Well, today is the day folks, NVIDIA is introducing three new ‘SUPER’ graphics cards in their Turing lineup. The new graphics cards include the GeForce RTX 2080 SUPER, the GeForce RTX 2070 SUPER, and the GeForce RTX 2060 SUPER, all of which are pitted against AMD’s entire Radeon lineup.
NVIDIA Launches GeForce RTX SUPER Lineup To Tackle 7nm AMD Navi – GeForce RTX 2080 SUPER Vs AMD Radeon VII, GeForce RTX 2070 SUPER Vs Radeon RX 5700 XT and GeForce RTX 2060 SUPER Vs Radeon RX 5700
The three graphics cards that are being introduced today are going to compete against the entire AMD Radeon 7nm lineup. The cards include the $699 US GeForce RTX 2080 SUPER, the $499 US GeForce RTX 2070 SUPER and the $399 US GeForce RTX 2060 SUPER. All three cards are based on the 12nm Turing GPU architecture and feature revised specs compared to their existing brethren.
NVIDIA GeForce RTX 2080 SUPER – Full TU104 GPU, 15.5 Gbps Memory
Based on the previous information and what we have seen so far, NVIDIA’s GeForce RTX 2080 SUPER would be using the TU104-450 GPU with 3072 CUDA cores, 8 GB of GDDR6 memory and would be clocked in at 15.5 Gbps along with a 256-bit bus interface. This would boost the total bandwidth to 496 GB/s which is just shy of that sweet 500 GB/s figures which could now easily be achieved with a slight overclock.
The core clocks would be maintained at 1650 MHz base and 1815 MHz boost. The card would have a TDP of 250W and would feature 8 Giga Rays/second worth of ray tracing horsepower. The card is expected to launch on the 23rd of July.
In terms of performance, the GeForce RTX 2080 SUPER is said to be around 10-15% faster on average than the Titan XP which makes it a lot faster than the GTX 1080 Ti, a card that the RTX 2080 was only able to match. The card is rated to deliver 11 TFLOPs of FP32 and 11 TFLOPs of INT32 Compute power and the tensor operations are rated at 89 TOPs which are clearly faster than RTX 2080s 10.1 TFLOPs FP32 and around 81 TOPs worth of horsepower.
It is still unclear about the wattage of this card but it is expected to hit the market later this month for $699 US. Those who have been saving up to buy a graphics card would find this a great high-end card compared to the original RTX 2080 or the Radeon VII. The pricing also puts it right next to the Radeon VII and while the RTX 2080 was able to trade blows with the Radeon VII, the RTX 2080 SUPER might end up being much faster at the same price point.
GeForce RTX 2080 SUPER Official Photo Gallery:
NVIDIA GeForce RTX 2070 SUPER – The Navi Killer For $499 US
The NVIDIA GeForce RTX 2070 SUPER is the replacement for the RTX 2070 and while the RTX 2070 was not as popular as its predecessors, the GTX 1070 or the GTX 970, the RTX 2070 SUPER might actually change that. For $499 US, the existing RTX 2070 was clearly priced a bit too high. Even if it was faster than the RTX 1080 ($649 US), the price point was higher for the card to get attention from the mainstream audience who had previously seen the **70 tier cards under $400 US. The RTX 2070 SUPER doesn’t change the price point but it changes the specs and now it’s no longer faster than the GTX 1080, it’s faster than the GTX 1080 Ti and just around the same performance of a reference RTX 2080.
In terms of specifications, the GeForce RTX 2070 SUPER is everything that the rumors have told us. The GeForce RTX 2070 SUPER would be utilizing the Turing TU104-410 GPU with 2560 CUDA Cores, 184 TMUs, and 64 ROPs. It would also feature 320 Tensor Cores and 40 RT cores. The clock speeds would be maintained at 1605 MHz base and 1770 MHz boost with the TGP (Total Graphics Power) being set at 215W. The chip will be accompanied by 8 GB of GDDR6 memory operating at 14Gbps along with a 256-bit wide bus interface, delivering a total bandwidth of 448 GB/s.
When it comes to competition, the card would compete against AMD’s recently announced, 7nm RDNA based Radeon RX 5700 XT which does cost $50 US less but doesn’t have the RTX feature set that GeForce cards do support. In addition to that, while the Radeon RX 5700 XT was shown to be about 10% faster than the RTX 2070 on average, the RTX 2070 SUPER is about 16% faster average and up to 24% faster. It also has a maximum compute power of 9.1 TFLOPs FP32 / 9.1 TFLOPs INT 32 and 72 Tensor OPs. Another surprising fact about this card is that it has 10W lower power than the Radeon offering and the reference design offers two axial tech-based fans compared to just one on AMD’s reference design. So in an all reference battle, you know who the real winner would turn out to be.
GeForce RTX 2070 SUPER Official Photo Gallery:
NVIDIA GeForce RTX 2060 SUPER – More VRAM, More Cores, Higher Clocks For $399
Out of all the cards, the GeForce RTX 2060 SUPER has received one of the major upgrades. The GeForce RTX 2070 SUPER would be utilizing the full Turing TU106-410 GPU die with 2176 CUDA Cores, 136 TMUs, and 64 ROPs. It would also feature 272 Tensor Cores and 32 RT cores. The clock speeds would be maintained at 1470 MHz base and 1650 MHz boost with the TGP (Total Graphics Power) being set at 175W. The chip will be accompanied with 8 GB of GDDR6 memory operating at 14Gbps along with a 256-bit wide bus interface, delivering a total bandwidth of 448 GB/s. The Vram would be the biggest upgrade over the 6 GB RTX 2060 which also featured a cut down 192-bit bus interface.
