请输入您要查询的百科知识:

 

词条 GeForce 20 series
释义

  1. Architecture

  2. Development platform

  3. Chipset table

  4. See also

  5. References

  6. Further reading

  7. External links

{{Infobox graphics processing unit
| name = GeForce 20 series
| image =
| img_w =
| caption =
| date = {{start date and age|September 20, 2018}}
| created =
| codename = TU10x
| architecture = Turing
| model = GeForce RTX series
| cores-nothread =
| numcores =
| process =
| fab = TSMC
| transistors1 = 10.6B 12 nm (TU106)
| transistors2 = 13.6B 12 nm (TU104)
| transistors3 = 18.6B 12 nm (TU102)
| midrange = GeForce RTX 2060
| highend = GeForce RTX 2070[1]{{ubl|GeForce RTX 2080[2]}}
| enthusiast = GeForce RTX 2080 Ti[3]
NVIDIA TITAN RTX
| d3dversion = Direct3D 12.0 (feature level 12_1)
| openclversion = OpenCL 1.2
| openglversion = OpenGL 4.6
| vulkanapi = Vulkan 1.1
| predecessor = GeForce 10 series
| variant = GeForce 16 series
| successor = {{abbr|TBA|To be announced}}
}}

The GeForce 20 Series is a family of graphics processing units developed by Nvidia, and was announced at Gamescom on August 20, 2018.[4] It is the successor to the GeForce 10 series,[5] and started shipping on September 20, 2018.[6]

Architecture

{{Main|Turing (microarchitecture)}}

The RTX 20 series is based on the Turing microarchitecture and features real-time ray tracing.[7] The cards are manufactured on an optimized 16nm node from TSMC, named 12nm 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 reflections, refractions and shadows, replacing traditional raster techniques such as cube maps and depth maps. Instead of replacing rasterization entirely, however, the information gathered from ray tracing can be used to augment the shading with information that is much more photo-realistic, especially in regards to off-camera action. This can only be utilized on games that support ray-tracing, which led to some controversy at launch because few games supported the feature at the time.

The second-generation Tensor cores (succeeding Volta's) work in cooperation with the RT cores, and are used to fill in the blanks in a partially ray traced image, a technique known as de-noising. Another of the applications of the Tensor cores is a new method to replace anti-aliasing called DLSS (deep learning super-sampling).[9] The Tensor cores perform the result of deep learning on supercomputers to codify how to, for example, increase the resolution of images. In the Tensor cores' primary usage, a problem to be solved is analyzed on a supercomputer, which is taught by example what results are desired, and the supercomputer determines a method to use to achieve those results, which is then done with the consumer's Tensor cores. These methods are delivered "over the air" to consumers.

New features in Turing:

  • CUDA Compute Capability 7.5
  • Ray tracing (RT) cores – bounding volume hierarchy acceleration[10]
  • 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

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.[11]

Development platform

{{main|Nvidia RTX}}

Nvidia RTX is the development platform introduced with the GeForce 20 series. RTX uses Microsoft's DXR, Nvidia's OptiX, and Vulkan for access to ray tracing.[12] The ray tracing technology used in the RTX Turing GPUs was in development at Nvidia for 10 years.[13]

