Rtx 3000 wiki

Rtx 3000 wiki DEFAULT

Radeon RX 6000 series

Series of video cards by AMD

Not to be confused with the Radeon HD 6000 series, an earlier series of GPUs developed by AMD.

AMD Radeon RX 6000 series wordmark.png
RX6900XT.jpg
Release dateRadeon RX 6600 and 6600 XT August 11, 2021; 2 months ago (2021-08-11)
Radeon RX 6700 XT March 18, 2021; 6 months ago (2021-03-18)
Radeon RX 6800 and Radeon RX 6800 XT November 18, 2020; 10 months ago (2020-11-18)
Radeon RX 6900 XT December 8, 2020; 10 months ago (2020-12-08)
Radeon RX 6600M, 6700M, and 6800M June 1, 2021; 4 months ago (2021-06-01)
CodenameNavi 2X (nicknamed "Big Navi")
ArchitectureRDNA 2
Transistors
  • 11.06B (Navi 23)[1]
  • 17.2B (Navi 22)
  • 26.8B (Navi 21)
Fabrication processTSMC7 nm
Mid-rangeRadeon RX 6600M
Radeon RX 6600
Radeon RX 6600 XT
High-endRadeon RX 6700M
Radeon RX 6700 XT
Radeon RX 6800M
Radeon RX 6800
Radeon RX 6800 XT
EnthusiastRadeon RX 6900 XT
PredecessorRadeon RX 5000 series

The Radeon RX 6000 series is a series of graphics processing units developed by AMD, based on their RDNA 2 architecture.[2] It was announced on October 28, 2020[3] and is the successor to the Radeon RX 5000 series. The lineup consists of the RX 6600, RX 6600 XT, RX 6700 XT, RX 6800, RX 6800 XT and RX 6900 XT for desktop computers, and the RX 6600M, RX 6700M, and RX 6800M for laptops.[4][5]

The lineup is designed to compete with Nvidia's GeForce 30 series of cards. These GPUs are also the first generation of AMD GPUs that support hardware accelerated real-time ray tracing.[6]

History[edit]

On September 14, 2020, AMD first teased the physical design of its RX 6000 series through a tweet shared on social messaging service Twitter. At the same time, the company launched a virtual island inside the video game Fortnite that contained a large-scale rendition of the RX 6000 hardware design, which players could freely explore using the game's "Creative" mode.[7]

AMD officially unveiled the first three cards of the lineup, the RX 6800, RX 6800 XT, and RX 6900 XT, in an event titled "Where Gaming Begins: Ep. 2" on October 28.[8] In the event, AMD announced the RX 6800 XT as its flagship graphics processor, comparing its performance to that of Nvidia's RTX 3080 graphics card in 1440p and 4K resolution gaming. The 6800 XT was announced with a price tag of $649 USD, which is $50 lower than the RTX 3080's starting price of $699.[8] AMD then introduced the RX 6800 as a competitor to Nvidia's previous-generation RTX 2080 Ti, but with a significantly lower price tag of $579, compared to $999 for the 2080 Ti.[8] Lastly, AMD introduced the RX 6900 XT as its top card of the lineup, claiming it produces similar performance to Nvidia's RTX 3090 but with lower power consumption, and announced a launch price of $999, $500 cheaper than the RTX 3090.[8]

The Radeon RX 6800 and 6800 XT were released on November 18, 2020, and the RX 6900 XT was released on December 8, 2020.[9][10]

On February 3, 2021, Gigabyte registered a range of RX 6700 XT graphics cards with the Eurasian Economic Commission (EEC), with the filing indicating that all seven registered models will ship with 12 GB of memory.[11] On March 3, 2021, AMD officially announced the RX 6700 XT graphics card, set to compete with Nvidia's RTX 3060 Ti and 3070 cards.[12] The card launched on March 18, 2021.[4]

On May 31, 2021, AMD announced the RX 6000M series of GPUs designed for laptops.[13][14] These include the RX 6600M, RX 6700M, and RX 6800M. These were made available beginning on June 1.[13]

On June 23, Gigabyte registered six RX 6600 XT graphics cards with the EEC, indicating that they would all have 8 GB of memory.[15][16][17] This was just over a month after ASRock had made similar filings for both the RX 6600 and 6600 XT, which listed 8 GB of memory for both models.[18][19][20] On July 5, VideoCardz discovered that Taiwanese graphics card retailer PowerColor had already created product pages for the unannounced Radeon 6600 and 6600 XT GPUs.[21][22]

On July 30, AMD announced the RX 6600 and 6600 XT GPUs, which were later released on August 11, 2021. The RX 6600 XT is available for $379 USD MSRP.[23]

Availability issues[edit]

See also: 2020–21 global chip shortage

Much like Nvidia's competing GeForce 30 series, releases sold out almost immediately, due to a combination of low stock and scalping bots.[24]

RX 6800 and 6800 XT[edit]

The RX 6800 and 6800 XT were launched on November 18, 2020, but due to low stock availability, they sold out at most retailers on the same day.[9][25][26] American retailer Micro Center restricted all sales to in-store only, claiming that stock "will be extremely limited at launch".[27]PCMag reported that stock for both cards on Newegg had sold out as early as 6:05 a.m. PST, and that stock was unavailable on AMD's own store website by 6:11 a.m.[25] Retailer B&H Photo Video outright refused to accept orders for the graphics cards, stating in part, "we do not know and are therefore unable to provide a date or time for when these items will become available to purchase."[25]

Scalpers were reportedly re-selling the GPUs on eBay for around US$1000 - $1500, roughly double the initial launch price.[9] Some frustrated social media users attempted to derail the listings by using bots to make fake bids on the scalped GPUs at absurd prices; in one instance, an auction for an RX 6800 XT saw bids go as high as $70,000.[28]

RX 6900 XT[edit]

The RX 6900 XT was launched on December 8, 2020, and similarly to the RX 6800 and 6800 XT, it sold out on the same day it was released.[29][10] According to PCMag, it was listed as out of stock on Newegg by 6:02 a.m. PST, just two minutes after it went on sale. AMD's store website, struggling to keep up with the high number of visitors, kept displaying 503 Service Temporarily Unavailable errors to customers attempting to buy the graphics card; by 6:35 a.m., it was sold out.[10]

Products[edit]

Desktop[edit]

Model
(codename)
Release Date
& Price
Architecture
& Fab
Transistors
& Die Size
Core Fillrate[a][b][c]Processing power[a][d]
(GFLOPS)
Memory TBPBus
interface
Config[e]Clock[a] (MHz) Texture
(GT/s)
Pixel
(GP/s)
HalfSingleDoubleSize
(GB)
Bandwidth
(GB/s)
Bus type
& width
Clock
(MT/s)
Infinity Cache Size
(MB)
Infinity Cache Bandwidth
(GB/s)
Radeon RX 6600
(Navi 23)[30]
October 13, 2021

$329 USD

RDNA 2
TSMC N7
11.06×109
237 mm2
1792:112:64

28 CU

1626

2491

228.9

279

130.8

159.4

14,654

17,860

7,325

8,928

457.8

558.0

8 224 GDDR6
128-bit
14000 32 832 132 W PCIe 4.0

x8[31]

Radeon RX 6600 XT
(Navi 23)[32][31][33][34]
August 11, 2021
$379 USD
2048:128:64
32 CU
1968
2589
251.9
331.4
126.0
165.7
16,122
21,209
8,061
10,605
503.8
662.8
256 16000 160 W
Radeon RX 6700 XT
(Navi 22)[35][36][37]
March 18, 2021
$479 USD
17.2×109
335 mm2
2560:160:64
40 CU
2321
2581
371.4
413
148.5
165.2
23,767
26,429
11,884
13,215
742.7
825.9
12 384 GDDR6
192-bit
96 1248 230 W PCIe 4.0

x16

Radeon RX 6800
(Navi 21) [38][39][40][41]
November 18, 2020
$579 USD
26.8×109
519.8 mm2
3840:240:96
60 CU
1700
2105
408
505.2
163.2
202.1
26,112
32,333
13,056
16,166
816
1,010.4
16 512 GDDR6
256-bit
128 1664 250 W
Radeon RX 6800 XT
(Navi 21) [38][39][42][41]
November 18, 2020
$649 USD
4608:288:128
72 CU
1825
2250
525.6
648
233.6
288
33,638
41,472
16,819
20,736
1,051.2
1,296
300 W
Radeon RX 6900 XT
(Navi 21) [38][39][43][41]
December 8, 2020
$999 USD
5120:320:128
80 CU
1825
2250
584
720
233.6
288
37,376
46,080
18,688
23,040
1,168
1,440
  1. ^ abcBoost values (if available) are stated below the base value in italic.
  2. ^Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
  3. ^Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
  4. ^Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  5. ^Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)

Mobile[edit]

Model Release
Date
GPU Memory Performance TBP
Type Config Clock Size Clock Bus type
& width
Processing power
(TFLOPS)
Fillrate Bandwidth
(GB/s)
ROPs CUs ALUs Texture Base Boost 32 bit 64 bit Pixel
(GP/s)
Texel
(GT/s)
Radeon RX 6600M[44]June 1, 2021 Navi 23 64 28 1792 128 n.n.2177 MHz 8 GB 7000 MHz 128-bit
GDDR6
7.80 n.n.147.2 278.7 224 100 W
Radeon RX 6700M[45]Navi 22 64 36 2304 144 n.n.2300 MHz 10 GB 8000 MHz 160-bit
GDDR6
10.60 n.n.147.2 331.2 320 135 W
Radeon RX 6800M[46]64 40 2560 160 2300 MHz n.n.12 GB 8000 MHz 192-bit
GDDR6
11.78 n.n.147.2 368.0 384 145+ W

See also[edit]

References[edit]

  1. ^Mujtaba, Hassan (August 31, 2021). "AMD Radeon RX 6900 XTX Graphics Card Rumored To Feature 18 Gbps GDDR6 Memory, Increased Clock Speeds With Navi 21 XTXH GPU, Faster Than RTX 3090". Wccftech. Retrieved October 2, 2021.
  2. ^"AMD Teases Radeon RX 6000 Card Performance Numbers: Aiming For 3080?". anandtech.com. AnandTech. October 8, 2020. Retrieved October 25, 2020.
  3. ^"AMD Announces Ryzen "Zen 3" and Radeon "RDNA2" Presentations for October: A New Journey Begins". anandtech.com. AnandTech. September 9, 2020. Retrieved October 25, 2020.
  4. ^ abRidley, Jacob (March 3, 2021). "AMD RX 6700 XT graphics card release date, specs, performance, and price". PC Gamer. Retrieved March 3, 2021.
  5. ^Cutress, Ian (January 12, 2021). "AMD to Launch Mid-Range RDNA 2 Desktop Graphics in First Half 2021". AnandTech. Retrieved January 4, 2021.
  6. ^Judd, Will (October 28, 2020). "AMD unveils three Radeon 6000 graphics cards with ray tracing and RTX-beating performance". Eurogamer. Retrieved August 1, 2021.
  7. ^Goslin, Austen (September 15, 2020). "AMD gives fans first look at new RX 6000 graphics cards ... in Fortnite". Polygon. Retrieved January 22, 2021.
  8. ^ abcdGoslin, Austen; Sarkar, Samit (October 28, 2020). "AMD announces Radeon RX 6000 series GPUs". Polygon. Retrieved January 22, 2021.
  9. ^ abcKlotz, Aaron (November 18, 2020). "Paper Launch? Radeon RX 6800, 6800 XT Out of Stock". Tom's Hardware. Retrieved January 8, 2021.
  10. ^ abcKan, Michael (December 9, 2020). "AMD's Radeon RX 6900 XT Graphics Cards Immediately Sell Out". PCMag. Retrieved January 20, 2021.
  11. ^Tyson, Mark (February 4, 2021). "Gigabyte Radeon RX 6700 XT range registered with the EEC". Hexus. Retrieved February 10, 2021.
  12. ^Judd, Will (March 3, 2021). "AMD announces $479 RX 6700 XT graphics card for 1440p gaming". Eurogamer. Retrieved March 3, 2021.
  13. ^ abChin, Monica (May 31, 2021). "AMD announces the Radeon RX 6000M series with RDNA 2 architecture". The Verge. Retrieved June 1, 2021.
  14. ^Takahashi, Dean (May 31, 2021). "AMD launches Radeon RX 6000M GPUs for gaming laptops". VentureBeat. Retrieved June 1, 2021.
  15. ^"Gigabyte expects Radeon RX 6600 XT to feature 8GB of memory". VideoCardz. June 23, 2021. Retrieved July 15, 2021.
  16. ^Thubron, Rob (June 23, 2021). "Gigabyte lists six AMD Radeon RX 6600 XT cards on EEC website". TechSpot. Retrieved July 15, 2021.
  17. ^White, Monica (June 23, 2021). "New leak shows that Gigabyte is releasing six RX 6600 XT cards". Digital Trends. Retrieved July 15, 2021.
  18. ^Ridley, Jacob (May 11, 2021). "Manufacturer hints at 8GB VRAM for AMD's unreleased RX 6600-series". PC Gamer. Retrieved July 15, 2021.
  19. ^Allan, Darren (May 11, 2021). "AMD RX 6600 and 6600 XT GPUs could have less VRAM than expected". TechRadar. Retrieved July 15, 2021.
  20. ^"ASRock Radeon RX 6600 (XT) series spotted in EEC filing". VideoCardz. May 11, 2021. Retrieved July 15, 2021.
  21. ^"AMD Radeon RX 6600 XT and RX 6600 listed on PowerColor website". VideoCardz. July 5, 2021. Retrieved July 15, 2021.
  22. ^Alderson, Alex (July 5, 2021). "PowerColor confirms that AMD is on the verge of announcing the Radeon RX 6600 and RX 6600 XT". Notebookcheck. Retrieved July 15, 2021.
  23. ^Ridley, Jacob (July 30, 2021). "AMD announces '1080p beast' Radeon RX 6600 XT for $379". PC Gamer. Retrieved July 30, 2021.
  24. ^Deakin, Daniel (December 15, 2020). "Nvidia GeForce RTX 30 series scalping generates over US$22 million in sales via eBay as AMD's Big Navi GPUs and Zen 3 CPUs also fall victim to profiteering". Notebook Check. Retrieved January 8, 2021.
  25. ^ abcKan, Michael (November 18, 2020). "AMD's Radeon RX 6800 Cards Sell Out Instantly, Sparking Cries of 'Paper Launch'". PCMag. Retrieved January 8, 2021.
  26. ^Sandhu, Tarinder (November 18, 2020). "AMD Radeon RX 6800 and RX 6800 XT stock levels disarmingly low". Hexus. Retrieved January 8, 2021.
  27. ^James, Dave (November 18, 2020). "AMD RX 6800-series stock 'extremely limited' at launch today". PC Gamer. Retrieved January 8, 2021.
  28. ^Martin, Alexander (November 27, 2020). "Gamers derail eBay listings to stop hardware scalpers profiting on latest technology". Sky News UK. Retrieved January 8, 2021.
  29. ^Endicott, Sean (December 8, 2020). "AMD Radeon RX 6900 XT is sold out, but you can still buy one in a prebuilt PC". Windows Central. Retrieved January 8, 2021.
  30. ^"AMD Radeon RX 6600 Graphics Card".
  31. ^ ab"AMD Radeon RX 6600 XT Specs". TechPowerUp. Retrieved August 6, 2021.
  32. ^"AMD Radeon RX 6600 XT Graphics". Amd.com. Retrieved July 30, 2021.
  33. ^"AMD Radeon RX 6600 XT". Phoronix. Retrieved July 30, 2021.
  34. ^"AMD announces Radeon RX 6600 XT at 379USD". VideoCardz.com. Retrieved July 30, 2021.
  35. ^"AMD Radeon RX 6700 XT Graphics".
  36. ^"AMD Radeon RX 6700 XT". TechPowerUp.
  37. ^"AMD Radeon RX 6700 XT 12 GB Reference Edition Review". Retrieved March 29, 2021.
  38. ^ abc"Compare Graphics Specifications". Retrieved October 28, 2020.
  39. ^ abcSmith, Ryan (October 28, 2020). "AMD Reveals The Radeon RX 6000 Series: RDNA2 Starts At The High-End, Coming November 18th". AnandTech. Retrieved October 28, 2020.
  40. ^"AMD Radeon RX 6800 Specs". TechPowerUp. Retrieved November 27, 2020.
  41. ^ abc"The new generation Radeon is based on "infinite cache"". Retrieved March 29, 2021.
  42. ^"AMD Radeon RX 6800 XT Specs". TechPowerUp. Retrieved November 27, 2020.
  43. ^"AMD Radeon RX 6900 XT Specs". TechPowerUp. Retrieved November 27, 2020.
  44. ^"AMD Radeon™ RX 6600M Mobile Graphics". AMD. Retrieved October 11, 2021.
  45. ^"AMD Radeon™ RX 6700M Mobile Graphics". AMD. Retrieved October 11, 2021.
  46. ^"AMD Radeon™ RX 6800M Mobile Graphics". AMD. Retrieved October 11, 2021.

External links[edit]

Sours: https://en.wikipedia.org/wiki/Radeon_RX_6000_series

Engineering:Nvidia Quadro

Short description
Brand of Nvidia graphics cards intended for use in workstations running professional applications

Quadro is Nvidia's brand for graphics cards intended for use in workstations running professional computer-aided design (CAD), computer-generated imagery (CGI), digital content creation (DCC) applications, scientific calculations and machine learning.

The GPU chips on Quadro-branded graphics cards are identical to those used on GeForce-branded graphics cards. Differences between the Quadro and GeForce cards include the use of ECC memory and enhanced floating point precision. These are desirable properties when the cards are used for calculations which, in contrast to graphics rendering, require reliability and precision.

The Nvidia Quadro product line directly competes with AMD's Radeon Pro line of professional workstation cards.[1]

History

The Quadro line of GPU cards emerged in an effort towards market segmentation by Nvidia.(citation?) In introducing Quadro, Nvidia was able to charge a premium for essentially the same graphics hardware in professional markets, and direct resources to properly serve the needs of those markets. To differentiate their offerings, Nvidia used driver software and firmware to selectively enable features vital to segments of the workstation market, such as high-performance anti-aliased lines and two-sided lighting, in the Quadro product.(citation?) The Quadro line also received improved support through a certified driver program.(citation?) These features were of little value to the gamers that Nvidia's products already sold to, but their lack prevented high-end customers from using the less expensive products.

There are parallels between the market segmentation used to sell the Quadro line of products to workstation (DCC) markets and the Tesla line of products to engineering and HPC markets.

In a settlement of a patent infringement lawsuit between SGI and Nvidia, SGI acquired rights to speed-binned Nvidia graphics chips which they shipped under the VPro product label. These designs were completely separate from the SGI Odyssey based VPro products initially sold on their IRIX workstations which used a completely different bus. SGI's Nvidia-based VPro line included the VPro V3 (Geforce 256), VPro VR3 (Quadro), VPro V7 (Quadro2 MXR), and VPro VR7 (Quadro2 Pro).[2][3]

Quadro SDI

Actual extra cards only for Quadro 4000 cards and higher:

Quadro Plex

Quadro Plex consists of a line of external servers for rendering videos. A Quadro Plex contains multiple Quadro FX video cards. A client computer connects to Quadro Plex (using PCI Express ×8 or ×16 interface card with interconnect cable) to initiate rendering. More data in Nvidia Tesla Cards.

Quadro SLI and SYNC

Scalable Link Interface, or SLI, is the next generation of Plex. SLI can improve Frame Rendering, FSAA.[6][7]

Quadro SLI support Mosaic for 2 Cards and 8 Monitors.[8]

With Quadro SYNC Card support of max. 16 Monitors (4 per Card) possible.[9][10]

Most Cards have SLI-Bridge-Slot for 2, 3 or 4 cards on one main board.[11]

Acceleration of scienctific calculations is possible with CUDA and OpenCL.[12][13][14]

Nvidia has 4 types of SLI bridges:

More see SLI.

Quadro VCA

Nvidia supports SLI and supercomputing with its 8-GPU Visual Computing Appliance.[19] Nvidia Iray,[20][21] Chaosgroup V-Ray[22] and Nvidia OptiX[23] accelerate Raytracing for Maya, 3DS Max, Cinema4D, Rhinoceros and others. All software with CUDA or OpenCL, such as ANSYS, NASTRAN, ABAQUS, and OpenFoam, can benefit from VCA. The DGX-1 is available with 8 GP100 Cards.[24]

More data in Nvidia Tesla Cards.

Quadro RTX

The Quadro RTX series is based on the Turing microarchitecture, and features real-time raytracing.[25] This 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 raytracing 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 physically correct, especially regarding off-camera action.

Tensor cores further enhance the image produced by raytracing, and are used to de-noise a partially rendered image. The Tensor core performs the result of deep learning on supercomputers to codify how to, for example, perform better up scaling than a standard algorithm would, which results in higher perceived resolution. In the Tensor core's 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 core. These methods are delivered "over the air" to consumers.

RTX is also the name of the development platform introduced for the Quadro RTX series. RTX leverages Microsoft's DXR, OptiX and Vulkan for access to raytracing.[26]

Turing is manufactured using TSMC's 12 nm FinFET semiconductor fabrication process.[27] Quadro RTX also uses GDDR6 memory from Samsung Electronics.[28]

Video cards

GeForce

Many of these cards use the same core as the game- and action-oriented GeForce video cards by Nvidia. Those cards that are identical to the desktop cards can be software modified to identify themselves as the equivalent Quadro cards and this allows optimized drivers intended for the Quadro cards to be installed on the system. While this may not offer all of the performance of the equivalent Quadro card,(citation?) it can improve performance in certain applications, but may require installing the MAXtreme driver for comparable speed.

The performance difference comes in the firmware controlling the card.(citation?) Given the importance of speed in a game, a system used for gaming can shut down textures, shading, or rendering after only approximating a final output—in order to keep the overall frame rate high. The algorithms on a CAD-oriented card tend rather to complete all rendering operations, even if that introduces delays or variations in the timing, prioritising accuracy and rendering quality over speed. A Geforce card focuses more on texture fillrates and high framerates with lighting and sound, but Quadro cards prioritize wireframe rendering and object interactions.

Software

With Caps Viewer (1.38 in 2018) all Windows Users can see data of the graphic Card, the installed Driver and can test some Features.[29] GPU-Z reads also data of the graphic cards and the user can send some data for better database.[30]

Quadro drivers

  • Curie-Architecture Last drivers see Driver Portal of Nvidia[31] (End-of-Life)
  • Tesla-Architecture (G80+, GT2xx) in Legacy Mode Quadro Driver 340+: OpenGL 3.3, OpenCL 1.1, DirectX 10.0/10.1[32] (End-of-Life)
  • Fermi (GFxxx): OpenCL 1.1, OpenGL 4.5, some OpenGL 2016 Features with Quadro Driver 375,[33] in legacy mode with version 391.74 (End-of-Life)
  • Kepler (GKxxx): OpenCL 1.2, OpenGL 4.6, Vulkan 1.2 with Quadro Driver 450+[34][35]
  • Maxwell (GMxxx): OpenCL 1.2, OpenGL 4.6, Vulkan 1.2 with Quadro Driver 450+[34]
  • Pascal (GPxxx): OpenCL 1.2, OpenGL 4.6, Vulkan 1.2 with Quadro driver 450+[34]
  • Volta (GVxxx): OpenCL 1.2, OpenGL 4.6, Vulkan 1.2 with Quadro driver 450+[34]
  • Turing (TUxxx): OpenCL 1.2, OpenGL 4.6, Vulkan 1.2 with Quadro driver 450+[34]

CUDA

  • Tesla Architecture and later

Supported CUDA Level of GPU and Card.[36]

  • CUDA SDK 6.5 support for Compute Capability 1.0 - 5.x (Tesla, Fermi, Kepler, Maxwell) Last Version with support for Tesla-Architecture with Compute Capability 1.x
  • CUDA SDK 7.5 support for Compute Capability 2.0 - 5.x (Fermi, Kepler, Maxwell)
  • CUDA SDK 8.0 support for Compute Capability 2.0 - 6.x (Fermi, Kepler, Maxwell, Pascal) Last version with support for compute capability 2.x (Fermi)
  • CUDA SDK 9.0/9.1/9.2 support for Compute Capability 3.0 - 7.2 (Kepler, Maxwell, Pascal, Volta)
  • CUDA SDK 10.0/10.1/10.2 support for Compute Capability 3.0 - 7.5 (Kepler, Maxwell, Pascal, Volta, Turing) Last version with support for compute capability 3.x (Kepler).
  • CUDA SDK 11.0 support for Compute Capability 5.2 - 7.5 (Maxwell, Pascal, Volta, Turing, Ampere)

For own Card Test see CUDA-Z Tool[37]

Desktop PCI Express

Quadro FX (without CUDA, OpenCL, or Vulkan)

  • Architecture Rankine, Curie
  • Rankine (NV3x): DirectX 9.0a, Shader Model 2.0a, OpenGL 2.1
  • Curie (NV4x, G7x): DirectX 9.0c, Shader Model 3.0, OpenGL 2.1
Quadro_FX
PCIe Model
Launch Core Core
clock
Memory clock
(eff.)
Memory size
(MiB)
Memory type Memory
bandwidth
3-pin
stereo
connector
Pixel
Rate
Texture
Rate
Open GLCUDA
OpenCL
VulkanPower
max.
Monitor Output Near GeForce Model Notes
UnitsMHzMHzMiBGiB/sGP/sGT/sWatt
Quadro FX 330[38]2004-06-28NV35GL (Rankine)250200 (400)6464-bit DDR3.2No0.51.02.1No211x DVIGeForce PCX 5300Shader Model 2.0
Quadro FX 350[39]2006-04-20G72GL (Curie)550405 (810)12864-bit DDR26.48No1.12.221DVI, VGAGeForce 7300LE
Quadro FX 540[40]2004-08-09NV43GL300250 (500)128128-bit GDDR8.8No2.42.435DVI, VGA, S-VideoGeForce 6600LE
Quadro FX 550[41]2006-04-20NV43GL360400 (800)128128-bit GDDR312.8No2.882.88252× dual-link DVI (max. only 2048×1536), S-Video
Quadro FX 560[42]2006-04-20G73GL350600 (1200)128128-bit GDDR319.2No2.804.2302x DL-DVI, S-VideoGeForce 7600
Quadro FX 1300[43]2004-08-09NV38GL350275 (550)128256-bit DDR17.6Yes2.802.80552x Single-Link DVI, S-VideoGeForce PCX 5950
Quadro FX 1400[44]2004-08-09NV41GL350300 (600)128256-bit DDR19.2Yes2.804.20702xSL-DVI, VESA StereoGeForce 6800
Quadro FX 1500[45]2006-04-20G71GL325625 (1250)256256-bit GDDR340.0No5.206.50652xDL-DVI, S-VideoGeForce 79xx (16 pixel, 6 vertex)
Quadro FX 3400[46]2004-06-28NV40 A1 (NV45GL)350450 (900)256256-bit GDDR328.8Yes4.604.601012x DL-DVI, S-VideoGeForce 6800
Quadro FX 3450[47]2005-06-28NV42GL (Curie)425500 (1000)256256-bit GDDR332.0Yes5.105.10832x DL-DVI, S-VideoGeForce 6800
Quadro FX 3500[48]2006-05-22G71GL450660 (1320)256256-bit GDDR342.2Yes7.209.00802x DVI, S-VideoGeForce 7900GSreduced Quadro FX 5500
Quadro FX 4000[49]2004-04-01NV42GL425500 (1000)256256-bit GDDR332.0Yes5.105.101422x DVI, S-Video
Quadro FX 4000 SDI[50]2004-04-19NV42GL425500 (1000)256256-bit GDDR332.0Yes5.105.10150DVI, 2x SDI HDTV2× SDI HDTV outputs + digital and analog genlock (using external controllers)
Quadro FX 4400[51]2005-06-28NV40 A1 (NV45GL)375525 (1050)512256-bit GDDR333.6Yes5.505.50832x DL-DVI, S-VideoGeForce 6800 PCI-EVariant FX 4400G with Genlock[52]
Quadro FX 4500[53]2005-06-28G70GL470525 (1050)512256-bit GDDR333.6Yes6.8810.31092x DL-DVI, S-VideoGeForce 7800GTX
Quadro FX 4500 SDI[54]2006-02-11G70GL470525 (1050)512256-bit GDDR333.6Yes6.8810.3116DL-DVI, 2x HDTVGeForce 7800GTXanalog and digital genlock
Quadro FX 4500 X2[55]2006-04-24G70GL (2x)500600 (1200)2×5122×256-bit GDDR32×33.6Yes2x 8.02x 12.01454x DL-DVIQuadro FX 4500Two GPU units on the same card
Quadro FX 5500[56]2006-04-20G71GL650500 (1000)1024256-bit GDDR332.3Yes10.415.6962xDL-DVI, S-VideoGeForce 7900GTX
Quadro FX 5500 SDI[57]2006-04-20G71GL650500 (1000)1024256-bit GDDR332.3Yes10.415.6104Quadro FX 5500with SDI, genlock/frame lock support (via external hardware)

Quadro FX (with CUDA and OpenCL, but no Vulkan)

  • Architecture Tesla (G80+, GT2xx) with OpenGL 3.3 and OpenCL 1.1
  • Tesla (G80+): DirectX 10, Shader Model 4.0, only Single Precision (FP32) available for CUDA and OpenCL
  • Tesla 2 (GT2xx): DirectX 10.1, Shader Model 4.1, Single Precision (FP32) available for CUDA and OpenCL (Double Precision (FP64) available for CUDA and OpenCL only for GT200 with Cuda Level 1.3 and higher)
Quadro_FX
PCIe Model
Launch Core Core
clock
Memory clock
(eff.)
Memory size
(MiB)
Memory type Memory
bandwidth
3-pin
stereo
connector
CUDA
cores
CUDA
Compute
Capa-
bility
Open GLOpen CLVulkanPower
max.
Monitor Output Near GeForce Model Notes
UnitsMHzMHzMiBGiB/sWatt
Quadro FX 370[58]2007-09-12G84 (Tesla)360500 (1000)25664-bit DDR26.4No161.13.31.1No351× Dual-link DVI-I, 1x single-link DVIShader Model 4.0 DirectX 10
Quadro FX 370 LP[59]2008-06-11G86540500 (1000)25664-bit DDR28No81.11.125DMS-59Low Profile
Quadro FX 380[60]2009-03-30G96450350 (700)256128-bit GDDR322.4No161.11.1342× Dual-link DVI-IGeForce 9400
Quadro FX 380 LP[61]2009-12-01GT218GL550400 (800)51264-bit DDR312.8No161.21.1281x Dual-link DVI-I, 1x DisplayPortLow Profile
Quadro FX 570[62]2007-09-12G84GL460400 (800)256128-bit DDR212.8No161.11.1382× Dual-link DVI-IShader Model 4.0, DirectX 10
Quadro FX 580[63]2009-04-09G96450 (OC 650)800 (1600)512128-bit GDDR325.6No321.11.1401× Dual-link DVI-I, 2× DP (10-bits per color)[64]GeForce 9500
Quadro FX 1700[65]2007-12-09G84GL460400 (800)512128-bit DDR212.8No321.11.1422xDL-DVI, S-Video (TV-Out)GeForce 8600GTShader Model 4.0, DirectX 10.
Quadro FX 1800[66]2009-03-30G94550 (shader clock 1375)800 (1600)768192-bit DDR338.4No641.11.1591× Dual-link DVI-I, 2× DP (10-bits per color)[67]Shader Model 4.0, DirectX 10.
Quadro FX 3700[68]2008-01-08G92500800 (1600)512256-bit GDDR351.2Yes1121.11.1782x DVI, S-VideoGeForce 8800GT, 8800GTS 512PCI Express 2.0, Energy Star 4.0 compliant (<= 80W)
Quadro FX 3800[69]2009-03-30GT200GL600800 (1600)1024256-bit GDDR351.2Yes1921.31.1107DVI, 2x DisplayPort (10bits per Color)GeForce GTX 260Stereo requires an optional 3 pin S Bracket
Quadro FX 3800 SDI[70]2009-03-30GT200GL600800 (1600)1024256-bit GDDR351.2Yes1921.31.1107DVI, 2x DisplayPortQuadro FX 3800HD-SDI Ports
Quadro FX 4600[71]2007-03-05G80GL400700 (1400)768384-bit GDDR367.2Yes1121.01.11342xDL-DVI, S-VideoGeForce 8800GTS (G80)One 6-pin power connector
Quadro FX 4600 SDI[72][73]2007-05-30G80GL400700 (1400)768384-bit GDDR367.2Yes1121.01.1154Quadro FX 4600with SDI, genlock/frame lock support (via external hardware), One 6-pin power connector
Quadro FX 4700 X2[74]2006-04-24G92500800 (1600)2×5122×256-bit GDDR32×51.2Yes2x 1121.11.12262xDL-DVI, S-VideoQuadro FX 3700Two GPU units on the same card
Quadro FX 5600[75]2007-03-05G80GL600800 (1600)1536384-bit GDDR376.8Yes1281.01.1 (1.0 OS X)1712x DVI, S-VideoGeForce 8800GTXTwo 6-pin power connectors
Quadro FX 5600 SDI[76]2007-03-05G80GL600800 (1600)1536384-bit GDDR376.8Yes1281.01.1 (1.0 OS X)1712x DVI, S-VideoQuadro FX 5600Two 6-pin power connectors, HD-SDI Version
Quadro FX 4800[77]2008-11-11D10U-20 (GT200GL)602800 (1600)1536384-bit GDDR377Yes1921.31.1 (1.0 Mac OS X)150DVI, 2x DP, S-Video55 nm version of GeForce GTX 260. Quadro CX without Elemental Technologies' CS4 plug-in., SDI Version available
Quadro FX 4800 SDI[78][79]2008-11-11D10U-20 (GT200GL)602800 (1600)1536384-bit GDDR377Yes1921.31.1 (1.0 Mac OS X)150DVI, 2x DP, S-Video, SDIFX 4800HD-SDI
Quadro FX 5800[80]2008-11-11D10U-30 (GT200GL)650800 (1600)4096512-bit GDDR3102Yes2401.31.1189DVI, 2x DP, S-VideoGeForce GTX 285SDI Version available[78]
Quadro FX 5800 SDI[78][81]2008-11-11D10U-30 (GT200GL)650800 (1600)4096512-bit GDDR3102Yes2401.31.1189DVI, 2x DP, S-VideoGeForce GTX 285HD-SDI
Quadro CX[82]2008-11-11D10U-20 (GT200GL)602800 (1600)1536384-bit GDDR376.8Yes1921.31.11501xDP, 1xDL-DVI, S-Video55 nm GeForce GTX 260optimised for Adobe Creative Suite 4, HD-SDI optional[79]
Quadro VX 200[83]2008-01-08G92450800 (1600)512GDDR351.2No921.11.178HDTV and 2× Dual-link DVIoptimised for Autodesk AutoCAD.

