This page contains one table listing key attributes of general purpose desktop GPU of Nvidia and AMD (ATI). It includes representative GPU products for each architecture but not mean to be comprehensive.
The table is Sortable by clicking a column heading in the top row. Clicking once, the table will be sorted from low to high, and clicking twice, the table will be sorted from high to low.
| Year | Graphics Card | GPU Name | Fab Process (nm) |
SM Count (SIMD) |
Stream Processors | Architecture | Company |
|---|---|---|---|---|---|---|---|
| 2006 | GeForce 8800 Ultra | G80 | 90 | 16 | 128 | Tesla | Nvidia |
| 2006 | GeForce 8800 GTX | G80 | 90 | 16 | 128 | Tesla | Nvidia |
| 2006 ? | GeForce 8800 GTS | G92 | 90 | 12 | 96 | Tesla | Nvidia |
| 2007 | GeForce 8800 GT | G92 | 65 | 14 | 112 | Tesla | Nvidia |
| 2008 | GeForce GTX 280 | GT200 | 65 | 10 | 240 | Tesla | Nvidia |
| 2010 | GeForce GTX 480 | GF100 | 40 ? | 14 | 448 | Fermi | Nvidia |
| 2010 | GeForce GTX 570 | GF110 | 40 | 15 | 480 | Fermi | Nvidia |
| 2010 | GeForce GTX 580 | GF110 | 40 | 16 | 512 | Fermi | Nvidia |
| 2012 | GeForce GTX 670 | GK104 | 28 | 7 | 1344 | Kepler | Nvidia |
| 2012 | GeForce GTX 680 | GK104 | 28 | 8 | 1536 | Kepler | Nvidia |
| 2013 | GeForce GTX 770 | GK104 | 28 | 8 | 1536 | Kepler | Nvidia |
| 2013 | GeForce GTX 780 | GK110 | 28 | 12 | 2304 | Kepler | Nvidia |
| 2013 | GeForce GTX 780 Ti | GK110 | 28 | 15 | 2880 | Kepler | Nvidia |
| 2014 | GeForce GTX 750 Ti | GM107 | 28 | 5 | 640 | Maxwell | Nvidia |
| 2014 | GeForce GTX 970 | GM204 | 28 | 13 | 1664 | Maxwell | Nvidia |
| 2014 | GeForce GTX 980 | GM204 | 28 | 16 | 2048 | Maxwell | Nvidia |
| 2015 | GeForce GTX 980 Ti | GM200 | 28 | 22 | 2816 | Maxwell | Nvidia |
| 2015 | GeForce GTX Titan X | GM200 | 28 | 24 | 3072 | Maxwell | Nvidia |
| 2016 | Tesla P100 | GP100 | 16 nm FinFET | 56 | 3360 | Pascal | Nvidia |
| 2007 | Radeon HD 2400 Pro | RV610 | 65 | 2 | 40 | TeraScale 1 | ATI |
| 2007 | Radeon HD 2600 XT | RV630 | 65 | 3 | 120 | TeraScale 1 | ATI |
| 2007 | Radeon HD 2900 XT | R60 PRO | 80 | 4 | 320 | TeraScale 1 | ATI |
| 2009 | Radeon HD 3410 | RV610 | 65 | 2 | 40 | TeraScale 1 | ATI |
| 2009 | Radeon HD 3610 | RV630 | 65 | 3 | 120 | TeraScale 1 | ATI |
| 2007 | Radeon HD 3870 | RV670 XT | 55 | 4 | 320 | TeraScale 1 | ATI |
| 2008 | Radeon HD 4350 | RV710 | 55 | 1 | 80 | TeraScale 1 | ATI |
| 2009 | Radeon HD 4870 | RV770 | 55 | 10 | 800 | TeraScale 1 | ATI |
| 2009 | Radeon HD 4890 | RV790 | 55 | 10 | 800 | TeraScale 1 | ATI |
| 2010 | Radeon HD 5450 | Cedar | 40 | 2 | 80 | TeraScale 2 (VLIW5) | ATI |
| 2009 | Radeon HD 5870 | Cypress | 40 | 20 | 1600 | TeraScale 2 (VLIW5) | ATI |
| 2011 | Radeon HD 6350 | Cedar PRO | 40 | 2 | 80 | TeraScale 3 (VLIW4) | AMD |
| 2011 | Radeon HD 6770 | Juniper XT | 40 | 10 | 800 | TeraScale 3 (VLIW4) | AMD |
| 2010 | Radeon HD 6970 | Cayman XT | 40 | 24 | 1536 | TeraScale 3 (VLIW4) | AMD |
| 2012 | Radeon HD 7450 | Caicos PRO | 40 | 2 | 160 | TeraScale 2 (VLIW5) | AMD |
| 2012 | Radeon HD 7670 | Turks XT | 40 | 6 | 480 | TeraScale 2 (VLIW5) | AMD |
| 2012 | Radeon HD 7970 | Tahiti XT | 28 | 128 | 2048 | GCN 1.0 | AMD |
| 2013 | Radeon HD 7730 | Cape Verde LE | 28 | 24 | 384 | GCN 1.0 | AMD |
| 2013 | Radeon HD 8350 | Cedar | 40 | 2 | 80 | TeraScale 2 (VLIW5) | AMD |
| 2013 | Radeon HD 8570 | Oland | 28 | 20 | 320 ? | GCN | AMD |
| 2013 | Radeon HD 8970 | Curacao XT | 28 | 160 | 2560 | GCN | AMD |
| 2013 | Rdeon R7 240 | Oland | 28 | 20 | 320 | GCN 1.0 | AMD |
| 2014 | Radeon R9 280 | Tahiti | 28 | 112 | 1792 | GCN 1.0 | AMD |
| 2013 | Radeon R9 290X | Hawaii | 28 | 176 | 2816 | GCN 1.1 | AMD |
| 2014 | Radeon R9 285 | Tonga | 28 | 112 | 1792 | GCN 1.2 | AMD |
| 2015 | Radeon R9 390 | Grenada | 28 | 160 | 2560 | GCN 1.1 | AMD |
| 2015 | Radeon R9 Nano | Fiji | 28 | 256 | 4096 | GCN 1.2 | AMD |
| Year | Graphics Card | GPU Name | Fab Process (nm) |
SM Count (SIMD) |
Stream Processors | Architecture | Company |
*:The evolution of GPGPU architecture of Nvidia is: Tesla, Fermi, Kepler, Maxwell, Pascal.
†:The evolution of GPGPU architecture for AMD (ATI) is: TeraScale, Graphics Core Next (GCN). TeraScale has three iterations: TeraScale 1, TeraScale 2 (VLIW5) and TeraScale 3 (VLIW4). TeraScale2 is used in "Evergreen" series GPUs. GCN also has three iterations: GCN 1.0 (Southern Islands), GCN 1.1 (Sea Islands), GCN 1.2 (Volcanic Islands).
‡:The number of streaming processors is the number of unified shader units.
#:In TeraScale architecture, the SIMD number is equal to the number of compute unit. However, each compute unit in GCN architecture contains 4 SIMDs.
**:The data of AMD (ATI) GPU is from [1] and [2], while the data of Nvidia GPU mainly from [3] and [4] and whitepapers of the different architectures.
This page is maintained by members of the VLSI Computation Laboratory at UC Davis.
Last update: June 18, 2016