GeForce 20 series
Release date | September 20, 2018 July 9, 2019 (Super refresh) |
---|---|
Codename | TU10x |
Architecture | Turing |
Models | GeForce RTX series |
Transistors |
|
Fabrication process | TSMC 12 nm (FinFET) |
Cards | |
Mid-range |
|
High-end | |
Enthusiast | GeForce RTX 2080 Ti[3] Nvidia Titan RTX |
API support | |
DirectX | Direct3D 12.0 (feature level 12_1) |
OpenCL | OpenCL 1.2 |
OpenGL | OpenGL 4.6 |
Vulkan | Vulkan 1.2 |
History | |
Predecessor | GeForce 10 series |
Variant | GeForce 16 series |
The GeForce 20 series is a family of graphics processing units developed by Nvidia, and was announced at Gamescom on August 20, 2018[4] and started shipping on September 20, 2018.[5] Serving as the successor to the GeForce 10 series,[6] the 20 series marked the introduction of Nvidia's Turing microarchitecture, and the first generation of RTX cards, the first in the industry to implement realtime hardware ray tracing in a consumer product. On July 2, 2019, the GeForce RTX Super line of cards was announced, which comprises higher-spec versions of the 2060, 2070 and 2080. In a departure from Nvidia's usual strategy, the 20 series doesn't have an entry level range, leaving it to the 16 series to cover this segment of the market.
Architecture
The RTX 20 series is based on the Turing microarchitecture and features real-time hardware ray tracing.[7] The cards are manufactured on an optimized 14 nm node from TSMC, named 12 nm FinFET NVIDIA (FFN).[8] This real-time ray tracing is accelerated by the use of new RT cores, which are designed to process quadtrees and spherical hierarchies, and speed up collision tests with individual triangles.
The ray tracing performed by the RT cores can be used to produce effects such as reflections, refractions, shadows, depth of field, light scattering and caustics, replacing traditional raster techniques such as cube maps and depth maps. Instead of replacing rasterization entirely, however, ray tracing is offered in a hybrid model, in which the information gathered from ray tracing can be used to augment the rasterized shading for more photo-realistic results.
The second generation Tensor Cores (succeeding Volta's) work in cooperation with the RT cores, and their AI features are used mainly to two ends: firstly, de-noising a partially ray traced image by filling in the blanks between rays cast; also another application of the Tensor cores is DLSS (deep learning super-sampling), a new method to replace anti-aliasing, by artificially generating detail to upscale the rendered image into a higher resolution.[9] The Tensor cores apply deep learning models (for example, an image resolution enhancement model) which are constructed using supercomputers. The problem to be solved is analyzed on the supercomputer, which is taught by example what results are desired. The supercomputer then outputs a model which is then executed on the consumer's Tensor cores. These methods are delivered to consumers as part of the cards' drivers.
New features in Turing:
- CUDA Compute Capability 7.5
- Mesh shaders[10]
- Ray tracing (RT) cores – bounding volume hierarchy acceleration[11]
- Tensor (AI) cores – neural net artificial intelligence – large matrix operations
- New memory controller with GDDR6 support
- DisplayPort 1.4a with Display Stream Compression (DSC) 1.2
- PureVideo Feature Set J hardware video decoding
- GPU Boost 4
- NVLink Bridge
- VirtualLink VR