Chipset table

ModelLaunchCode name(s)Fab (nm)Transistors (billion)Die size (mm2)Bus interfaceShader processorsTexture mapping unitsRender output unitsRay tracing coresTensor cores{{efn|name="Tensor cores"SM count{{efn|name="SMs"L2 cache (KB)Clock speedsFillrateMemoryProcessing power (GFLOPS)Ray tracing performanceTDP (watts)NVLink SupportLaunch price (USD)
Base core clock (MHz) Boost core clock (MHz) Memory (MT/s)name="pixel fillrate"name="texture fillrate" Size (GB) Bandwidth (GB/s) Bus type Bus width (bit) Single precision (Boost) Double precision (Boost) Half precision (boost) Rays/s (Billions) RTX-OPS (Trillions) Tensor FLOPS (Trillions)MSRP Founders Edition
GeForce RTX 2060[14] January 15, 2019 TU106-200A-KA-A11210.8445PCIe 3.0 x1619201204830240303072136516801400065.52163.86336GDDR61925242 (6451)164 (202)10483 (12902)53752160 rowspan="3" {{No}}$349
GeForce RTX 2070[15]October 17, 2018TU106-400-A1230414464362883640961410162090.24203.0484482566497 (7465)203 (233)12994 (14930)64559.7175$499{{N/A}}
TU106-400A-A11620+6497 (7465+)203 (233+)12994 (14930+)$499+$599
GeForce RTX 2080[16]September 20, 2018TU104-400-A113.654529441846446368461515171096.96278.768920 (10068)279 (315)17840 (20137)86080.52152-way NVLink$699{{N/A}}
TU104-400A-A11710+8920 (10068+)279 (315+)17840 (20137+)$699+$799
GeForce RTX 2080 Ti[17]September 27, 2018TU102-300-K1-A118.67544352272886854468614413501545118.8367.21161635211750 (13448)367 (421)23500 (26896)1078107.6250$999{{N/A}}
TU102-300A-K1-A11545+11750 (13448+)367 (421+)23500 (26896+)$999+$1,199
NVIDIA TITAN RTX[18]December 18, 2018TU102-400-A146082889672576721770129.6388.82467238412442 (16312)389 (510)24884 (32625)1184130280$2,499
{{notelist|refs={{efn|name="Tensor cores"|A Tensor core is a mixed-precision FPU specifically designed for matrix arithmetic.}}{{efn|name="SMs"|The number of Streaming multi-processors on the GPU.}}{{efn|name="pixel fillrate"|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.}}{{efn|name="texture fillrate"|Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.}}
}}

See also

{{Portal|Computers}}
  • GeForce 10 series
  • GeForce 16 series
  • Nvidia Quadro
  • Nvidia Tesla