Quadro

  • Architecture Fermi (GFxxx), Kepler (GKxxx), Maxwell (GMxxx), Pascal (GPxxx), Volta (GVxxx) (except Quadro 400 with Tesla 2)
  • All Cards with Display Port 1.1+ can support 10bit per Channel for OpenGL (HDR for Graphics Professional (Adobe Photoshop and more))
  • Vulkan 1.1 available with Driver Windows 419.17, Linux 418.43 for Kepler, Maxwell, Pascal, Volta[84]
  • All Kepler, Maxwell, Pascal, Volta and later can do OpenGL 4.6 with Driver 418+[85]
  • All Quadro can do OpenCL 1.1. Kepler and later can do OpenCL 1.2 and incomplete OpenCL 2.0 with Driver 378.66 and higher.
  • All can do Double Precision with Compute Capability 1.3 and higher (see CUDA)
Quadro
GPU
Launch Core Core
clock
Memory clock Memory size
(MiB)
Memory type Memory
bandwidth
3-pin
stereo
connector
CUDA
cores
CUDA
Compute
Capa-
bility
DirectXOpen GLOpen CLVulkanPower
max.
MonitorOutput Near GeForce Model Notes
UnitsMHzMHzMiBGiB/sWatt
Quadro 400[86]2011-04-05GT216GL (40 nm)45080051264-bit DDR312.31.1481.210.13.31.1No321x Dual-link DVI-I, 1x DP 1.1a, HDMI 1.3a (via adapter)[87]GeForce GT 220GeForce 200 Series Tesla-2-based
Quadro 600[88]2010-12-13GF108GL6408001024128-bit GDDR325.6No962.111.0
(11_0)
4.6401×DL-DVI-I, 1× DisplayPort 1.1a, HDMI 1.3a (via adapter).[89]GeForce GT 430Based on the GeForce 400 Series Fermi-based
Quadro 2000[90]2010-12-24GF106GL62513001024128-bit GDDR541.6No1922.1621×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[91]GeForce GTS 450Fermi-based
Quadro 2000D[92]2011-10-05GF106GL62513001024128-bit GDDR541.6No1922.1622×DL-DVI-I, 1x DP 1.1a GeForce GTS 45010 and 12 bit per each rgb Channel (10-bits internal)[93]
Quadro 4000 (SDI)[94]2010-11-02GF100GL4757002048256-bit GDDR589.6Yes2562.01421×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[95]?HD-SDI optional[96][97]
Quadro 5000 (SDI)[98]2011-02-23GF100GL (Fermi)5137502560320-bit GDDR5 ECC120Yes3522.01521×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[99]GeForce GTX 465/470 (cutdown)GeForce 400 Series, HD-SDI optional[100]
Quadro 6000 (SDI)[101]2010-12-10GF100GL (Fermi)5747506144384-bit GDDR5 ECC144Yes4482.02041×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[102]GeForce GTX 480 (cutdown)GeForce 400 Series, HD-SDI optional[103]
Quadro 7000[104]2012-05-12GF110GL65092512288384-bit GDDR5 ECC177.4Yes5122.02042x DP 1.1a, DVI, S-Video GeForce GTX 580Fermi-based
Quadro Plex 7000[105]2011-07-252x GF100GL5747502x 61442x 384-bit GDDR5 ECC2x 144Yes2x 5122.06004x DP 1.1a, 2x S-Video GeForce GTX 590Based on two Quadro 6000.
Quadro 410[106][107]2012-08-07GK107GLM (28 nm)[108]70689151264-bit DDR314No1923.012.0
(11_0)
1.21.1381x Single-link DVI-I, 1x DP 1.2, HDMI 1.4 (via adapter)[109]GeForce GT 630 (Kepler)GeForce 600 Series Kepler-based
Quadro K420[110]2014-07-14GK107GL7809001024128-bit GDDR329No1923.0411x DL-DVI, 1x DP 1.2 GeForce GT 630 (Kepler)Kepler-based[111]
Quadro K600[112]2013-03-01GK107GL8759001024128-bit GDDR329No1923.0411x DL-DVI-I, 1x DP 1.2 GeForce GT 630 (Kepler)Kepler-based[111]
Quadro K620[113]2014-07-14GM107GL10009002048128-bit GDDR329No3845.0451x DL-DVI, 1x DP 1.2, GeForce GTX 745 (OEM)Maxwell-based[111]
Quadro K1200[114]2015-01-28GM107GL100012504096128-bit GDDR580No5125.0454x Mini-DP 1.2 GeForce GTX 750Maxwell-based[111]
Quadro K2000[115]2013-03-01GK107GL95410002048128-bit GDDR564No3843.0511x DL-DVI-I, 2x DP 1.2 GeForce GTX 650Kepler-based[111]
Quadro K2000D[116]2013-03-01GK107GL95010002048128-bit GDDR564No3843.0512x DL-DVI-I, 1x DP 1.2 GeForce GTX 650Kepler-based[111]
Quadro K2200[117][118]2014-07-22GM107GL104612504096128-bit GDDR580No6405.0681x DL-DVI-I, 2x DP 1.2 GeForce GTX 750 TiMaxwell-based[111]
Quadro K4000[119][120]2013-03-01GK106GL80014003072192-bit GDDR5134Yes7683.0801x DL-DVI-I, 2x DP1.2 GeForce GTX 650 Ti BoostKepler-based,[111] HD-SDI optional with extra Card[121]
Quadro K4200[122][123]2014-07-22GK104GL78013504096256-bit GDDR5173Yes13443.01081x DL-DVI-I, 2x DP 1.2 GeForce GTX 670Kepler-based,[111] HD-SDI optional
Quadro K5000[124]2012-08-17GK104GL70613504096256-bit GDDR5 ECC173Yes15363.01222x DP 1.2 GeForce GTX 770/680Kepler-based,[111][125] HD-SDI optional[126]
Quadro K5200[127][128]2014-07-22GK110GL65015008192256-bit GDDR5 ECC192Yes23043.51501x DL-DVI-I, 1x DL-DVI-D, 2x DP 1.2 GeForce GTX 780Kepler-based, HD-SDI optional
Quadro K6000[129]2013-07-23GK110GL700150012288384-bit GDDR5 ECC288Yes28803.52252x DP 1.2 GeForce GTX TITAN BlackKepler-based,[111] HD-SDI optional[130]
Quadro M2000[131]2016-04-08GM206-875796-116316534096128-bit GDDR5105.8No7685.212.0
(12_1)
754x DP 1.2 GeForce GTX 950Maxwell-based
Quadro M4000[132]2015-06-29GM204-85077315028192256-bit GDDR5192.3Yes16645.21204x DP 1.2 GeForce GTX 970Maxwell-based
Quadro M5000[133]2015-06-29GM204-875861-103816538192256-bit GDDR5 ECC211.6Yes20485.21504x DP 1.2 GeForce GTX 980Maxwell-based
Quadro M6000[134]2015-03-15GM200GL988-1114165312288384-bit GDDR5 ECC317.4Yes30725.22504x DP 1.2 GeForce GTX TITAN XMaxwell-based
Quadro M6000 24GB[135]2016-03-05GM200-880988-1114165324576384-bit GDDR5 ECC317.4Yes30725.22504x DP 1.2 GeForce GTX TITAN XMaxwell-based
Quadro P400 2017-02-06GP107-8251228-12521003204864-bit GDDR532.1No2566.1303x mini-DP 1.4 GeForce GT 1030Pascal-based[111]
Quadro P600 2017-02-06GP107-8501329-155710032048128-bit GDDR564.2No3846.1404x mini-DP 1.4 GeForce GT 1030Pascal-based[111]
Quadro P620 2018-02-01GP107-8551266-135412522048128-bit GDDR580.13No5126.1404x mini-DP 1.4 GeForce GTX 1050Pascal-based[111]
Quadro P1000 2017-02-06GP107-8601266-148112534096128-bit GDDR580.19No6406.1474x mini-DP 1.4 GeForce GTX 1050Pascal-based[111]
Quadro P2000 2017-02-06GP106-8751076-148017525120160-bit GDDR5140.2No10246.1754x DP 1.4 GeForce GTX 1060Pascal-based[111]
Quadro P2200 2019-06-10GP106GL1000-149312535120160-bit GDDR5X200.5No12806.1754x DP 1.4 GeForce GTX 1060Pascal-based[111]
Quadro P4000 2017-02-06GP104-8501202-148019018192256-bit GDDR5243.3Yes17926.1105DVI, 4x DP 1.4 GeForce GTX 1070Pascal-based[111]
Quadro P5000 2016-10-01GP104-8751607-1733112716384256-bit GDDR5X288.5Yes25606.1180DVI, 4x DP 1.4 GeForce GTX 1080Pascal-based[111][136]
Quadro P6000 2016-10-01GP102-8751506-1645112724576384-bit GDDR5X432.8Yes38406.1250DVI, 4x DP 1.4 Nvidia TITAN XpPascal-based[111][136]
Quadro GP100[137][138]2017-02-06GP100GL1304-1442715163844096-bit HBM2732.2Yes35846.0235Dual-Link DVI, 4x DP 1.4 GeForce GTX 1080 TiPascal-based[111][136]
Quadro GV100[139]2018-03-27GV100-8751132-1627848327684096-bit HBM2868.4Yes51207.02504x DP 1.4 Nvidia TITAN VVolta-based[140]

1 Nvidia Quadro 342.01 WHQL: support of OpenGL 3.3 and OpenCL 1.1 for legacy Tesla microarchitecture Quadros.[32]

2 Nvidia Quadro 377.83 WHQL: support of OpenGL 4.5, OpenCL 1.1 for legacy Fermi microarchitecture Quadros.[33]

3 Nvidia Quadro 451.77 WHQL: support of OpenGL 4.6, OpenCL 1.2 for Kepler, Maxwell, Pascal & Volta.[34]

4 OpenCL 1.1 is available for Tesla-Chips,[141] OpenCL 1.0 for some Cards with G8x, G9x and GT200 by MAC OS X[142]

Quadro RTX

[150][151][152][153]

Desktop AGP

  • Architecture Celsius (NV1x): DirectX 7, OpenGL 1.2 (1.3)
  • Architecture Kelvin (NV2x): DirectX 8 (8.1), OpenGL 1.3 (1.5), Pixel Shader 1.1 (1.3)
  • Architecture Rankine (NV3x): DirectX 9.0a, OpenGL 1.5 (2.1), Shader Model 2.0a
  • Architecture Curie (NV4x): DirectX 9.0c, OpenGL 2.1, Shader Model 3.0
Quadro_AGP
Model
Launch Core Core clock
Memory clock
(effective)
Memory size
Memory type Memory
bandwidth
Interface AGP 3-pin
stereo
connector
Monitor Output Near GeForce Model Notes
UnitsMHzMHzMiBGiB/s
Quadro[154]2000-01-01NV10GL (Celsius)13516632128-bit SDR2.66No1x VGAGeForce 256
Quadro2 Pro[155]2000-07-25NV15GL25040064128-bit DDR6.4NoDVI, VGA, S-VideoGeForce 2 GTS
Quadro2 MXR[156]2000-07-25NV11GL20018332128-bit SDR2.93No1x VGAGeForce 2 MX/400
Quadro2 MXR LP[157]2000-07-25NV11GL20018332128-bit SDR2.934xNo1x VGAGeForce 2 MX/400
Quadro DCC[158]2001-03-14NV20GL (Kelvin)20023064128-bit DDR7.3NoDVI, VGA, S-VideoGeForce 3/Ti
Quadro4 380 XGL[159]2002-11-12NV18GL27551364128-bit DDR8.2NoDVI, VGA, S-VideoGeForce 4 MX 440 (AGP 8×)
Quadro4 500 XGL[160]2002-02-19NV17GL250166128128-bit SDR2.664 xNoDVIGeForce 4 MX 420
Quadro4 550 XGL[161]2002-02-19NV17GL27040064128-bit DDR6.4NoDVIGeForce 4 MX 440
Quadro4 580 XGL[162]2002-11-12NV18GL30040064128-bit DDR6.4NoDVIGeForce 4 MX 440 (AGP 8×)
Quadro4 700 XGL[163]2002-02-19NV25GL27555064128-bit DDR7.2No2x DVI, S-VideoGeForce 4 Ti 4200
Quadro4 750 XGL[164]2002-02-19NV25GL275550128128-bit DDR7.2Yes2x DVI, S-VideoGeForce 4 Ti 4400
Quadro4 780 XGL[165]2002-11-12NV28GL275550128128-bit DDR8.84xYes2x DVI, S-VideoGeForce 4 Ti 4200 (AGP 8×)
Quadro4 900 XGL[166]2002-02-19NV25GL300650128128-bit DDR10.4Yes2x DVI, S-VideoGeForce 4 Ti 4600
Quadro4 980 XGL[167]2002-11-12NV28GL300650128128-bit DDR10.4Yes2x DVI, S-VideoGeForce 4 Ti 4800
Quadro FX 500[168]2003-05-21NV34GL (Rankine)270243128128-bit DDR7.7NoDVI, VGAGeForce FX 5200
Quadro FX 700[169]2004-03-17NV31GL275275128128-bit DDR8.8NoDVI, VGAGeForce FX 5600
Quadro FX 1000[170]2003-01-21NV30GL300600128128-bit GDDR29.6Yes2x DVI, S-VideoGeForce FX 5800
Quadro FX 1100[171]2004-04-01NV36GL425325128128-bit DDR10.4Yes2x DVI, S-VideoGeForce FX 5700
Quadro FX 2000[172]2003-01-21NV30GL400400128128-bit GDDR212.8Yes2x DVI, S-VideoGeForce FX 5800
Quadro FX 3000[173]2003-07-22NV35GL400425256256-bit DDR27.2Yes2x DVI, S-VideoGeForce FX 5900
Quadro FX 3000G[174]2003-07-22NV35GL400425256256-bit DDR27.2Yes2x DL-DVI (via external controller), S-VideoGeForce FX 5900has external stereo frame sync connector
Quadro FX 4000[49]2004-04-01NV40GL375500256256-bit GDDR332.0Yes2x Dual-link DVI, S-VideoGeForce 6800 GT2nd link using external TMDS transmitter
Quadro FX 4000 SDI[50]2004-04-19NV40GL (Curie)375500256256-bit GDDR332.0YesDVI, 2x SDI HDTVGeForce 6800 GTwith digital and analog genlock (using external controllers)

Desktop PCI

  • Architecture Rankine (NV3x): DirectX 9.0a, OpenGL 1.5 (2.1), Shader Model 2.0a
Quadro
PCI Model
Launch Core Core clock
(MHz)
Memory clock
(effective) (MHz)
Memory size
(MiB)
Memory type Memory
bandwidth
(GB/s)
3-pin
stereo
connector
Monitor Output Notes
Quadro FX 600 PCI[175]2004-03-17NV34GL (Rankine)270480128128-bit DDR7.8Yes2x DVI, S-Videoalso GeForce 5200 Ultra

For business NVS

The Nvidia Quadro NVS graphics processing units (GPUs) provide business graphics solutions for manufacturers of small, medium, and enterprise-level business workstations. The Nvidia Quadro NVS desktop solutions enable multi-display graphics for businesses such as financial traders.

  • Architecture Celsius (NV1x): DirectX 7, OpenGL 1.2 (1.3)
  • Architecture Kelvin (NV2x): DirectX 8 (8.1), OpenGL 1.3 (1.5), Pixel Shader 1.1 (1.3)
  • Architecture Rankine (NV3x): DirectX 9.0a, OpenGL 1.5 (2.1), Shader Model 2.0a
  • Architecture Curie (NV4x): DirectX 9.0c, OpenGL 2.1, Shader Model 3.0
  • Architecture Tesla (G80+): DirectX 10.0, OpenGL 3.3, Shader Model 4.0, CUDA 1.0 or 1.1, OpenCL 1.1
  • Architecture Tesla 2 (GT2xx): DirectX 10.1, OpenGL 3.3, Shader Model 4.1, CUDA 1.2 or 1.3, OpenCL 1.1
  • Architecture Fermi (GFxxx): DirectX 11.0, OpenGL 4.6, Shader Model 5.0, CUDA 2.x, OpenCL 1.1
  • Architecture Kepler (GKxxx): DirectX 11.2, OpenGL 4.6, Shader Model 5.0, CUDA 3.x, OpenCL 1.2, Vulkan 1.1
  • Architecture Maxwell 1 (GM1xx): DirectX 12.0, OpenGL 4.6, Shader Model 5.0, CUDA 5.0, OpenCL 1.2, Vulkan 1.1
Quadro
NVS model
Launch Max. resolution
(digital)
Interface Display connectors Displays
supported
Power
consumption
Core Notes
UnitsWatt
Quadro NVS 50[176]2005-05-311600×1200AGP 8× / PCIDVI-I, S-Video110NV18 (Celsius)OpenGL 1.3, DirectX 8.0
Quadro4 NVS 100[177][178]2003-12-222048×1536AGP 4× / PCI1x DVI-I, VGA, S-Video210NV17(A3)
Quadro NVS 200[179]2003-12-221280×1024AGP 4× / PCILFH-60211NV17
Quadro NVS 210s[180]2003-12-221720x1200Onboard (nForce 430)DVI + VGA?11MCP51no PureVideoHD, only SD
Quadro NVS 280 (PCI)[181]2003-10-281600×1200PCIDMS-59212NV34 A1
Quadro NVS 280 (AGP, PCIe)[182][183]2004-05-251600×1200PCI-E ×16 / AGP 8×DMS-59212NV34 A1
Quadro NVS 285[184]2006-06-061920×1200PCI-Express ×1/×16DMS-59213/18NV44
Quadro NVS 290[185]2007-10-041920×1200PCI-Express ×1/×16DMS-59221G86Tesla based
Quadro NVS 295[186]2009-05-072560×1600PCI-Express ×1/×162× DisplayPort or 2× DVI-D223G98Tesla based
Quadro NVS 400[187]2004-07-161280×1024PCI2× DMS-594182× NV17 A3
Quadro NVS 420[188]2009-01-202560×1600PCI-Express ×1/×16VHDCI (4× DisplayPort or 4× DVI-D)4402× G98
Quadro NVS 440[189]2009-03-091920×1200PCI-Express ×1/×162× DMS-594312× NV43
Quadro NVS 450[190]2008-11-112560×1600PCI-Express ×164× DisplayPort4352× G98
NVS 300[191]2011-01-082560×1600PCI-Express ×1/×16DMS-59217.5GT218Tesla 2 based
NVS 310[192]2012-06-262560×1600PCI-Express ×162× DisplayPort219.5GF119Fermi based (GeForce 510)
NVS 315[193]2013-03-102560×1600PCI-Express ×16DMS-59219.5GF119
NVS 510[194]2012-10-233840x2160PCI-Express 2.0 x164× Mini-DisplayPort435GK107Kepler-based
NVS 810[195]2015-11-044096x2160 ([email protected] Hz, [email protected] Hz)PCI-Express 3.0 x168× Mini-DisplayPort8682× GM107Maxwell based

Mobile applications

Quadro FX M (without Vulkan)

  • Architecture Rankine (NV3x), Curie (NV4x, G7x) and Tesla (G80+, GT2xx)
Quadro FX M Model Launch YYYY-MM-dd Core Fab Bus
interface
Core
clock
Shader
clock
Memory
clock
Config core Fillrate Memory Bus
width
Processing
Power (GFLOPs)
API support TDP
Pixel Texture Size Band-
with
Type Single
precision
Double
precision
DirectXOpenGLCUDA
Compute
Capability
OpenCLVulkan
UnitsnmMHzMHzMHzGP/sGT/sMiBGB/sbitWatt
Quadro FX Go 540[196]2004-08-09NV43GL110MXM-II 300300550 4:8:8:8 2.42.4 1288.8GDDR3128 No 9.0c2.1 NoNo 42
Quadro FX Go 700[197]2003-06-25NV31GLM130AGP 4x 295295590 3:4:4:4 1.181.18 1289.44DDR3128 9.0a2.1 unknown
Quadro FX Go 1000[198]2005-02-25NV36GLM130AGP 4x 295295570 3:4:4:4 1.181.18 1289.12DDR3128 9.0a2.1 unknown
Quadro FX Go 1400[199]2005-02-25NV41GLM110MXM-III 275275590 5:8:8:8 2.22.2 25618.88DDR3256 9.0c2.1 unknown
Quadro FX 350M[200]2006-03-13 G72GLM (Curie) 90 PCI-E 1.0 ×16 450450900 3:4:4:2 0.91.8 25614.4GDDR3128 9.0c2.1 15
Quadro FX 360M[201]2007-05-09 G86GLM (Tesla) 80 PCI-E 1.0 ×16 400 800 1200 16:8:4:2 1.6 3.2 256 9.6 GDDR2 64 25.6 10 3.3 1.1 1.1 17
Quadro FX 370M[202]2008-08-15 G98GLM (Tesla) 65 PCI-E 2.0 ×16 550 1400 1200 8:4:4:1 2.2 2.2 256 9.6 GDDR3 64 22.4 10 3.3 1.1 1.1 20
Quadro FX 380M[203]2010-01-07 GT218GLM (Tesla 2) 40 PCI-E 2.0 ×16 625 1530 1600 16:8:4:2 2.4 4.8 512 12.6 GDDR3 64 47.0 No, only GT200 1/8 of SP 10.1 3.3 1.2 1.1 25
Quadro FX 550M[204]2006-03-13 G73GLM (Curie) 90 PCI-E 1.0 ×16 480 480 1000 5:12:12:8 4 6 512 19.2 GDDR3 128 No 9.0c 2.1 No 35
Quadro FX 560M[205]2006-03-13 G73GLM (Curie) 90 PCI-E 1.0 ×16 500 500 1200 5:12:12:8 4 6 512 19.2 GDDR3 128 9.0c 2.1 35
Quadro FX 570M[206]2007-06-01 G84GLM (Tesla) 80 PCI-E 1.0 ×16 475 950 1400 32:16:8:2 3.8 7.6 512 22.4 GDDR3 128 60.8 10 3.3 1.1 1.1 45
Quadro FX 770M[207]2008-08-14 G96GLM (Tesla) 65 PCI-E 2.0 ×16 500 1250 1600 32:16:8:2 4 8 512 25.6 GDDR3 128 80 10 3.3 1.1 1.1 35
Quadro FX 880M[208]2010-01-07 GT216GLM (Tesla 2) 40 PCI-E 2.0 ×16 550 1210 1600 48:16:8:2 4.4 8.8 1024 25.6 GDDR3 128 116 No, only GT200 1/8 of SP 10.1 3.3 1.2 1.1 35
Quadro FX 1500M[209]2006-04-18 G71GLM 90 PCI-E 1.0 ×16 375 375 1000 8:24:24:16 6 9 512 32 GDDR3 256 No 9.0c 2.1 No 45
Quadro FX 1600M[210]2007-06-01 G84GLM 80 PCI-E 1.0 ×16 625 1250 1600 32:16:8:2 5 10 512 25.6 GDDR3 128 80 10 3.3 1.1 1.1 50
Quadro FX 1700M[211]2008-10-01 G96GLM 65 PCI-E 2.0 ×16 625 1550 1600 32:16:8:2 5 10 512 25.6 GDDR3 128 99.2 10 3.3 1.1 1.1 50
Quadro FX 1800M[212]2009-06-15 GT215GLM 40 PCI-E 2.0 ×16 450 1080 1600
2200
72:24:8:3 3.6 10.8 1024 25.6
35.2
GDDR3
GDDR5
128 162 No, only GT200 1/8 of SP 10.1 3.3 1.2 1.1 45
Quadro FX 2500M[213]2005-09-29 G71GLM 90 PCI-E 1.0 ×16 500 500 1200 8:24:24:16 8 12 512 38.4 GDDR3 256 No 9.0c 2.1 No 45
Quadro FX 2700M[214]2008-08-14 G94GLM 65 PCI-E 2.0 ×16 530 1325 1600 48:24:16:3 8.48 12.72 512 51.2 GDDR3 256 127 10 3.3 1.1 1.1 65
Quadro FX 2800M[215]2009-12-01 G92GLM 55 PCI-E 2.0 ×16 500 1250 2000 96:48:16:6 8 16 1024 64 GDDR3 256 288 10 3.3 1.1 1.1 75
Quadro FX 3500M[216]2007-03-01 G71GLM 90 PCI-E 1.0 ×16 575 575 1200 8:24:24:16 9.2 13.8 512 38.4 GDDR3 256 9.0c 2.1 No 45
Quadro FX 3600M[217]2008-02-23 G92GLM 65 PCI-E 2.0 ×16 500 1250 1600 64:32:16:4
96:48:16:6
8
8
16
24
1024 51.2 GDDR3 256 160
240
10 3.3 1.1 1.1 70
Quadro FX 3700M[218]2008-08-14 G92GLM 65 PCI-E 2.0 ×16 550 1375 1600 128:64:16:8 8.8 35.2 1024 51.2 GDDR3 256 352 10 3.3 1.1 1.1 75
Quadro FX 3800M[219]2008-08-14 G92GLM 55 PCI-E 2.0 ×16 675 1688 2000 128:64:16:8 10.8 43.2 1024 64 GDDR3 256 422 10 3.3 1.1 1.1 100

