Live data from Hacker News

Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

theverge.com

161–170 of 776 posts

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#161
post #4

32GB of GDDR7 at 1.8TB/sec for $2000, best of luck to the gamers trying to buy one of those while AI people are buying them by the truckload. Presumably the pro hardware based on the same silicon will have 64GB, they usually double whatever the gaming cards have.

At what point do we stop calling them graphics cards?

We've looped back to the "math coprocessor" days.

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

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#162
post #151
post #4

32GB of GDDR7 at 1.8TB/sec for $2000, best of luck to the gamers trying to buy one of those while AI people are buying them by the truckload. Presumably the pro hardware based on the same silicon will have 64GB, they usually double whatever the gaming cards have.

Why do you need one of those as a gamer? 1080ti was 120+ fps in heavy realistic looking games. 20xx RT slashed that back to 15 fps, but is RT really necessary to play games? Who cares about real-world reflections? And reviews showed that RT+DLSS introduced so many artefacts sometimes that the realism argument seemed absurd. Any modern card under $1000 is more than enough for graphics in virtually all games. The gamin…

> is RT really necessary to play games? Who cares about real-world reflections?

I barely play video games but I definitely do

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#163

Earlier quoted context omitted.

Seems kinda silly to make an 8K video card when ... nobody on the planet has an 8K screen

Perhaps you don't, but several of us do. They've been around a while, available in your local bestbuy/costco if you're rocking a 4:4:4 TV they're not even particularly pricey and great for computing (depending on the subpixel layout). On the planet? Many people. Maybe you're thinking 12K or 16K.

It's been a few years since I worked at [big tech retailer], but 8K TVs basically didn't sell at the time. There was basically no native content - even the demos were upscaled 4K - and it was very hard to tell the difference between the two unless you were so close to the screen that you couldn't see the whole thing. For the content that was available, either you were dealing with heavy compression or setting up a high-capacity server, since file sizes basically necessitated most of the space on what people would consider a normal-sized hard drive to store just a few movies.

The value just wasn't there and probably won't ever be for most use cases. XR equipment might be an exception, video editing another.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#164
post #156

Pretty interesting watching their tech explainers on YouTube about the changes in their AI solutions. Apparently they switched from CNNs to transformers for upscaling (with ray tracing support) if I understood correctly though for frame generation makes even more sense to me. 32 GB VRAM on the highest end GPU seems almost small after running LLMs with 128 GB RAM on the M3 Max, but the speed will most likely more than…

Check out their project digits announcement, 128GB unified memory with infiniband capabilities for $3k.

For more of the fast VRAM you would be in Quadro territory.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#167
post #47

Earlier quoted context omitted.

Don't necessarily count Intel out.

Intel hate making money even more than AMD.

Starting around 2000, Intel tried to make money via attempts at everything but making a better product (pushing RAMBUS RAM, itanium, cripling low-end chips more than they needed to be, focusing more on keeping chip manufacturing in-house thereby losing out on economy of scale). The result was engineers were (not always, but too often) nowhere near the forefront of technology. Now AMD, NVIDIA, ARM are all chipping away (pun intended).

It's not dissimilar to what happened to Boeing. I'm a capitalist, but the current accounting laws (in particular corporate taxation rules) mean that all companies are pushed to use money for stock buybacks than R&D (which Intel spent more on the former over the latter over the past decade and I'm watching Apple stagnate before my eyes).

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#168
post #137

Earlier quoted context omitted.

> modern games + modern cards can't even do 4k at high fps What "modern games" and "modern cards" are you specifically talking about here? There are plenty of AAA games released last years that you can do 4K at 60fps with a RTX 3090 for example.

> There are plenty of AAA games released last years that you can do 4K at 60fps with a RTX 3090 for example. Not when you turn on ray tracing. Also 60fps is pretty low, certainly isn't "high fps" anyway

This.

You can't get high frame rates with path tracing and 4K. It just doesn't happen. You need to enable DLSS and frame gen to get 100fps with more complete ray and path tracing implementations.

People might be getting upset because the 4090 is WAY more power than games need, but there are games that try and make use of that power and are actually limited by the 4090.

Case in point Cyberpunk and Indiana Jones with path tracing don't get anywhere near 100FPS with native resolution.

Now many might say that's just a ridiculous ask, but that's what GP was talking about here. There's no way you'd get more than 10-15fps (if that) with path tracing at 8K.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#169
post #7

Let's see the new version of frame generation. I enabled DLSS frame generation on Diablo 4 using my 4060 and I was very disappointed with the results. Graphical glitches and partial flickering made the game a lot less enjoyable than good old 60fps with vsync.

The main edge Nvidia has in gaming is ray tracing performance. I'm not playing any RT heavy titles and frame gen being a mixed bag is why I saved my coin and got a 7900 XTX.

Re: Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

#170
post #145

Earlier quoted context omitted.

NVidia's pricing isn't based on how much it takes to produce their cards, but since they have no competition, it's purely based on how much consumers are grudgingly willing to pay up. If AMD continues to sleep, they'll sale these cards for the same price, even if they could produce them for free.

AMD is not sleeping. They publicly admitted that they threw in the towel- they have exited the high end market.

And if these 50-series specs are anything to go by, they made a good call in doing so. All the big improvements are coming in mid-range cards, where AMD, nVidia, and Intel(!) are trading blows.

If the only way to get better raw frames in modern GPUs is to basically keep shoveling power into them like an old Pentium 4, then that’s not exactly an enticing or profitable space to be in. Best leave that to nVidia and focus your efforts on a competitive segment where cost and efficiency are more important.

Post reply on HN