Following Jensen Huang's reveal of the RTX family of Turing-based graphics cards, Asus announced that it will have graphics cards from its ROG Strix, Dual, and Turbo product lines available in mid-September. The new graphics cards will be based around the NVIDIA Geforce RTX 2080 Ti and the Geforce RTX 2080 GPUs.
According to Asus, their new Turing-based graphics cards will be built using their Auto-Extreme technology and with redesigned coolers to increase card-to-card product consistency and cooling efficiency. The triple fan ROG Strix and dual fan Dual series cards use a new 2.7 slot design that results in 20% and 50% increases (respectively) in cooling array surface area versus their 1000 series predecessors. The ROG Strix card uses Axial fans that reportedly offer better airflow and IP5X dust resistance while the Dual series cards use Wing Blade fans that also offer dust resistance along with being allegedly quieter while pushing more air. Meanwhile, the Turbo series uses a blower-style cooler that has been redesigned and uses an 80mm dual ball bearing fan with a new shroud that allows for more airflow even in small cases or when cards are sandwiched together in a multi-GPU setup.
The ROG Strix RTX 2080 Ti and RTX 2080 cards will have one USB Type-C (VirtualLink), two HDMI 2.0b, and two Display Port 1.4a outputs. The Dual RTX 2080 Ti and RTX 2080 cards will have one USB Type-C, one HDMI 2.0b, and three Display Port 1.4 outputs. Finally, the Turbo series RTX 2080 Ti and RTX 2080 cards will have one USB Type-C, one HDMI 2.0b, and two Display Port 1.4 ports.
| RTX 2080 Ti | RTX 2080 | |
|---|---|---|
| GPU | TU102 | TU104 |
| GPU Cores | 4352 | 2944 |
| Base Clock | 1350 MHz (Turbo model) | 1515 MHz (Turbo model) |
| Boost Clock | 1545 MHz (Turbo model) | 1710 MHz (Turbo model) |
| Tensor Cores | 576 | 384 |
| Ray Tracing Speed | 10 GRays/s | 8 GRays/s |
| Memory | 11GB | 8GB |
| Memory Clock | 14000 MHz | 14000 MHz |
| Memory Interface | 352-bit G6 | 256-bit G6 |
| Memory Bandwidth | 616GB/s | 448 GB/s |
| TDP | ? | ? |
| Process Tech | 12nm | 12nm |
Exact specification are still unknown though Asus did reveal clockspeeds for the Turbo models which are listed above. The clockspeeds for the Dual and ROG Strix cards should be quite a bit higher than those thanks to the much beefier coolers, and the OC Editions in particular should be clocked higher than reference specs.
Asus did not disclose exact MSRP pricing, but it did state that several models will be available for pre-order starting today and will be officially avaialble in the middle of September. It appears that a couple RTX 2080 Ti and RTX 2080 cards have already appeared on Newegg, but not all of them have shown up yet. The models slated to be available for preorder include the Dual GeForce RTX 2080 Ti OC Edition, Turbo RTX 2080 Ti, ROG Strix GeForce RTX 2080 OC Edition, and the Dual RTX 2080 OC Edition.
Related reading:
- NVIDIA Announces GeForce RTX 2070, RTX 2080 and RTX 2080 Ti at Gamescom 2018
- Newegg Lists GeForce RTX 2080 and 2080 Ti Graphics Cards Before Announcement
- NVIDIA Announcement Live Stream at 12:00 PM Eastern Today
- NVIDIA Officially Announces Turing GPU Architecture at SIGGRAPH 2018
- Real time ray tracing in still life
Will games out now benefit
Will games out now benefit from the new ray tracing or will that logic need to be built from the ground up and only available in upcoming releases?
Thats THE question. No one
Thats THE question. No one knows EXACTLY what or how this “new fangled tech” will perform.
All Nvidia has done thus far is fuel the hype machine with almost meaningless marketing jargon. As others have pointed out, until Nvidia releases white papers all this is a bit of smoke and mirrors.
Well Ray Tracing done outside
Well Ray Tracing done outside of the ROPs for lighting/Shadow effects can take some of the stress off of the raster piplines. So intead of the fully Raster created light/shadow effects the Ray Traced light/Shadow calculations done on RT cores, or compute Shaders cores will help for gaming.