Quadro M

  • Architecture Fermi, Kepler,[220] Maxwell,[221] Pascal
  • Fermi, Kepler, Maxwell, Pascal can do OpenGL 4.6 with actual Driver 381+ for Linux or 390+ for windows[85]
  • All can do Double Precision with compute Capability 1.3 and higher
  • Vulkan 1.0 and 1.1 with Kepler and later
Quadro M Model Launch Core Fab Bus
interface
Core
clock
Shader
clock
Memory
clock effective
Config core Fillrate Memory Bus
width
Processing
Power (GFLOPs)
API support TDP
Pixel Texture Size Band-
with
Type Single
precision
Double
precision
DirectXOpenGLCUDA
Compute
Capability
OpenCLVulkan
UnitsnmMHzMHzMHzGP/sGT/sMiBGB/sbitWatt
Quadro K500M[222]2012-06-01GK10728MXM-A (3.0) 8508501800 192:16:8:1 3.413.6 102412.8DDR364 326 1/24 of SP 11.24.63.01.21.1 35
Quadro K510M[223]2013-07-23GK20828 MXM-A (3.0) 846 846 2400 192:16:8:1 3.4 13.5 102419.2 GDDR564 325 11.24.63.5 30
Quadro K610M[224]2013-07-23GK20828 PCI-E 2.0 ×8 9809802600 192:16:8:1 3.915.7 102420.8GDDR564 376 11.24.63.5 30
Quadro 1000M[225][226]2011-01-13GF108GLM40 PCI-E 2.0 ×16 70014001800 96:16:4:4 5.611.2 204828.8DDR3128 269 1/12 of SP 114.62.11.1No 45
Quadro K1000M[227]2012-06-01GK107GL28 PCI-E 3.0 ×16 8508501800 192:16:16:1 3.413.6 204828.8DDR3128 326 1/24 of SP 11.24.63.01.21.1 45
Quadro K1100M[228]2013-07-23GK107GL28 PCI-E 3.0 ×16 7067062800 384:32:16:2 5.6522.6 204844.8GDDR5128 542 11.24.63.0 45
Quadro 2000M[229]2011-01-13GF106GLM40 PCI-E 2.0 ×16 55011001800 192:32:16:4 4.417.6 204828.8DDR3128 422 1/12 of SP 114.62.11.1No 55
Quadro K2000M[230]2012-06-01GK10728 PCI-E 3.0 ×16 7459001800 384:32:16:2 5.9623.84 204828.8DDR3128 572 1/24 of SP 11.24.63.01.21.1 55
Quadro K2100M[231]2013-07-23GK10628 PCI-E 3.0 ×16 6677503000 576:48:16:3 8.032.0 204848.0GDDR5128 768 11.24.63.0 55
Quadro 3000M[232]2011-02-22GF104GLM40 MXM-B (3.0) 4509002500 240:40:32:5 4.518 204880GDDR5256 432 1/12 of SP 114.62.11.1No 75
Quadro K3000M[233]2012-06-01GK10428 PCI-E 3.0 ×16 6546542800 576:48:32:3 7.8531.4 204889.6GDDR5256 753 1/24 of SP 11.24.63.01.21.1 75
Quadro K3100M[234]2013-07-23GK10428 PCI-E 3.0 ×16 6836833200 768:64:32:4 11.345.2 4096102.4GDDR5256 1084 11.24.63.0 75
Quadro 4000M[235]2011-02-22GF104GLM40 PCI-E 2.0 ×16 4759502400 336:56:32:7 6.6526.6 204880GDDR5256 638 1/12 of SP 114.62.11.1No 100
Quadro K4000M[236]2012-06-01GK10428 PCI-E 3.0 ×16 6006002800 960:80:32:5 12.048.1 409689.6GDDR5256 1154 1/24 of SP 11.24.63.01.21.1 100
Quadro K4100M[237]2013-07-23GK10428 PCI-E 3.0 ×16 7067063200 1152:96:32:6 16.967.8 4096102.4GDDR5256 1627 11.24.63.0 100
Quadro 5000M[238]2010-07-27GF100GLM40 PCI-E 2.0 ×16 4058102400 320:40:32:10 8.1016.2 179276.8GDDR5256 518 1/2 of SP 114.62.01.1No 100
Quadro 5010M[239]2011-02-22GF110GLM40 PCI-E 2.0 ×16 4509002600 384:48:32:12 10.821.6 409683.2GDDR5256 691 114.62.0 100
Quadro K5000M[240]2012-08-07GK10428 PCI-E 3.0 ×16 7067063000 1344:112:32:7 16.867.3 409696.0GDDR5256 1615 1/24 of SP 11.24.63.01.21.1 100
Quadro K5100M[241]2013-07-23GK10428 PCI-E 3.0 ×16 7717713600 1536:128:32:8 24.798.7 8192115.2GDDR5256 2368 11.24.63.0 100
Quadro M500M[242]2016-04-27GM10828 PCI-E 3.0 ×16 102911241800 384:32:16:2 8.216.5 204814.4DDR364 729 1/32 of SP 12.04.65.0 30
Quadro M520 Mobile[243][244]2017-01-11 GM108 28 MXM-A (3.0) 1041 ? 5012 384:16:8:2 8.3 16.7 2048 40.1 GDDR5 64 799 12.04.65.0 25
Quadro M600M[245]2015-08-18GM10728 PCI-E 3.0 ×16 102911245000 384:32:16:2 8.216.5 204880GDDR5128 790 12.04.65.0 30
Quadro M620 Mobile[243][246]2017-01-11 GM107 28 MXM-A (3.0) 977 ? 5012 512:32:16:4 16.6 31.3 2048 80.2 GDDR5 128 1000 12.04.65.0 30
Quadro M1000M[247]2015-08-18GM10728 PCI-E 3.0 ×16 100012505000 512:32:16:4 15.931.8 409680.2GDDR5128 1017 12.04.65.0 55
Quadro M1200 Mobile[243][248]2017-01-11 GM107 28 MXM-A (3.0) 1093 ? 5000 640:40:32:5 35.0 43.7 4096 80.2 GDDR5 128 1399 12.04.65.0 45
Quadro M2000M[249]2015-12-03GM10728 MXM-A (3.0) 102910295000 640:40:32:5 32.941.2 409680GDDR5128 1317 12.04.65.0 55
Quadro M2200 Mobile[243][250]2017-01-11 GM206 28 MXM-A (3.0) 1025 ? 5500 1024:64:32:8 32.8 65.6 4096 88 GDDR5 128 2099 12.14.65.2 55
Quadro M3000M[251]2015-08-18GM20428 PCI-E 3.0 ×16 54010805000 1024:64:32:8 17.334.6 4096160GDDR5256 1106 12.14.65.2 55
Quadro M4000M[252]2015-08-18GM20428 PCI-E 3.0 ×16 97512505000 1280:80:64:10 62.478.0 4096160.4GDDR5256 2496 12.14.65.2 100
Quadro M5000M[253]2015-08-18GM20428 PCI-E 3.0 ×16 97512505000 1536:96:64:12 62.493.6 8192160GDDR5256 2995 12.14.65.2 100
Quadro M5500[254]2016-04-16GM20428 PCI-E 3.0 ×16 86117507000 2048:128:64:16 55.1110 8192160GDDR5256 3527 12.14.65.2 150
Quadro P500[255][256]2018-01-05 GP108 14 1455 5012 256:16:16 24.3 24.3 2048 40 GDDR5 64 777 12.1 4.6 6.1 18
Quadro P600[257][256]2017-02-07 GP107 14 1430 5012 384:24:16 24.9 37.4 4096 80 GDDR5 128 1196 12.1 4.6 6.1 25
Quadro P1000[258][256]2017-02-07 GP107 14 1303 6008 512:32:16 23.9 47.8 4096 96 GDDR5 128 1529 12.1 4.6 6.1 40
Quadro P2000[259][256]2017-02-06 GP107 14 1557 6008 768:64:32 51.4 77.1 4096 96 GDDR5 128 2468 12.1 4.6 6.1 50
Quadro P3000 Mobile[260][243]2017-01-11GP10416 MXM-B 3.0 ×16 121012107012 1280:80:32:10 38.796.8 6144168GDDR5192 3098 12.14.66.1 75
Quadro P3200[261][256]2018-02-21 GP104 16 1328 7012 1792:112:64 98.8 172.8 6144 168 GDDR5 192 5530 12.1 4.6 6.1 75
Quadro P4000 Mobile[262][243]2017-01-11GP10416 MXM-B 3.0 ×16 122712277012 1792:112:64:14 78.5137.4 8192192.3GDDR5256 4398 12.14.66.1 100
Quadro P4200[263][256]2018-02-21 GP104 16 MXM-B 3.0 ×16 1227 1227 6008 2304:144:64:18 105.4 237.2 8192 192.3 GDDR5 256 7589 12.1 4.6 6.1 100
Quadro P5000 Mobile[264][243]2017-01-11GP10416 MXM-B 3.0 ×16 151315136012 2048:128:64:16 96.8193.7 16384192.3GDDR5256 6197 12.14.66.1 100
Quadro P5200[265][256]2018-02-21 GP104 16 MXM-B 3.0 ×16 1556 1556 7200 2560:160:64:20 111.7 279.4 16384 230.4 GDDR5 256 8940 12.1 4.6 6.1 100
Quadro Model Launch Core Fab
(nm)
Bus
interface
Core
clock
(MHz)
Shader
clock
(MHz)
Memory
clock
(MHz)
Config core Fillrate Memory Bus
width (bit)
Processing
Power (GFLOPs)
API support TDP (watts)
Pixel
(GP/s)
Texture
(GT/s)
Size
(MiB)
Band-
with (GB/s)
Type Single
precision
Double
precision
DirectXOpenGLCUDA
Compute
Capability
OpenCLVulkan

Quadro RTX Mobile

Quadro
GPU
Launch Core Core
clock
Memory clock Memory size
(MiB)
Memory type Memory
bandwidth
CUDA
cores
CUDA
Compute
Capa-
bility
Half
precision
Single
precision
Double
precision
DirectXOpen GLOpen CLVulkanPower
max.
UnitsMHzMHzMiBGiB/sTFLOPSTFLOPSGFLOPSWatt
Quadro RTX 3000 Mobile[266]2019-05-27 TU106(N19E-Q1-KA) 1390 1750 6144 192-bit GDDR6 336 2304 7.5 12.8 6.4 199 12.0 (12_1) 4.6 1.2 1.1 80
Quadro RTX 4000 Mobile[267]2019-05-27 TU104(N19E-Q3) 1560 1750 8192 256-bit GDDR6 448 2560 7.5 16.0 8.0 250 12.0 (12_1) 4.6 1.2 1.1 110
Quadro RTX 5000 Mobile[268]2019-05-27 TU104(N19E-Q5) 1530 1750 16384 256-bit GDDR6 448 3072 7.5 18.89.4297 12.0 (12_1) 4.6 1.2 1.1 110
Quadro
GPU
Launch Core Core
clock
(MHz)
Memory
clock
(MHz)
Memory
size
(MiB)
Memory
(type)
Memory
bandwidth
(GiB/s)
CUDA
cores
CUDA
Compute
Capa-
bility
Half
precision
Single
precision
Double
precision
DirectXOpen GLOpen CLVulkanPower
max.
(W)

Quadro NVS M

  • Architecture Curie (NV4x, G7x): DirectX 9.0c, OpenGL 2.1, Shader Model 3.0
  • Architecture Tesla (G80+): DirectX 10.0, OpenGL 3.3, Shader Model 4.0, CUDA 1.0 or 1.1, OpenCL 1.1
  • Architecture Tesla 2 (GT2xx): DirectX 10.1, OpenGL 3.3, Shader Model 4.1, CUDA 1.2 or 1.3, OpenCL 1.1
  • Architecture Fermi (GFxxx): DirectX 11.0, OpenGL 4.6, Shader Model 5.0, CUDA 2.x, OpenCL 1.1
  • Architecture Kepler (GKxxx): DirectX 11.2, OpenGL 4.6, Shader Model 5.0, CUDA 3.x, OpenCL 1.2, Vulkan 1.1
  • Architecture Maxwell 1 (GM1xx): DirectX 12.0, OpenGL 4.6, Shader Model 5.0, CUDA 5.0, OpenCL 1.2, Vulkan 1.1
Quadro NVS Mobile Launch Core Core clock
speed
Memory
clock speed
Memory size Memory
type
Memory
bandwidth
CUDA
cores
Max.
power
Interface 3-pin
stereo
connector
Note
UnitsMHzMHzMiBGB/sWatt
Quadro NVS 110M[269]2006-06-01G72M300600128 / 256 / 51264-bit DDR4.80no10PCIe 1.0x16VariesGo 7300 based
Quadro NVS 120M[270]2006-06-01G72GLM450700128 / 256 / 51264-bit DDR211.2no10MXM-IIIVariesQuadro FX 350M/Go 7400 based
Quadro NVS 130M[271]2007-05-09G86M400400128 / 25664-bit6.41610PCIe 2.0x16Varies8400M based
Quadro NVS 135M[272]2007-05-09G86M400600128 / 25664-bit9.551610PCIe 2.0x16Varies8400M GS based
Quadro NVS 140M[273]2007-05-09G86M400700128 / 256 / 51264-bit9.61610PCIe 2.0x16Varies8500M GT based
Quadro NVS 150M[274]2008-08-15G98M530700128 / 25664-bit11.22810MXM-IVaries9200M GS based
Quadro NVS 160M[275]2008-08-15G98M58070025664-bit11.22812MXM-IVaries9300M GS based
NVS 2100M[276]2010-01-07GT218535160051264-bit GDDR312.81612PCIe 2.0x16VariesGeForce G 305M based
Quadro NVS 300M[277]2006-05-24G73GLM450500128 / 256 / 512128-bit GDDR316.16no16PCIe 1.0x16VariesGo 7600 based
Quadro NVS 320M[278]2007-06-09G84M575700128 / 256 / 512128-bit GDDR322.553220MXM-HEVaries8700M based
NVS 3100M[279]2010-01-07GT218600160051264-bit GDDR312.81614PCIe 2.0x16VariesGeForce G 210M/310M based
NVS 4200M[280]2011-02-11GF1198101600102464-bit DDR312.84825MXMVariesGeForce 410M based
Quadro NVS 510M[281]2006-08-21G71GLM500600256 / 512 256-bit GDDR338.4no35PCI ExpressVariesGo 7900 GTX based
Quadro NVS 5100M[282]2010-01-07GT21655016001024128-bit GDDR325.64835MXM-A 3.0VariesGeForce GT 330M/Quadro FX 880M based
NVS 5200M[283]2012-06-01GF1176251800102464-bit DDR314.49625MXMVariesGeForce 710M/GT 620M based
NVS 5400M[284]2012-06-01GF10866018001024128-bit DDR328.89635MXMVariesGeForce GT 630M/Quadro 1000M based

NVENC Support Matrix

HW accelerated encode and decode are supported on NVIDIA Quadro products with Fermi, Kepler, Maxwell and Pascal generation GPUs.[285]

Board Family Chip Server/
Desktop/
Mobile
# of
NVENC/chip
Max # of
concurrent sessions
H.264 (AVCHD) YUV 4:2:0 H.264 (AVCHD) YUV 4:4:4 H.264 (AVCHD) Lossless H.265 (HEVC) 4K YUV 4:2:0 H.265 (HEVC) 4K YUV 4:4:4 H.265 (HEVC) 4K Lossless H.265 (HEVC) 8k HEVC B Frame support
Quadro P500 / P520 PascalGP108M10NoNoNoNoNoNoNoNo
Quadro P400 PascalGP107D13YesYesYesYesYesYesYesNo
Quadro P600 / P620/ P1000 PascalGP107D/M13YesYesYesYesYesYesYesNo
Quadro P2000 PascalGP107M1UnrestrictedYesYesYesYesYesYesYesNo
Quadro P2000 / P2200 PascalGP106D1UnrestrictedYesYesYesYesYesYesYesNo
Quadro P3200 / P4200 / P5200 PascalGP104M2UnrestrictedYesYesYesYesYesYesYesNo
Quadro P4000 PascalGP104D1UnrestrictedYesYesYesYesYesYesYesNo
Quadro P5000 PascalGP104D2UnrestrictedYesYesYesYesYesYesYesNo
Quadro P6000 PascalGP102D2UnrestrictedYesYesYesYesYesYesYesNo
Quadro GP100 PascalGP100D3UnrestrictedYesYesYesYesYesYesNoNo
Quadro GV100 VoltaGV100D3UnrestrictedYesYesYesYesYesYesYesNo
Quadro T1000 TuringTU117M13YesYesYesYesYesYesYesYes
Quadro T2000 TuringTU117M1UnrestrictedYesYesYesYesYesYesYesYes
Quadro RTX 3000 TuringTU106M1UnrestrictedYesYesYesYesYesYesYesYes
Quadro RTX 5000/RTX 4000 TuringTU104D/M1UnrestrictedYesYesYesYesYesYesYesYes
Quadro RTX 6000/RTX 8000 TuringTU102D1UnrestrictedYesYesYesYesYesYesYesYes

See also

  • AMD Radeon Pro – AMD's competing workstation graphics solution
  • Comparison of Nvidia graphics processing units
  • CUDA – Nvidia CUDA technology
  • Nvidia Tesla – Nvidia's first dedicated general purpose GPU (graphics processing unit)
  • Sun Visualization System – uses Nvidia Quadro FX for 3D rendering and graphics acceleration

References

  1. ↑Ung, Gordon Mah (25 July 2016). "AMD introduces a new Radeon Pro WX series to replace FirePro". PC World. http://www.pcworld.com/article/3099850/hardware/amd-introduces-a-new-radeon-pro-wx-series-to-replace-firepro.html. Retrieved 19 August 2016. 
  2. ↑Pitts, Martin. "SGI Announces New Additions to SGI VPro Graphics". Linux Today. http://linuxpr.com/releases/3061.html. Retrieved 27 September 2011. 
  3. ↑"NVIDIA Drivers FAQ". Silicon Graphics International Corp.. http://www.sgi.com/products/legacy/multilink/nvidia_faq.html. Retrieved 27 September 2011. 
  4. ↑"NVIDIA® Quadro® SDI Capture card enables uncompressed video to be streamed directly to Quadro SDI-enabled GPU memory.". http://www.nvidia.com/object/product_quadro_sdi_capture_us.html. 
  5. ↑"NVIDIA® Quadro® SDI Output card provides an integrated graphics-to-video solution enabling 2D and 3D effects to be composited in real-time with 2K, HD and SD video.". http://www.nvidia.com/object/product_quadro_sdi_output_us.html. 
  6. ↑"SLI Frame Rendering - NVIDIA SLI for Quadro Solutions-NVIDIA". http://www.nvidia.com/object/quadro_sli_rendering.html. 
  7. ↑"SLI FSAA (Full Scene Anti Aliasing) - NVIDIA SLI for Quadro Solutions-NVIDIA". http://www.nvidia.com/object/quadro_sli_fsaa.html. 
  8. ↑"NVIDIA Mosaic Technology for Multiple Displays". http://www.nvidia.com/object/nvidia-mosaic-technology.html. 
  9. ↑"Quadro Scalable Visualization Solutions (SVS) - NVIDIA". http://www.nvidia.com/object/quadro-scalable-visualization-solutions.html. 
  10. ↑"Video Wall Synchronization with NVIDIA Quadro Sync". http://www.nvidia.com/object/quadro-sync.html. 
  11. ↑"SLI Certified Systems and Motherboards - NVIDIA". http://www.nvidia.com/object/sli-certified-systems-and-motherboards.html. 
  12. ↑"Multi-GPU Technology, Systems, and Applications from NVIDIA Quadro". http://www.nvidia.com/object/multi-gpu-technology.html. 
  13. ↑"Multi-GPU FAQ" (PDF). http://international.download.nvidia.com/quadro/industry-solution/pdf/Multi-GPU-FAQ-Updated-0707.pdf. Retrieved 2017-07-14. 
  14. ↑"NVIDIA's 2nd Generation Maximus" (PDF). http://www.nvidia.com/content/quadro/maximus/nvidias-2nd-generation-maximus-dawn-of-the-hybrid-designer-by-moor-insights-strategy.pdf. Retrieved 2017-07-14. 
  15. ↑"[EVGA New Pro SLI Bridges V2"]. http://www.overclock.net/t/1550293/evga-new-pro-sli-bridges-v2/50#post_23775474. 
  16. ↑"SLI - FAQ - GeForce". http://www.geforce.com/hardware/technology/sli/faq#g1. 
  17. ↑"[EVGA New Pro SLI Bridges V2"]. http://www.overclock.net/t/1550293/evga-new-pro-sli-bridges-v2/50#post_23775443. 
  18. ↑"Nvidia GeForce GTX 1080 Pascal Display Pipeline & SLI". 17 May 2016. http://www.tomshardware.com/reviews/nvidia-geforce-gtx-1080-pascal,4572-4.html. 
  19. ↑"Quadro Visual Computing Appliance (VCA)". http://www.nvidia.com/object/visual-computing-appliance.html. 
  20. ↑"Photorealistic Rendering with NVIDIA Iray". http://www.nvidia.com/object/vca-for-iray.html. 
  21. ↑Keller, Alexander; Wächter, Carsten; Raab, Matthias; Seibert, Daniel; Van Antwerpen, Dietger; Korndörfer, Johann; Kettner, Lutz (2017). "The iray light transport simulation and rendering system". ACM SIGGRAPH 2017 Talks on - SIGGRAPH '17. p. Article No. 34. doi:10.1145/3084363.3085050. ISBN 978-1-4503-5008-2. 
  22. ↑"NVIDIA Quadro VCA for Chaos V-Ray RT". http://www.nvidia.com/object/vca-for-vray.html. 
  23. ↑"The NVIDIA Quadro Visual Computing Appliance (VCA) for OptiX". http://www.nvidia.com/object/vca-for-optix.html. 
  24. ↑"Archived copy". Archived from the original on 2016-11-03. https://web.archive.org/web/20161103234802/http://images.nvidia.com/content/quadro/vca/pdf/167106-dgx-1-datasheet-siggraph-july16-r6.pdf. Retrieved 2016-11-02. 
  25. ↑"Nvidia announces RTX 2000 GPU series with ‘6 times more performance’ and ray-tracing". The Verge. https://www.theverge.com/2018/8/20/17758724/nvidia-geforce-rtx-2080-specs-pricing-release-date-features. Retrieved 2018-08-20. 
  26. ↑"NVIDIA RTX™ platform". Nvidia. https://developer.nvidia.com/rtx. 
  27. ↑"NVIDIA TURING GPU ARCHITECTURE: Graphics Reinvented". Nvidia. 2018. https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf. Retrieved 28 June 2019. 
  28. ↑"NVIDIA TURING GPU ARCHITECTURE: Graphics Reinvented". Nvidia. 2018. https://www.nvidia.com/content/dam/en-zz/Solutions/design-visualization/technologies/turing-architecture/NVIDIA-Turing-Architecture-Whitepaper.pdf. Retrieved 28 June 2019. 
  29. ↑JeGX/Geeks3D.com. "GPU Caps Viewer: Graphics card and GPU information utility, OpenGL, OpenCL and CUDA API support, NVIDIA GeForce, ATI Radeon - oZone3D.Net". http://www.ozone3d.net/gpu_caps_viewer/. 
  30. ↑"TechPowerUp". https://www.techpowerup.com/gpuz/. 
  31. ↑"Advanced Driver Search - NVIDIA". http://www.nvidia.com/Download/Find.aspx?lang=en-us. 
  32. 32.032.1"Release 340 Quadro, NVS, Tesla, & Notebook Drivers - Version 342.01" (PDF). http://us.download.nvidia.com/Windows/Quadro_Certified/342.01/342.01-win10-quadro-release-notes.pdf. Retrieved 2017-07-14. 
  33. 33.033.1"Release 375 Quadro, NVS, Tesla, & Notebook Drivers - Version 377.83" (PDF). http://us.download.nvidia.com/Windows/Quadro_Certified/377.83/377.83-win10-quadro-grid-release-notes.pdf. Retrieved 2018-01-18. 
  34. 34.034.134.234.334.434.5"Release 450 Quadro, NVS, Tesla, & Notebook Drivers - Version 451.77" (PDF). http://us.download.nvidia.com/Windows/Quadro_Certified/451.77/451.77-win10-win8-win7-quadro-release-notes.pdf. Retrieved 2020-07-16. 
  35. ↑https://developer.nvidia.com/vulkan-driver
  36. ↑"Nvidia Developer - CUDA GPUs". http://developer.nvidia.com/cuda-gpus. Retrieved 19 August 2018.
Sours: https://handwiki.org/wiki/Engineering:Nvidia_Quadro
  1. Nier pc port
  2. Desert moon chords
  3. Michael taylor md

Nvidia

For the screen reader known as "NVDA", see NonVisual Desktop Access.

American multinational technology company

Coordinates: 37°22′14.62″N121°57′49.46″W / 37.3707278°N 121.9637389°W / 37.3707278; -121.9637389

Nvidia Corporation[note 1] (en-VID-ee-ə) is an American multinational technology company incorporated in Delaware and based in Santa Clara, California.[2] It designs graphics processing units (GPUs) for the gaming and professional markets, as well as system on a chip units (SoCs) for the mobile computing and automotive market. Its primary GPU line, labeled "GeForce", is in direct competition with the GPUs of the "Radeon" brand by Advanced Micro Devices (AMD). Nvidia expanded its presence in the gaming industry with its handheld game consolesShield Portable, Shield Tablet, and Shield Android TV and its cloud gaming serviceGeForce Now. Its professional line of GPUs are used in workstations for applications in such fields as architecture, engineering and construction, media and entertainment, automotive, scientific research, and manufacturing design.[3]

In addition to GPU manufacturing, Nvidia provides an application programming interface (API) called CUDA that allows the creation of massively parallel programs which utilize GPUs.[4][5] They are deployed in supercomputing sites around the world.[6][7] More recently, it has moved into the mobile computing market, where it produces Tegra mobile processors for smartphones and tablets as well as vehicle navigation and entertainment systems.[8][9][10] In addition to AMD, its competitors include Intel and Qualcomm.[11][12]

Nvidia announced plans on September 13, 2020 to acquire Arm Ltd. from SoftBank, pending regulatory approval, for a value of US$40 billion in stock and cash, which would be the largest semiconductor acquisition to date. SoftBank Group will acquire slightly less than a 10% stake in Nvidia, and Arm will maintain its headquarters in Cambridge.[13][14][15][16][17]

History[edit]

Nvidia was founded on April 5, 1993,[18][19][20] by Jensen Huang (CEO as of 2020[update]), a Taiwanese American, previously director of CoreWare at LSI Logic and a microprocessor designer at Advanced Micro Devices (AMD), Chris Malachowsky, an electrical engineer who worked at Sun Microsystems, and Curtis Priem, previously a senior staff engineer and graphics chip designer at Sun Microsystems.[21][22]

In 1993, the three co-founders believed that the proper direction for the next wave of computing was accelerated or graphics-based computing because it could solve problems that general-purpose computing could not. They also observed that video games were simultaneously one of the most computationally challenging problems and would have incredibly high sales volume. Video games became the company's flywheel to reach large markets and funding huge R&D to solve massive computational problems. With only $40,000 in the bank, the company was born.[23] The company subsequently received $20 million of venture capital funding from Sequoia Capital and others.[24] Nvidia initially had no name and the co-founders named all their files NV, as in "next version". The need to incorporate the company prompted the co-founders to review all words with those two letters, leading them to "invidia", the Latin word for "envy".[23] Nvidia went public on January 22, 1999.[25][26][27]

Releases and acquisitions[edit]

The release of the RIVA TNT in 1998 solidified Nvidia's reputation for developing capable graphics adapters. In late 1999, Nvidia released the GeForce 256 (NV10), most notably introducing on-board transformation and lighting (T&L) to consumer-level 3D hardware. Running at 120 MHz and featuring four-pixel pipelines, it implemented advanced video acceleration, motion compensation, and hardware sub-picture alpha blending. The GeForce outperformed existing products by a wide margin.

Due to the success of its products, Nvidia won the contract to develop the graphics hardware for Microsoft's Xbox game console, which earned Nvidia a $200 million advance. However, the project took many of its best engineers away from other projects. In the short term this did not matter, and the GeForce2 GTS shipped in the summer of 2000. In December 2000, Nvidia reached an agreement to acquire the intellectual assets of its one-time rival 3dfx, a pioneer in consumer 3D graphics technology leading the field from mid 1990s until 2000.[28][29] The acquisition process was finalized in April 2002.[30]

In July 2002, Nvidia acquired Exluna for an undisclosed sum. Exluna made software-rendering tools and the personnel were merged into the Cg project.[31] In August 2003, Nvidia acquired MediaQ for approximately US$70 million.[32] On April 22, 2004, Nvidia acquired iReady, also a provider of high performance TCP/IP and iSCSI offload solutions.[33] In December 2004, it was announced that Nvidia would assist Sony with the design of the graphics processor (RSX) in the PlayStation 3 game console. On December 14, 2005, Nvidia acquired ULI Electronics, which at the time supplied third-party southbridge parts for chipsets to ATI, Nvidia's competitor.[34] In March 2006, Nvidia acquired Hybrid Graphics.[35] In December 2006, Nvidia, along with its main rival in the graphics industry AMD (which had acquired ATI), received subpoenas from the U.S. Department of Justice regarding possible antitrust violations in the graphics card industry.[36]

Forbes named Nvidia its Company of the Year for 2007, citing the accomplishments it made during the said period as well as during the previous five years.[37] On January 5, 2007, Nvidia announced that it had completed the acquisition of PortalPlayer, Inc.[38] In February 2008, Nvidia acquired Ageia, developer of the PhysXphysics engine and physics processing unit. Nvidia announced that it planned to integrate the PhysX technology into its future GPU products.[39][40]

In July 2008, Nvidia took a write-down of approximately $200 million on its first-quarter revenue, after reporting that certain mobile chipsets and GPUs produced by the company had "abnormal failure rates" due to manufacturing defects. Nvidia, however, did not reveal the affected products. In September 2008, Nvidia became the subject of a class action lawsuit over the defects, claiming that the faulty GPUs had been incorporated into certain laptop models manufactured by Apple Inc., Dell, and HP. In September 2010, Nvidia reached a settlement, in which it would reimburse owners of the affected laptops for repairs or, in some cases, replacement.[41][42] On January 10, 2011, Nvidia signed a six-year, $1.5 billion cross-licensing agreement with Intel, ending all litigation between the two companies.[43]

In November 2011, after initially unveiling it at Mobile World Congress, Nvidia released its Tegra 3ARMsystem-on-a-chip for mobile devices. Nvidia claimed that the chip featured the first-ever quad-core mobile CPU.[44][45] In May 2011, it was announced that Nvidia had agreed to acquire Icera, a baseband chip making company in the UK, for $367 million.[46] In January 2013, Nvidia unveiled the Tegra 4, as well as the Nvidia Shield, an Android-based handheld game console powered by the new system-on-chip.[47] On July 29, 2013, Nvidia announced that they acquired PGI from STMicroelectronics.[48]

Since 2014, Nvidia has diversified its business focusing on three markets: gaming, automotive electronics, and mobile devices.[49]

On May 6, 2016, Nvidia unveiled the first GPUs of the GeForce 10 series, the GTX 1080 and 1070, based on the company's new Pascal microarchitecture. Nvidia claimed that both models outperformed its Maxwell-based Titan X model; the models incorporate GDDR5X and GDDR5 memory respectively, and use a 16 nm manufacturing process. The architecture also supports a new hardware feature known as simultaneous multi-projection (SMP), which is designed to improve the quality of multi-monitor and virtual reality rendering.[50][51][52] Laptops that include these GPUs and are sufficiently thin – as of late 2017, under 0.8 inches (20 mm) – have been designated as meeting Nvidia's "Max-Q" design standard.[53]

In July 2016, Nvidia agreed to a settlement for a false advertising lawsuit regarding its GTX 970 model, as the models were unable to use all of their advertised 4 GB of RAM due to limitations brought by the design of its hardware.[54] In May 2017, Nvidia announced a partnership with Toyota which will use Nvidia's Drive PX-series artificial intelligence platform for its autonomous vehicles.[55] In July 2017, Nvidia and Chinese search giant Baidu announced a far-reaching AI partnership that includes cloud computing, autonomous driving, consumer devices, and Baidu's open-source AI framework PaddlePaddle. Baidu unveiled that Nvidia's Drive PX 2 AI will be the foundation of its autonomous-vehicle platform.[56]

Nvidia officially released the Titan V on December 7, 2017.[57][58]

Nvidia officially released the Nvidia Quadro GV100 on March 27, 2018.[59] Nvidia officially released the RTX 2080 GPUs in September 27, 2018. In 2018, Google announced that Nvidia's Tesla P4 graphic cards would be integrated into Google Cloud service's artificial intelligence.[60]

In May 2018, on the Nvidia user forum, a thread was started[61] asking the company to update users when they would release web drivers for its cards installed on legacy Mac Pro machines up to mid-2012 5,1 running the macOS Mojave operating system 10.14. Web drivers are required to enable graphics acceleration and multiple display monitor capabilities of the GPU. On its Mojave update info website, Apple stated that macOS Mojave would run on legacy machines with 'Metal compatible' graphics cards[62] and listed Metal compatible GPUs, including some manufactured by Nvidia.[63] However, this list did not include Metal compatible cards that currently work in macOS High Sierra using Nvidia developed web drivers. In September, Nvidia responded, "Apple fully control drivers for Mac OS. But if Apple allows, our engineers are ready and eager to help Apple deliver great drivers for Mac OS 10.14 (Mojave)."[64] In October, Nvidia followed this up with another public announcement, "Apple fully controls drivers for Mac OS. Unfortunately, Nvidia currently cannot release a driver unless it is approved by Apple,"[65] suggesting a possible rift between the two companies.[66] By January 2019, with still no sign of the enabling web drivers, Apple Insider weighed into the controversy with a claim that Apple management "doesn't want Nvidia support in macOS".[67] The following month, Apple Insider followed this up with another claim that Nvidia support was abandoned because of "relational issues in the past",[68] and that Apple was developing its own GPU technology.[69] Without Apple approved Nvidia web drivers, Apple users are faced with replacing their Nvidia cards with a competing supported brand, such as AMD Radeon from the list recommended by Apple.[70]

On March 11, 2019, Nvidia announced a deal to buy Mellanox Technologies for $6.9 billion[71] to substantially expand its footprint in the high-performance computing market. In May 2019, Nvidia announced new RTX Studio laptops. The creators say that the new laptop is going to be seven times faster than a top-end MacBook Pro with a Core i9 and AMD's Radeon Pro Vega 20 graphics in apps like Maya and RedCine-X Pro.[72] In August 2019, Nvidia announced Minecraft RTX, an official Nvidia-developed patch for the game Minecraft adding real-time DXR raytracing exclusively to the Windows 10 version of the game. The whole game is, in Nvidia's words, "refit" with path tracing, which dramatically affects the way light, reflections, and shadows work inside the engine.[73]

In May 2020, Nvidia's top scientists developed an open-sourceventilator in order to address the shortage resulting from the global coronavirus pandemic.[74] On May 14, 2020, Nvidia officially announced their Ampere GPU microarchitecture and the Nvidia A100 GPU accelerator.[75][76] In July 2020, it was reported that Nvidia was in talks with SoftBank to buy Arm, a UK-based chip designer, for $32 billion.[77]

On September 1, 2020, Nvidia officially announced the GeForce 30 series based on the company's new Ampere microarchitecture.[78][79]

On September 13, 2020, it was announced that Nvidia would buy Arm Holdings from SoftBank Group for $40 billion, subject to the usual scrutiny, with the latter retaining a 10% share of Nvidia.[16][15][80][81]

In October 2020, Nvidia announced its plan to build the most powerful computer in Cambridge, England. Named Cambridge-1, the computer will employ AI to support healthcare research, with an expected completion by the end of 2020, at a cost of approximately £40 million. According to Jensen Huang, "The Cambridge-1 supercomputer will serve as a hub of innovation for the UK, and further the groundbreaking work being done by the nation’s researchers in critical healthcare and drug discovery."[82]

Also in October 2020, along with the release of Nvidia RTX A6000, Nvidia announced it is retiring its workstation GPU brand Quadro, shifting product name to Nvidia RTX for future products and the manufacturing to be Nvidia Ampere architecture based.[83]

In August 2021, the proposed takeover of Arm Holdings was stalled after the UK's Competition and Markets Authority raised "significant competition concerns".[84]

Finances[edit]

For the fiscal year 2020, Nvidia reported earnings of US$2.796 billion, with an annual revenue of US$10.918 billion, a decline of 6.8% over the previous fiscal cycle. Nvidia's shares traded at over $531 per share, and its market capitalization was valued at over US$328.7 billion in January 2021.[85]

For the Q2 of 2020, Nvidia reported sales of $3.87 billion, which was a 50% rise from the same period in 2019. The surge in sales and people's higher demand for computer technology. According to the financial chief of the company, Colette Kress, the effects of the pandemic will "likely reflect this evolution in enterprise workforce trends with a greater focus on technologies, such as Nvidia laptops and virtual workstations, that enable remote work and virtual collaboration."[86]

GPU Technology Conference[edit]

Nvidia's GPU Technology Conference (GTC), now called Nvidia GTC, is a series of technical conferences held around the world.[87] It originated in 2009 in San Jose, California, with an initial focus on the potential for solving computing challenges through GPUs.[88] In recent years, the conference focus has shifted to various applications of artificial intelligence and deep learning, including: self-driving cars, healthcare, high performance computing, and Nvidia Deep Learning Institute (DLI) training.[89] GTC 2018 attracted over 8400 attendees.[87] GTC 2020 was converted to a digital event and drew roughly 59,000 registrants.[90]

Product families[edit]

Nvidia's family includes graphics, wireless communication, PC processors, and automotive hardware/software.

