NVIDIA Project Beyond GTC Keynote Address: Expect the Expected (RTX 4090)

[btarunr]

NVIDIA just kicked off the GTC Autumn 2022 Keynote address that culminates in Project Beyond, the company's launch vehicle for its next-generation GeForce RTX 40-series graphics cards based on the "Ada" architecture. These are expected to nearly double the performance over the present generation, ushering in a new era of photo-real graphics as we inch closer to the metaverse. NVIDIA CEO Jensen Huang is expected to take center-stage to launch these cards.




15:00 UTC: The show is on the road.


15:00 UTC: AI remains the center focus, including how it plays with gaming.




15:01 UTC: Racer X is a real-time interactive tech demo. Coming soon.
15:02 UTC: Future games will be simulations, not pre-baked- Jensen Huang


15:03 UTC: This is seriously good stuff (RacerX). It runs on a single GPU, in real-time, uses RTX Neural Rendering


15:05 UTC: Ada Lovelace is a huge GPU


15:06 UTC: 76 billion transistors, over 18,000 shaders. 76 billion transistors, Micron GDDR6X memory. Shader execution reordering is major innovation, as big as out-of-order execution for CPUs, gains up to 25% in-game performance. Ada built on TSMC 4 nm, using 4N, a custom process designed in together with NVIDIA.

There's a new streaming multiprocessor design, with a total of 90 TFLOPS. Power efficiency is doubled over Ampere.
Ray Tracing is on the third generation now, with 200 RT TFLOPS and twice the triangle intersection speed.
Deep Learning AI uses 4th gen Tensor Cores, 1400 TFLOPS, "Optical Flow Accelerator"


15:07 UTC: Shader Execution Reordering similar to the one we saw with Intel Xe-HPG


15:08 UTC: Several new hardware-accelerated ray tracing innovations with 3rd gen RTX.


15:09 UTC: DLSS 3 is announced. It brings with it several new innovations, including temporal components, and Reflex latency optimizations. Generates new frames without involving the graphics pipeline.


15:11 UTC: Cyberpunk 2077 to get DLSS 3 and SER. 16 times increase in effective performance using DLSS 3 vs. DLSS 1. MS Flight Simulator to get DLSS 3 support


15:13 UTC: Portal RTX, a remaster just like Quake II RTX, available from November, created with Omniverse RTX Remix.


15:14 UTC: Ada offers a giant leap in total performance. Everything has been increased 40 -> 90 TFLOPS shader, 78 -> 200 TFLOPS RTX, 126 -> 300 TFLOPS OFA, 320 -> 1400 TFLOPS Tensor.


15:17 UTC: Power efficiency is more than doubled, but power goes up to 450 W now.


15:18 UTC: GeForce RTX 4090 will be available on October 12, priced at $1600. It comes with 24 GB GDDR6X and is 2-4x faster than RTX 3090 Ti.


15:18 UTC: RTX 4080 is available in two versions, 16 GB and 12 GB. The 16 GB version starts at $1200, the 12 GB at $900. 2-4x faster than RTX 3080 Ti.


15:19 UTC: New pricing for RTX 30-series, "for mainstream gamers", RTX 40-series "for enthusiasts".


15:19 UTC: "Ada is a quantum leap for gamers"—improved ray tracing, shader execution reordering, DLSS 3.


15:20 UTC: Updates to Omniverse

15:26 UTC: Racer X demo was built by a few dozen artists in just 3 months.


15:31 UTC: Digital twins would play a vital sole in product development and lifecycle maintenence.


15:31 UTC: Over 150 connectors to Omniverse.


15:33 UTC: GDN (graphics delivery network) is the new CDN. Graphics rendering over the Internet will be as big in the future as streaming video is today.


15:37 UTC: Omniverse Cloud, a planetary-scale GDN


15:37 UTC: THOR SuperChip for automotive applications.


15:41 UTC: NVIDIA next-generation Drive

View at TechPowerUp Main Site

 

[DeathtoGnomes]

Future games will be simulations, not pre-baked- Jensen Huang

Thats gonna take a cpu core or two. /s

 

[dgianstefani]

This is some hot stuff.

God damn the omniverse RTX remix tool to remaster old games is insane.

The "digital twin" concept of the omniverse sounds extremely promising too. I have architect friends who have exactly the kind of workflow issues that this will fix.

 

[dir_d]

Those prices are garbage

 

[ExplodingCaps]

Those prices are garbage

Always has been

 

[diatribe]

Those prices are garbage

Pretty much in line with past generations. At least they didn't go crazy with a $2500 4090. $1599, $1199 and $899 for the 4090, 4080(16?) and 4080(12) are not bad considering.

October 12th.

 

[LFaWolf]

I want the 4090 but there is no mention of the power usage.the 4080 16gb is priced too closely to the 4090. Otherwise, that would be my choice.

 

[Chaitanya]

prices are absurd, but given overstock of previous gen not surprising at all.

 

[LifeOnMars]

RTX Remix looks insane.

 

[CyberCT]

What is the availability date of the 4080 16GB? Also October?

 

[TTPPUU]

Prices are fine, I expected $2000 or $2500 for 4090

 

[cvaldes]

What is the availability date of the 4080 16GB? Also October?