- Improved NVENC codec
- Dedicated Integer (INT) cores for concurrent execution of integer and floating point operations[12]
Nvidia segregates the GPU dies for Turing into A and non-A variants, which is appended or excluded on the hundreds part of the GPU code name. Non-A variants are not allowed to be factory overclocked, whilst A variants are.[13]
The GeForce 20 series was launched with GDDR6 memory chips from Micron Technology. However, due to reported faults with launch models, Nvidia switched to using GDDR6 memory chips from Samsung Electronics by November 2018.[14]
Software
With the GeForce 20 series, Nvidia introduced the RTX development platform. RTX uses Microsoft's DXR, Nvidia's OptiX, and Vulkan for access to ray tracing.[15] The ray tracing technology used in the RTX Turing GPUs was in development at Nvidia for 10 years.[16]
Chipset table
All of the cards in the series are PCIe 3.0 x16 cards, manufactured using a 12 nm FinFET process from TSMC, and use GDDR6 memory (initially Micron chips upon launch, and later Samsung chips from November 2018).[14]
Model | Launch | Code name(s)[17] | Transistors (billion) | Fab (nm) |
Die size (mm2) |
Shader processors | Texture mapping units | Render output units | Ray tracing cores | Tensor cores[a] | SM count[b] |
L2 cache (MB) |
Clock speeds | Fillrate | Memory | Processing power (GFLOPS) | Ray tracing performance | TDP (watts) |
NVLink support |
Launch MSRP (USD) | Code name(s)[17] | Model | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Base core clock (MHz) |
Boost core clock (MHz) |
Memory (MT/s) |
Pixel (GP/s)[c] |
Texture (GT/s)[d] |
Size (GB) |
Bandwidth (GB/s) |
Bus width (bits) |
Single precision (boost) |
Double precision (boost) |
Half precision (boost) |
Rays/s (billions) |
RTX-OPS (trillions) |
Tensor FLOPS (trillions) |
Standard | Founders Edition | |||||||||||||||||
GeForce RTX 2060[18] | January 15, 2019 | TU106-200A-KA-A1 | 10.8 | 12 | 445 | 1920 | 120 | 48 | 30 | 240 | 30 | 3 | 1365 | 1680 | 14000 | 65.52 | 163.8 | 6 | 336 | 192 | 5242 (6451) | 164 (202) | 10483 (12902) | 5 | 37 | 51.6 | 160 | No | $349 | TU106-200A-KA-A1 | GeForce RTX 2060[19] | |
GeForce RTX 2060 TU104 | January 10, 2020 | TU104-150-KC-A1 | 13.6 | 545 | $300 | TU104-150-KC-A1 | GeForce RTX 2060 TU104 | |||||||||||||||||||||||||
GeForce RTX 2060 Super[20][21] | July 9, 2019 | TU106-410-A1 | 10.8 | 445 | 2176 | 136 | 64 | 34 | 272 | 34 | 4 | 1470 | 1650 | 90.05 | 191.4 | 8 | 448 | 256 | 6123 (7181) | 191 (224) | 12246 (14362) | 6 | 41 | 57.4 | 175 | $399 | TU106-410-A1 | GeForce RTX 2060 Super[22][23] | ||||
GeForce RTX 2070[24] | October 17, 2018 | TU106-400-A1 | 2304 | 144 | 36 | 288 | 36 | 1410 | 1620 | 90.24 | 203.04 | 6497 (7465) | 203 (233) | 12994 (14930) | 45 | 59.7 | $499 | — | TU106-400-A1 | GeForce RTX 2070[25] | ||||||||||||
TU106-400A-A1 | 1620+ | 6497 (7465+) | 203 (233+) | 12994 (14930+) | $499+ | $599 | TU106-400A-A1 | |||||||||||||||||||||||||
GeForce RTX 2070 Super[26][27] | July 9, 2019 | TU104-410-A1 | 13.6 | 545 | 2560 | 160 | 40 | 320 | 40 | 1605 | 1770 | 102.72 | 256.8 | 8218 (9062) | 257 (283) | 16435 (18125) | 7 | 52 | 72.5 | 215 | 2-way NVLink | $499 | TU104-410-A1 | GeForce RTX 2070 Super[28][29] | ||||||||
GeForce RTX 2080[30] | September 20, 2018 | TU104-400-A1 | 2944 | 184 | 46 | 368 | 46 | 1515 | 1710 | 96.96 | 278.76 | 8920 (10068) | 279 (315) | 17840 (20137) | 8 | 60 | 80.5 | $699 | — | TU104-400-A1 | GeForce RTX 2080[31] | |||||||||||