Some families are listed below:

  • GeForce, consumer-oriented graphics processing products
  • Nvidia RTX, professional visual computing graphics processing products (replacing Quadro)
  • NVS, multi-display business graphics solution
  • Tegra, a system on a chip series for mobile devices
  • Tesla, dedicated general-purpose GPU for high-end image generation applications in professional and scientific fields
  • nForce, a motherboard chipset created by Nvidia for Intel (Celeron, Pentium and Core 2) and AMD (Athlon and Duron) microprocessors
  • Nvidia GRID, a set of hardware and services by Nvidia for graphics virtualization
  • Nvidia Shield, a range of gaming hardware including the Shield Portable, Shield Tablet and, most recently, the Shield Android TV
  • Nvidia Drive automotive solutions, a range of hardware and software products for designers and manufacturers of autonomous vehicles. The Drive PX-series is a high performance computer platform aimed at autonomous driving through deep learning,[91] while Driveworks is an operating system for driverless cars.[92]
  • BlueField, a range of Data Processing Units, initially inherited from their acquisition of Mellanox Technologies[93][94]
  • Nvidia Datacenter/Server class CPU, codenamed Nvidia Grace, coming in 2023[95][96]

Open-source software support[edit]

See also: Free and open-source graphics device driver, Mesa 3D, nouveau (software), and OpenPOWER Foundation

Until September 23, 2013, Nvidia had not published any documentation for its advanced hardware,[97] meaning that programmers could not write free and open-sourcedevice driver for its products without resorting to (clean room) reverse engineering.

Instead, Nvidia provides its own binary GeForce graphics drivers for X.Org and an open-source library that interfaces with the Linux, FreeBSD or Solaris kernels and the proprietary graphics software. Nvidia also provided but stopped supporting an obfuscated open-source driver that only supports two-dimensional hardware acceleration and ships with the X.Org distribution.[98]

The proprietary nature of Nvidia's drivers has generated dissatisfaction within free-softwarecommunities.[99] Some Linux and BSD users insist on using only open-source drivers and regard Nvidia's insistence on providing nothing more than a binary-only driver as inadequate, given that competing manufacturers such as Intel offer support and documentation for open-source developers and that others (like AMD) release partial documentation and provide some active development.[100][101]

Because of the closed nature of the drivers, Nvidia video cards cannot deliver adequate features on some platforms and architectures given that the company only provides x86/x64 and ARMv7-A driver builds.[102] As a result, support for 3D graphics acceleration in Linux on PowerPC does not exist, nor does support for Linux on the hypervisor-restricted PlayStation 3 console.

Some users claim that Nvidia's Linux drivers impose artificial restrictions, like limiting the number of monitors that can be used at the same time, but the company has not commented on these accusations.[103]

In 2014, with Maxwell GPUs, Nvidia started to require firmware by them to unlock all features of its graphics cards. Up to now, this state has not changed and makes writing open-source drivers difficult.[104][105][106]

Deep learning[edit]

Nvidia GPUs are used in deep learning, and accelerated analytics due to Nvidia's API CUDA which allows programmers to utilize the higher number of cores present in GPUs to parallelizeBLAS operations which are extensively used in machine learning algorithms.[107] They were included in many Tesla vehicles before Elon Musk announced at Tesla Autonomy Day in 2019 that the company developed its own SoC and Full Self-Driving computer now and would stop using Nvidia hardware for their vehicles.[108][109] These GPUs are used by researchers, laboratories, tech companies and enterprise companies.[110] In 2009, Nvidia was involved in what was called the "big bang" of deep learning, "as deep-learning neural networks were combined with Nvidia graphics processing units (GPUs)".[111] That year, the Google Brain used Nvidia GPUs to create Deep Neural Networks capable of machine learning, where Andrew Ng determined that GPUs could increase the speed of deep-learning systems by about 100 times.[112]

DGX[edit]

Main article: Nvidia DGX

DGX is a line of supercomputers by Nvidia.

In April 2016, Nvidia produced the DGX-1 based on an 8 GPU cluster, to improve the ability of users to use deep learning by combining GPUs with integrated deep learning software.[113] It also developed Nvidia Tesla K80 and P100 GPU-based virtual machines, which are available through Google Cloud, which Google installed in November 2016.[114]Microsoft added GPU servers in a preview offering of its N series based on Nvidia's Tesla K80s, each containing 4992 processing cores. Later that year, AWS's P2 instance was produced using up to 16 Nvidia Tesla K80 GPUs. That month Nvidia also partnered with IBM to create a software kit that boosts the AI capabilities of Watson,[115] called IBM PowerAI.[116][117] Nvidia also offers its own NVIDIA Deep Learning software development kit.[118] In 2017, the GPUs were also brought online at the Riken Center for Advanced Intelligence Project for Fujitsu.[119] The company's deep learning technology led to a boost in its 2017 earnings.[120]

In May 2018, researchers at the artificial intelligence department of Nvidia realized the possibility that a robot can learn to perform a job simply by observing the person doing the same job. They have created a system that, after a short revision and testing, can already be used to control the universal robots of the next generation. In addition to GPU manufacturing, Nvidia provides parallel processing capabilities to researchers and scientists that allow them to efficiently run high-performance applications.[121]

Inception Program[edit]

Nvidia's Inception Program was created to support startups making exceptional advances in the fields of artificial intelligence and data science. Award winners are announced at Nvidia's GTC Conference. As of March 2018, there were 2,800 startups in the Inception Program. As of August 2021, NVIDIA Inception has surpassed 8,500 members in 90 countries, with cumulative funding of $60 billion (USD).[122][123][124]

2018 winners[edit]

  • Subtle Medical (healthcare)
  • AiFi (enterprise)
  • Kinema Systems (autonomous vehicles)

2017 winners[edit]

  • Genetesis (social innovation)
  • Athelas (hottest emerging)
  • Deep Instinct (most disruptive)

Controversies[edit]

Maxwell advertising dispute[edit]

GTX 970 hardware specifications[edit]

Issues with the GeForce GTX 970's specifications were first brought up by users when they found out that the cards, while featuring 4 GB of memory, rarely accessed memory over the 3.5 GB boundary. Further testing and investigation eventually led to Nvidia issuing a statement that the card's initially announced specifications had been altered without notice before the card was made commercially available, and that the card took a performance hit once memory over the 3.5 GB limit were put into use.[125][126][127]

The card's back-end hardware specifications, initially announced as being identical to those of the GeForce GTX 980, differed in the amount of L2 cache (1.75 MB versus 2 MB in the GeForce GTX 980) and the number of ROPs (56 versus 64 in the 980). Additionally, it was revealed that the card was designed to access its memory as a 3.5 GB section, plus a 0.5 GB one, access to the latter being 7 times slower than the first one.[128] The company then went on to promise a specific driver modification in order to alleviate the performance issues produced by the cutbacks suffered by the card.[129] However, Nvidia later clarified that the promise had been a miscommunication and there would be no specific driver update for the GTX 970.[130] Nvidia claimed that it would assist customers who wanted refunds in obtaining them.[131] On February 26, 2015, Nvidia CEO Jen-Hsun Huang went on record in Nvidia's official blog to apologize for the incident.[132] In February 2015 a class-action lawsuit alleging false advertising was filed against Nvidia and Gigabyte Technology in the U.S. District Court for Northern California.[133][134]

Nvidia revealed that it is able to disable individual units, each containing 256KB of L2 cache and 8 ROPs, without disabling whole memory controllers.[135] This comes at the cost of dividing the memory bus into high speed and low speed segments that cannot be accessed at the same time unless one segment is reading while the other segment is writing because the L2/ROP unit managing both of the GDDR5 controllers shares the read return channel and the write data bus between the two GDDR5 controllers and itself.[135] This is used in the GeForce GTX 970, which therefore can be described as having 3.5 GB in its high speed segment on a 224-bit bus and 0.5 GB in a low speed segment on a 32-bit bus.[135]

On July 27, 2016, Nvidia agreed to a preliminary settlement of the U.S. class action lawsuit,[133] offering a $30 refund on GTX 970 purchases. The agreed upon refund represents the portion of the cost of the storage and performance capabilities the consumers assumed they were obtaining when they purchased the card.[136]

Async compute support[edit]

While the Maxwell series was marketed as fully DirectX 12 compliant,[137][138] Oxide Games, developer of Ashes of the Singularity, uncovered that Maxwell-based cards do not perform well when async compute is utilized.[139][140][141][137]

It appears that while this core feature is in fact exposed by the driver,[142] Nvidia partially implemented it through a driver-based shim, coming at a high performance cost.[141] Unlike AMD's competing GCN-based graphics cards which include a full implementation of hardware-based asynchronous compute,[143][144] Nvidia planned to rely on the driver to implement a software queue and a software distributor to forward asynchronous tasks to the hardware schedulers, capable of distributing the workload to the correct units.[145] Asynchronous compute on Maxwell therefore requires that both a game and the GPU driver be specifically coded for asynchronous compute on Maxwell in order to enable this capability.[146] The 3DMark Time Spy benchmark shows no noticeable performance difference between asynchronous compute being enabled or disabled.[146] Asynchronous compute is disabled by the driver for Maxwell.[146]

Oxide claims that this led to Nvidia pressuring them not to include the asynchronous compute feature in their benchmark at all, so that the 900 series would not be at a disadvantage against AMD's products which implement asynchronous compute in hardware.[140]

Maxwell requires that the GPU be statically partitioned for asynchronous compute to allow tasks to run concurrently.[147] Each partition is assigned to a hardware queue. If any of the queues that are assigned to a partition empty out or are unable to submit work for any reason (e.g. a task in the queue must be delayed until a hazard is resolved), the partition and all of the resources in that partition reserved for that queue will idle.[147] Asynchronous compute therefore could easily hurt performance on Maxwell if it is not coded to work with Maxwell's static scheduler.[147] Furthermore, graphics tasks saturate Nvidia GPUs much more easily than they do to AMD's GCN-based GPUs which are much more heavily weighted towards compute, so Nvidia GPUs have fewer scheduling holes that could be filled by asynchronous compute than AMD's.[147] For these reasons, the driver forces a Maxwell GPU to place all tasks into one queue and execute each task in serial, and give each task the undivided resources of the GPU no matter whether or not each task can saturate the GPU or not.[147]

GeForce Partner Program[edit]

Main article: GeForce Partner Program

The Nvidia GeForce Partner Program was a marketing program designed to provide partnering companies with benefits such as public relations support, video game bundling, and marketing development funds.[148] The program proved to be controversial, with complaints about it possibly being an anti-competitive practice.[149]

First announced in a blog post on March 1, 2018,[150] it was canceled on May 4, 2018.[151]

Hardware Unboxed controversy[edit]

On December 10, 2020, Nvidia told popular YouTube tech reviewer Steven Walton of Hardware Unboxed that it would no longer supply him with GeForce Founders Edition graphics card review units.[152][153] In a Twitter message, Hardware Unboxed said, "Nvidia have officially decided to ban us from receiving GeForce Founders Edition GPU review samples. Their reasoning is that we are focusing on rasterization instead of ray tracing. They have said they will revisit this 'should your editorial direction change.'"[154]

In emails that were disclosed by Walton from Nvidia Senior PR Manager Bryan Del Rizzo, Nvidia had said:

...your GPU reviews and recommendations have continued to focus singularly on rasterization performance, and you have largely discounted all of the other technologies we offer gamers. It is very clear from your community commentary that you do not see things the same way that we, gamers, and the rest of the industry do.[155]

TechSpot, partner site of Hardware Unboxed, said, "this and other related incidents raise serious questions around journalistic independence and what they are expecting of reviewers when they are sent products for an unbiased opinion."[155]

A number of prominent technology reviewers came out strongly against Nvidia's move.[156][157]Linus Sebastian, of Linus Tech Tips, titled the episode of his popular weekly WAN Show, "NVIDIA might ACTUALLY be EVIL..."[158] and was highly critical of the company's move to dictate specific outcomes of technology reviews.[159] The popular review site Gamers Nexus said it was, "Nvidia's latest decision to shoot both its feet: They've now made it so that any reviewers covering RT will become subject to scrutiny from untrusting viewers who will suspect subversion by the company. Shortsighted self-own from NVIDIA."[160]

Two days later, Nvidia reversed their stance.[161][162] Hardware Unboxed sent out a Twitter message, "I just received an email from Nvidia apologizing for the previous email & they've now walked everything back."[163][156] On December 14, Hardware Unboxed released a video explaining the controversy from their viewpoint.[164] Via Twitter, they also shared a second apology sent by Nvidia's Del Rizzo that said "to withhold samples because I didn't agree with your commentary is simply inexcusable and crossed the line."[165][166]

See also[edit]

Notes[edit]

  1. ^Officially written as NVIDIA and stylized in its logo as nVIDIA with the lowercase "n" the same height as the uppercase "VIDIA"; formerly stylized as nVIDIA with a large italicized lowercase "n" on products from the mid 1990s to early-mid 2000s. "NVIDIA Logo Guidelines at a Glance"(PDF). nvidia.com. Nvidia. Retrieved March 21, 2018.

References[edit]

  1. ^ abcdef"NVIDIA Annual Reports 2020"(PDF). nvidianews.nvidia.com. Nvidia. December 2020.
  2. ^"NVIDIA Corporation – Investor Resources – FAQs". investor.nvidia.com.
  3. ^Smith, Ryan. "Quadro No More? NVIDIA Announces Ampere-based RTX A6000 & A40 Video Cards For Pro Visualization". www.anandtech.com. Retrieved March 10, 2021.
  4. ^"NVIDIA Doesn't Want Cryptocurrency Miners to Buy Its Gaming GPUs". MSN. Retrieved April 5, 2021.
  5. ^Kirk, David; Hwu, Wen-Mei (2017). Programming Massively Parallel Processors (Third ed.). Elsevier. p. 345. ISBN .
  6. ^Clark, Don (August 4, 2011). "J.P. Morgan Shows Benefits from Chip Change". WSJ Digits Blog. Retrieved September 14, 2011.
  7. ^"Top508 Supercomputing Sites". Top500. Retrieved September 14, 2011.
  8. ^Burns, Chris (August 3, 2011). "2011 The Year of Nvidia dominating Android Superphones and tablets". SlashGear. Retrieved September 14, 2011.
  9. ^"Tegra Super Tablets". Nvidia. Retrieved September 14, 2011.
  10. ^"Tegra Super Phones". Nvidia. Retrieved September 14, 2011.
  11. ^Jennewine, Trevor (January 15, 2021). "Why Intel's Competitive Edge Is Crumbling". The Motley Fool. Retrieved April 16, 2021.
  12. ^Neiger, Chris (January 26, 2021). "Better Buy: NVIDIA vs. Qualcomm". The Motley Fool. Retrieved April 16, 2021.
  13. ^"NVIDIA to Acquire Arm for $40 Billion, Creating World's Premier Computing Company for the Age of AI". NVIDIA (Press release). Retrieved December 2, 2020.
  14. ^"NVIDIA to Acquire Arm for $40 Billion, Creating World's Premier Computing Company for the Age of AI". NVIDIA. September 13, 2020. Retrieved November 21, 2020.
  15. ^ abRosoff, Matt (September 13, 2020). "Nvidia to buy Arm Holdings from SoftBank for $40 billion". CNBC. Retrieved September 13, 2020.
  16. ^ abMoorhead, Patrick. "It's Official- NVIDIA Acquires Arm For $40B To Create What Could Be A Computing Juggernaut". Forbes. Retrieved September 14, 2020.
  17. ^Lyons, Kim (September 13, 2020). "Nvidia is acquiring Arm for $40 billion". The Verge. Retrieved September 15, 2020.
  18. ^"Company Info". Nvidia.com. Retrieved November 9, 2010.
  19. ^"Jensen Huang: Executive Profile & Biography". Bloomberg News. Retrieved June 21, 2018.
  20. ^"Articles of Incorporation of Nvidia Corporation". California Secretary of State. Retrieved October 23, 2019 – via California Secretary of State Business Database.
  21. ^"NVIDIA Company History: Innovations Over the Years". NVIDIA. Retrieved April 17, 2021.
  22. ^"NVIDIA Corporation | History, Headquarters, & Facts". Encyclopedia Britannica. Retrieved April 17, 2021.
  23. ^ abNusca, Andrew (November 16, 2017). "This Man Is Leading an AI Revolution in Silicon Valley—And He's Just Getting Started". Fortune. Archived from the original on November 16, 2017. Retrieved November 28, 2017.
  24. ^Williams, Elisa (April 15, 2002). "Crying wolf". Forbes. Retrieved February 11, 2017.
  25. ^Feinstein, Ken (January 22, 1999). "Nvidia Goes Public". gamecenter.co. Archived from the original on October 12, 1999. Retrieved July 13, 2019.
  26. ^Takahashi, Dean (January 25, 1999). "Shares of Nvidia Surge 64% After Initial Public Offering". The Wall Street Journal. Retrieved July 13, 2019.
  27. ^"NVIDIA Corporation Announces Initial Public Offering of 3,500,000 Shares of Common Stock". nvidia.com. January 22, 1999. Retrieved July 13, 2019.
  28. ^Perez, Derek; Hara, Michael (December 15, 2000). "NVIDIA to Acquire 3dfx Core Graphics Assets" (Press release). Santa Clara, CA. Retrieved January 23, 2017.
  29. ^Leupp, Alex; Sellers, Scott (December 15, 2000). "3dfx Announces Three Major Initiatives To Protect Creditors and Maximize Shareholder Value" (Press release). San Jose, CA. Archived from the original on February 5, 2001. Retrieved January 23, 2017.
  30. ^Kanellos, Michael (April 11, 2002). "NNvidia buys out 3dfx graphics chip business". CNET. Retrieved January 23, 2017.
  31. ^Becker, David. "Nvidia buys out Exluna". News.cnet.com. Retrieved November 9, 2010.
  32. ^"NVIDIA Completes Purchase of MediaQ". Press Release. NVIDIA Corporation. August 21, 2003. Archived from the original on January 9, 2014. Retrieved August 21, 2016.
  33. ^"NVIDIA Announces Acquisition of iReady". Press Release. NVIDIA Corporation. April 22, 2004. Retrieved August 21, 2016.
  34. ^"NVIDIA to Acquire ULi Electronics, a Leading Developer of Core Logic Technology". Press Release. NVIDIA Corporation. December 14, 2005. Retrieved August 21, 2016.
  35. ^Smith, Tony (March 22, 2006). "Nvidia acquires Hybrid Graphics – Middleware purchase". Hardware. The Register. Archived from the original on January 16, 2013. Retrieved August 21, 2016.
  36. ^Krazit, Tom; McCarthy, Caroline (December 1, 2006). "Justice Dept. subpoenas AMD, Nvidia". New York Times. Archived from the original on December 8, 2006.
  37. ^Brian Caulfield (January 7, 2008). "Shoot to Kill". Forbes. Retrieved December 26, 2007.
  38. ^"Nvidia acquires PortalPlayer". Press Release. NVIDIA Corporation. January 5, 2007. Retrieved August 21, 2016.
  39. ^"Nvidia to acquire Ageia for the PhysX chip". CNET. Retrieved May 26, 2017.
  40. ^"Did NVIDIA cripple its CPU gaming physics library to spite Intel?". Ars Technica. July 9, 2010. Retrieved May 26, 2017.
  41. ^"Nvidia GPU Class-Action Settlement Offers Repairs, New Laptops". PC Magazine. Retrieved May 26, 2017.
  42. ^"Update: Nvidia Says Older Mobile GPUs, Chipsets Failing". ExtremeTech. Retrieved May 26, 2017.
  43. ^"Intel agrees to pay NVIDIA $1.5b in patent license fees, signs cross-license". Engadget. Retrieved May 26, 2017.
  44. ^"Nvidia Tegra 3: what you need to know". Techradar. November 9, 2011. Retrieved May 26, 2017.
  45. ^"Nvidia Quad Core Mobile Processors Coming in August". PC World. Retrieved February 15, 2011.
  46. ^"Cambridge coup as Icera goes to Nvidia for £225m". Business Weekly. May 9, 2011. Retrieved May 10, 2011.
  47. ^"Nvidia announces Project Shield handheld gaming system with 5-inch multitouch display, available in Q2 of this year". The Verge. January 7, 2013. Retrieved May 26, 2017.
  48. ^"NVIDIA Pushes Further into HPC With Portland Group Acquisition – insideHPC". insideHPC. July 29, 2013. Retrieved August 25, 2017.
  49. ^Team, Trefis (December 31, 2014). "Nvidia's Performance In 2014: Factors That Are Driving Growth". Forbes. Retrieved October 7, 2020.
  50. ^"Nvidia's new graphics cards are a big deal". The Verge. May 7, 2016. Retrieved May 26, 2017.
  51. ^Mark Walton (May 7, 2016). "Nvidia's GTX 1080 and GTX 1070 revealed: Faster than Titan X at half the price". Ars Technica.
  52. ^Joel Hruska (May 10, 2016). "Nvidia's Ansel, VR Funhouse apps will enhance screenshots, showcase company's VR technology". ExtremeTech.
  53. ^Crider, Michael (October 5, 2017). "What Are NVIDIA MAX-Q Laptops?". How-To Geek. Retrieved December 18, 2017.
  54. ^Smith, Ryan. "Update: NVIDIA GeForce GTX 970 Settlement Claims Website Now Open". Anandtech. Purch, Inc. Retrieved November 15, 2016.
  55. ^Alexandria Sage (May 10, 2017). "Nvidia says Toyota will use its AI technology for self-driving cars". Reuters.
  56. ^"Nvidia and Baidu join forces in far reaching AI partnership".
  57. ^Newsroom, NVIDIA. "NVIDIA TITAN V Transforms the PC into AI Supercomputer". NVIDIA Newsroom Newsroom.
  58. ^"Introducing NVIDIA TITAN V: The World's Most Powerful PC Graphics Card". NVIDIA.
  59. ^News Archive | NVIDIA Newsroom
  60. ^"Google Cloud gets support for Nvidia's Tesla P4 inferencing accelerators". Tech Crunch. Retrieved August 30, 2018.
  61. ^May 10, 2018. 'When will the Nvidia Web Drivers be released for macOS Mojave 10.14'. Nvidia
  62. ^Upgrade to macOS Mojave.Apple Computer
  63. ^Install macOS 10.14 Mojave on Mac Pro (mid 2010) and Mac Pro (mid 2012). Apple Computer
  64. ^September 28, 2018. CUDA 10 and macOS 10.14. Nvidia
  65. ^October 18, 2018. FAQ about MacOS 10.14 (Mojave) NVIDIA drivers
  66. ^Florian Maislinger. January 22, 2019. 'Apple and Nvidia are said to have a silent hostility'. PC Builders Club.
  67. ^William Gallagher and Mike Wuerthele. January 18, 2019. 'Apple's management doesn't want Nvidia support in macOS, and that's a bad sign for the Mac Pro'
  68. ^Vadim Yuryev. February 14, 2019. Video: Nvidia support was abandoned in macOS Mojave, and here's why. Apple Insider
  69. ^Daniel Eran Dilger. April 4, 2017. 'Why Apple's new GPU efforts are a major disruptive threat to Nvidia'. Apple Insider
  70. ^'Install macOS 10.14 Mojave on Mac Pro (mid 2010) and Mac Pro (mid 2012)'Apple Inc.
  71. ^"Nvidia to acquire Mellanox Technologies for about $7 billion in cash". www.cnbc.com. March 11, 2019. Retrieved March 11, 2019.
  72. ^Byford, Sam (May 27, 2019). "Nvidia announces RTX Studio laptops aimed at creators". The Verge. Retrieved May 27, 2019.
  73. ^"Minecraft with RTX: The World's Best Selling Videogame Is Adding Ray Tracing". www.nvidia.com. Retrieved April 25, 2020.
  74. ^"NVIDIA's top scientist develops open-source ventilator that can be built with $400 in readily-available parts". TechCrunch. Retrieved May 1, 2020.
  75. ^NVIDIA’s New Ampere Data Center GPU in Full Production | NVIDIA Newsroom
  76. ^NVIDIA A100 | NVIDIA
  77. ^Massoudi, Arash; Bradshaw, Tim; Fontanella-Khan, James (July 31, 2020). "Nvidia in talks to buy Arm from SoftBank for more than $32bn". Financial Times. Retrieved July 3, 2020.
  78. ^"NVIDIA Delivers Greatest-Ever Generational Leap with GeForce RTX 30 Series GPUs" (Press release). NVIDIA. September 1, 2020. Retrieved August 5, 2021.
  79. ^"GeForce RTX 30 Series Graphics Cards: The Ultimate Play". NVIDIA. September 1, 2020. Retrieved August 5, 2021.
  80. ^Arash Massoudi; Robert Smith; James Fontanella-Khan (September 12, 2020). "SoftBank set to sell UK's Arm Holdings to Nvidia for $40bn". Financial Times. Retrieved September 12, 2020.
  81. ^"NVIDIA to Acquire Arm for $40 Billion, Creating World's Premier Computing Company for the Age of AI". September 13, 2020. Retrieved September 13, 2020.
  82. ^Sam Shead (October 5, 2020). "Nvidia pledges to build Britain's largest supercomputer following $40 billion bid for Arm". CNBC. Retrieved October 5, 2020.
  83. ^Smith, Ryan. "Quadro No More? NVIDIA Announces Ampere-based RTX A6000 & A40 Video Cards For Pro Visualization". www.anandtech.com. Retrieved March 10, 2021.
  84. ^Browne, Ryan (August 20, 2021). "Nvidia's $40 billion Arm takeover warrants an in-depth competition probe, UK regulator says". CNBC. Retrieved August 20, 2021.
  85. ^ ab"NVIDIA Corporation – Financial Info – Annual Reports and Proxies". investor.nvidia.com. Retrieved November 18, 2018.
  86. ^Armental, Maria (August 19, 2020). "Nvidia Posts Record Sales as Pandemic Sustains Demand for Gaming, Data-Center Chips". The Wall Street Journal. Retrieved August 20, 2020.
  87. ^ ab"GPU Technology Conference". GPU Technology Conference. Retrieved September 7, 2021.
  88. ^"Company History | NVIDIA". www.nvidia.com. Retrieved September 7, 2021.
  89. ^"Deep Learning and GPU-Programming Workshops at GTC 2021". NVIDIA. Retrieved September 7, 2021.
  90. ^"Deep Learning and GPU-Programming Workshops at GTC 2018". NVIDIA. March 2, 2020. Retrieved March 2, 2020.
  91. ^"Nvidia automotive solutions". Nvidia. Retrieved March 29, 2016.
  92. ^"Nvidia unveils driverless car OS and partnership with TomTom". September 29, 2016. Retrieved October 20, 2016.
  93. ^"NVIDIA BlueField Data Processing Units". NVIDIA. Retrieved May 29, 2021.
  94. ^Deierling, Kevin (May 21, 2020). "What Is a DPU? | NVIDIA Blog". The Official NVIDIA Blog. Retrieved May 29, 2021.
  95. ^"NVIDIA Announces CPU for Giant AI and High Performance Computing Workloads" (Press release). NVIDIA. April 12, 2021. Retrieved August 5, 2021.
  96. ^"NVIDIA Grace CPU". NVIDIA. Retrieved August 5, 2021.
  97. ^"Nvidia Offers to Release Public Documentation on Certain Aspects of Their GPUs". September 23, 2013. Retrieved September 24, 2013.
  98. ^"nv". Retrieved August 6, 2015.
  99. ^"Linus Torvalds: 'Damn You, Nvidia' for not Supporting Linux". The Verge. June 17, 2012. Retrieved July 9, 2013.
  100. ^"X.org, distributors, and proprietary modules". Linux Weekly News. Eklektix. August 14, 2006. Retrieved November 3, 2008.
  101. ^An overview of graphic card manufacturers and how well they work with Ubuntu Ubuntu Gamer, January 10, 2011 (Article by Luke Benstead)
  102. ^"Unix Drivers". Retrieved August 6, 2015.
  103. ^Kevin Parrish (October 3, 2013). "Nvidia Removed Linux Driver Feature Due to Windows". Tom's Hardware. Retrieved August 6, 2015.
  104. ^NVIDIA Begins Requiring Signed GPU Firmware Images, slashdot, 2014-09-27.
  105. ^Linux-Firmware Adds Signed NVIDIA Firmware Binaries For Turing's Type-C Controller, phoronix, 2019-02-13.
  106. ^The Open-Source NVIDIA "Nouveau" Driver Gets A Batch Of Fixes For Linux 5.3, phoronix, 2019-07-19.
  107. ^Kirk, David; Hwu, Wen-Mei (2017). Programming Massively Parallel Processors (Third ed.). Elsevier. p. 345. ISBN .
  108. ^"Nvidia's Self-Driving Vehicle Approach — from Tesla to DHL to Mercedes". CleanTechnica. August 13, 2020. Retrieved October 28, 2020.
  109. ^"Google Cloud adds NVIDIA Tesla K80 GPU support to boost deep learning performance – TechRepublic".
  110. ^"Intel, Nvidia Trade Shots Over AI, Deep Learning". August 25, 2016.
  111. ^"Nvidia CEO bets big on deep learning and VR". April 5, 2016.
  112. ^"From not working to neural networking". The Economist. June 23, 2016.
  113. ^Coldewey, Devin. "NVIDIA announces a supercomputer aimed at deep learning and AI".
  114. ^Nichols, Shaun (February 21, 2017). "Google rents out Nvidia Tesla GPUs in its cloud. If you ask nicely, that'll be 70 cents an hour, bud". The Register.
  115. ^"IBM, NVIDIA partner for 'fastest deep learning enterprise solution' in the world – TechRepublic".
  116. ^"IBM and Nvidia team up to create deep learning hardware". November 14, 2016.
  117. ^"IBM and Nvidia make deep learning easy for AI service creators with a new bundle". November 15, 2016.
  118. ^"Facebook 'Big Basin' AI Compute Platform Adopts NVIDIA Tesla P100 For Next Gen Data Centers". Archived from the original on November 26, 2020. Retrieved April 19, 2017.
  119. ^"Nvidia to Power Fujitsu's New Deep Learning System at RIKEN – insideHPC". March 5, 2017.
  120. ^Tilley, Aaron (February 9, 2017). "Nvidia Beats Earnings Estimates As Its Artificial Intelligence Business Keeps On Booming". Forbes. Retrieved
Sours: https://en.wikipedia.org/wiki/Nvidia

List of Nvidia graphics processing units

Wikipedia list article

This list contains general information about graphics processing units (GPUs) and video cards from Nvidia, based on official specifications. In addition some Nvidia motherboards come with integrated onboard GPUs. Limited/Special/Collectors' Editions or AIB versions are not included.