When it comes to performance, you are paying $100 US lower for the same performance as the GeForce RTX 2070. This places the card ideally against AMD’s Radeon RX 5700 (non-XT) which will be priced at $379 US. The GeForce RTX 2060 SUPER is 15% faster on average than the existing RTX 2060 in 1440p.
GeForce RTX 2060 SUPER Official Photo Gallery:
NVIDIA GeForce RTX 20 SUPER Lineup Specifications:
Graphics Card Name | NVIDIA GeForce RTX 2060 | NVIDIA GeForce RTX 2060 SUPER | NVIDIA GeForce RTX 2070 | NVIDIA GeForce RTX 2070 SUPER | NVIDIA GeForce RTX 2080 | NVIDIA GeForce RTX 2080 SUPER | NVIDIA GeForce RTX 2080 Ti |
---|---|---|---|---|---|---|---|
GPU Architecture | Turing GPU (TU106) | Turing GPU (TU106) | Turing GPU (TU106) | Turing GPU (TU104) | Turing GPU (TU104) | Turing GPU (TU104) | Turing GPU (TU102) |
Process | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN | 12nm FNN |
Die Size | 445mm2 | 445mm2 | 445mm2 | 545mm2 | 545mm2 | 545mm2 | 754mm2 |
Transistors | 10.6 Billion | 10.6 Billion | 10.6 Billion | 13.6 Billion | 13.6 Billion | 13.6 Billion | 18.6 Billion |
CUDA Cores | 1920 Cores | 2176 Cores | 2304 Cores | 2560 Cores | 2944 Cores | 3072 Cores | 4352 Cores |
TMUs/ROPs | 120/48 | 136/64 | 144/64 | 184/64 | 192/64 | 192/64 | 288/96 |
GigaRays | 5 Giga Rays/s | 6 Giga Rays/s | 6 Giga Rays/s | 7 Giga Rays/s | 8 Giga Rays/s | 8 Giga Rays/s | 10 Giga Rays/s |
Cache | 4 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 4 MB L2 Cache | 6 MB L2 Cache |
Base Clock | 1365 MHz | 1470 MHz | 1410 MHz | 1605 MHz | 1515 MHz | 1650 MHz | 1350 MHz |
Boost Clock | 1680 MHz | 1650 MHz | 1620 MHz 1710 MHz OC |
1770 MHz | 1710 MHz 1800 MHz OC |
1815 MHz | 1545 MHz 1635 MHz OC |
Compute | 6.5 TFLOPs | 7.5 TFLOPs | 7.5 TFLOPs | 9.1 TFLOPs | 10.1 TFLOPs | 11.1 TFLOPs | 13.4 TFLOPs |
Memory | Up To 6 GB GDDR6 | Up To 8 GB GDDR6 | Up To 8 GB GDDR6 | Up To 8 GB GDDR6 | Up To 8 GB GDDR6 | Up To 8 GB GDDR6 | Up To 11 GB GDDR6 |
Memory Speed | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps | 14.00 Gbps | 15.50 Gbps | 14.00 Gbps |
Memory Interface | 192-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 352-bit |
Memory Bandwidth | 336 GB/s | 448 GB/s | 448 GB/s | 448 GB/s | 448 GB/s | 496 GB/s | 616 GB/s |
Power Connectors | 8 Pin | 8 Pin | 8 Pin | 8+6 Pin | 8+8 Pin | 8+8 Pin | 8+8 Pin |
TDP | 160W | 175W | 185W (Founders) 175W (Reference) |
215W | 225W (Founders) 215W (Reference) |
250W | 260W (Founders) 250W (Reference) |
Starting Price | $349 US | $399 US | $499 US | $499 US | $699 US | $699 US | $999 US |
Price (Founders Edition) | $349 US | $399 US | $599 US | $499 US | $699 US | $699 US | $1,199 US |
Launch | January 2019 | July 2019 | October 2018 | July 2019 | September 2018 | July 2019 | September 2018 |
In addition to the specs/price update, NVIDIA’s RTX technologies are being widely adopted major game engines and APIs such as Microsft DirectX (DXR), Vulkan, Unreal Engine, Unity and Frostbite. While there were only three RTX titles around the launch of the RTX 20 series cards, NVIDIA claims that they have at least 13 new titles coming soon which would utilize their RTX feature set to offer real-time ray tracing. These titles include the hugely anticipated Cyberpunk 2077, DOOM Eternal, Call of Duty Modern Warfare, Watch Dogs Legion, Wolfenstein Youngblood, and Vampire: The Masquerade – Bloodlines 2. In addition to that, with the upcoming consoles confirmed to feature ray tracing, developers can also make use of the RTX technology to fine-tune future games for the GeForce RTX hardware.
The NVIDIA GeForce RTX 2070 SUPER and GeForce RTX 2060 SUPER are available for purchase right from NVIDIA GeForce’s page but if you’re interested in the custom models, they arrive on 9th July so about a week after the official launch. Let us know your thoughts below of the NVIDIA GeForce RTX SUPER lineup and don’t forget to read our review on the cards here.
Share
Tweet
Submit
[ad_2]