Jump to content

GeForce 30 series

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 110.159.129.107 (talk) at 18:17, 18 September 2020. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

GeForce 30 series
File:GeForce RTX 30 Series logo with slogan.png
File:RTX3000.png
Geforce RTX 3080
Release dateSeptember 17, 2020; 4 years ago (2020-09-17)
CodenameGA10x
ArchitectureAmpere
ModelsGeForce RTX series
Fabrication processSamsung 8 nm
Cards
High-endGeForce RTX 3070
GeForce RTX 3080
EnthusiastGeForce RTX 3090
API support
DirectXDirect3D 12.0 Ultimate (feature level 12_2)
OpenGLOpenGL 4.6
VulkanVulkan 1.2
History
PredecessorGeForce 20 series

The GeForce 30 series is an upcoming family of graphics processing units developed by Nvidia, succeeding the GeForce 20 series.

The line was announced on September 1, 2020, and started shipping on September 17, 2020.[1][2]

These cards are announced to have real-time raytracing (RTX) with Nvidia's 2nd generation of RT cores and 3rd generation Tensor Cores.[3] They support HDMI 2.1 and DisplayPort 1.4a.[4]

The cards are built on the Ampere architecture, which runs at roughly double the performance and energy efficiency of the preceding Turing architecture.[5][6]

History

Release

The lack of pre-order functionality and high demand resulted in a large number of online retailers struggling with the sheer number of purchases on launch day for the RTX 3080, September 17.[7] Newegg had completely sold out within five minutes of the launch, and stated that they received higher site traffic than would be expected on Black Friday. Long lines formed outside physical stores with stock, such as Microcenter.[8]

Products

All the cards below feature PCIe 4.0 interface and are manufactured using Samsung's 8N (8 nanometer) MOSFET fabrication process.[6] Unlike the GeForce 20 series, the GeForce 30 series lack support for single-root input/output virtualization (SR-IOV) as NVIDIA has decided to reserve the feature for Quadro enterprise class cards.[9]

Model Launch Code name(s) Transistors (billion) Die size
(mm2) 		Shader processors Texture mapping units Render output units Clock speeds Fillrate Memory Processing power (GFLOPS) TDP (watts) NVLink support Launch price

(USD)

Base core clock (MHz) Boost core clock (MHz) Memory (MT/s) Pixel
(GP/s)[a] 		Texture
(GT/s)[b] 		Size (GB) Bandwidth (GB/s) Type Bus width (bit) Single precision (boost) Double precision (boost) Half precision (boost)
GeForce RTX 3070[10] October 15, 2020[11][12] GA104-300-A1 17.4 392.5[13] 5888 184[14] 64 1500 1730 14000 96 (110,7) 276 (318.3) 8 448 GDDR6 256 17664 (20372) 552 (637) 35328 (40745) 220 No $499
GeForce RTX 3080[15] September 17, 2020 GA102-200-K1-A1 28.3 628.4[16][17] 8704 272 96[18] 1440 1710 9500 (19000) [c] [14] 138.2 (164.2)[14] 391.7 (465.1)[14] 10 760 GDDR6X 320 25068 (29768) 783 (930) 50135 (59535) 320 $699
GeForce RTX 3090[19] September 24, 2020 GA102-300-A1 10496 328 112[18] 1400 1700 9750 (19500) [c] [14] 156.8 (190.4)[14] 459.2 (557.6)[14] 24 936 384 29389 (35686) 918 (1115) 58778 (71373) 350 2-way NVLink $1,499
  1. ^ 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.
  2. ^ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
  3. ^ a b Cards with GDDR6X send two bits per transfer. Equivalent transfer rate to GDDR6 in brackets used for comparing bit rate. Please note transfer rate should not be confused with bit rate.

See also

References

  1. ^ https://nvidianews.nvidia.com/news/nvidia-delivers-greatest-ever-generational-leap-in-performance-with-geforce-rtx-30-series-gpus
  2. ^ "GeForce Special Event". Nvidia. Retrieved September 1, 2020.
  3. ^ "NVIDIA GeForce RTX 30 Series GPUs Powered by Ampere Architecture". NVIDIA. Retrieved 2020-09-02.
  4. ^ "Compare Geforce RTX 30 Series Graphics Cards". NVIDIA. Retrieved 2020-09-03.
  5. ^ https://www.anandtech.com/show/16057/nvidia-announces-the-geforce-rtx-30-series-ampere-for-gaming-starting-with-rtx-3080-rtx-3090
  6. ^ a b Walton, Jarred (August 31, 2020). "Nvidia GeForce RTX 3090 and GA102: Everything We Know". Tom's Hardware.
  7. ^ https://www.pcgamer.com/uk/nvidia-geforce-rtx-3080-how-to-buy/
  8. ^ https://www.tomshardware.com/uk/news/nvidia-newegg-rtx-3080-apologize
  9. ^ "Ryan Smith on Twitter". Twitter. Retrieved 2020-09-12.
  10. ^ "NVIDIA GeForce RTX 3070 Graphics Card". NVIDIA. Retrieved 2020-09-01.
  11. ^ "RTX 3080 Founders Edition Review Date". NVIDIA. 2020-09-11. Retrieved 2020-09-11.
  12. ^ "Nvidia's $500 GeForce RTX 3070 gets an October 15 release date". PCWorld. 2020-09-12. Retrieved 2020-09-13.
  13. ^ https://wccftech.com/nvidia-slyly-announces-the-geforce-rtx-3070-availability-sliding-in-before-rx-6000-announcement/amp/
  14. ^ a b c d e f g "NVIDIA GeForce Ampere Architecture, Board Design, Gaming Tech & Software". techpowerup. Retrieved 5 September 2020.
  15. ^ "NVIDIA GeForce RTX 3080 Graphics Card". NVIDIA. Retrieved 2020-09-01.
  16. ^ https://www.nvidia.com/content/dam/en-zz/Solutions/geforce/ampere/pdf/NVIDIA-ampere-GA102-GPU-Architecture-Whitepaper-V1.pdf
  17. ^ https://wccftech.com/nvidia-geforce-rtx-30-series-ampere-graphics-cards-deep-dive/
  18. ^ a b "NVIDIA GeForce RTX 30-Series: Under The Hood Of Ampere". Hot Hardware. Retrieved 5 September 2020.
  19. ^ "NVIDIA GeForce RTX 3090 Graphics Card". www.nvidia.com. Retrieved 2020-09-01.
Notelist
Retrieved from "https://en.wikipedia.org/enwiki/w/index.php?title=GeForce_30_series&oldid=979086177"