Field explanations[edit]

The fields in the table listed below describe the following:

  • Model – The marketing name for the processor, assigned by Nvidia.
  • Launch – Date of release for the processor.
  • Code name – The internal engineering codename for the processor (typically designated by an NVXY name and later GXY where X is the series number and Y is the schedule of the project for that generation).
  • Fab – Fabrication process. Average feature size of components of the processor.
  • Bus interface – Bus by which the graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCI-Express).
  • Memory – The amount of graphics memory available to the processor.
  • SM Count – Number of streaming multiprocessors.[1]
  • Core clock – The factory core clock frequency; while some manufacturers adjust clocks lower and higher, this number will always be the reference clocks used by Nvidia.
  • Memory clock – The factory effective memory clock frequency (while some manufacturers adjust clocks lower and higher, this number will always be the reference clocks used by Nvidia). All DDR/GDDR memories operate at half this frequency, except for GDDR5, which operates at one quarter of this frequency.
  • Core config – The layout of the graphics pipeline, in terms of functional units. Over time the number, type, and variety of functional units in the GPU core has changed significantly; before each section in the list there is an explanation as to what functional units are present in each generation of processors. In later models, shaders are integrated into a unified shader architecture, where any one shader can perform any of the functions listed.
  • Fillrate – Maximum theoretical fill rate in textured pixels per second. This number is generally used as a maximum throughput number for the GPU and generally, a higher fill rate corresponds to a more powerful (and faster) GPU.
  • Memory subsection
    • Bandwidth – Maximum theoretical bandwidth for the processor at factory clock with factory bus width. GHz = 109 Hz.
    • Bus type – Type of memory bus or buses used.
    • Bus width – Maximum bit width of the memory bus or buses used. This will always be a factory bus width.
  • API support section
    • Direct3D – Maximum version of Direct3D fully supported.
    • OpenGL – Maximum version of OpenGL fully supported.
    • OpenCL – Maximum version of OpenCL fully supported.
    • Vulkan – Maximum version of Vulkan fully supported.
  • Features – Added features that are not standard as a part of the two graphics libraries.

Desktop GPUs[edit]

Pre-GeForce[edit]

See Fahrenheit (microarchitecture)

Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm²) BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1FillrateMemory API support
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3DOpenGL
STG-2000May 22, 1995 NV1 SGS500 nm1[3]90 PCI 12 75 1:1:1 12 12 12 0 2
4
0.6 EDO
VRAM
64 n/a n/a
Riva 128August 25, 1997 NV3 SGS 350 nm[4]4 90 AGP 1x,[5] PCI 100 100 100 100 100 4 1.6 SDR 128 5.0 1.0
Riva 128ZXFebruary 23, 1998 SGS/TSMC 350 nm AGP 2x, PCI 8 1.6
Riva TNTJune 15, 1998 NV4 TSMC 350 nm 7[6]90 90 110 2:2:2 180 180 180 8
16
1.76 6.0 1.2
Vanta March 22, 1999 NV6 TSMC 250 nmAGP 4x, PCI 100 125 200 200 200 16 1 64
Vanta LT March 2000 AGP 2x 80 100 160 160 160 8
16
0.8
Riva TNT2 M64 October 1999 AGP 4x, PCI 125 150 250 250 250 8
16
32
1.2
Riva TNT2March 15, 1999 NV5 15[7]90 16
32
2.4 128
Riva TNT2 Pro October 12, 1999 TSMC 220 nm 143 166 286 286 286 16
32
2.656
Riva TNT2 Ultra March 15, 1999 TSMC 250 nm 150 183 300 300 300 16
32
2.928
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm²) BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3DOpenGL
FillrateMemory API support

GeForce 256 series[edit]

Further information: GeForce 256 and Celsius (microarchitecture)

  • All models are made via 220 nm fabrication process
  • All models support Direct3D 7.0 and OpenGL 1.2
  • All models support hardware Transform and Lighting (T&L) and Cube Environment Mapping

GeForce2 series[edit]

Further information: GeForce 2 series and Celsius (microarchitecture)

  • All models support Direct3D 7 and OpenGL 1.2
  • All models support TwinView Dual-Display Architecture, Second Generation Transform and Lighting (T&L), Nvidia Shading Rasterizer (NSR), High-Definition Video Processor (HDVP)
  • GeForce2 MX models support Digital Vibrance Control (DVC)
Model Launch

Code name

Fab (nm)[2]

Transistors (million)

Die size (mm²)

Businterface

Core clock (MHz)

Memory clock (MHz)

Core config1

FillrateMemory

MOperations/s

MPixels/s

MTexels/s

MVertices/s

Size (MB)

Bandwidth (GB/s)

Bus type

Bus width (bit)

GeForce2 MX IGP + nForce 220/420 June 4, 2001 NV1A (IGP) / NV11 (MX) TSMC180 nm20[10]64 FSB 175 133 2:4:2 350 350 700 0 Up to 32 system RAM 2.128
4.256
DDR 64
128
GeForce2 MX200 March 3, 2001 AGP 4x, PCI 166 32
64
1.328 SDR 64
GeForce2 MX June 28, 2000 2.656 128
GeForce2 MX400 March 3, 2001 200 166,200 (SDR)
166 (DDR)
400 400 800 2.656, 3.200 SDR
DDR
128 (SDR)
64 (DDR)
GeForce2 GTS April 26, 2000 NV15 25[11]88 AGP 4x 166 4:8:4 800 800 1600 5.312 DDR 128
GeForce2 Pro December 5, 2000 200 6.4
GeForce2 Ti October 1, 2001 TSMC 150 nm 250 1000 1000 2000
GeForce2 Ultra August 14, 2000 NV16 TSMC 180 nm 230 64 7.36

GeForce3 series[edit]

Further information: GeForce 3 series and Kelvin (microarchitecture)

  • All models are made via 150 nm fabrication process
  • All models support Direct3D 8.0 and OpenGL 1.3
  • All models support 3D Textures, Lightspeed Memory Architecture (LMA), nFiniteFX Engine, Shadow Buffers
Model Launch

Code name

Fab (nm)[2]

Transistors (million)

Die size (mm²)

Businterface

Core clock (MHz)

Memory clock (MHz)

Core config1

FillrateMemory

MOperations/s

MPixels/s

MTexels/s

MVertices/s

Size (MB)

Bandwidth (GB/s)

Bus type

Bus width (bit)

GeForce3 Ti200 October 1, 2001 NV20 TSMC 150 nm 57 128 AGP 4x, PCI 175 200 4:1:8:4 700 700 1400 42.75 64
128
6.4 DDR 128
GeForce3 February 27, 2001 200 230 800 800 1600 50 64 7.36
GeForce3 Ti500 October 1, 2001 240 250 960 960 1920 60 64
128
8

GeForce4 series[edit]

Further information: GeForce 4 series and Kelvin (microarchitecture)

  • All models are manufactured with a 150 nm manufacturing process
  • All models support Accuview Antialiasing (AA), Lightspeed Memory Architecture II (LMA II), nView
Model Launch

Code name

Fab (nm)[2]

Transistors (million)

Die size (mm²)

Businterface

Core clock (MHz)

Memory clock (MHz)

Core config1

FillrateMemory Supported API version

MOperations/s

MPixels/s

MTexels/s

MVertices/s

Size (MB)

Bandwidth (GB/s)

Bus type

Bus width (bit)

Direct3D

OpenGL

GeForce4 MX IGP + nForce2 October 1, 2002 NV1F TSMC 150 nm ?

?

FSB 250 133
200[a]
2:0:4:2 500 500 1000 0 Up to 128 system RAM 2.128
6.4[b]
DDR 64
128
7.0 1.2
GeForce4 MX420 February 6, 2002 NV17 29[12]65 AGP 4x
PCI
166 64 2.656 SDR

DDR

128 (SDR)

64 (DDR)

GeForce4 MX440 SE 2002 64
128
5.312 DDR 128
GeForce MX4000 December 14, 2003 NV18B 29 65 AGP 8x
PCI
2.656 64
GeForce PCX4300 February 19, 2004 PCIe x16 128
GeForce4 MX440 February 6, 2002 NV17 29 65 AGP 4x
PCI
275 200 550 550 1100 64
128
6.4 128
GeForce4 MX440 8x September 25, 2002 NV18 29[13]65 AGP 8x
PCI
250 8
GeForce4 MX460 February 6, 2002 NV17 29 65 AGP 4x
PCI
300 275 600 600 1200
GeForce4 Ti4200 April 16, 2002 NV25 63[14]142 AGP 4x 250 222 (128 MB)
250 (64 MB)
4:2:8:4 1000 1000 2000 125 7.104 (128 MB)
8 (64 MB)
8.0a 1.3
GeForce4 Ti4200 8x September 25, 2002 NV28 36[15]101 AGP 8x 250 128 8
GeForce4 Ti4400 February 6, 2002 NV25 63 142 AGP 4x 275 275 1100 1100 2200 137.5 8.8
GeForce4 Ti4400 8x
(Ti4800SE2)
January 20, 2003 NV28 36 101 AGP 8x
GeForce4 Ti4600 February 6, 2002 NV25 63 142 AGP 4x 300 325 1200 1200 2400 150 10.4
GeForce4 Ti4600 8x
(Ti48003)
January 20, 2003 NV28 36 101 AGP 8x
  • 1Pixel shaders: vertex shaders: texture mapping units: render output units
  • 2 GeForce4 Ti4400 8x: Card manufacturers utilizing this chip, labeled the card as a Ti4800SE. The surface of the chip has "Ti-8x" printed on it.
  • 3 GeForce4 Ti4600 8x: Card manufacturers utilizing this chip, labeled the card as a Ti4600, and in some cases as a Ti4800. The surface of the chip has "Ti-8x" printed on it, as well as "4800" printed at the bottom.
Model Features
nFiniteFX II Engine Video Processing Engine (VPE)
GeForce4 MX420 No Yes
GeForce4 MX440 SE No Yes
GeForce4 MX4000 No Yes
GeForce4 PCX4300 No Yes
GeForce4 MX440 No Yes
GeForce4 MX440 8X No Yes
GeForce4 MX460 No Yes
GeForce4 Ti4200 Yes No
GeForce4 Ti4200 8x Yes No
GeForce4 Ti4400 Yes No
GeForce4 Ti4400 8x Yes No
GeForce4 Ti4600 Yes No
GeForce4 Ti4600 8x Yes No

GeForce FX (5xxx) series[edit]

Further information: GeForce FX series and Rankine (microarchitecture)

  • All models support Direct3D 9.0a and OpenGL 1.5 (2.1 (software) with latest drivers)
  • The GeForce FX series runs vertex shaders in an array
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm²) BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1FillrateMemory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
GeForce FX 5100 March 2003 NV34 TSMC 150 nm 45[16]124 AGP 8x 200 166 4:2:4:4 800 800 800 50 64
128
2.7 DDR 64
GeForce FX 5200 LE 250 1000 1000 1000 62.5 64
128
256
2.7
5.3
64
128
GeForce FX 5200 AGP 8x
PCI
200 3.2
6.4
64
128
GeForce FX 5200 Ultra March 6, 2003 AGP 8x 325 325 1300 1300 1300 81.25 10.4 128
GeForce PCX 5300 March 17, 2004 PCIe x16 250 166 1000 1000 1000 62.5 128
256
2.7 64
GeForce FX 5500 March 2004 NV34B TSMC 140 nm 45[17]91 AGP 8x
AGP 4x
PCI
270 200 1080 1080 1080 67.5 64
128
256
3.2
6.4
64
128
GeForce FX 5600 XT October 2003 NV31 TSMC 130 nm80[18]121 AGP 8x 235 940 940 940 58.75 64
128
3.2
6.4
64
128
GeForce FX 5600 March 2003 AGP 8x
PCI
325 275 1300 1300 1300 81.25 64
128
256[19]
8.8 128
GeForce FX 5600 Ultra March 6, 2003 AGP 8x 350 350 1400 1400 1400 87.5 64
128
11.2
GeForce FX 5600 Ultra Rev.2 400 400 1600 1600 1600 100 12.8
GeForce FX 5700 VE September 2004 NV36 IBM 130 nm 82[20]133 235 200 4:3:4:4 940 940 940 106.5 128
256
3.2

6.4

64
128
GeForce FX 5700 LE March 2004 AGP 8x
PCI
250 1000 1000 1000 187.5
GeForce FX 5700 2003 AGP 8x 425 250 1700 1700 1700 318.75 8 128
GeForce PCX 5750 March 17, 2004 PCIe x16 128
GeForce FX 5700 Ultra October 23, 2003 AGP 8x 475 450 1900 1900 1900 356.25 128
256
14.4 GDDR2
GeForce FX 5700 Ultra GDDR3 March 15, 2004 475 15.2 GDDR3
GeForce FX 5800 January 27, 2003 NV30 TSMC 130 nm 125[21]199 400 400 4:2:8:4 1600 1600 3200 200 128 12.8 GDDR2
GeForce FX 5800 Ultra 500 500 2000 2000 4000 16
GeForce FX 5900 ZT December 15, 2003 NV35 135[22]207 325 350 4:3:8:4 1300 1300 2600 343.75 22.4 DDR 256
GeForce FX 5900 XT December 15, 2003[23]390 1600 1600 3200 300
GeForce FX 5900 May 2003 400 425 27.2
GeForce FX 5900 Ultra May 12, 2003 450 1800 1800 3600 337.5 128
256
GeForce PCX 5900 March 17, 2004 PCIe x16
GeForce FX 5950 Ultra October 23, 2003 NV38 135[24]207 AGP 8x 475 475 1900 1900 3800 356.25 256 30.4
GeForce PCX 5950 February 17, 2004 PCIe x16 GDDR3
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm²) BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1FillrateMemory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)

GeForce 6 (6xxx) series[edit]

Further information: GeForce 6 series and Curie (microarchitecture)

  • All models support Direct3D 9.0c and OpenGL 2.1
  • All models support Transparency AA (starting with version 91.47 of the ForceWare drivers) and PureVideo
Model Launch Code nameFab (nm)[2]Transistors (million)

Die size (mm²)

BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1FillrateMemory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
GeForce 6100 + nForce 410 October 20, 2005 MCP51 TSMC90 nmHyperTransport425 100–200 (DDR)
200–533 (DDR2)
2:1:2:1 850 425 850 106.25 Up to 256 system RAM 1.6–6.4 (DDR)
3.2–17.056 (DDR2)
DDR
DDR2
64
128
GeForce 6150 SE + nForce 430 June 2006 MCP61 200
400[citation needed]
3.2
16.0[citation needed]
DDR2
GeForce 6150 LE + nForce 430 MCP61 100–200 (DDR)
200–533 (DDR2)
1.6–6.4 (DDR)
3.2–17.056 (DDR2)
DDR
DDR2
GeForce 6150 + nForce 430 October 20, 2005 MCP51 475 950 475 950 118.75 1.6–6.4 (DDR)
3.2–17.056 (DDR2)
GeForce 6200 LE 2005 NV44 TSMC 110 nm 75

110[25]

AGP 8x
PCIe x16
350 266 700 700 700 87.5 128
256
4.256 DDR 64
GeForce 6200A April 4, 2005 NV44A 75

110[26]

AGP 8x 350[27]250
533 (DDR2)[27]
4:3:4:2 1400[27]700[27]1400[27]175
225 (DDR2)[28]
128
256 (DDR2)[27]
512 (DDR2)[27]
4
13.3 (DDR2)[29]
DDR
DDR2[28]
64[28]
GeForce 6200 October 12, 2004 (PCIe)
January 17, 2005 (AGP)
NV43 146

154[30]

AGP 8x
PCI
PCIe x16
300 275 4:3:4:4 1200 1200 1200 225 128
256
8.8 DDR2 128
GeForce 6200 TurboCache December 15, 2004 NV44 75

110[25]

PCIe x16 350 350 4:3:4:2 1400 700 1400 262.5 128–256 System RAM incl.16/32–64/128 onboard 5.6 DDR 64
GeForce 6500 October 1, 2005 400 333 1600 800 1600 300 128
256
5.328
GeForce 6600 LE 2005 NV43 146

154[30]

AGP 8x
PCIe x16
300 200 4:3:4:4 1200 1200 1200 225 6.4 128
GeForce 6600 August 12, 2004 275

400

8:3:8:4 2400 2400 8.8

12.8

DDR

DDR2

GeForce 6600 GT August 12, 2004 (PCIe)
November 14, 2004 (AGP)
500 475 (AGP)
500 (PCIe)
4000 2000 4000 375 15.2[31] (AGP)
16 (PCIe)
GDDR3
GeForce 6800 LE July 22, 2004 (AGP)
January 16, 2005 (PCIe)
NV40 (AGP)
NV41, NV42 (PCIe)
IBM 130 nm 222

287

(NV40)[32]

222

225

(NV41)[33]

198

222

(NV42)[34]

320 (AGP)
325 (PCIe)
350 8:4:8:8 2560 (AGP)
2600 (PCIe)
2560 (AGP)
2600 (PCIe)
2560 (AGP)
2600 (PCIe)
320 (AGP)
325 (PCIe)
128 22.4 DDR 256
GeForce 6800 XT September 30, 2005 300 (64 Bit)

325

266 (64 Bit)

350

500 (GDDR3)

2400

2600

2400

2600

2400

2600

300

325

256 4.256

11.2

22.4

32 (GDDR3)

DDR

DDR2

GDDR3

64[35]

128[36]

256

GeForce 6800 April 14, 2004 (AGP)
November 8, 2004 (PCIe)
325 350 12:5:12:12 3900 3900 3900 406.25 128
256
22.4 DDR 256
GeForce 6800 GTO April 14, 2004 NV45 222

287

(NV45)[37]

PCIe x16 450 4200 4200 4200 437.5 256 28.8 GDDR3
GeForce 6800 GS November 7, 2005 (PCIe)
December 8, 2005 (AGP)
NV42 (PCIe)
NV40 (AGP)
TSMC 110 nm 222

287

(NV40)[32]

198

222

(NV42)[34]

AGP 8x
PCIe x16
425 (PCIe)
350 (AGP)
500 5100 5100 5100 531.25 128
256
32
GeForce 6800 GT May 4, 2004 (AGP)
June 28, 2004 (PCIe)
NV40 (AGP)
NV45 (PCIe)
IBM 130 nm 222

287

(NV40)[32]

222

287

(NV45)[37]

AGP 8x
PCIe x16
350 16:6:16:16 5600 5600 5600 525
GeForce 6800 Ultra May 4, 2004 (AGP)
June 28, 2004 (PCIe)
March 14, 2005 (512 MB)
400 525 (512 MB)
550 (256 MB)
6400 6400 6400 600 256
512
33.6 (512 MB)
35.2 (256 MB)
GeForce 6800 Ultra Extreme Edition May 4, 2004 NV40 222

287

(NV40)[32]

AGP 8x 450 600 7200 7200 7200 675 256 35.2
Model Launch Code nameFab (nm)[2]Transistors (million)

Die size (mm²)

BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1FillrateMemory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)

Features[edit]

Model Features
OpenEXR HDR Scalable Link Interface (SLI) TurboCachePureVideo WMV9 Decoding
GeForce 6100 No No No Limited
GeForce 6150 SE No No Driver-Side Only Limited
GeForce 6150 No No No Yes
GeForce 6150 LE No No Driver-Side Only Yes
GeForce 6200 No No Yes (PCIe only) Yes
GeForce 6500 No Yes Yes Yes
GeForce 6600 LE Yes Yes (No SLI Connector) No Yes
GeForce 6600 Yes Yes (SLI Connector or PCIe Interface) No Yes
GeForce 6600 DDR2 Yes Yes (SLI Connector or PCIe Interface) No Yes
GeForce 6600 GT Yes Yes No Yes
GeForce 6800 LE Yes No No No
GeForce 6800 XT Yes Yes (PCIe only) No Yes (NV42 only)
GeForce 6800 Yes Yes (PCIe only) No Yes (NV41, NV42 only)
GeForce 6800 GTO Yes Yes No No
GeForce 6800 GS Yes Yes (PCIe only) No Yes (NV42 only)
GeForce 6800 GT Yes Yes (PCIe only) No No
GeForce 6800 Ultra Yes Yes (PCIe only) No No

GeForce 7 (7xxx) series[edit]

Further information: GeForce 7 series and Curie (microarchitecture)

  • All models support Direct3D 9.0c and OpenGL 2.1
  • All models support Transparency AA (starting with version 91.47 of the ForceWare drivers)
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm²) BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1FillrateMemory
MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
GeForce 7025 + nForce 630a July 2007 MCP68S TSMC 110 nm HyperTransport425 200 (DDR)

400 (DDR2)

933 (DDR3)

2:1:2:2 850 850 850 106.25 Up to 256 system RAM 6.4

12.8

34

DDR

DDR2

DDR3

64

128

GeForce 7050PV + nForce 630a MCP67QV
GeForce 7050 + nForce 610i/630i MCP73 TSMC 90 nm HyperTransport/FSB500 333 1000 1000 1000 125 5.336 DDR2 64
GeForce 7100 + nForce 630i MCP76 FSB 600 400 1200 1200 1200 150 6.4
GeForce 7150 + nForce 630i 630 1260 1260 1260 157.5
GeForce 7100 GS August 8, 2006 NV44 TSMC 110 nm 75[25]110 PCIe x16 350 300 4:3:4:2 1400 700 1400 262.5 128
256
2.4

4.8

DDR

DDR2

32

64

GeForce 7200 GS January 18, 2006 G72 TSMC 90 nm 112[38]81 450 400 2:2:4:2 1800 900 1800 337.5 3.2

6.4

DDR2
GeForce 7300 SE March 22, 2006 350 333 4:3:4:2 128 2.656

5.328

GeForce 7300 LE
GeForce 7300 GS January 18, 2006 550 400 2200 1100 2200 412.5 128
256
6.4 64
GeForce 7300 GT May 15, 2006 G73 177[39]125 AGP 8x
PCIe x16
350 325 (DDR2)

700 (GDDR3)

8:5:8:4 2800 1400 2800 437.5 10.4

22.4

DDR2

GDDR3

128
GeForce 7500 LE 2006 G72 112[38]81 PCIe x16 263
324
275 4:3:4:2 900
1100
900
1100
2200 412.5 64
128
256
2.6
6.8
DDR2 32
64
GeForce 7600 GS March 22, 2006 (PCIe)
July 1, 2006 (AGP)
G73 177[39]125 AGP 8x
PCIe x16
400 400 (DDR2)

700 (GDDR3)

12:5:12:8 4800 3200 4800 500 256 12.8

22.4

DDR2

GDDR3

128
GeForce 7600 GT March 9, 2006 (PCIe)
July 15, 2006 (AGP)
560 6720 4480 6720 700
GeForce 7600 GT 80 nm January 8, 2007 G73-B1 TSMC 80 nm
GeForce 7650 GS March 22, 2006 G73 PCIe x16 450 400 5400 3600 5400 562.5 12.7 DDR2
GeForce 7800 GS February 2, 2006 G70 TSMC 110 nm 302[40]333 AGP 8x 375 600 16:8:16:8 6000 3000 6000 750 38.4 GDDR3 256
GeForce 7800 GT August 11, 2005 PCIe x16 400 500 20:7:20:16 8000 6400 8000 700 32
GeForce 7800 GTX June 22, 2005 (256 MB)
November 14, 2005 (512 MB)
430 (256 MB)
550 (512 MB)
600 (256 MB)
850 (512 MB)
24:8:24:16 10320 (256 MB)
13200 (512 MB)
6880 (256 MB)
8800 (512 MB)
10320 (256 MB)
13200 (512 MB)
860 (256 MB)
1100 (512 MB)
256
512
38.4 (256 MB)
54.4 (512 MB)
GeForce 7900 GS May 2006 (PCIe)
April 2, 2007 (AGP)
G71 TSMC 90 nm 278[41]196 AGP 8x
PCIe x16
450 660 20:7:20:16 9000 7200 9000 787.5 256 42.24
GeForce 7900 GT March 9, 2006 PCIe x16 24:8:24:16 10800 10800 900
GeForce 7900 GTO October 1, 2006 650 15600 10400 15600 1300 512
GeForce 7900 GTX March 9, 2006 800 51.2
GeForce 7900 GX2 2x G71 500 600 2x 24:8:24:16 24000 16000 24000 2000 2x 512 2x 38.4
GeForce 7950 GT September 6, 2006 (PCIe)
April 2, 2007 (AGP)
G71 AGP 8x
PCIe x16
550 700 24:8:24:16 13200 8800 13200 1100 512 44.8
GeForce 7950 GX2 June 5, 2006 2x G71 PCIe x16 500 600 2x 24:8:24:16 24000 16000 24000 2000 2x 512 2x 38.4
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm²) BusinterfaceCore clock (MHz) Memory clock (MHz) Core config1MOperations/s MPixels/s MTexels/s MVertices/s Size (MB) Bandwidth (GB/s) Bus type Bus width (bit)
FillrateMemory

Features[edit]

Model Features
Gamma-correct antialiasing 64-bit OpenEXR HDR Scalable Link Interface (SLI) TurboCache Dual Link DVI
GeForce 7100 GS No No Yes (PCIe only, No SLI bridge) Yes No
GeForce 7200 GS Yes Yes No Yes No
GeForce 7300 SE Yes Yes No Yes No
GeForce 7300 LE Yes Yes No Yes No
GeForce 7300 GS Yes Yes Yes (PCIe only) Yes No
GeForce 7300 GT Yes Yes Yes (PCIe only, No SLI bridge) No One port
GeForce 7600 GS Yes Yes Yes (PCIe only) No One port
GeForce 7600 GT Yes Yes Yes (PCIe only) No One port
GeForce 7600 GT (80 nm) Yes Yes Yes No One port
GeForce 7650 GS (80 nm) Yes Yes Yes (Depending on OEM Design) No One port
GeForce 7800 GS Yes Yes No No One port
GeForce 7800 GT Yes Yes Yes No One port
GeForce 7800 GTX Yes Yes Yes No One port
GeForce 7800 GTX 512 Yes Yes Yes No One port
GeForce 7900 GS Yes Yes Yes (PCIe only) No Two ports
GeForce 7900 GT Yes Yes Yes No Two ports
GeForce 7900 GTO Yes Yes Yes No Two ports
GeForce 7900 GTX Yes Yes Yes No Two ports
GeForce 7900 GX2 (GTX Duo) Yes Yes Yes No Two ports
GeForce 7950 GT Yes Yes Yes (PCIe only) No Two ports
GeForce 7950 GX2 Yes Yes Yes No Two ports

GeForce 8 (8xxx) series[edit]

Further information: GeForce 8 series and Tesla (microarchitecture)

All models support coverage sample anti-aliasing, angle-independent anisotropic filtering, and 128-bit OpenEXR HDR.

Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm2) BusinterfaceCore config1Clock rate FillrateMemory Supported API version Processing power (GFLOPS)3TDP (Watts) Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3DOpenGLSingle precision
GeForce 8100 mGPU[44]2008 MCP78 TSMC 80 nm Un­known Un­known PCIe 2.0 x16 8:8:4 500 1200 400
(system memory)
2 4 Up to 512 from system memory 6.4
12.8
DDR2 64
128
10.0 3.3 28.8 Un­known The block of decoding of HD-video PureVideo HD is disconnected
GeForce 8200 mGPU[44]Un­known Un­known gt Un­known PureVideo 3 with VP3
GeForce 8300 mGPU[44]Un­known Un­known 1500 Up to 512 from system memory 36 Un­known
GeForce 8300 GS[45]July 2007 G86 210 127 PCIe 1.0 x16 450 900 400 1.8 3.6 128
512
6.4 64 14.4 40 OEM only
GeForce 8400 GS June 15, 2007 PCIe 1.0 x16
PCI
16:8:4 128
256
512
28.8
GeForce 8400 GS rev.2 December 10, 2007 G98 TSMC 65 nm 86 PCIe 2.0 x16
PCIe x1
PCI
8:8:4 567 1400 2.268 4.536 22.4 25
GeForce 8400 GS rev.3 July 12, 2010 GT218 TSMC 40 nm 260 57 PCIe 2.0 x16 8:4:4 520
589
1230 400 (DDR2)

600 (DDR3)

2.08
2.356
2.08
2.356
512
1024
4.8

6.4
9.6

DDR2

DDR3

32
64
10.1 19.7
GeForce 8500 GT April 17, 2007 G86 TSMC 80 nm 210 127 PCIe 1.0 x16
PCI
16:8:4 450 900 400 1.8 3.6 256
512
1024
12.8 DDR2 128 10.0 28.8 45
GeForce 8600 GS April 2007 G84 289 169 PCIe 1.0 x16 16:8:8 540 1180 4.32 4.32 256
512
75.5 47 OEM only
GeForce 8600 GT April 17, 2007 PCIe 1.0 x16
PCI
32:16:8 1188 400
700
8.64 256
512
1024
12.8
22.4
DDR2
GDDR3
76
GeForce 8600 GTS PCIe 1.0 x16 675 1450 1000 5.4 10.8 256
512
32 GDDR3 92.8 71
GeForce 8800 GS January 2008 G92 TSMC 65 nm 754 324 PCIe 2.0 x16 96:48:12 550 1375 800 6.6 26.4 384
768
38.4 192 264 105
GeForce 8800 GTS (G80) February 12, 2007 (320)
November 8, 2006 (640)
G80 TSMC 90 nm 681 484 PCIe 1.0 x16 96:24:20 513 1188 10.3 12.3 320
640
64 320 228 146
GeForce 8800 GTS 112 (G80) November 19, 2007 112:282:20 500 1200 10 14 640 268.8 150 only XFX, EVGA and BFG models, very short-lived[46]
GeForce 8800 GT October 29, 2007 (512)
December 11, 2007 (256, 1024)
G92 TSMC 65 nm 754 324 PCIe 2.0 x16 112:56:16 600 1500 700 (256)
900 (512, 1024)
9.6 33.6 256
512
1024
57.6 256 336 125
GeForce 8800 GTS (G92) December 11, 2007 128:64:16 650 1625 970 10.4 41.6 512 62.1 416 135
GeForce 8800 GTX November 8, 2006 G80 TSMC 90 nm 681 484 PCIe 1.0 x16 128:322:24 575 1350 900 13.8 18.4 768 86.4 384 345.6 145
GeForce 8800 Ultra May 2, 2007 612 1500 1080 14.7 19.6 103.7 384 175
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm2) BusinterfaceCore config1Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3DOpenGLSingle precisionTDP (Watts) Comments
Clock rate FillrateMemory Supported API version Processing power (GFLOPS)3

Features[edit]

  • Compute Capability 1.1: has support for Atomic functions, which are used to write thread-safe programs.
  • Compute Capability 1.2: for details see CUDA
Model Features
Scalable
Link
Interface
(SLI)
3-Way
SLI
PureVideo HD
with VP1
PureVideo 2 with VP2,

BSP Engine, and AES128 Engine

PureVideo 3 with VP3,

BSP Engine, and AES128 Engine

PureVideo 4 with VP4 Compute
ability
GeForce 8300 GS (G86) No No No Yes No No 1.1
GeForce 8400 GS Rev. 2 (G98) No No No No Yes No 1.1
GeForce 8400 GS Rev. 3 (GT218) No No No No No Yes 1.2
GeForce 8500 GT Yes No No Yes No No 1.1
GeForce 8600 GT Yes No No Yes No No 1.1
GeForce 8600 GTS Yes No No Yes No No 1.1
GeForce 8800 GS (G92) Yes No No Yes No No 1.1
GeForce 8800 GTS (G80) Yes No Yes No No No 1.0
GeForce 8800 GTS Rev. 2 (G80) Yes No Yes No No No 1.0
GeForce 8800 GT (G92) Yes No No Yes No No 1.1
GeForce 8800 GTS (G92) Yes No No Yes No No 1.1
GeForce 8800 GTX Yes Yes Yes No No No 1.0
GeForce 8800 Ultra Yes Yes Yes No No No 1.0

GeForce 9 (9xxx) series[edit]

Further information: GeForce 9 series and Tesla (microarchitecture)

All models support Coverage Sample Anti-Aliasing, Angle-Independent Anisotropic Filtering, 128-bit OpenEXR HDR

Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm2) BusinterfaceCore config1Clock rate FillrateMemory Supported API version Processing power (GFLOPS)2TDP (Watts) Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3DOpenGLSingle precision
GeForce 9300 mGPU October 2008 MCP7A-S 65 nm 282 162 PCIe 2.0 x16 16:8:4 450 1200 400
666
1.8 3.6 Up to 512 from system memory 6.4/12.8
10.664/21.328
DDR2
DDR3
64
128
10.0 3.3 57.6 Un­known based on 8400 GS
GeForce 9400 mGPU MCP7A-U 580 1400 2.32 4.64 67.2 12
GeForce 9300 GE[47]June 2008 G98 TSMC 65 nm 210 86 8:8:4 540 1300 500 2.16 4.32 256 8.0 DDR2 64 20.8 25
GeForce 9300 GS[47]567 1400 2.268 4.536 22.4
GeForce 9400 GT August 27, 2008 G96-200-c1
G96a
G96b
TSMC 55 nm 314 144 PCIe 2.0 x16
PCI
16:8:4 550 400
800
2.2 4.4 256
512
1024
12.8
25.6
DDR2
GDDR3
128 44.8 50
GeForce 9500 GT July 29, 2008 G96-300-C1 UMC 65 nm 32:16:8 500
800
4.4 8.8 16.0
25.6
DDR2
GDDR3
89.6
GeForce 9600 GS G94a TSMC 65 nm 505 240 48:24:12 500 1250 500 6 12 768 24.0 DDR2 192 120 Un­known OEM
GeForce 9600 GSO May 2008 G92-150-A2 754 324 PCIe 2.0 x16 96:48:12 550 1375 800 6.6 26.4 384
768
1536
38.4 GDDR3 264 84
GeForce 9600 GSO 512 October 2008 G94a
G94b
TSMC 65 nm
TSMC 55 nm
505 240
196?[citation needed]
48:24:16 650 1625 900 10.4 15.6 512 57.6 256 156 90
GeForce 9600 GT Green Edition 2009 G94b TSMC 55 nm 196?[citation needed]64:32:16 600
625
1500
1625
700/900
900[citation needed]
9.6
10.0
19.2
20.0
512
1024
44.8/57.6
57.6[citation needed]
192
208
59 Core Voltage = 1.00v
GeForce 9600 GT February 21, 2008 G94-300-A1 TSMC 65 nm 240
196?[citation needed]
650 1625 900 10.4 20.8 57.6 208 95
GeForce 9800 GT Green Edition 2009 G92a2

G92b

TSMC/UMC 65 nm
TSMC/UMC 55 nm
754 324

260

112:56:16 550 1375 700
800
900
8.8 30.8 44.8
51.2
57.6
308 75 Core Voltage = 1.00v
GeForce 9800 GT July 2008 G92a
G92b
UMC 55 nm 600 1500 900 9.6 33.6 57.6 336 125
105
GeForce 9800 GTX April 1, 2008 G92-420-A2 TSMC 65 nm 324 128:64:16 675 1688 1100 10.8 43.2 512 70.4 432 140
GeForce 9800 GTX+ July 16, 2008 G92b TSMC 55 nm 260 738 1836 1100 11.808 47.232 512
1024
470 141
GeForce 9800 GX2 March 18, 2008 2x G92 TSMC/UMC 65 nm 2x 754 2x 324 2x 128:64:16 600 1500 1000 2x 9.6 2x 38.4 2x 512 2x 64.0 2x 256 2x 384 197
Model Launch Code nameFab (nm)[2]Transistors (million) Die size (mm2) BusinterfaceCore config1Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) Bus type Bus width (bit) Direct3DOpenGLSingle precisionTDP (Watts) Comments
Clock rate FillrateMemory Supported API version Processing power (GFLOPS)2

Features[edit]

  • Compute Capability: 1.1 has support for Atomic functions, which are used to write thread-safe programs.
Model Features
Scalable Link Interface (SLI) PureVideo 2 with VP2,

BSP Engine, and AES128 Engine

PureVideo 3 with VP3,

BSP Engine, and AES128 Engine

GeForce 9300 GE (G98) Yes No Yes
GeForce 9300 GS (G98)
GeForce 9400 GT Yes No
GeForce 9500 GT
GeForce 9600 GSO
GeForce 9600 GT
GeForce 9800 GT
GeForce 9800 GTX Yes
3-way
GeForce 9800 GTX+
GeForce 9800 GX2 Yes

GeForce 100 series[edit]

Further information: GeForce 100 series and Tesla (microarchitecture)

Model Launch Code nameFab (nm) Transistors (million) Die size (mm2) BusinterfaceCore config1Clock rate FillrateMemory configuration Supported API version Processing power (GFLOPS)2TDP (Watts) Comments
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) DRAM type Bus width (bit) Direct3DOpenGLSingle precision
GeForce G 100 March 10, 2009 G98 TSMC 65 nm 210 86 PCIe 2.0 x16 8:8:4 567 1400 500 2.15 4.3 512 8.0 DDR2 64 10.0 3.3 22.4 35 OEM products
GeForce GT 120 G96b TSMC 55 nm 314 121 32:16:8 500 800 4.4 8.8 16.0 128 89.6 50
GeForce GT 130 G94b 505 196 48:24:12 1250 500 6 12 1536 24.0 192 120 75
GeForce GT 140 64:32:16 650 1625 1800 10.4 20.8 512 1024 57.6 GDDR3 256 208 105
GeForce GTS 150 G92b 754 260 128:64:16 738 1836 1000 11.808 47.232 1024 64.0 470 141

GeForce 200 series[edit]

Further information: GeForce 200 series and Tesla (microarchitecture)

All models support Coverage Sample Anti-Aliasing, Angle-Independent Anisotropic Filtering, 240-bit OpenEXR HDR

Model Launch Code nameFab (nm) Transistors (million) Die size (mm2) BusinterfaceCore config1Clock rate FillrateMemory configuration Supported API version Processing power (GFLOPS)2TDP (Watts) Comments Release Price (USD)
Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Size (MB) Bandwidth (GB/s) DRAM type Bus width (bit) Direct3DOpenGLSingle precision
GeForce 205 November 26, 2009 GT218 TSMC40 nm260 57 PCIe 2.0 x16 8:4:4 589 1402 1000 2.356 2.356 512 8 DDR2 64 10.1 3.3 22.4 30.5 OEM only
GeForce 210 October 12, 2009 GT218-325-B1 PCIe 2.0 x16
PCIe x1
PCI
16:8:4 520
589
1230
1402
1000–1600 2.356 4.712 512
1024
4.0
8.0
12.8
DDR2
DDR3
32
64
36.4

44.9

30.5
GeForce GT 220 GT216-300-A2 TSMC 40 nm 486 100 PCIe 2.0 x16 48:16:8 615(OEM)
625
1335(OEM)
1360
1000
1580
5 10 512
1024
16.0
25.3
DDR2
DDR3
64
128
128.2(OEM)
130.6
58
GeForce GT 230 October 12, 2009[48]G94b TSMC/UMC 55 nm 505 196? 48:24:16 650 1625 1800 10.4 15.6 512
1024
57.6 GDDR3 256 10 156 75 OEM only
April 27, 2009[49]G92b 754 260 96:48:12 500 1242 1000 6 24 1536 24 DDR2 192 238.5
GeForce GT 240 November 17, 2009 GT215-450-A2 TSMC 40 nm 727 139 96:32:8 550 1340 1800
2000
3400(GDDR5)
4.4 17.6 512
1024
28.8(OEM)
32
54.4(GDDR5)
DDR3
GDDR3
GDDR5
128 10.1 257.3 69
GeForce GTS 240 July 1, 2009[50]G92a
G92b
TSMC 65 nm
TSMC/UMC 55 nm
754 324
260
112:56:16 675 1620 2200 10.8 37.8 1024 70.4 GDDR3 256 10.0 362.9 120 OEM only
GeForce GTS 250 2009 G92b TSMC/UMC 55 nm 260 128:64:16 702 1512 2000 11.2 44.9 512
1024
64.0 387 130
March 3, 2009 G92-428-B1 TSMC 65 nm
TSMC/UMC 55 nm
738 1836 2000
2200
11.808 47.232 512
1024
64.0
70.4
470 150 Some cards are rebranded GeForce 9800 GTX+ $150
($130 512MB)
GeForce GTX 260
Sours: https://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units

Wiki rtx 3000

GeForce 30 series

Series of GPUs by Nvidia

The GeForce 30 series is a family of graphics processing units developed by Nvidia, succeeding the GeForce 20 series. The series was announced on September 1, 2020, and started shipping on September 17, 2020.[1][2] The cards are based on the Ampere architecture and feature hardware-accelerated raytracing (RTX) with Nvidia's second-generation RT cores and third-generation Tensor Cores.[3] The lineup is designed to compete with AMD's Radeon RX 6000 series of cards.

Release and availability issues[edit]

See also: 2020–21 global chip shortage

Launch day for the RTX 3080 was September 17, 2020.[4] The lack of pre-order functionality and high demand exacerbated by the COVID-19 pandemic, and boost in popularity of cryptomining, resulted in a large number of online retailers struggling with the sheer number of purchases.[4][5]Newegg had completely sold out as expected on Black Friday. Long lines formed outside physical stores with stock, such as Micro Center in the United States,[6] and Dospara [ja] in Japan.[7] Twitter users reported that they used bots to buy large numbers of cards to resell for higher prices.[8]

Nvidia released a statement the following day, apologizing for the difficulties with their online store, which went down on launch day due to high traffic.[9] On October 2, Nvidia announced that it would delay the release of RTX 3070 cards by two weeks to guarantee availability.[10] On October 5, Nvidia CEO Jensen Huang announced delays due to supply shortages, which were expected to go on until 2021.[11] On October 9, the company announced that all Founder's Edition graphic cards in the United States would temporarily be sold via Best Buy, while the official web store would be upgraded to improve the shopping experience.[12][13][14] In early December, Nvidia blamed continued component shortages on Samsung wafer shortages, resulting in chip shortages, among other factors.[15]

Shortages of RTX 30 series cards continue into 2021.[16] In an effort to limit purchases by cryptominers, Nvidia announced in February that the RTX 3060 cards would be able to detect algorithms for mining of the Ethereum cryptocurrency and halve the hash rate.[17] Shortly after release, NVIDIA accidentally released a driver update which disabled the detection.[18] In March, TechRadar reported that the shortages could continue until the third quarter of the year, in part blaming a global GDDR6 memory shortage and the cards' supply being bought out by cryptominers.[19] In April, Hong Kong Customs and Excise seized 300 non-video CMP cards.[20]

Nvidia officially announced new RTX 3080, RTX 3070, RTX 3060 Ti LHR SKUs on May 18, 2021.[21]

Nvidia released the RTX 3080 Ti on June 3, and the RTX 3070 Ti one week later, on June 10. Both included the cryptocurrency mining hash rate limiter.[22]

There have been multiple attempts to meet the demand. EVGA has a system designed to put people into a queue, the goal is to prevent cards from selling out quickly and decreasing wait time.[23]

Details[edit]

Architectural improvements of the Ampere architecture include the following:

  • CUDA Compute Capability 8.6[24]
  • Samsung8 nm
  • Doubled FP32 performance per SM on Ampere GPUs
  • Third-generation Tensor Cores with FP16, bfloat16, TensorFloat-32 (TF32) and sparsity acceleration
  • Second-generation Ray Tracing Cores, plus concurrent ray tracing and shading and compute
  • GDDR6X memory support (RTX 3070 Ti, RTX 3080, RTX 3080 Ti and RTX 3090)
  • PCI Express 4.0
  • NVLink 3.0 (RTX 3090)
  • HDMI 2.1 with full 48Gbps bandwidth[25]
  • PureVideo Feature Set K hardware video decoding with AV1 hardware decoding[26]

GeForce 30 (30xx) series[edit]

Only the RTX 3090 supports 2-way NVLink.

All the RTX 30 GPUs are made using the 8nm Samsung node.[27]

  1. ^Shader Processors : Texture mapping units : Render output units : Ray tracing cores : Tensor Cores
  2. ^The number of Streaming multi-processors on the GPU.
  3. ^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.
  4. ^Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
  5. ^ abCards with GDDR6X send two bits per transfer. Equivalent transfer rate to GDDR6 in brackets used for comparing bit rate. The transfer rate should not be confused with the bit rate.

GeForce 30 (30xx) series for notebooks[edit]

Model Launch Code name(s) Process (nm) Transistors (billion) Die size
(mm2)
Core config SM
count
L2 cache
(MB)
Clock speeds FillrateMemory Processing power (TFLOPS) Ray tracing performance TDP (watts)
Base core clock (MHz) Boost core clock (MHz) Memory (MT/s) Pixel
(GP/s)
Texture
(GT/s)
Size (GB) Bandwidth (GB/s) Type Bus width (bit) Single precision (boost) Double precision (boost) Half precision (boost) Rays/s
(billions)
RTX-OPS
(trillions)
Tensor FLOPS
(trillions)
GeForce RTX 3050 Laptop[39]May 11, 2021 GA107 Samsung 8N ? ? 2048:64:40:64:16

(16) (3)

16 2 713-1530 1057-1740 12000

14000

? ? 4 224 GDDR6 128 ? 60 96 2.92-6.27

4.33-7.13

0.016-0.098

0.068-0.111

2.92-6.27

4.33-7.13

35-80
GeForce RTX 3050 Ti Laptop[39]GA107 2560:80:48:80:20

(20) (3)

20 735-1463 1035-1695 ? ? 4 ? 71.28 118.8 3.76-7.49

5.30-8.68

0.059-0.117

0.083-0.136

3.76-7.49

5.30-8.68

35-80
GeForce RTX 3060 Laptop[39]February 25, 2021 GA106 13.25 276 3840:120:48:120:30

(30) (3)

30 3 900-1387 1283-1703 ? ? 6 336 192 ? 68.4 171.0 6.91-10.65

9.85-13.08

0.108-0.166

0.154-0.204

6.91-10.65

9.85-13.08

60-115
GeForce RTX 3070 Laptop[39]January 12, 2021 GA104-770-A1 17.4 392 5120:160:80:160:40

(40) (6)

40 4 1110-1215 1290-1620 ? ? 8


8/16

448 256 ? 124.8 249.6 11.37-12.44

13.21-16.59

0.178-0.194

0.206-0.259

11.37-12.44

13.21-16.59

80-125
GeForce RTX 3080 Laptop[39]GA104-775-A1 6144:192:96:192:48

(48) (6)

48 1110-1350 1245-1710 ? 148.3 296.6 13.64-16.59

15.30-21.01

0.213-0.259

0.239-0.328

13.64-16.59

15.30-21.01

80-150+

See also[edit]

References[edit]

  1. ^Newsroom, NVIDIA. "NVIDIA Delivers Greatest-Ever Generational Leap with GeForce RTX 30 Series GPUs". NVIDIA Newsroom Newsroom.
  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. ^ abD'Anastasio, Cecilia (November 13, 2020). "Desperate Gamers Camp Out in the Pandemic for $700 GPUs". Wired.
  5. ^Ridley, Jacob (September 24, 2020). "Here's the latest on RTX 3080 stock, according to retailers and manufacturers". PC Gamer.
  6. ^Freedman, Andrew (September 17, 2020). "Nvidia, Newegg Address Nearly Non-Existent RTX 3080 Availability". Tom's Hardware.
  7. ^株式会社インプレス (2020-09-18). "GeForce RTX 3080の夜間販売に自作PCファン集結、120名以上の人で賑わうドスパラにはキャンセル分を求める行列も". AKIBA PC Hotline! (in Japanese). Retrieved 2020-09-27.
  8. ^Kan, Michael (September 17, 2020). "How a Bot Bought Dozens of RTX 3080 Units Before Consumers Could Grab Them". PCMag UK.
  9. ^"NVIDIA issues a statement on GeForce RTX 3080 going immediately out of stock". VideoCardz. September 17, 2020.
  10. ^ ab"GeForce RTX 3070 Availability Update". NVIDIA. Retrieved 2020-10-02.
  11. ^Lyles, Taylor (2020-10-05). "Nvidia CEO anticipates supply shortages for the RTX 3080 and 3090 to last until 2021". The Verge. Retrieved 2020-10-05.
  12. ^"NVIDIA Store Update, GeForce RTX 3080 and RTX 3090 Founders Edition". NVIDIA. Retrieved 2020-10-18.
  13. ^Allan, Darren (October 10, 2020). "Nvidia admits defeat with RTX 3080 and 3090 Founders Edition stock, passes baton to Best Buy". TechRadar. Retrieved October 20, 2020.
  14. ^"NVIDIA GeForce RTX 30 series Founders Edition locked to Best Buy in US". TweakTown. 2020-10-11. Retrieved 2020-10-20.
  15. ^"NVIDIA: Ampere RTX 30 Stock Issues Is not only based on GPU shortages". Guru3D. 2020-12-03.
  16. ^Evangelho, Jason. "What's Really Going On With Nvidia RTX 30 Series Supply?". Forbes. Retrieved 2021-04-06.
  17. ^Wuebbling, Matt (2021-02-18). "GeForce Is Made for Gaming, CMP Is Made to Mine". The Official NVIDIA Blog. Retrieved 2021-04-06.
  18. ^Loeffler, John (March 15, 2021). "Did Nvidia just unlock RTX 3060 cryptomining by mistake?". TechRadar. Retrieved May 5, 2021.
  19. ^Page, Carly (15 March 2021). "Nvidia RTX 3080 shortage could continue until Q3". TechRadar. Retrieved 2021-04-06.
  20. ^Roach, Jason (7 April 2021). "Smugglers transported 300 GPUs in a Mission Impossible-style speed boat chase". www.digitaltrends.com. Digital Trends. Archived from the original on 8 April 2021.
  21. ^https://blogs.nvidia.com/blog/2021/05/18/lhr/
  22. ^Warren, Tom (June 1, 2021). "Nvidia announces new RTX 3080 Ti, priced at $1,199 and launching June 3rd". The Verge. Retrieved June 16, 2021.
  23. ^Ridley, Jacob (2020-10-06). "EVGA's new virtual queue will auto-reserve you an Nvidia RTX 3080". PC Gamer. Retrieved 2021-09-25.
  24. ^"I.7. Compute Capability 8.x". docs.nvidia.com. Retrieved 2020-09-23.
  25. ^https://www.nvidia.com/en-us/geforce/news/rtx-30-series-hdmi-2-1/
  26. ^"GeForce RTX 30 Series GPUs: Ushering In A New Era of Video Content With AV1 Decode". NVIDIA.
  27. ^James, Dave (2020-09-01). "Nvidia confirms Samsung 8nm process for RTX 3090, RTX 3080, and RTX 3070". PC Gamer. Retrieved 2021-06-01.
  28. ^https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/rtx-3060-3060ti/
  29. ^ abcdefhttps://www.nvidia.com/content/dam/en-zz/Solutions/geforce/ampere/pdf/NVIDIA-ampere-GA102-GPU-Architecture-Whitepaper-V1.pdf
  30. ^https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/rtx-3060-ti/
  31. ^"NVIDIA Slyly Announces The GeForce RTX 3070 Availability, Sliding In Before RX 6000 Announcement". September 12, 2020.
  32. ^ ab"NVIDIA GeForce RTX 3070 Family". NVIDIA. Retrieved 2021-06-01.
  33. ^https://www.nvidia.com/content/PDF/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf
  34. ^ abcdef"NVIDIA GeForce Ampere Architecture, Board Design, Gaming Tech & Software". techpowerup. Retrieved 5 September 2020.
  35. ^ ab"NVIDIA Announces GeForce RTX 3080 Ti & 3070 Ti: Upgraded Ampere Cards Coming in June". June 1, 2021.
  36. ^ ab"NVIDIA GeForce RTX 3080 Family". NVIDIA. Retrieved 2021-06-01.
  37. ^Mujtaba, Hassan (September 4, 2020). "NVIDIA GeForce RTX 30 Ampere GPU Deep-Dive, Full Specs, Thermals, Power & Performance Detailed".
  38. ^"NVIDIA GeForce RTX 3090 Graphics Card". Nvidia.com. Retrieved 2020-09-01.
  39. ^ abcde"NVIDIA GeForce RTX 30 Series Laptops". NVIDIA. Retrieved 2021-06-02.
Notelist

External links[edit]

Sours: https://en.wikipedia.org/wiki/GeForce_30_series
NVIDIA GeForce RTX 30 Series - Official Launch Event [4K]

Turing (microarchitecture)

GPU microarchitecture by Nvidia

Turing is the codename for a graphics processing unit (GPU) microarchitecture developed by Nvidia. It is named after the prominent mathematician and computer scientist Alan Turing. The architecture was first introduced in August 2018 at SIGGRAPH 2018 in the workstation-oriented Quadro RTX cards,[2] and one week later at Gamescom in consumer GeForce RTX 20 series graphics cards.[3] Building on the preliminary work of its HPC-exclusive predecessor, the Turing architecture introduces the first consumer products capable of real-time ray tracing, a longstanding goal of the computer graphics industry. Key elements include dedicated artificial intelligence processors ("Tensor cores") and dedicated ray tracing processors. Turing leverages DXR, OptiX, and Vulkan for access to ray-tracing. In February 2019, Nvidia released the GeForce 16 series of GPUs, which utilizes the new Turing design but lacks the ray tracing and artificial intelligence cores.

Turing is manufactured using TSMC's 12 nmFinFETsemiconductor fabrication process. The high-end TU102 GPU includes 18.6 billion transistors fabricated using this process.[4] Turing also uses GDDR6 memory from Samsung Electronics, and previously Micron Technology.

Details[edit]

The Turing microarchitecture combines multiple types of specialized processor core, and enables an implementation of limited real-time ray tracing.[5] This is accelerated by the use of new RT (ray-tracing) cores, which are designed to process quadtrees and spherical hierarchies, and speed up collision tests with individual triangles.

Features in Turing:

The GDDR6 memory is produced by Samsung Electronics for the Quadro RTX series.[7] The RTX 20 series initially launched with Micron memory chips, before switching to Samsung chips by November 2018.[8]

Rasterization[edit]

Nvidia reported rasterization (CUDA) performance gains for existing titles of approximately 30–50% over the previous generation.[9][10]

Ray-tracing[edit]

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. Nvidia said the ray-tracing performance increased about 8 times over the previous consumer architecture, Pascal.

Tensor cores[edit]

Generation of the final image is further accelerated by the Tensor cores, which are used to fill in the blanks in a partially rendered image, a technique known as de-noising. The Tensor cores perform the result of deep learning to codify how to, for example, increase the resolution of images generated by a specific application or game. 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 via driver updates to consumers.[9] The supercomputer uses a large number of Tensor cores itself.

Chips[edit]

  • TU102
  • TU104
  • TU106
  • TU116
  • TU117

Development[edit]

Main article: Nvidia RTX

Turing's development platform is called RTX. RTX ray-tracing features can be accessed using Microsoft's DXR, OptiX, as well using Vulkan extensions (the last one being also available on Linux drivers).[11] It includes access to AI-accelerated features through NGX. The Mesh Shader, Shading Rate Image functionalities are accessible using DX12, Vulkan and OpenGL extensions on Windows and Linux platforms.[12]

Windows 10 October 2018 update includes the public release of DirectX Raytracing.[13][14]

Products using Turing[edit]

  • GeForce 16 series
    • GeForce GTX 1650
    • GeForce GTX 1650 (Mobile)
    • GeForce GTX 1650 Max-Q (Mobile)
    • GeForce GTX 1650 (GDDR6)
    • GeForce GTX 1650 Super
    • GeForce GTX 1650 Ti (Mobile)
    • GeForce GTX 1660
    • GeForce GTX 1660 (Mobile)
    • GeForce GTX 1660 Super
    • GeForce GTX 1660 Ti
    • GeForce GTX 1660 Ti (Mobile)
    • GeForce GTX 1660 Ti Max-Q (Mobile)
  • GeForce 20 series
    • GeForce RTX 2060
    • GeForce RTX 2060 (Mobile)
    • GeForce RTX 2060 Max-Q (Mobile)
    • GeForce RTX 2060 Super
    • GeForce RTX 2060 Super (Mobile)
    • GeForce RTX 2070
    • GeForce RTX 2070 (Mobile)
    • GeForce RTX 2070 Max-Q (Mobile)
    • GeForce RTX 2070 Max-Q Refresh (Mobile)
    • GeForce RTX 2070 Super
    • GeForce RTX 2070 Super (Mobile)
    • GeForce RTX 2070 Super Max-Q (Mobile)
    • GeForce RTX 2080
    • GeForce RTX 2080 (Mobile)
    • GeForce RTX 2080 Max-Q (Mobile)
    • GeForce RTX 2080 Super
    • GeForce RTX 2080 Super (Mobile)
    • GeForce RTX 2080 Super Max-Q (Mobile)
    • GeForce RTX 2080 Ti
    • Titan RTX
  • Nvidia Quadro
    • Quadro RTX 3000 (Mobile)
    • Quadro RTX 4000
    • Quadro RTX 5000
    • Quadro RTX 6000
    • Quadro RTX 8000
  • Nvidia Tesla

See also[edit]

References[edit]

  1. ^Tom Warren; James Vincent (May 14, 2020). "Nvidia's first Ampere GPU is designed for data centers and AI, not your PC". The Verge.
  2. ^https://www.anandtech.com/show/13214/nvidia-reveals-next-gen-turing-gpu-architecture
  3. ^"NVIDIA Announces the GeForce RTX 20 Series: RTX 2080 Ti & 2080 on Sept. 20th, RTX 2070 in October". Anandtech.
  4. ^"NVIDIA TURING GPU ARCHITECTURE: Graphics Reinvented"(PDF). Nvidia. 2018. Retrieved June 28, 2019.
  5. ^"Nvidia announces RTX 2000 GPU series with '6 times more performance' and ray-tracing". The Verge. Retrieved August 20, 2018.
  6. ^"The NVIDIA Turing GPU Architecture Deep Dive: Prelude to GeForce RTX". AnandTech.
  7. ^Mujtaba, Hassan (August 14, 2018). "Samsung GDDR6 Memory Powers NVIDIA's Turing GPU Based Quadro RTX Cards". wccftech.com. Retrieved June 19, 2019.
  8. ^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.
  9. ^ ab"#BeForTheGame". Twitch.tv.
  10. ^Jeff Fisher. "GeForce RTX Propels PC Gaming's Golden Age with Real-Time Ray Tracing". Nvidia.
  11. ^"NVIDIA RTX platform". Nvidia.
  12. ^"Turing Extensions for Vulkan and OpenGL". Nvidia.
  13. ^https://blogs.nvidia.com/blog/2018/10/02/real-time-ray-tracing-rtx-windows-10-october-update/
  14. ^https://blogs.msdn.microsoft.com/directx/2018/10/02/directx-raytracing-and-the-windows-10-october-2018-update/

External links[edit]

Sours: https://en.wikipedia.org/wiki/Turing_(microarchitecture)

Now discussing:

Quadro

This article is about the graphics card brand. For the fraudulent tracking device, see Quadro Tracker.