It's probably best to wait until they finish their presentation. They may not have covered everything yet.

Or it's possible that they won't address this topic today.

Either way, we will all need to wait until the presentation has concluded. It's not like anyone here can read Jensen's brain.

 

[usiname]

Pretty much in line with past generations. At least they didn't go crazy with a $2500 4090. $1599, $1199 and $899 for the 4090, 4080(16?) and 4080(12) are not bad considering.

October 12th.

Do you know that 4080 12GB is 4070? Literraly $400 bump (80%) for one generation for xx70 card

 

[Zyll Goliat]

Prices are fine, I expected $2000 or $2500 for 4090

Hmm...not sure about that because miners ain't buying like before so maybe the prices are going to be as actual MSRP or close to that......

 

[oxrufiioxo]

The 4080s are more expensive than I expected but the 4090 is cheaper if performance is 2x 3080ti and 3090ti like they claim it's not terrible I guess.

 

[Valantar]

Love how one of Nvidia's announcements here is "yes, the RTX 3060 has the same MSRP as it did a year and a half ago."

Also noticing the "subtle" upward shift of the RTX 4090 now suddenly costing as much as the previous 3090 Ti. And the purposely vague "starting at" price of the 4080. For the 12GB variant, that is. And what are the specs? Do the 12GB and 16GB variants differ beyond VRAM, or are they charging $300 for 4GB of VRAM?

The 4090 sure looks impressive in raw performance, but what about the power draw? Is it 450W, as indicated by that vague graph (which for some reason makes it look like Ampere topped out at 350W)?

 

[Space Lynx]

RDNA3 going to maybe be 5% less fast in pure raw FPS for like $799. Be patient folks. lol that leather jacket tax. I still don't give a flying fuck about Ray Tracing. Come on AMD, give me what I want baby.

 

[defaultluser]

finally out-of-order shaders

going to nab the now guaranteed to be widely-available rtx 4050 8gb with 3060 ti performance level for $270 (or if the eBay crash lasts longer, maybe on-clearance at $215)

 

[dir_d]

Love how one of Nvidia's announcements here is "yes, the RTX 3060 has the same MSRP as it did a year and a half ago."

Also noticing the "subtle" upward shift of the RTX 4090 now suddenly costing as much as the previous 3090 Ti. And the purposely vague "starting at" price of the 4080. For the 12GB variant, that is. And what are the specs? Do the 12GB and 16GB variants differ beyond VRAM, or are they charging $300 for 4GB of VRAM?

The 4090 sure looks impressive in raw performance, but what about the power draw? Is it 450W, as indicated by that vague graph (which for some reason makes it look like Ampere topped out at 350W)?

4080 16Gb is $1200 but with no specs

 

[Dragokar]

The question is, can you buy the FEs without a hassle, or is it just again a lottery. Also, I would like to see the new prices for RTX 30 and the 3060 finally for 329....

 

[oxrufiioxo]

Love how one of Nvidia's announcements here is "yes, the RTX 3060 has the same MSRP as it did a year and a half ago."

Also noticing the "subtle" upward shift of the RTX 4090 now suddenly costing as much as the previous 3090 Ti. And the purposely vague "starting at" price of the 4080 - I assume that's the 12GB. What's the price for the 16GB? What are the specs?

The 4090 sure looks impressive in raw performance, but what about the power draw? Is it 450W, as indicated by that vague graph (which for some reason makes it look like Ampere topped out at 350W)?

Technically the 4090 is 400 cheaper than the launch 3090ti given that it's 2-4x faster depending on what you're doing with it thay isn't bad

The 1200 usd 4080 16GB being twice as fast as a 3080ti likely at lower wattage sounds ok as well

The 4080 12GB at $900 usd is kinda hard to swallow for most though probably I felt they needed a $699 card that performs well above ampere to get more people excited especially given the market I guess that'll be a 4070.

These prices seem more about selling ampere than them wanting to sell 3080s.

 

[Valantar]

The question is, can you buy the FEs without a hassle, or is it just again a lottery. Also, I would like to see the new prices for RTX 30 and the 3060 finally for 329....

Yes, I too would like to see a product finally sold for its MSRP a year and a half after it launched

 

[dir_d]

finally out-of-order shaders

going to nab the now guaranteed to be widely-available rtx 4050 8gb with 3060 ti performance level for $270

He said its for Ray Tracing, didnt say anything about regular shaders for graphics.

 

[Space Lynx]

15:33 UTC: GDN (graphics delivery network) is the new CDN. Graphics rendering over the Internet will be as big in the future as streaming video is today.


Disgusting. These may be the last traditional gpu's we ever get.

 

[cvaldes]

The question is, can you buy the FEs without a hassle, or is it just again a lottery. Also, I would like to see the new prices for RTX 30 and the 3060 finally for 329....

NVIDIA doesn't have that answer. No one here does. The market will determine that. There's a basic economics concept known as supply and demand. NVIDIA controls supply. They don't control demand.

As for the pricing of the 30 Series generation, you'll just have to wait. I believe the announcement isn't over so it's possible they will cover this at a later point whether it be during the actual presentation or in a conventional press release.

Either way, it appears that you are asking questions that can't be answered yet by anyone here.