TU104-400A-A1 | 1710+ | 8920 (10068+) | 279 (315+) | 17840 (20137+) | $699+ | $799 | TU104-400A-A1 | |||||||||||||||||||||||||
GeForce RTX 2080 Super[32][33] | July 23, 2019 | TU104-450-A1 | 3072 | 192 | 48 | 384 | 48 | 1650 | 1815 | 15500 | 105.6 | 316.8 | 496 | 10138 (11151) | 317 (349) | 20275 (22303) | 63 | 89.2 | 250 | $699 | TU104-450-A1 | GeForce RTX 2080 Super[34][35] | ||||||||||
GeForce RTX 2080 Ti[36] | September 27, 2018 | TU102-300-K1-A1 | 18.6 | 754 | 4352 | 272 | 88 | 68 | 544 | 68 | 5.5 | 1350 | 1545 | 14000 | 118.8 | 367.2 | 11 | 616 | 352 | 11750 (13448) | 367 (421) | 23500 (26896) | 10 | 78 | 107.6 | $999 | — | TU102-300-K1-A1 | GeForce RTX 2080 Ti[37] | |||
TU102-300A-K1-A1 | 1545+ | 11750 (13448+) | 367 (421+) | 23500 (26896+) | $999+ | $1,199 | TU102-300A-K1-A1 | |||||||||||||||||||||||||
Nvidia Titan RTX[38] | December 18, 2018 | TU102-400-A1 | 4608 | 288 | 96 | 72 | 576 | 72 | 6 | 1770 | 129.6 | 388.8 | 24 | 672 | 384 | 12442 (16312) | 389 (510) | 24884 (32625) | 11 | 84 | 130.5 | 280(up to 320W Max) | $2,499 | TU102-400-A1 | Nvidia Titan RTX[39] |
- ^ A Tensor core is a mixed-precision FPU specifically designed for matrix arithmetic.
- ^ The number of Streaming multi-processors on the GPU.
- ^ Pixel fillrate is calculated as the lowest of three numbers: number of ROPs multiplied by the base core clock speed, number of rasterizers multiplied by the number of fragments they can generate per rasterizer multiplied by the base core clock speed, and the number of streaming multiprocessors multiplied by the number of fragments per clock that they can output multiplied by the base clock rate.
- ^ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
See also
References
- ^ "Introducing NVIDIA GeForce RTX 2070 Graphics Card". NVIDIA. Retrieved August 20, 2018.
- ^ "NVIDIA GeForce RTX 2080 Founders Edition Graphics Card". NVIDIA. Retrieved August 20, 2018.
- ^ "Graphics Reinvented: NVIDIA GeForce RTX 2080 Ti Graphics Card". NVIDIA. Retrieved August 20, 2018.
- ^ "GeForce RTX 2080 launch live blog: Nvidia's Gamescom press conference as it happens". TechRadar. Retrieved August 21, 2018.
- ^ "Nvidia's new RTX 2080, 2080 Ti video cards shipped on Sept 20, starting at $799". Ars Technica. Retrieved August 20, 2018.
- ^ "Nvidia unveils powerful new RTX 2070, RTX 2080, RTX 2080 Ti graphics cards". Polygon. Retrieved August 20, 2018.
- ^ "Nvidia announces RTX 2000 GPU series with '6 times more performance' and ray-tracing". The Verge. Retrieved August 20, 2018.
- ^ "NVIDIA Announces the GeForce RTX 20 Series: RTX 2080 Ti & 2080 on Sept. 20th, RTX 2070 in October". Anandtech. Retrieved December 6, 2018.
- ^ "NVIDIA Deep Learning Super-Sampling (DLSS) Shown To Press". www.legitreviews.com. Retrieved September 14, 2018.
- ^ "Introduction to Turing Mesh Shaders". Retrieved September 1, 2019.
- ^ "The NVIDIA Turing GPU Architecture Deep Dive: Prelude to GeForce RTX". AnandTech.
- ^ "NVIDIA Reveals Next-Gen Turing GPU Architecture: NVIDIA Doubles-Down on Ray Tracing, GDDR6, & More". AnandTech.
- ^ "NVIDIA Segregates Turing GPUs; Factory Overclocking Forbidden on the Cheaper Variant". TechPowerUP. Retrieved December 7, 2018.
- ^ a b Maislinger, Florian (November 21, 2018). "Faulty RTX 2080 Ti: Nvidia switches from Micron to Samsung for GDDR6 memory". PC Builder's Club. Retrieved July 15, 2019.
- ^ "NVIDIA RTX™ platform". Nvidia.