Brand of Nvidia graphics cards intended for use in workstations running professional applications

Quadro was Nvidia's brand for graphics cards intended for use in workstations running professional computer-aided design (CAD), computer-generated imagery (CGI), digital content creation (DCC) applications, scientific calculations and machine learning.

Differences between the Quadro and GeForce cards include the use of ECC memory and enhanced floating point precision. These are desirable properties when the cards are used for calculations which, in contrast to graphics rendering, require reliability and precision.

The Nvidia Quadro product line directly competed with AMD's Radeon Pro (formerly FirePro/FireGL) line of professional workstation cards.[1]

Nvidia is moving away from the Quadro branding for new products, starting with the launch of the Nvidia Ampere architecture-based RTX A6000 on October 5, 2020.[2] To indicate the upgrade to the Nvidia Ampere architecture for their graphics cards technology, Nvidia RTX is the product line being produced and developed moving forward for use in professional workstations.

History[edit]

The Quadro line of GPU cards emerged in an effort towards market segmentation by Nvidia.[citation needed] In introducing Quadro, Nvidia was able to charge a premium for essentially the same graphics hardware in professional markets, and direct resources to properly serve the needs of those markets.[dubious – discuss] To differentiate their offerings, Nvidia used driver software and firmware to selectively enable features vital to segments of the workstation market, such as high-performance anti-aliased lines and two-sided lighting, in the Quadro product.[citation needed] The Quadro line also received improved support through a certified driver program.[citation needed] These features were of little value to the gamers that Nvidia's products already sold to, but their lack prevented high-end customers from using the less expensive products.

There are parallels between the market segmentation used to sell the Quadro line of products to workstation (DCC) markets and the Tesla line of products to engineering and HPC markets.

In a settlement of a patent infringement lawsuit between SGI and Nvidia, SGI acquired rights to speed-binned Nvidia graphics chips which they shipped under the VPro product label. These designs were completely separate from the SGI Odyssey based VPro products initially sold on their IRIX workstations which used a completely different bus. SGI's Nvidia-based VPro line included the VPro V3 (Geforce 256), VPro VR3 (Quadro), VPro V7 (Quadro2 MXR), and VPro VR7 (Quadro2 Pro).[3][4]

Quadro SDI[edit]

Actual extra cards only for Quadro 4000 cards and higher:

Quadro Plex[edit]

Quadro Plex consists of a line of external servers for rendering videos. A Quadro Plex contains multiple Quadro FX video cards. A client computer connects to Quadro Plex (using PCI Express ×8 or ×16 interface card with interconnect cable) to initiate rendering. More data in Nvidia Tesla Cards.

Quadro SLI and SYNC[edit]

Scalable Link Interface, or SLI, is the next generation of Plex. SLI can improve Frame Rendering, FSAA.[7][8]

Quadro SLI support Mosaic for 2 Cards and 8 Monitors.[9]

With Quadro SYNC Card support of max. 16 Monitors (4 per Card) possible.[10][11]

Most Cards have SLI-Bridge-Slot for 2, 3 or 4 cards on one main board.[12]

Acceleration of scienctific calculations is possible with CUDA and OpenCL.[13][14][15]

Nvidia has 4 types of SLI bridges:

More see SLI.

Quadro VCA[edit]

Nvidia supports SLI and supercomputing with its 8-GPU Visual Computing Appliance.[20] Nvidia Iray,[21][22] Chaosgroup V-Ray[23] and Nvidia OptiX[24] accelerate Raytracing for Maya, 3DS Max, Cinema4D, Rhinoceros and others. All software with CUDA or OpenCL, such as ANSYS, NASTRAN, ABAQUS, and OpenFoam, can benefit from VCA. The DGX-1 is available with 8 GP100 Cards.[25]

More data in Nvidia Tesla Cards.

Quadro RTX[edit]

See also: Turing (microarchitecture)

The Quadro RTX series is based on the Turing microarchitecture, and features real-time raytracing.[26] This 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 raytracing 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 physically correct, especially regarding off-camera action.

Tensor cores further enhance the image produced by raytracing, and are used to de-noise a partially rendered image.[citation needed]

RTX is also the name of the development platform introduced for the Quadro RTX series. RTX leverages Microsoft's DXR, OptiX and Vulkan for access to raytracing.[27]

Turing is manufactured using TSMC's 12 nmFinFETsemiconductor fabrication process.[28] Quadro RTX also uses GDDR6 memory from Samsung Electronics.[29]

Video cards[edit]

GeForce[edit]

Many of these cards use the same core as the game- and action-oriented GeForce video cards by Nvidia. Those cards that are identical to the desktop cards can be software modified to identify themselves as the equivalent Quadro cards and this allows optimized drivers intended for the Quadro cards to be installed on the system. While this may not offer all of the performance of the equivalent Quadro card,[citation needed] it can improve performance in certain applications, but may require installing the MAXtreme driver for comparable speed.

The performance difference comes in the firmware controlling the card.[citation needed] Given the importance of speed in a game, a system used for gaming can shut down textures, shading, or rendering after only approximating a final output—in order to keep the overall frame rate high. The algorithms on a CAD-oriented card tend rather to complete all rendering operations, even if that introduces delays or variations in the timing, prioritising accuracy and rendering quality over speed. A Geforce card focuses more on texture fillrates and high framerates with lighting and sound, but Quadro cards prioritize wireframe rendering and object interactions.

Software[edit]

With Caps Viewer (1.38 in 2018) all Windows Users can see data of the graphic Card, the installed Driver and can test some Features.[30] GPU-Z reads also data of the graphic cards and the user can send some data for better database.[31]

Quadro drivers[edit]

  • Curie-Architecture Last drivers see Driver Portal of Nvidia[32] (End-of-Life)
  • Tesla-Architecture (G80+, GT2xx) in Legacy Mode Quadro Driver 340: OpenGL 3.3, OpenCL 1.1, DirectX 10.0/10.1[33] (End-of-Life)
  • Fermi (GFxxx): OpenCL 1.1, OpenGL 4.5, some OpenGL 2016 Features with Quadro Driver 375,[34] in legacy mode with version 391.74 (End-of-Life)
  • Kepler (GKxxx): OpenCL 1.2, OpenGL 4.6, Vulkan 1.2 with RTX Enterprise/Quadro Driver 470[35] (End-of-Life)
  • Maxwell (GMxxx): OpenCL 3.0, OpenGL 4.6, Vulkan 1.2 with RTX Enterprise/Quadro Driver 495+[36]
  • Pascal (GPxxx): OpenCL 3.0, OpenGL 4.6, Vulkan 1.2 with RTX Enterprise/Quadro driver 495+[36]
  • Volta (GVxxx): OpenCL 3.0, OpenGL 4.6, Vulkan 1.2 with RTX Enterprise/Quadro driver 495+[36]
  • Turing (TUxxx): OpenCL 3.0, OpenGL 4.6, Vulkan 1.2 with RTX Enterprise/Quadro driver 495+[36]
  • Ampere (GAxxx): OpenCL 3.0, OpenGL 4.6, Vulkan 1.2 with RTX Enterprise/Quadro driver 495+[36]

CUDA[edit]

  • Tesla Architecture and later

Supported CUDA Level of GPU and Card.[37]

  • CUDA SDK 6.5 support for Compute Capability 1.0 - 5.x (Tesla, Fermi, Kepler, Maxwell) Last Version with support for Tesla-Architecture with Compute Capability 1.x
  • CUDA SDK 7.5 support for Compute Capability 2.0 - 5.x (Fermi, Kepler, Maxwell)
  • CUDA SDK 8.0 support for Compute Capability 2.0 - 6.x (Fermi, Kepler, Maxwell, Pascal) Last version with support for compute capability 2.x (Fermi)
  • CUDA SDK 9.0/9.1/9.2 support for Compute Capability 3.0 - 7.2 (Kepler, Maxwell, Pascal, Volta)
  • CUDA SDK 10.0/10.1/10.2 support for Compute Capability 3.0 - 7.5 (Kepler, Maxwell, Pascal, Volta, Turing) Last version with support for compute capability 3.x (Kepler).
  • CUDA SDK 11.0/11.1/11.2/11.3/11.4 support for Compute Capability 3.5 - 8.6 (Kepler(GK110, GK208, GK210 only), Maxwell, Pascal, Volta, Turing, Ampere)

For own Card Test see CUDA-Z Tool[38]

Desktop PCI Express[edit]

Quadro FX (without CUDA, OpenCL, or Vulkan)[edit]

  • Rankine (NV3x): DirectX 9.0a, Shader Model 2.0a, OpenGL 2.1
  • Curie (NV4x, G7x): DirectX 9.0c, Shader Model 3.0, OpenGL 2.1
Quadro_FX
PCIe Model
Launch Core Core
clock
Memory clock
(eff.)
Memory size
(MB)
Memory type Memory
bandwidth
3-pin
stereo
connector
Pixel
Rate
Texture
Rate
Open GLCUDA
OpenCL
VulkanPower
max.
Monitor Output Near GeForce Model Notes
UnitsMHzMHzMBGiB/sGP/sGT/sWatt
Quadro FX 330[39]2004-06-28NV35GL (Rankine)250200 (400)6464-bit DDR3.2No0.51.02.1No211x DVIGeForce PCX 5300Shader Model 2.0
Quadro FX 350[40]2006-04-20G72GL (Curie)550405 (810)12864-bit DDR26.48No1.12.221DVI, VGAGeForce 7300LE
Quadro FX 540[41]2004-08-09NV43GL300250 (500)128128-bit GDDR8.8No2.42.435DVI, VGA, S-VideoGeForce 6600LE
Quadro FX 550[42]2006-04-20NV43GL360400 (800)128128-bit GDDR312.8No2.882.88252× dual-link DVI (max. only 2048×1536), S-Video
Quadro FX 560[43]2006-04-20G73GL350600 (1200)128128-bit GDDR319.2No2.804.2302x DL-DVI, S-VideoGeForce 7600
Quadro FX 1300[44]2004-08-09NV38GL350275 (550)128256-bit DDR17.6Yes2.802.80552x Single-Link DVI, S-VideoGeForce PCX 5950
Quadro FX 1400[45]2004-08-09NV41GL350300 (600)128256-bit DDR19.2Yes2.804.20702xSL-DVI, VESA StereoGeForce 6800
Quadro FX 1500[46]2006-04-20G71GL325625 (1250)256256-bit GDDR340.0No5.206.50652xDL-DVI, S-VideoGeForce 79xx (16 pixel, 6 vertex)
Quadro FX 3400[47]2004-06-28NV40 A1 (NV45GL)350450 (900)256256-bit GDDR328.8Yes4.604.601012x DL-DVI, S-VideoGeForce 6800
Quadro FX 3450[48]2005-06-28NV42GL (Curie)425500 (1000)256256-bit GDDR332.0Yes5.105.10832x DL-DVI, S-VideoGeForce 6800
Quadro FX 3500[49]2006-05-22G71GL450660 (1320)256256-bit GDDR342.2Yes7.209.00802x DVI, S-VideoGeForce 7900GSreduced Quadro FX 5500
Quadro FX 4000[50]2004-04-01NV42GL425500 (1000)256256-bit GDDR332.0Yes5.105.101422x DVI, S-Video
Quadro FX 4000 SDI[51]2004-04-19NV42GL425500 (1000)256256-bit GDDR332.0Yes5.105.10150DVI, 2x SDI HDTV2× SDI HDTV outputs + digital and analog genlock (using external controllers)
Quadro FX 4400[52]2005-06-28NV40 A1 (NV45GL)375525 (1050)512256-bit GDDR333.6Yes5.505.50832x DL-DVI, S-VideoGeForce 6800 PCI-EVariant FX 4400G with Genlock[53]
Quadro FX 4500[54]2005-06-28G70GL470525 (1050)512256-bit GDDR333.6Yes6.8810.31092x DL-DVI, S-VideoGeForce 7800GTX
Quadro FX 4500 SDI[55]2006-02-11G70GL470525 (1050)512256-bit GDDR333.6Yes6.8810.3116DL-DVI, 2x HDTVGeForce 7800GTXanalog and digital genlock
Quadro FX 4500 X2[56]2006-04-24G70GL (2x)500600 (1200)2×5122×256-bit GDDR32×33.6Yes2x 8.02x 12.01454x DL-DVIQuadro FX 4500Two GPU units on the same card
Quadro FX 5500[57]2006-04-20G71GL650500 (1000)1024256-bit GDDR332.3Yes10.415.6962xDL-DVI, S-VideoGeForce 7900GTX
Quadro FX 5500 SDI[58]2006-04-20G71GL650500 (1000)1024256-bit GDDR332.3Yes10.415.6104Quadro FX 5500with SDI, genlock/frame lock support (via external hardware)

Quadro FX (with CUDA and OpenCL, but no Vulkan)[edit]

  • Architecture Tesla (G80+, GT2xx) with OpenGL 3.3 and OpenCL 1.1
  • Tesla (G80+): DirectX 10, Shader Model 4.0, only Single Precision (FP32) available for CUDA and OpenCL
  • Tesla 2 (GT2xx): DirectX 10.1, Shader Model 4.1, Single Precision (FP32) available for CUDA and OpenCL (Double Precision (FP64) available for CUDA and OpenCL only for GT200 with CUDA Compute Capability 1.3 )
Quadro_FX
PCIe Model
Launch Core Core
clock
Memory clock
(eff.)
Memory size
(MB)
Memory type Memory
bandwidth
3-pin
stereo
connector
CUDA
cores
CUDA
Compute
Capa-
bility
Open GLOpen CLVulkanPower
max.
Monitor Output Near GeForce Model Notes
UnitsMHzMHzMBGiB/sWatt
Quadro FX 370[59]2007-09-12G84 (Tesla)360500 (1000)25664-bit GDDR26.4No161.13.31.1No351× Dual-link DVI-I, 1x single-link DVIShader Model 4.0 DirectX 10
Quadro FX 370 LP[60]2008-06-11G86540500 (1000)25664-bit GDDR28No81.11.125DMS-59Low Profile
Quadro FX 380[61]2009-03-30G96450350 (700)256128-bit GDDR322.4No161.11.1342× Dual-link DVI-IGeForce 9400
Quadro FX 380 LP[62]2009-12-01GT218GL550400 (800)51264-bit GDDR312.8No161.21.1281x Dual-link DVI-I, 1x DisplayPortLow Profile
Quadro FX 570[63]2007-09-12G84GL460400 (800)256128-bit GDDR212.8No161.11.1382× Dual-link DVI-IShader Model 4.0, DirectX 10
Quadro FX 580[64]2009-04-09G96450 (OC 650)800 (1600)512128-bit GDDR325.6No321.11.1401× Dual-link DVI-I, 2× DP (10-bits per color)[65]GeForce 9500
Quadro FX 1700[66]2007-12-09G84GL460400 (800)512128-bit GDDR212.8No321.11.1422xDL-DVI, S-Video (TV-Out)GeForce 8600GTShader Model 4.0, DirectX 10.
Quadro FX 1800[67]2009-03-30G94550 (shader clock 1375)800 (1600)768192-bit GDDR338.4No641.11.1591× Dual-link DVI-I, 2× DP (10-bits per color)[68]Shader Model 4.0, DirectX 10.
Quadro FX 3700[69]2008-01-08G92500800 (1600)512256-bit GDDR351.2Yes1121.11.1782x DVI, S-VideoGeForce 8800GT, 8800GTS 512PCI Express 2.0, Energy Star 4.0 compliant (<= 80W)
Quadro FX 3800[70]2009-03-30GT200GL600800 (1600)1024256-bit GDDR351.2Yes1921.31.1107DVI, 2x DisplayPort (10bits per Color)GeForce GTX 260Stereo requires an optional 3 pin S Bracket
Quadro FX 3800 SDI[71]2009-03-30GT200GL600800 (1600)1024256-bit GDDR351.2Yes1921.31.1107DVI, 2x DisplayPortQuadro FX 3800HD-SDI Ports
Quadro FX 4600[72]2007-03-05G80GL400700 (1400)768384-bit GDDR367.2Yes1121.01.11342xDL-DVI, S-VideoGeForce 8800GTS (G80)One 6-pin power connector
Quadro FX 4600 SDI[73][74]2007-05-30G80GL400700 (1400)768384-bit GDDR367.2Yes1121.01.1154Quadro FX 4600with SDI, genlock/frame lock support (via external hardware), One 6-pin power connector
Quadro FX 4700 X2[75]2006-04-24G92500800 (1600)2×5122×256-bit GDDR32×51.2Yes2x 1121.11.12262xDL-DVI, S-VideoQuadro FX 3700Two GPU units on the same card
Quadro FX 5600[76]2007-03-05G80GL600800 (1600)1536384-bit GDDR376.8Yes1281.01.1 (1.0 OS X)1712x DVI, S-VideoGeForce 8800GTXTwo 6-pin power connectors
Quadro FX 5600 SDI[77]2007-03-05G80GL600800 (1600)1536384-bit GDDR376.8Yes1281.01.1 (1.0 OS X)1712x DVI, S-VideoQuadro FX 5600Two 6-pin power connectors, HD-SDI Version
Quadro FX 4800[78]2008-11-11D10U-20 (GT200GL)602800 (1600)1536384-bit GDDR377Yes1921.31.1 (1.0 Mac OS X)150DVI, 2x DP, S-Video55 nm version of GeForce GTX 260. Quadro CX without Elemental Technologies' CS4 plug-in., SDI Version available
Quadro FX 4800 SDI[79][80]2008-11-11D10U-20 (GT200GL)602800 (1600)1536384-bit GDDR377Yes1921.31.1 (1.0 Mac OS X)150DVI, 2x DP, S-Video, SDIFX 4800HD-SDI
Quadro FX 5800[81]2008-11-11D10U-30 (GT200GL)650800 (1600)4096512-bit GDDR3102Yes2401.31.1189DVI, 2x DP, S-VideoGeForce GTX 285SDI Version available[79]
Quadro FX 5800 SDI[79][82]2008-11-11D10U-30 (GT200GL)650800 (1600)4096512-bit GDDR3102Yes2401.31.1189DVI, 2x DP, S-VideoGeForce GTX 285HD-SDI
Quadro CX[83]2008-11-11D10U-20 (GT200GL)602800 (1600)1536384-bit GDDR376.8Yes1921.31.11501xDP, 1xDL-DVI, S-Video55 nm GeForce GTX 260optimised for Adobe Creative Suite 4, HD-SDI optional[80]
Quadro VX 200[84]2008-01-08G92450800 (1600)512GDDR351.2No921.11.178HDTV and 2× Dual-link DVIoptimised for Autodesk AutoCAD.

Quadro[edit]

  • Architecture Fermi (GFxxx), Kepler (GKxxx), Maxwell (GMxxx), Pascal (GPxxx), Volta (GVxxx) (except Quadro 400 with Tesla 2)
  • All Cards with Display Port 1.1+ can support 10bit per Channel for OpenGL (HDR for Graphics Professional (Adobe Photoshop and more))
  • Vulkan 1.2 available with Driver Windows 456.38, Linux 455.23.04 for Kepler, Maxwell, Pascal, Volta[85]
  • All Kepler, Maxwell, Pascal, Volta and later can do OpenGL 4.6 with Driver 418+[86]
  • All Quadro can do OpenCL 1.1. Kepler can do OpenCL 1.2, Maxwell and later can do OpenCL 3.0
  • All can do Double Precision with Compute Capability 2.0 and higher (see CUDA)
Quadro
GPU
Launch Core Core
clock
Memory clock Memory size
(MB)
Memory type Memory
bandwidth
3-pin
stereo
connector
CUDA
cores
CUDA
Compute
Capa-
bility
DirectXOpen GLOpen CLVulkanPower
max.
MonitorOutput Near GeForce Model Notes
UnitsMHzMHzMBGiB/sWatt
Quadro 400[87]2011-04-05GT216GL (40 nm)45080051264-bit GDDR312.31.1481.210.13.31.1No321x Dual-link DVI-I, 1x DP 1.1a, HDMI 1.3a (via adapter)[88]GeForce GT 220GeForce 200 Series Tesla-2-based
Quadro 600[89]2010-12-13GF108GL6408001024128-bit GDDR325.6No962.111.0
(11_0)
4.6401×DL-DVI-I, 1× DisplayPort 1.1a, HDMI 1.3a (via adapter).[90]GeForce GT 430Based on the GeForce 400 Series Fermi-based
Quadro 2000[91]2010-12-24GF106GL62513001024128-bit GDDR541.6No1922.1621×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[92]GeForce GTS 450Fermi-based
Quadro 2000D[93]2011-10-05GF106GL62513001024128-bit GDDR541.6No1922.1622×DL-DVI-I, 1x DP 1.1a GeForce GTS 45010 and 12 bit per each rgb Channel (10-bits internal)[94]
Quadro 4000 (SDI)[95]2010-11-02GF100GL4757002048256-bit GDDR589.6Yes2562.01421×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[96]?HD-SDI optional[97][98]
Quadro 5000 (SDI)[99]2011-02-23GF100GL (Fermi)5137502560320-bit GDDR5 ECC120Yes3522.01521×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[100]GeForce GTX 465/470 (cutdown)GeForce 400 Series, HD-SDI optional[101]
Quadro 6000 (SDI)[102]2010-12-10GF100GL (Fermi)5747506144384-bit GDDR5 ECC144Yes4482.02041×DL-DVI-I, 2× DP 1.1a, HDMI 1.3a (via adapter)[103]GeForce GTX 480 (cutdown)GeForce 400 Series, HD-SDI optional[104]
Quadro 7000[105]2012-05-12GF110GL6509256144384-bit GDDR5 ECC177.4Yes5122.02042x DP 1.1a, DVI, S-Video GeForce GTX 580Fermi-based
Quadro Plex 7000[106]2011-07-252x GF100GL5747502x 61442x 384-bit GDDR5 ECC2x 144Yes2x 5122.06004x DP 1.1a, 2x S-Video GeForce GTX 590Based on two Quadro 6000.
Quadro 410[107][108]2012-08-07GK107GLM (28 nm)[109]70689151264-bit DDR314No1923.012.0
(11_0)
3.01.2381x Single-link DVI-I, 1x DP 1.2, HDMI 1.4 (via adapter)[110]GeForce GT 630 (Kepler)GeForce 600 Series Kepler-based
Quadro K420[111]2014-07-14GK107GL7809001024128-bit GDDR329No1923.0411x DL-DVI, 1x DP 1.2 GeForce GT 630 (Kepler)Kepler-based[112]
Quadro K600[113]2013-03-01GK107GL8759001024128-bit GDDR329No1923.0411x DL-DVI-I, 1x DP 1.2 GeForce GT 630 (Kepler)Kepler-based[112]
Quadro K620[114]2014-07-14GM107GL10009002048128-bit GDDR329No3845.0451x DL-DVI, 1x DP 1.2, GeForce GTX 745 (OEM)Maxwell-based[112]
Quadro K1200[115]2015-01-28GM107GL100012504096128-bit GDDR580No5125.0454x Mini-DP 1.2 GeForce GTX 750Maxwell-based[112]
Quadro K2000[116]2013-03-01GK107GL95410002048128-bit GDDR564No3843.0511x DL-DVI-I, 2x DP 1.2 GeForce GTX 650Kepler-based[112]
Quadro K2000D[117]2013-03-01GK107GL95010002048128-bit GDDR564No3843.0512x DL-DVI-I, 1x DP 1.2 GeForce GTX 650Kepler-based[112]
Quadro K2200[118][119]2014-07-22GM107GL104612504096128-bit GDDR580No6405.0681x DL-DVI-I, 2x DP 1.2 GeForce GTX 750 TiMaxwell-based[112]
Quadro K4000[120][121]2013-03-01GK106GL80014003072192-bit GDDR5134Yes7683.0801x DL-DVI-I, 2x DP1.2 GeForce GTX 650 Ti BoostKepler-based,[112] HD-SDI optional with extra Card[122]
Quadro K4200[123][124]2014-07-22GK104GL78013504096256-bit GDDR5173Yes13443.01081x DL-DVI-I, 2x DP 1.2 GeForce GTX 670Kepler-based,[112] HD-SDI optional
Quadro K5000[125]2012-08-17GK104GL70613504096256-bit GDDR5 ECC173Yes15363.01222x DP 1.2 GeForce GTX 770/680Kepler-based,[112][126] HD-SDI optional[127]
Quadro K5200[128][129]2014-07-22GK110GL65015008192256-bit GDDR5 ECC192Yes23043.51501x DL-DVI-I, 1x DL-DVI-D, 2x DP 1.2 GeForce GTX 780Kepler-based, HD-SDI optional
Quadro K6000[130]2013-07-23GK110GL700150012288384-bit GDDR5 ECC288Yes28803.52252x DP 1.2 GeForce GTX TITAN BlackKepler-based,[112] HD-SDI optional[131]
Quadro M2000[132]2016-04-08GM206-875796-116316534096128-bit GDDR5105.8No7685.212.0
(12_1)
754x DP 1.2 GeForce GTX 950Maxwell-based
Quadro M4000[133]2015-06-29GM204-85077315028192256-bit GDDR5192.3Yes16645.21204x DP 1.2 GeForce GTX 970Maxwell-based
Quadro M5000[134]2015-06-29GM204-875861-103816538192256-bit GDDR5 ECC211.6Yes20485.21504x DP 1.2 GeForce GTX 980Maxwell-based
Quadro M6000[135]2015-03-15GM200GL988-1114165312288384-bit GDDR5 ECC317.4Yes30725.22504x DP 1.2 GeForce GTX TITAN XMaxwell-based
Quadro M6000 24GB[136]2016-03-05GM200-880988-1114165324576384-bit GDDR5 ECC317.4Yes30725.22504x DP 1.2 GeForce GTX TITAN XMaxwell-based
Quadro P400 2017-02-06GP107-8251228-12521003204864-bit GDDR532.1No2566.1303x mini-DP 1.4 GeForce GT 1030Pascal-based[112]
Quadro P600 2017-02-06GP107-8501329-155710032048128-bit GDDR564.2No3846.1404x mini-DP 1.4 GeForce GT 1030Pascal-based[112]
Quadro P620 2018-02-01GP107-8551266-135412522048128-bit GDDR580.13No5126.1404x mini-DP 1.4 GeForce GTX 1050Pascal-based[112]
Quadro P1000 2017-02-06GP107-8601266-148112534096128-bit GDDR580.19No6406.1474x mini-DP 1.4 GeForce GTX 1050Pascal-based[112]
Quadro P2000 2017-02-06GP106-875-K11076-148017525120160-bit GDDR5140.2No10246.1754x DP 1.4 GeForce GTX 1060Pascal-based[112]
Quadro P2200 2019-06-10GP106-880-K11000-149312535120160-bit GDDR5X200.5No12806.1754x DP 1.4 GeForce GTX 1060Pascal-based[112]
Quadro P4000 2017-02-06GP104-8501202-148019018192256-bit GDDR5243.3Yes17926.1105DVI, 4x DP 1.4 GeForce GTX 1070Pascal-based[112]
Quadro P5000 2016-10-01GP104-8751607-1733112716384256-bit GDDR5X288.5Yes25606.1180DVI, 4x DP 1.4 GeForce GTX 1080Pascal-based[112][137]
Quadro P6000 2016-10-01GP102-8751506-1645112724576384-bit GDDR5X432.8Yes38406.1250DVI, 4x DP 1.4 Nvidia TITAN XpPascal-based[112][137]
Quadro GP100[138][139]2017-02-06GP100GL1304-1442715163844096-bit HBM2732.2Yes35846.0235Dual-Link DVI, 4x DP 1.4 Nvidia TITAN XpPascal-based[112][137]
Quadro GV100[140]2018-03-27GV100-8751132-1627848327684096-bit HBM2868.4Yes51207.02504x DP 1.4 Nvidia TITAN VVolta-based[141]

1 Nvidia Quadro 342.01 WHQL: support of OpenGL 3.3 and OpenCL 1.1 for legacy Tesla microarchitecture Quadros.[33]

2 Nvidia Quadro 377.83 WHQL: support of OpenGL 4.5, OpenCL 1.1 for legacy Fermi microarchitecture Quadros.[34]

3 Nvidia Quadro 472.12 WHQL: support of OpenGL 4.6, OpenCL 1.2 for Kepler.[35]

4 Nvidia Quadro 496.13 WHQL: support of OpenGL 4.6, OpenCL 3.0 for Maxwell, Pascal & Volta.[36]

5 OpenCL 1.1 is available for Tesla-Chips,[142] OpenCL 1.0 for some Cards with G8x, G9x and GT200 by MAC OS X[143]

Quadro RTX/RTX series (With Ray tracing)[edit]

  • Turing (TU10x) microarchitecture
  • Ampere (GA10x) microarchitecture

[172][173][174][175]

Desktop AGP[edit]

  • Architecture Celsius (NV1x): DirectX 7, OpenGL 1.2 (1.3)
  • Architecture Kelvin (NV2x): DirectX 8 (8.1), OpenGL 1.3 (1.5), Pixel Shader 1.1 (1.3)
  • Architecture Rankine (NV3x): DirectX 9.0a, OpenGL 1.5 (2.1), Shader Model 2.0a
  • Architecture Curie (NV4x): DirectX 9.0c, OpenGL 2.1, Shader Model 3.0
Quadro_AGP
Model
Launch Core Core clock
Memory clock
(effective)
Memory size
Memory type Memory
bandwidth
Interface AGP 3-pin
stereo
connector
Monitor Output Near GeForce Model Notes
UnitsMHzMHzMBGiB/s
Quadro[176]2000-01-01NV10GL (Celsius)13516632128-bit SDR2.66No1x VGAGeForce 256
Quadro2 Pro[177]2000-07-25NV15GL25040064128-bit DDR6.4NoDVI, VGA, S-VideoGeForce 2 GTS
Quadro2 MXR[178]2000-07-25NV11GL20018332128-bit SDR2.93No1x VGAGeForce 2 MX/400
Quadro2 MXR LP[179]2000-07-25NV11GL20018332128-bit SDR2.934xNo1x VGAGeForce 2 MX/400
Quadro DCC[180]2001-03-14NV20GL (Kelvin)20023064128-bit DDR7.3NoDVI, VGA, S-VideoGeForce 3/Ti
Quadro4 380 XGL[181]2002-11-12NV18GL27551364128-bit DDR8.2NoDVI, VGA, S-VideoGeForce 4 MX 440 (AGP 8×)
Quadro4 500 XGL[182]2002-02-19NV17GL250166128128-bit SDR2.664 xNoDVIGeForce 4 MX 420
Quadro4 550 XGL[183]2002-02-19NV17GL27040064128-bit DDR6.4NoDVIGeForce 4 MX 440
Quadro4 580 XGL[184]2002-11-12NV18GL30040064128-bit DDR6.4NoDVIGeForce 4 MX 440 (AGP 8×)
Quadro4 700 XGL[185]2002-02-19NV25GL27555064128-bit DDR7.2No2x DVI, S-VideoGeForce 4 Ti 4200
Quadro4 750 XGL[186]2002-02-19NV25GL275550128128-bit DDR7.2Yes2x DVI, S-VideoGeForce 4 Ti 4400
Quadro4 780 XGL[187]2002-11-12NV28GL275550128128-bit DDR8.84xYes2x DVI, S-VideoGeForce 4 Ti 4200 (AGP 8×)
Quadro4 900 XGL[188]2002-02-19NV25GL300650128128-bit DDR10.4Yes2x DVI, S-VideoGeForce 4 Ti 4600
Quadro4 980 XGL[189]2002-11-12NV28GL300650128128-bit DDR10.4Yes2x DVI, S-VideoGeForce 4 Ti 4800
Quadro FX 500[190]2003-05-21NV34GL (Rankine)270243128128-bit DDR7.7NoDVI, VGAGeForce FX 5200
Quadro FX 700[191]2004-03-17NV31GL275275128128-bit DDR8.8NoDVI, VGAGeForce FX 5600
Quadro FX 1000[192]2003-01-21NV30GL300600128128-bit GDDR29.6Yes2x DVI, S-VideoGeForce FX 5800
Quadro FX 1100[193]2004-04-01NV36GL425325128128-bit DDR10.4Yes2x DVI, S-VideoGeForce FX 5700
Quadro FX 2000[194]2003-01-21NV30GL400400128128-bit GDDR212.8Yes2x DVI, S-VideoGeForce FX 5800
Quadro FX 3000[195]2003-07-22NV35GL400425256256-bit DDR27.2Yes2x DVI, S-VideoGeForce FX 5900
Quadro FX 3000G[196]2003-07-22NV35GL400425256256-bit DDR27.2Yes2x DL-DVI (via external controller), S-VideoGeForce FX 5900has external stereo frame sync connector
Quadro FX 4000[50]2004-04-01NV40GL375500256256-bit GDDR332.0Yes2x Dual-link DVI, S-VideoGeForce 6800 GT2nd link using external TMDS transmitter
Quadro FX 4000 SDI[51]2004-04-19NV40GL (Curie)375500256256-bit GDDR332.0YesDVI, 2x SDI HDTVGeForce 6800 GTwith digital and analog genlock (using external controllers)

Desktop PCI[edit]

  • Architecture Rankine (NV3x): DirectX 9.0a, OpenGL 1.5 (2.1), Shader Model 2.0a
Quadro
PCI Model
Launch Core Core clock
(MHz)
Memory clock
(effective) (MHz)
Memory size
(MB)
Memory type Memory
bandwidth
(GB/s)
3-pin
stereo
connector
Monitor Output Notes
Quadro FX 600 PCI[197]2004-03-17NV34GL (Rankine)270480128128-bit DDR7.8Yes2x DVI, S-Videoalso GeForce 5200 Ultra

For business NVS[edit]

The Nvidia Quadro NVS graphics processing units (GPUs) provide business graphics solutions for manufacturers of small, medium, and enterprise-level business workstations. The Nvidia Quadro NVS desktop solutions enable multi-display graphics for businesses such as financial traders.