References

1. ^{{Cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2070/|title=Introducing NVIDIA GeForce RTX 2070 Graphics Card|website=NVIDIA|language=en-us|access-date=2018-08-20}}
2. ^{{Cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080/|title=NVIDIA GeForce RTX 2080 Founders Edition Graphics Card|website=NVIDIA|language=en-us|access-date=2018-08-20}}
3. ^{{Cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080-ti/|title=Graphics Reinvented: NVIDIA GeForce RTX 2080 Ti Graphics Card|website=NVIDIA|language=en-us|access-date=2018-08-20}}
4. ^{{Cite news|url=https://www.techradar.com/news/nvidia-gamescom-2018-press-conference-live-blog-will-we-see-the-geforce-rtx-2080|title=GeForce RTX 2080 launch live blog: Nvidia's Gamescom press conference as it happens|work=TechRadar|access-date=2018-08-21|language=en}}
5. ^{{Cite news|url=https://www.polygon.com/2018/8/20/17760038/nvidia-geforce-rtx-2080-ti-2070-specs-release-date-price-turing|title=Nvidia unveils powerful new RTX 2070, RTX 2080, RTX 2080 Ti graphics cards|work=Polygon|access-date=2018-08-20}}
6. ^{{Cite news|url=https://arstechnica.com/gaming/2018/08/nvidia-announces-new-raytracing-focused-rtx-2080-2080-ti-graphics-cards/|title=Nvidia’s new RTX 2080, 2080 Ti video cards shipped on Sept 20, starting at $799|work=Ars Technica|access-date=2018-08-20|language=en-us}}
7. ^{{Cite news|url=https://www.theverge.com/2018/8/20/17758724/nvidia-geforce-rtx-2080-specs-pricing-release-date-features|title=Nvidia announces RTX 2000 GPU series with ‘6 times more performance’ and ray-tracing|work=The Verge|access-date=2018-08-20}}
8. ^{{Cite news|url=https://www.anandtech.com/show/13249/nvidia-announces-geforce-rtx-20-series-rtx-2080-ti-2080-2070|title=NVIDIA Announces the GeForce RTX 20 Series: RTX 2080 Ti & 2080 on Sept. 20th, RTX 2070 in October|work=Anandtech|access-date=2018-12-06}}
9. ^{{Cite web|url=https://www.legitreviews.com/nvidia-deep-learning-super-sampling-dlss-shown-to-press_207461|title=NVIDIA Deep Learning Super-Sampling (DLSS) Shown To Press|website=www.legitreviews.com|language=en||access-date=2018-09-14}}
10. ^{{cite web|url=https://www.anandtech.com/show/13282/nvidia-turing-architecture-deep-dive/5|title=The NVIDIA Turing GPU Architecture Deep Dive: Prelude to GeForce RTX|publisher=AnandTech}}
11. ^{{Cite news|url=https://www.techpowerup.com/247660/nvidia-segregates-turing-gpus-factory-overclocking-forbidden-on-the-cheaper-variant|title=NVIDIA Segregates Turing GPUs; Factory Overclocking Forbidden on the Cheaper Variant|work=TechPowerUP|access-date=2018-12-07}}
12. ^{{cite web|url=https://developer.nvidia.com/rtx|title=NVIDIA RTX™ platform|publisher=Nvidia}}
13. ^https://www.youtube.com/watch?v=02h_dNl-C-s
14. ^{{cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2060/|title=NVIDIA GeForce RTX 2060 Graphics Card|website=NVIDIA}}
15. ^{{cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2070/|title=NVIDIA GeForce RTX 2070 Graphics Card|website=NVIDIA}}
16. ^{{cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080/|title=NVIDIA GeForce RTX 2080 Founders Edition Graphics Card|website=NVIDIA}}
17. ^{{cite web|url=https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080-ti/|title=Graphics Reinvented: NVIDIA GeForce RTX 2080 Ti Graphics Card|website=NVIDIA}}
18. ^{{Cite web|url=https://www.nvidia.com/en-us/titan/titan-rtx/|title=NVIDIA TITAN RTX|website=NVIDIA|language=en-us|access-date=2018-12-18}}

Further reading

  • {{Cite web|url=https://web.archive.org/web/20180924094921/https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf|title=Nvidia Turing GPU Architecture: Graphics Reinvented|publisher=Nvidia Corporation|work=Nvidia}}

External links

  • {{official|https://www.nvidia.com/en-us/geforce/20-series/}}
  • [https://www.nvidia.com/en-us/geforce/news/geforce-rtx-founders-graphics-card-breakdown/ GeForce RTX Founders Edition Graphics Cards: Cool and Quiet, and Factory Overclocked]
  • [https://www.nvidia.com/en-us/geforce/news/nvidia-geforce-rtx-2060/ Introducing The GeForce RTX 2060: Turing For Every Gamer]
  • [https://www.nvidia.com/en-us/geforce/news/geforce-rtx-20-series-laptops/ GeForce RTX GPUs Come to 40+ Laptops, Global Availability January 29]
  • [https://www.nvidia.com/en-us/titan/titan-rtx/ NVIDIA TITAN RTX]
  • [https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080-ti/ GeForce RTX 2080 Ti]
  • [https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080/ GeForce RTX 2080]
  • [https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2070/ GeForce RTX 2070]
  • [https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2060/ GeForce RTX 2060]
  • [https://developer.nvidia.com/nsight-visual-studio-edition Nvidia Nsight]
{{NVIDIA}}

4 : Computer-related introductions in 2018|GeForce Series|Graphics processing units|Video cards

随便看

 

开放百科全书收录14589846条英语、德语、日语等多语种百科知识,基本涵盖了大多数领域的百科知识,是一部内容自由、开放的电子版国际百科全书。

 

Copyright © 2023 OENC.NET All Rights Reserved
京ICP备2021023879号 更新时间:2024/9/21 0:52:38