- ^ https://www.youtube.com/watch?v=02h_dNl-C-s
- ^ a b NVIDIA no longer differentiates A and non-A GeForce RTX 2070 and 2080 dies after May 2019, with later dies for the affected models marked without 'A' suffix. "Nvidia to Stop Binning Turing A-Dies For GeForce RTX 2080 And RTX 2070 GPUs: Report". Tom's Hardware.
- ^ "NVIDIA GeForce RTX 2060 Graphics Card". NVIDIA.
- ^ "NVIDIA GeForce RTX 2060 Graphics Card". NVIDIA.
- ^ Smith, Ryan. "The GeForce RTX 2070 Super & RTX 2060 Super Review: Smaller Numbers, Bigger Performance". www.anandtech.com. Retrieved July 3, 2019.
- ^ "Your Graphics, Now With SUPER Powers". NVIDIA. Retrieved July 3, 2019.
- ^ Smith, Ryan. "The GeForce RTX 2070 Super & RTX 2060 Super Review: Smaller Numbers, Bigger Performance". www.anandtech.com. Retrieved July 3, 2019.
- ^ "Your Graphics, Now With SUPER Powers". NVIDIA. Retrieved July 3, 2019.
- ^ "NVIDIA GeForce RTX 2070 Graphics Card". NVIDIA.
- ^ "NVIDIA GeForce RTX 2070 Graphics Card". NVIDIA.
- ^ Smith, Ryan. "The GeForce RTX 2070 Super & RTX 2060 Super Review: Smaller Numbers, Bigger Performance". www.anandtech.com. Retrieved July 3, 2019.
- ^ "Your Graphics, Now With SUPER Powers". NVIDIA. Retrieved July 3, 2019.
- ^ Smith, Ryan. "The GeForce RTX 2070 Super & RTX 2060 Super Review: Smaller Numbers, Bigger Performance". www.anandtech.com. Retrieved July 3, 2019.
- ^ "Your Graphics, Now With SUPER Powers". NVIDIA. Retrieved July 3, 2019.
- ^ "NVIDIA GeForce RTX 2080 Founders Edition Graphics Card". NVIDIA.
- ^ "NVIDIA GeForce RTX 2080 Founders Edition Graphics Card". NVIDIA.
- ^ Smith, Ryan. "The GeForce RTX 2070 Super & RTX 2060 Super Review: Smaller Numbers, Bigger Performance". www.anandtech.com. Retrieved July 3, 2019.
- ^ "Your Graphics, Now With SUPER Powers". NVIDIA. Retrieved July 3, 2019.
- ^ Smith, Ryan. "The GeForce RTX 2070 Super & RTX 2060 Super Review: Smaller Numbers, Bigger Performance". www.anandtech.com. Retrieved July 3, 2019.
- ^ "Your Graphics, Now With SUPER Powers". NVIDIA. Retrieved July 3, 2019.
- ^ "Graphics Reinvented: NVIDIA GeForce RTX 2080 Ti Graphics Card". NVIDIA.
- ^ "Graphics Reinvented: NVIDIA GeForce RTX 2080 Ti Graphics Card". NVIDIA.
- ^ "NVIDIA TITAN RTX". NVIDIA. Retrieved December 18, 2018.
- ^ "NVIDIA TITAN RTX". NVIDIA. Retrieved December 18, 2018.
Further reading
- "Nvidia Turing GPU Architecture: Graphics Reinvented" (PDF). Nvidia. Nvidia Corporation.
- https://devblogs.nvidia.com/nvidia-turing-architecture-in-depth/
External links
- Official website
- GeForce RTX Founders Edition Graphics Cards: Cool and Quiet, and Factory Overclocked
- Introducing GeForce RTX SUPER Graphics Cards: Best In Class Performance, Plus Ray Tracing
- Introducing The GeForce RTX 2060: Turing For Every Gamer
- Announcing New GeForce Laptops, Combining New Max-Q Tech with GeForce RTX SUPER GPUs, For Up To 2X More Efficiency Than Last-Gen
- GeForce RTX GPUs Come to 40+ Laptops, Global Availability January 29
- Nvidia Titan RTX
- GeForce RTX 2080 Ti
- GeForce RTX 2080 Super
- GeForce RTX 2080
- GeForce RTX 2070 Super
- GeForce RTX 2070
- GeForce RTX 2060 Super
- GeForce RTX 2060
- Nvidia Nsight