Ray Tracing libraries have been around a long time done on CPUs and a long time done on GPUs via CUDA/OpenCL so that’s been available. MS’s DXR and even Vulkan/Metal extenions on the API level make use of Ray Tracing libraries. Nvidia’s RT cores can be made available via drivers just like GPU make available various in hardware accelerated sound/other encoding hardware. So Nvidia can make those “RT” cores hardware available via Extentions to DX12/Vuklan/Metal or any other Graphics APIs.
Nvidia in advance of Turing’s release has already created the driver/API and gaming engine software SDK plugin ecosystem to allow games makers to make use of its new Turing features. AMD does the same for any of its New GPU hadrware features, but Nvidia has more funds to help more for that sort of necessary support.
Really software like Blender/Maya/others have extensive Ray Tracing capabilities but they are tuned for non real time full ray tracing effects. But the code base is still the same for CPU/GPU or any other processor based Ray Tacing software. Nvidia just makes more efforts for gaming to optimize that process for games usage of some hybrid Ray Tracing mixed with the standard Raster Operations process on Nvidia’s Turing hardware to get better effects for gaming at high FPS.
Look at the IT’s PowerVR Wizard Ray Tracing demos and that in GPU hardware Ray Tracing when those articles appeared. That Nvidia Ray Tracing is not new look at IT’s PowerVR Wizard demos from 2 years back! Nvidia has the funds to pay for Ray Tracing on treir GPU’s adoption whereas IT’s barely in business and had to be bought out after Apple stopped using IT’s GPU IP. IT lack the funds to get their Ray Tracing adopted but its still available to be licensed by others.
Thank you for the
Thank you for the information!
For those of you that are
For those of you that are interested in what Nvidia’s NVLink based SLI as opposed to the Old SLI Bridge based IP may imply for Dual GPU Gaming on RTX/Turing and future systems. The Hot Chips symposium is ongoing and Nvidia’s NVSwitch Anandtech coverage is interesting(1).
That persentation is now over but the slides and Ians’ commentary is a good read. Both NVLink and AMD’s Infinity Fabric will come into play even more as GPU’s go over to being MCM based at some point in time. But even for Dual GPU gaming both NVLink and Infinity Fabric will begin to play a greater role.
(1)
“Hot Chips 2018: Going Deep on NVSwitch Live Blog (8:45am PT, 3:45pm UTC)
by Ian Cutress on August 21, 2018 11:40 AM EST”
https://www.anandtech.com/show/13251/hot-chips-2018-going-deep-on-nvswitch-live-blog
The base and boost clocks are
The base and boost clocks are backwards for the two cards. The 2080 Ti is faster than the 2080.
Hmm the information i have
Hmm the information i have is:
ASUS TURBO-RTX2080-8G: 1515 MHz / 1710 MHz (base/boost)
ASUS TURBO-RTX2080TI-11G: 1350 MHz / 1545 MHz (base/boost)
The NV website for reference (non FE) cards is 1545 boost for 2080 Ti and 1710 for 2080 as well.
Sorry, you are exactly right.
Sorry, you are exactly right. Bad assumption on my part. I guess it is like a CPU which has more cores but a lower clock rate to prevent them from overheating. Faster overall but each core runs at a lower frequency.
I think i will wait to see
I think i will wait to see EVGAs lineup
14000 MHz VRAM clock….lol!
14000 MHz VRAM clock….lol!
No HDMI 2.1 ports? NVIDIA
No HDMI 2.1 ports? NVIDIA really wants to avoid being compatible with alternatives to G-Sync: HDMI 2.1 VRR.
Hard pass.
I have been keeping an eye on
I have been keeping an eye on GTX 1080Ti prices and they havent moved since this announcement. Should I just wait more or just buy it now?
amazon has one at
amazon has one at $526:
https://www.amazon.com/ZOTAC-GeForce-352-bit-Graphics-ZT-P10810D-10P/dp/B06XXVVQYH/ref=sr_1_2?s=pc&ie=UTF8&qid=1534883663&sr=1-2&keywords=1080ti&refinements=p_n_feature_four_browse-bin%3A16955282011