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)
As is usual in all of these kind of presentations, NVIDIA decides on what to highlight and what to relegate to a press release or specification page on the website. It's not like they're going to prattle on for 4-5 hours about every single data point.
And any power specifications they publish would be for reference models or their limited Founders Edition cards.
I don't know if you realize this but AIB partners often build models that exceed NVIDIA's standard specifications. NVIDIA builds in a buffer to left people extract extra performance.
It's really up to third-party reviewers to test individual cards to provide more useful real-world performance metrics. We have to wait a few days/weeks for those to trickle in.
I'm also very interested in how the 12GB varient performs and if it warrants it's 900 price tag.
Maybe I missed it in the keynote but I'm also wondering if DLSS 3.0 is exclusive to Ada
So.... Maybe I'll sit this one out and keep playing on my power sipping 320W 3080
NVIDIA introduces GeForce RTX 4090/4080 series, RTX 4090 launches October 12th for 1599 USD - VideoCardz.com
Another thing to mention is that RTX 4080 12 GB is a different card, not the same as the 16 GB version.
Quite a weird naming, they should call it RTX 4070 12 GB or something...
Say, doesn't GTA usually debut on consoles?
I doubt it, for some of the reasons you stated. But if it does, then it'll be huge. It would imply that at 4K (which they're likely talking about) a 4060 would perform like a 3080, and a 4070 would outperform anything from Ampere.
But if they follow their standard pattern for the last couple of releases, it is more likely a 4060 will get a 30% bump, meaning it will perform like a 3060 Ti at 4K.
I remember I had 2x HD7970 Matrix Platinum to run GTA V at maximum graphics...
Of course this also comes down to GPUs and PC gaming becoming interesting to more people, including more rich people, and thus addressing a broader (and wealthier) market, plus a whole heap of other factors. But it's undeniable that GPU makers' margins have been increasing rapidly in the last few years.Same here. I'd be happy to see that, but not surprised if they kept pace, sadly.
My guess is that the later PC port will run pretty well on mid-tier graphics cards. After all, who would want to play it on a PC using an $800 graphics card if it's only marginally better graphics-wise than a $500 console?
let me guess. an actual board partner card in europe after taxes costs like 2200€+...
A wiser approach would be to wait for third-party PC reviewers to assess performance and then decide yourself on the value proposition that each product has in your market.
I've only visited Germany as a tourist so I don't know if residents have different ideas about how to buy things there. But that would seem to be a more sensible strategy than to look at a model number on a box.
At least here in the USA, Joe Consumer will heavily lean toward whatever is cheaper. Today's cards aren't mass market models though. Joe Consumer buys Toyota Celicas not Mercedes-Benz S600 or whatever.
The last xx80 tier card was $699.
About a week or two ago, rumors for the 4070 disappeared then reappeared as the 12gb 4080. Make no mistake, this is a renamed 4070 with a higher pricetag.
I expected the 4090 to be $2000 and the 16gb 4080 to be about $1000.....but I see what Nvidia did there. Why buy an AIB 16gb 4080 when a 4090 FE will be just $100-200 more?
Nvidia is trying to grab as much money as they can until worldwide economic conditions take a plunge. Also, Shareholders don't know any better and they think high prices means Nvidia has a really good product that can command such a high price.