Tuesday, September 20th 2022
NVIDIA Project Beyond GTC Keynote Address: Expect the Expected (RTX 4090)
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
15:02 UTC: Future games will be simulations, not pre-baked- Jensen Huang
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"
15:26 UTC: Racer X demo was built by a few dozen artists in just 3 months.
333 Comments on NVIDIA Project Beyond GTC Keynote Address: Expect the Expected (RTX 4090)
My guess is that NVIDIA prefers to focus on the positive aspects of the new technology in today's event rather than business in today's rockier economic climate.
/s, in case that wasn't clear.I'd really love to see AMD compete on value again. Sadly they haven't seemed motivated to do so since they caught up with the competition in the past couple of years. I might be wrong, but I blame shareholder pressure (and the leadership culture that encourages) to increase margins rather than sales volumes. Such an odd strategy for a company with ~20% market share though.
Other than the 1080ti which launched quite a bit after the 1080 which was the flagship pascal at launch we typically got 30-40% gains at most gen on gen with almost none other than the 2080ti with turning other than RT.
This past gen we got 50% ish 2080ti to 3090
And now it seems 100% for this gen.
Don't get me wrong I think the 4080s are priced too high and the 4090 priced ok but I'll reserve final judgment for reviews.
Nobody had expected that ...
That is also a disadvantage of just-in-time production since barely no one want to have party in stock warehouse.
I am still happy to see new GPUs, but will probably don't use 4080 and 4090 due to its TGP/TDP. My personal max is between 200-250w, and I am not going down that route that the industry is going. Now it is waiting for the full release and RDNA3 as well, beside the Intel VaporArc.
i.e. I don't think it's correct to compare a 2080 Ti to anything other than a 3080 Ti. Otherwise you have to start looking at Titan which doesn't exist now.
It's like if you bought a Ford Fusion before the Ford Taurus came out, and choose to compare the pricing to a new Taurus because the Fusion was the top line Ford sedan at the time you bought it. It's just not a valid comparison, it's a different model that is more upscale. Everyone is doing this in all industries, can't compare house prices from 30 years ago to new houses because new houses are 40% larger.
Me personally I agree with @Dragokar. I want to see what both AMD and Nvidia can do below 225W.
It's not a tree hugger / green thing, I just don't want to get a bigger PSU and noisier GPU for something I spend maybe 10% of my time doing. I also don't like how the market has moved beyond what a typical consumer can do with an OEM rig, which will usually limit you down to a 6-pin power connector for a GPU. It gets even worse when you look at 75W cards, seems like forever since that market has moved much at all.
All these cards could be good or bad depending on performance vs ampere and RDNA3 I'm personally rooting for much better priced amd cards I'm also not holding my breath.
I do think it was a little fishy the games that were used to compare the 4090, i want to see it vs real AAA games. Is the NDA release before Oct 12? so we can see 3rd party reviews before we buy?
The point is that they don't know who the buyer is: a university purchasing agent for some research lab, a PC gamer, a crypto miner (less likely today), or a scalper who won't actually use the card but will sell it to one of the first three.
NVIDIA should actually care about scalpers because customer satisfaction is partially based on the value proposition. By using AIB partners and a third-party retail store marketplace, NVIDIA has very little control over scalping. They had very limited success thwarting scalping of Ampere cards in the USA, even their own Founders Edition models sold directly through their sole representative, Best Buy.
Certainly mining demand won't be there like it was two years ago but there's nothing preventing scalpers from scooping up available 4090 inventory and reselling to gamers, technical users, content creators, etc.
We'll all just have to wait and see what happens in October with the 4090 release.
New DP 2.0 monitors are being validated and certified as we speak, and will launch soon.
For such expensive products, almost 2023 products, it's not acceptable not to move to newly available DP standard. Let's see whether AMD's RDNA3 cards deliver on what has been releaved by Phoronix code. Those cards are thought to have support for 80 Gbps ports in software.