb to find my mistakes when it didn't work. I feel the leaps we have made since then are amazing and going from sprite based games to movie quality games is huge. Technology is advancing all the time and I embrace it.

Amiga games was my favourite gaming time though but that was probably down to Xcopy and bulletin boards and my age but I still enjoy gaming now and playing on a Pimax 5K+ is jaw dropping.

Same here

 

[MeddlE]

Likewise started on a ZX Spectrum 16k in 1981. Definitely the Amiga was the best time for gaming. I still have a 500, 600 and 1200.

As for the brick wall I don't think so. AMD haven't been competitive for a long time and Intel and nVidia have got lazy. Now AMD are back though. Potentially exciting times ahead.

 

[Rroff]

Not even close to a brick wall - but the problem is the upheaval in terms of architecture and software support needed for the next leap - in the long run ray tracing and similar techniques will overtake traditional rasterisation and enable a level of parallelisation with graphics processing through the whole pipeline that simply isn't possible with today's approaches.

As LePhuronn put it we've hit a period of stagnation for various reasons rather than a brick wall.

EDIT: We have also reached a place where current semiconductor nodes are about maxed out but the next generation of nodes aren't quite ready but ultimately there is a limit with most architectures how much you can iteratively just add on more without hitting diminishing returns due to the type of data you are processing so clockspeed is still king as well.

 

[pagepack]

Maybe I'm all misty eyed, but the early 2000's seemed like a golden age for graphics cards. New cards it seemed every year from Nvidia and ATI, the battle was tight. Graphical quality moved on massively.

 

[Nasher]

I think we are close to it. CPUs are closer.

I doubt the next big leap will happen until we move on from silicone based chips. At that point things will be significantly faster and run cooler. Then it will keep improving until we run in to the same issue again.

 

[Rroff]

I think we are close to it. CPUs are closer.

I doubt the next big leap will happen until we move on from silicone based chips. At that point things will be significantly faster and run cooler. Then it will keep improving until we run in to the same issue again.

Thing is with stuff like ray tracing you literally can go wide without the inefficiencies normally seen with SLI/CF, etc. and that kind of setup does work well with chiplet type designs.

 

[Apone70]

I think we are only still scratching the surface in regards to ray tracing etc.

 

[kazuya1337]

The only thing slowing down advancement is capitalism, companies need to squeeze every last drop of blood from the husk of each baby step they restrict themselves to.

 

[MissChief]

Likewise started on a ZX Spectrum 16k in 1981. Definitely the Amiga was the best time for gaming. I still have a 500, 600 and 1200.

As for the brick wall I don't think so. AMD haven't been competitive for a long time and Intel and nVidia have got lazy. Now AMD are back though. Potentially expensive times ahead.

FTFY.

I think graphics are now at a point where there’s very little more developers and publishers can do as well as hardware manufacturers. Games have conceivably lifelike graphics and cards that can push 4K @60FPS in most titles are out there now. This causes issues for Nvidia and AMD who rely on PC gamers to upgrade regularly for more FPS and higher detail. RTX is a gamble on NV’s part to try and get people to upgrade from 10x0 series when most of these cards still work and work well at higher resolutions and FPS.

 

[pagepack]

The only thing slowing down advancement is capitalism, companies need to squeeze every last drop of blood from the husk of each baby step they restrict themselves to.

Nvidia and Sergey bubka are peas out of the same pod

 

[Troezar]

Nvidia and Sergey bubka are peas out of the same pod

Very good analogy. He made a lot of money, one centimetre at a time!

 

[robfosters]

Very good analogy. He made a lot of money, one centimetre at a time!

And the javelin bloke, Jan Zelezny.