  • Architecture Celsius (NV1x): DirectX 7, OpenGL 1.2 (1.3)
  • Architecture Kelvin (NV2x): DirectX 8 (8.1), OpenGL 1.3 (1.5), Pixel Shader 1.1 (1.3)
  • Architecture Rankine (NV3x): DirectX 9.0a, OpenGL 1.5 (2.1), Shader Model 2.0a
  • Architecture Curie (NV4x): DirectX 9.0c, OpenGL 2.1, Shader Model 3.0
  • Architecture Tesla (G80+): DirectX 10.0, OpenGL 3.3, Shader Model 4.0, CUDA 1.0 or 1.1, OpenCL 1.1
  • Architecture Tesla 2 (GT2xx): DirectX 10.1, OpenGL 3.3, Shader Model 4.1, CUDA 1.2 or 1.3, OpenCL 1.1
  • Architecture Fermi (GFxxx): DirectX 11.0, OpenGL 4.6, Shader Model 5.0, CUDA 2.x, OpenCL 1.1
  • Architecture Kepler (GKxxx): DirectX 11.2, OpenGL 4.6, Shader Model 5.0, CUDA 3.x, OpenCL 1.2, Vulkan 1.1
  • Architecture Maxwell 1 (GM1xx): DirectX 12.0, OpenGL 4.6, Shader Model 5.0, CUDA 5.0, OpenCL 1.2, Vulkan 1.1
Quadro
NVS model
Launch Max. resolution
(digital)
Interface Display connectors Displays
supported
Power
consumption
Core Notes
UnitsWatt
Quadro NVS 50[198]2005-05-311600×1200AGP 8× / PCIDVI-I, S-Video110NV18 (Celsius)OpenGL 1.3, DirectX 8.0
Quadro4 NVS 100[199][200]2003-12-222048×1536AGP 4× / PCI1x DVI-I, VGA, S-Video210NV17(A3)
Quadro NVS 200[201]2003-12-221280×1024AGP 4× / PCILFH-60211NV17
Quadro NVS 210s[202]2003-12-221720×1200Onboard (nForce 430)DVI + VGA?11MCP51no PureVideoHD, only SD
Quadro NVS 280 (PCI)[203]2003-10-281600×1200PCIDMS-59212NV34 A1
Quadro NVS 280 (AGP, PCIe)[204][205]2004-05-251600×1200PCI-E ×16 / AGP 8×DMS-59212NV34 A1
Quadro NVS 285[206]2006-06-061920×1200PCI-Express ×1/×16DMS-59213/18NV44
Quadro NVS 290[207]2007-10-041920×1200PCI-Express ×1/×16DMS-59221G86Tesla based
Quadro NVS 295[208]2009-05-072560×1600PCI-Express ×1/×162× DisplayPort or 2× DVI-D223G98Tesla based
Quadro NVS 400[209]2004-07-161280×1024PCI2× DMS-594182× NV17 A3
Quadro NVS 420[210]2009-01-202560×1600PCI-Express ×1/×16VHDCI (4× DisplayPort or 4× DVI-D)4402× G98
Quadro NVS 440[211]2009-03-091920×1200PCI-Express ×1/×162× DMS-594312× NV43
Quadro NVS 450[212]2008-11-112560×1600PCI-Express ×164× DisplayPort4352× G98
NVS 300[213]2011-01-082560×1600PCI-Express ×1/×16DMS-59217.5GT218Tesla 2 based
NVS 310[214]2012-06-262560×1600PCI-Express ×162× DisplayPort219.5GF119Fermi based (GeForce 510)
NVS 315[215]2013-03-102560×1600PCI-Express ×16DMS-59219.5GF119
NVS 510[216]2012-10-233840×2160PCI-Express 2.0 ×164× Mini-DisplayPort435GK107Kepler-based
NVS 810[217]2015-11-044096×2160 ([email protected] Hz, [email protected] Hz)PCI-Express 3.0 ×168× Mini-DisplayPort8682× GM107Maxwell based

Mobile applications[edit]

Quadro FX M (without Vulkan)[edit]

  • Architecture Rankine (NV3x), Curie (NV4x, G7x) and Tesla (G80+, GT2xx)
Quadro FX M Model Launch YYYY-MM-dd Core Fab Bus
interface
Core
clock
Shader
clock
Memory
clock
Config core Fillrate Memory Bus
width
Processing
Power (GFLOPs)
API support TDP
Pixel Texture Size Band-
with
Type Single
precision
Double
precision
DirectXOpenGLCUDA
Compute
Capability
OpenCLVulkan
UnitsnmMHzMHzMHzGP/sGT/sMBGB/sbitWatt
Quadro FX Go 540[218]2004-08-09NV43GL110MXM-II 300300550 4:8:8:8 2.42.4 1288.8GDDR3128 No 9.0c2.1 NoNo 42
Quadro FX Go 700[219]2003-06-25NV31GLM130AGP 4x 295295590 3:4:4:4 1.181.18 1289.44DDR3128 9.0a2.1 unknown
Quadro FX Go 1000[220]2005-02-25NV36GLM130AGP 4x 295295570 3:4:4:4 1.181.18 1289.12DDR3128 9.0a2.1 unknown
Quadro FX Go 1400[221]2005-02-25NV41GLM110MXM-III 275275590 5:8:8:8 2.22.2 25618.88DDR3256 9.0c2.1 unknown
Quadro FX 350M[222]2006-03-13 G72GLM (Curie) 90 PCI-E 1.0 ×16 450450900 3:4:4:2 0.91.8 25614.4GDDR3128 9.0c2.1 15
Quadro FX 360M[223]2007-05-09 G86GLM (Tesla) 80 PCI-E 1.0 ×16 400 800 1200 16:8:4:2 1.6 3.2 256 9.6 GDDR2 64 25.6 10 3.3 1.1 1.1 17
Quadro FX 370M[224]2008-08-15 G98GLM (Tesla) 65 PCI-E 2.0 ×16 550 1400 1200 8:4:4:1 2.2 2.2 256 9.6 GDDR3 64 22.4 10 3.3 1.1 1.1 20
Quadro FX 380M[225]2010-01-07 GT218GLM (Tesla 2) 40 PCI-E 2.0 ×16 625 1530 1600 16:8:4:2 2.4 4.8 512 12.6 GDDR3 64 47.0 No, only GT200 1/8 of SP 10.1 3.3 1.2 1.1 25
Quadro FX 550M[226]2006-03-13 G73GLM (Curie) 90 PCI-E 1.0 ×16 480 480 1000 5:12:12:8 4 6 512 19.2 GDDR3 128 No 9.0c 2.1 No 35
Quadro FX 560M[227]2006-03-13 G73GLM (Curie) 90 PCI-E 1.0 ×16 500 500 1200 5:12:12:8 4 6 512 19.2 GDDR3 128 9.0c 2.1 35
Quadro FX 570M[228]2007-06-01 G84GLM (Tesla) 80 PCI-E 1.0 ×16 475 950 1400 32:16:8:2 3.8 7.6 512 22.4 GDDR3 128 60.8 10 3.3 1.1 1.1 45
Quadro FX 770M[229]2008-08-14 G96GLM (Tesla) 65 PCI-E 2.0 ×16 500 1250 1600 32:16:8:2 4 8 512 25.6 GDDR3 128 80 10 3.3 1.1 1.1 35
Quadro FX 880M[230]2010-01-07 GT216GLM (Tesla 2) 40 PCI-E 2.0 ×16 550 1210 1600 48:16:8:2 4.4 8.8 1024 25.6 GDDR3 128 116 No, only GT200 1/8 of SP 10.1 3.3 1.2 1.1 35
Quadro FX 1500M[231]2006-04-18 G71GLM 90 PCI-E 1.0 ×16 375 375 1000 8:24:24:16 6 9 512 32 GDDR3 256 No 9.0c 2.1 No 45
Quadro FX 1600M[232]2007-06-01 G84GLM 80 PCI-E 1.0 ×16 625 1250 1600 32:16:8:2 5 10 512 25.6 GDDR3 128 80 10 3.3 1.1 1.1 50
Quadro FX 1700M[233]2008-10-01 G96GLM 65 PCI-E 2.0 ×16 625 1550 1600 32:16:8:2 5 10 512 25.6 GDDR3 128 99.2 10 3.3 1.1 1.1 50
Quadro FX 1800M[234]2009-06-15 GT215GLM 40 PCI-E 2.0 ×16 450 1080 1600
2200
72:24:8:3 3.6 10.8 1024 25.6
35.2
GDDR3
GDDR5
128 162 No, only GT200 1/8 of SP 10.1 3.3 1.2 1.1 45
Quadro FX 2500M[235]2005-09-29 G71GLM 90 PCI-E 1.0 ×16 500 500 1200 8:24:24:16 8 12 512 38.4 GDDR3 256 No 9.0c 2.1 No 45
Quadro FX 2700M[236]2008-08-14 G94GLM 65 PCI-E 2.0 ×16 530 1325 1600 48:24:16:3 8.48 12.72 512 51.2 GDDR3 256 127 10 3.3 1.1 1.1 65
Quadro FX 2800M[237]2009-12-01 G92GLM 55 PCI-E 2.0 ×16 500 1250 2000 96:48:16:6 8 16 1024 64 GDDR3 256 288 10 3.3 1.1 1.1 75
Quadro FX 3500M[238]2007-03-01 G71GLM 90 PCI-E 1.0 ×16 575 575 1200 8:24:24:16 9.2 13.8 512 38.4 GDDR3 256 9.0c 2.1 No 45
Quadro FX 3600M[239]2008-02-23 G92GLM 65 PCI-E 2.0 ×16 500 1250 1600 64:32:16:4
96:48:16:6
8
8
16
24
1024 51.2 GDDR3 256 160
240
10 3.3 1.1 1.1 70
Quadro FX 3700M[240]2008-08-14 G92GLM 65 PCI-E 2.0 ×16 550 1375 1600 128:64:16:8 8.8 35.2 1024 51.2 GDDR3 256 352 10 3.3 1.1 1.1 75
Quadro FX 3800M[241]2008-08-14 G92GLM 55 PCI-E 2.0 ×16 675 1688 2000 128:64:16:8 10.8 43.2 1024 64 GDDR3 256 422 10 3.3 1.1 1.1 100

Quadro NVS M[edit]

  • Architecture Curie (NV4x, G7x): DirectX 9.0c, OpenGL 2.1, Shader Model 3.0
  • Architecture Tesla (G80+): DirectX 10.0, OpenGL 3.3, Shader Model 4.0, CUDA 1.0 or 1.1, OpenCL 1.1
  • Architecture Tesla 2 (GT2xx): DirectX 10.1, OpenGL 3.3, Shader Model 4.1, CUDA 1.2 or 1.3, OpenCL 1.1
  • Architecture Fermi (GFxxx): DirectX 11.0, OpenGL 4.6, Shader Model 5.0, CUDA 2.x, OpenCL 1.1
  • Architecture Kepler (GKxxx): DirectX 11.2, OpenGL 4.6, Shader Model 5.0, CUDA 3.x, OpenCL 1.2, Vulkan 1.1
  • Architecture Maxwell 1 (GM1xx): DirectX 12.0, OpenGL 4.6, Shader Model 5.0, CUDA 5.0, OpenCL 1.2, Vulkan 1.1
Quadro NVS Mobile Launch Core Core clock
speed
Memory
clock speed
Memory size Memory
type
Memory
bandwidth
CUDA
cores
Max.
power
Interface 3-pin
stereo
connector
Note
UnitsMHzMHzMBGB/sWatt
Quadro NVS 110M[242]2006-06-01G72M300600128 / 256 / 51264-bit DDR4.80no10PCIe 1.0 ×16VariesGo 7300 based
Quadro NVS 120M[243]2006-06-01G72GLM450700128 / 256 / 51264-bit DDR211.2no10MXM-IIIVariesQuadro FX 350M/Go 7400 based
Quadro NVS 130M[244]2007-05-09G86M400400128 / 25664-bit6.41610PCIe 2.0 ×16Varies8400M based
Quadro NVS 135M[245]2007-05-09G86M400600128 / 25664-bit9.551610PCIe 2.0 ×16Varies8400M GS based
Quadro NVS 140M[246]2007-05-09G86M400700128 / 256 / 51264-bit9.61610PCIe 2.0 ×16Varies8500M GT based
Quadro NVS 150M[247]2008-08-15G98M530700128 / 25664-bit11.22810MXM-IVaries9200M GS based
Quadro NVS 160M[248]2008-08-15G98M58070025664-bit11.22812MXM-IVaries9300M GS based
NVS 2100M[249]2010-01-07GT218535160051264-bit GDDR312.81612PCIe 2.0 ×16VariesGeForce G 305M based
Quadro NVS 300M[250]2006-05-24G73GLM450500128 / 256 / 512128-bit GDDR316.16no16PCIe 1.0 ×16VariesGo 7600 based
Quadro NVS 320M[251]2007-06-09G84M575700128 / 256 / 512128-bit GDDR322.553220MXM-HEVaries8700M based
NVS 3100M[252]2010-01-07GT218600160051264-bit GDDR312.81614PCIe 2.0 ×16VariesGeForce G 210M/310M based
NVS 4200M[253]2011-02-11GF1198101600102464-bit DDR312.84825MXMVariesGeForce 410M based
Quadro NVS 510M[254]2006-08-21G71GLM500600256 / 512 256-bit GDDR338.4no35PCI ExpressVariesGo 7900 GTX based
Quadro NVS 5100M[255]2010-01-07GT21655016001024128-bit GDDR325.64835MXM-A 3.0VariesGeForce GT 330M/Quadro FX 880M based
NVS 5200M[256]2012-06-01GF1176251800102464-bit DDR314.49625MXMVariesGeForce 710M/GT 620M based
NVS 5400M[257]2012-06-01GF10866018001024128-bit DDR328.89635MXMVariesGeForce GT 630M/Quadro 1000M based

Quadro M[edit]

  • Architecture Fermi, Kepler,[258] Maxwell,[259] Pascal
  • Fermi, Kepler, Maxwell, Pascal can do OpenGL 4.6 with actual Driver 381+ for Linux or 390+ for windows[86]
  • All can do Double Precision with compute Capability 1.3 and higher
  • Vulkan 1.0 and 1.1 with Kepler and later
  • Quadro 5000M has 2048MB of VRAM, of which 1792MB is usable with ECC enabled.
Model Launch Core Fab Bus
interface
Core
clock
Shader
clock
Memory
clock effective
Config core Fillrate Memory Bus
width
Processing
Power (GFLOPs)
API support TDP
Pixel Texture Size Band-
with
Type Single
precision
Double
precision
DirectXOpenGLCUDA
Compute
Capability
OpenCLVulkan
UnitsnmMHzMHzMHzGP/sGT/sMBGB/sbitWatt
Quadro 1000M[260][261]2011-01-13GF108GLM40 PCI-E 2.0 ×16 70014001800 96:16:4:4 5.611.2 204828.8DDR3128 269 1/12 of SP 114.62.11.1No 45
Quadro 2000M[262]2011-01-13GF106GLM40 PCI-E 2.0 ×16 55011001800 192:32:16:4 4.417.6 204828.8DDR3128 422 1/12 of SP 114.62.11.1No 55
Quadro 3000M[263]2011-02-22GF104GLM40 MXM-B (3.0) 4509002500 240:40:32:5 4.518 204880GDDR5256 432 1/12 of SP 114.62.11.1No 75
Quadro 4000M[264]2011-02-22GF104GLM40 PCI-E 2.0 ×16 4759502400 336:56:32:7 6.6526.6 204880GDDR5256 638 1/12 of SP 114.62.11.1No 100
Quadro 5000M[265]2010-07-27GF100GLM40 PCI-E 2.0 ×16 4058102400 320:40:32:10 8.1016.2 204876.8GDDR5256 518 1/2 of SP 114.62.01.1No 100
Quadro 5010M[266]2011-02-22GF110GLM40 PCI-E 2.0 ×16 4509002600 384:48:32:12 10.821.6 409683.2GDDR5256 691 114.62.0 100
Quadro K500M[267]2012-06-01GK10728MXM-A (3.0) 8508501800 192:16:8:1 3.413.6 102412.8DDR364 326 1/24 of SP 11.24.63.01.21.1 35
Quadro K510M[268]2013-07-23GK20828 MXM-A (3.0) 846 846 2400 192:16:8:1 3.4 13.5 102419.2 GDDR564 325 11.24.63.5 30
Quadro K610M[269]2013-07-23GK20828 PCI-E 2.0 ×8 9809802600 192:16:8:1 3.915.7 102420.8GDDR564 376 11.24.63.5 30
Quadro K1000M[270]2012-06-01GK107GL28 PCI-E 3.0 ×16 8508501800 192:16:16:1 3.413.6 204828.8DDR3128 326 1/24 of SP 11.24.63.01.21.1 45
Quadro K1100M[271]2013-07-23GK107GL28 PCI-E 3.0 ×16 7067062800 384:32:16:2 5.6522.6 204844.8GDDR5128 542 11.24.63.0 45
Quadro K2000M[272]2012-06-01GK10728 mxm-a 7459001800 384:32:16:2 5.9623.84 204828.8DDR3128 572 1/24 of SP 11.24.63.01.21.1 55
Quadro K2100M[273]2013-07-23GK10628 PCI-E 3.0 ×16 6677503000 576:48:16:3 8.032.0 204848.0GDDR5128 768 11.24.63.0 55
Quadro K3000M[274]2012-06-01GK10428 PCI-E 3.0 ×16 6546542800 576:48:32:3 7.8531.4 204889.6GDDR5256 753 1/24 of SP 11.24.63.01.21.1 75
Quadro K3100M[275]2013-07-23GK10428 PCI-E 3.0 ×16 6836833200 768:64:32:4 11.345.2 4096102.4GDDR5256 1084 11.24.63.0 75
Quadro K4000M[276]2012-06-01GK10428 PCI-E 3.0 ×16 6006002800 960:80:32:5 12.048.1 409689.6GDDR5256 1154 1/24 of SP 11.24.63.01.21.1 100
Quadro K4100M[277]2013-07-23GK10428 PCI-E 3.0 ×16 7067063200 1152:96:32:6 16.967.8 4096102.4GDDR5256 1627 11.24.63.0 100
Quadro K5000M[278]2012-08-07GK10428 PCI-E 3.0 ×16 7067063000 1344:112:32:7 16.867.3 409696.0GDDR5256 1615 1/24 of SP 11.24.63.01.21.1 100
Quadro K5100M[279]2013-07-23GK10428 PCI-E 3.0 ×16 7717713600 1536:128:32:8 24.798.7 8192115.2GDDR5256 2368 11.24.63.0 100
Quadro M500M[280]2016-04-27GM10828 PCI-E 3.0 ×16 102911241800 384:32:16:2 8.216.5 204814.4DDR364 729 1/32 of SP 12.04.65.0 30
Quadro M520[281][282]2017-01-11 GM108 28 MXM-A (3.0) 1041 ? 5012 384:16:8:2 8.3 16.7 2048 40.1 GDDR5 64 799 12.04.65.0 25
Quadro M600M[283]2015-08-18GM10728 PCI-E 3.0 ×16 102911245000 384:32:16:2 8.216.5 204880GDDR5128 790 12.04.65.0 30
Quadro M620[281][284]2017-01-11 GM107 28 MXM-A (3.0) 977 ? 5012 512:32:16:4 16.6 31.3 2048 80.2 GDDR5 128 1000 12.04.65.0 30
Quadro M1000M[285]2015-08-18GM10728 PCI-E 3.0 ×16 100012505000 512:32:16:4 15.931.8 409680.2GDDR5128 1017 12.04.65.0 55
Quadro M1200[281][286]2017-01-11 GM107 28 MXM-A (3.0) 1093 ? 5000 640:40:32:5 35.0 43.7 4096 80.2 GDDR5 128 1399 12.04.65.0 45
Quadro M2000M[287]2015-12-03GM10728 MXM-A (3.0) 102910295000 640:40:32:5 32.941.2 409680GDDR5128 1317 12.04.65.0 55
Quadro M2200[281][288]2017-01-11 GM206 28 MXM-A (3.0) 1025 ? 5500 1024:64:32:8 32.8 65.6 4096 88 GDDR5 128 2099 12.14.65.2 55
Quadro M3000M[289]2015-08-18GM20428 PCI-E 3.0 ×16 54010805000 1024:64:32:8 17.334.6 4096160GDDR5256 1106 12.14.65.2 55
Quadro M4000M[290]2015-08-18GM20428 PCI-E 3.0 ×16 97512505000 1280:80:64:10 62.478.0 4096160.4GDDR5256 2496 12.14.65.2 100
Quadro M5000M[291]2015-08-18GM20428 PCI-E 3.0 ×16 97512505000 1536:96:64:12 62.493.6 8192160GDDR5256 2995 12.14.65.2 100
Quadro M5500[292]2016-04-16GM20428 PCI-E 3.0 ×16 86117507000 2048:128:64:16 55.1110 8192160GDDR5256 3527 12.14.65.2 150
Quadro P500[293][294]2018-01-05 GP108 14 1455 5012 256:16:16 24.3 24.3 2048 40 GDDR5 64 777 12.1 4.6 6.1 18
Quadro P600[295][294]2017-02-07 GP107 14 1430 5012 384:24:16 24.9 37.4 4096 80 GDDR5 128 1196 12.1 4.6 6.1 25
Quadro P1000[296][294]2017-02-07 GP107 14 1303 6008 512:32:16 23.9 47.8 4096 96 GDDR5 128 1529 12.1 4.6 6.1 40
Quadro P2000[297][294]2017-02-06 GP107 14 1557 6008 768:64:32 51.4 77.1 4096 96 GDDR5 128 2468 12.1 4.6 6.1 50
Quadro P3000[298][281]2017-01-11GP10416 MXM-B 3.0 ×16 121012107012 1280:80:32:10 38.796.8 6144168GDDR5192 3098 12.14.66.1 75
Quadro P3200[299][294]2018-02-21 GP104 16 1328 7012 1792:112:64 98.8 172.8 6144 168 GDDR5 192 5530 12.1 4.6 6.1 75
Quadro P4000[300][281]2017-01-11GP10416 MXM-B 3.0 ×16 122712277012 1792:112:64:14 78.5137.4 8192192.3GDDR5256 4398 12.14.66.1 100
Quadro P4200[301][294]2018-02-21 GP104 16 MXM-B 3.0 ×16 1227 1227 6008 2304:144:64:18 105.4 237.2 8192 192.3 GDDR5 256 7589 12.1 4.6 6.1 100
Quadro P5000[302][281]2017-01-11GP10416 MXM-B 3.0 ×16 151315136012 2048:128:64:16 96.8193.7 16384192.3GDDR5256 6197 12.14.66.1 100
Quadro P5200[303][294]2018-02-21 GP104 16 MXM-B 3.0 ×16 1556 1556 7200 2560:160:64:20 111.7 279.4 16384 230.4 GDDR5 256 8940 12.1 4.6 6.1 100
Quadro Model Launch Core Fab
(nm)
Bus
interface
Core
clock
(MHz)
Shader
clock
(MHz)
Memory
clock
(MHz)
Config core Fillrate Memory Bus
width (bit)
Processing
Power (GFLOPs)
API support TDP (watts)
Pixel
(GP/s)
Texture
(GT/s)
Size
(GB)
Band-
with (GB/s)
Type Single
precision
Double
precision
DirectXOpenGLCUDA
Compute
Capability
OpenCLVulkan

Quadro RTX[edit]

  • Turing, Ampere microarchitecture

NVENC and NVDEC support matrix[edit]

HW accelerated encode and decode are supported on NVIDIA Quadro products with Fermi, Kepler, Maxwell and Pascal generation GPUs.[313]

Board Family Chip Server/
Desktop/
Mobile
# of
NVENC/chip
Max # of
concurrent sessions
H.264 (AVCHD) YUV 4:2:0 H.264 (AVCHD) YUV 4:4:4 H.264 (AVCHD) Lossless H.265 (HEVC) 4K YUV 4:2:0 H.265 (HEVC) 4K YUV 4:4:4 H.265 (HEVC) 4K Lossless H.265 (HEVC) 8k HEVC B Frame support
Quadro K420 / K600 KeplerGK107D13YesNoNoNoNoNoNoNo
Quadro K2000 / K2000D KeplerGK107D1UnrestrictedYesNoNoNoNoNoNoNo
Quadro K2100 > K5100 KeplerGK106M1UnrestrictedYesNoNoNoNoNoNoNo
Quadro K4000 KeplerGK106D1UnrestrictedYesNoNoNoNoNoNoNo
Quadro K100 > K2000 + K5100 KeplerGK104M1UnrestrictedYesNoNoNoNoNoNoNo
Quadro K4200 / K5000 KeplerGK104D1UnrestrictedYesNoNoNoNoNoNoNo
Quadro K5200 / K6000 Kepler (2nd Gen)GK110BD1UnrestrictedYesNoNoNoNoNoNoNo
Quadro K620 / K1200 Maxwell (1st Gen)GM107D13YesYesYesNoNoNoNoNo
Quadro K2200 Maxwell (1st Gen)GM107D1UnrestrictedYesYesYesNoNoNoNoNo
Quadro M500 / M520 Maxwell (1st Gen)GM108M0n/aNoNoNoNoNoNoNoNo
Quadro M600 / M620 Maxwell (1st Gen)GM107M1UnrestrictedYesYesYesNoNoNoNoNo
Quadro M1000 / M1200 / M2000 Maxwell (1st Gen)GM107M1UnrestrictedYesYesYesNoNoNoNoNo
Quadro M2000 Maxwell (GM206)GM206D1UnrestrictedYesYesYesYesNoNoNoNo
Quadro M2200 Maxwell (GM206)GM206M1UnrestrictedYesYesYesYesNoNoNoNo
Quadro M3000 / M4000 / M5500 Maxwell (2nd Gen)GM204M2UnrestrictedYesYesYesYesNoNoNoNo
Quadro M4000 / M5000 Maxwell (2nd Gen)GM204D2UnrestrictedYesYesYesYesNoNoNoNo
Quadro M6000 Maxwell (2nd Gen)GM200D2UnrestrictedYesYesYesYesNoNoNoNo
Quadro P500 / P520 PascalGP108M13NoNoNoNoNoNoNoNo
Quadro P400 PascalGP107D13YesYesYesYesYesYesYesNo
Quadro P600 / P620/ P1000 PascalGP107D/M13YesYesYesYesYesYesYesNo
Quadro P2000 PascalGP107M1UnrestrictedYesYesYesYesYesYesYesNo
Quadro P2000 / P2200 PascalGP106D1UnrestrictedYesYesYesYesYesYesYesNo
Quadro P3200 / P4200 / P5200 PascalGP104M2UnrestrictedYesYesYesYesYesYesYesNo
Quadro P4000 PascalGP104D1UnrestrictedYesYesYesYesYesYesYesNo
Quadro P5000 PascalGP104D2UnrestrictedYesYesYesYesYesYesYesNo
Quadro P6000 PascalGP102D2UnrestrictedYesYesYesYesYesYesYesNo
Quadro GP100 PascalGP100D3UnrestrictedYesYesYesYesYesYesNoNo
Quadro GV100 VoltaGV100D3UnrestrictedYesYesYesYesYesYesYesNo
Quadro T1000 TuringTU117M13YesYesYesYesYesYesYesYes
Quadro T2000 TuringTU117M1UnrestrictedYesYesYesYesYesYesYesYes
Quadro RTX 3000 TuringTU106M1UnrestrictedYesYesYesYesYesYesYesYes
Quadro RTX 5000/RTX 4000 TuringTU104D/M1UnrestrictedYesYesYesYesYesYesYesYes
Quadro RTX 6000/RTX 8000 TuringTU102D1UnrestrictedYesYesYesYesYesYesYesYes
Board Family Chip Desktop/
Mobile/
Server
# Of Chips # Of NVDEC
/Chip
Total # of NDEC MPEG-1 MPEG-2 VC-1 VP8 VP9 H.264
(AVCHD)
H.265 (HEVC) 4:2:0 H.265 (HEVC) 4:4:4
8 bit 10 bit 12 bit 8 bit 10 bit 12 bit 8 bit 10 bit 12 bit
Quadro K420 / K600 KeplerGK107D111YesYesYesNoNoNoNoYesNoNoNoNoNoNo
Quadro K2000 / K2000D KeplerGK107D111YesYesYesNoNoNoNoYesNoNoNoNoNoNo
Quadro K2100 > K5100 KeplerGK106M111YesYesYesNoNoNoNoYesNo
Sours: https://en.wikipedia.org/wiki/Quadro


13444 13445 13446 13447 13448