Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs

theverge.com

Post reply on HN
Print view View original

131–140 of 776 posts

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

#131

Post by out_of_protocol »

dijit wrote: post #84
ziml77 wrote: post #55

Earlier quoted context omitted.

The 4090 already seemed positioned as a card for consumer AI enthusiast workloads. But this $1000 price gap between the 5080 and 5090 seems to finally cement that. Though we're probably still going to see tons of tech YouTubers making videos specifically about how the 5090 isn't a good value for gaming as if it even matters. The people who want to spend $2000 on a GPU for gaming don't care about the value and everyon…

From all the communication I’ve had with Nvidia, the prevailing sentiment was that the 4090 was an 8K card, that happened to be good for AI due to vram requirements from 8K gaming. However, I’m a AAA gamedev CTO and they might have been telling me what the card means to me .

Well, modern games + modern cards can't even do 4k at high fps and no dlss. 8k story is totally fairy tale. Maybe "render at 540p, display at 8k"-kind of thing?

P.S. Also, VR. For VR you need 2x4k at 90+ stable fps. There's (almost) no vr games though

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

#132

Post by out_of_protocol »

Our_Benefactors wrote: post #24
ericfrederich wrote: post #18

Earlier quoted context omitted.

4k gaming is dumb. I watched a LTT video that came out today where Linus said he primarily uses gaming monitors and doesn't mess with 4k.

There are good 4K gaming monitors, but they start at over $1200 and if you don't also have a 4090 tier rig, you won’t be able to get full FPS out of AAA games at 4k.

Also, ultrawide monitors. They exist, provide more immersion. And typical resolution is 3440x1440 which is high and and the same time have low ppi (basically regular 27" 1440p monitor with extra width). Doubling that is way outside modern GPU capabilities

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

#133

Post by blitzar »

kaibee wrote: post #47
smallmancontrov wrote: post #25

Earlier quoted context omitted.

Yes, but Nvidia thinks enough of them get pushed up to the 5090 to make the gap worthwhile. Only way to fix this is for AMD to decide it likes money. I'm not holding my breath.

Don't necessarily count Intel out.

Intel hate making money even more than AMD.

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

#135

Post by formerly_proven »

sliken wrote: post #123
simondotau wrote: post #60

Earlier quoted context omitted.

Nvidia is also clearly differentiating the 5090 as the gaming card for people who want the best and an extra thousand dollars is a rounding error. They could have sold it for $1500 and still made big coin, but no doubt the extra $500 is pure wealth tax. It probably serves to make the 4070 look reasonably priced, even though it isn't.

Double the bandwidth, double the ram, double the pins, and double the power isn't cheap. I wouldn't be surprised if the profit on the 4090 was less than the 4080, especially since any R&D costs will be spread over significantly less units.

There have been numerous reports over the years that the 4090 actually outsold the 4080.

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

#136

Post by alkonaut »

thefz wrote: post #128

> GeForce RTX 5070 Ti: 2X Faster Than The GeForce RTX 4070 Ti 2x faster in DLSS . If we look at the 1:1 resolution performance, the increase is likely 1.2x.

That's what I'm wondering. What's the actual raw render/compute difference in performance, if we take a game that predates DLSS?

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

#137

Post by diggan »

out_of_protocol wrote: post #131
dijit wrote: post #84

Earlier quoted context omitted.

From all the communication I’ve had with Nvidia, the prevailing sentiment was that the 4090 was an 8K card, that happened to be good for AI due to vram requirements from 8K gaming. However, I’m a AAA gamedev CTO and they might have been telling me what the card means to me .

Well, modern games + modern cards can't even do 4k at high fps and no dlss. 8k story is totally fairy tale. Maybe "render at 540p, display at 8k"-kind of thing? P.S. Also, VR. For VR you need 2x4k at 90+ stable fps. There's (almost) no vr games though

> 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.

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

#138

Post by diggan »

lxdlam wrote: post #125

I have a serious question about the term "AI TOPS". I find many conflicting definitions while others say nothing. A meaningful metric should at least be well defined on its own term, like in "TOPS" or expanded "Tera Operations Per Second", what operation it will measure? Seemingly NVIDIA is just playing number games, like wow 3352 is a huge leap compared to 1321 right? But how does it really help us in LLMs, diffusio…

It would be cool if something like vast.ai's "DLPerf" would become popular enough for the hardware producers to start using it too.

> DLPerf (Deep Learning Performance) - is our own scoring function. It is an approximate estimate of performance for typical deep learning tasks. Currently, DLPerf predicts performance well in terms of iters/second for a few common tasks such as training ResNet50 CNNs. For example, on these tasks, a V100 instance with a DLPerf score of 21 is roughly ~2x faster than a 1080Ti with a DLPerf of 10. [...] Although far from perfect, DLPerf is more useful for predicting performance than TFLops for most tasks.

https://vast.ai/faq#dlperf

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

#139

Post by nickpsecurity »

ryao wrote: post #117
nickpsecurity wrote: post #58

Earlier quoted context omitted.

It's a good question. I'll note that, even in the GPGPU days (eg BrookGPU), they were architecturally designed for graphics applications (eg shaders). The graphics hardware was being re-purposed to do something else. It was quite a stretch to do the other things compared to massively-parallel, general-purpose designs. They started adding more functionality to them, like physics. Now, tensors. While they've come a lon…

GPUs have been processing “tensors” for decades. What they added that is new is explicit “tensor” instructions. A tensor operation is a generalization of a matrix operation to include higher order dimensions. Tensors as used in transformers do not use any of those higher order dimensions. They are just simple matrix operations (either GEMV or GEMM, although GEMV can be done by GEMM). Similarly, vectors are matrices,…

Thanks for the correction and insights!

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

#140

Post by kcb »

ryao wrote: post #104
kcb wrote: post #23

Earlier quoted context omitted.

Yup, the days of the value high end card are dead it seems like. I thought we would see a cut down 4090 at some point last generation but it never happened. Surely there's a market gap somewhere between 5090 and 5080.

The xx90 cards are really Titan cards. The 3090 was the successor to the Titan RTX, while the 3080 Ti was the successor to the 2080 Ti, which succeeded the 1080 Ti. This succession continued into the 40 series and now the 50 series. If you consider the 2080 Ti to be the "value high end card" of its day, then it would follow that the 5080 is the value high end card today, not the 5090.

In all those historical cases the second tier card was a cut down version of the top tier one. Now the 4080 and 5080 are a different chip and there's a gulf of a performance gap between them and the top tier. That's the issue I am highlighting, the 5080 is half a 5090, in the past a 3080 was only 10% off a 3090 performance wise.
Post reply on HN