Report an Error

NVIDIA Tesla K20m

Graphics Processor
GK110
Cores
2496
TMUs
208
ROPs
40
Memory Size
5 GB
Memory Type
GDDR5
Bus Width
320 bit
GPU Chip
GPU
The Tesla K20m was an enthusiast-class professional graphics card by NVIDIA, launched on January 5th, 2013. Built on the 28 nm process, and based on the GK110 graphics processor, the card supports DirectX 12. The GK110 graphics processor is a large chip with a die area of 561 mm² and 7,080 million transistors. Unlike the fully unlocked GeForce GTX TITAN, which uses the same GPU but has all 2688 shaders enabled, NVIDIA has disabled some shading units on the Tesla K20m to reach the product's target shader count. It features 2496 shading units, 208 texture mapping units, and 40 ROPs. NVIDIA has paired 5 GB GDDR5 memory with the Tesla K20m, which are connected using a 320-bit memory interface. The GPU is operating at a frequency of 706 MHz, memory is running at 1300 MHz (5.2 Gbps effective).
Being a dual-slot card, the NVIDIA Tesla K20m draws power from 1x 6-pin + 1x 8-pin power connector, with power draw rated at 225 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla K20m is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 267 mm in length, and features a dual-slot cooling solution. Its price at launch was 3199 US Dollars.

Graphics Processor

GPU Name
GK110
Architecture
Kepler
Foundry
TSMC
Process Size
28 nm
Transistors
7,080 million
Density
12.6M / mm²
Die Size
561 mm²
Chip Package
BGA-2152

Graphics Card

Release Date
Jan 5th, 2013
Generation
Tesla Kepler
(Kxx)
Predecessor
Tesla Fermi
Successor
Tesla Maxwell
Production
End-of-life
Launch Price
3,199 USD
Bus Interface
PCIe 2.0 x16

Relative Performance

GeForce 210
3%
GeForce 9400 GT
4%
Radeon HD 4550
5%
Radeon HD 5450
6%
Radeon HD 6450
7%
GeForce GT 520
7%
GeForce GT 220
9%
GeForce GT 430
12%
Radeon HD 5570
12%
Radeon HD 4670
13%
GeForce GT 440
14%
GeForce GT 240
14%
GeForce 9600 GT
16%
Radeon HD 5670
17%
GeForce GT 640
18%
GeForce 9800 GT
19%
Radeon HD 6670
20%
Radeon HD 4830
21%
Radeon HD 4770
22%
Radeon HD 4850
23%
GeForce GTS 250
24%
GeForce GTS 450
24%
Radeon HD 5750
25%
Radeon HD 7750
29%
Radeon HD 5770
29%
GeForce GTX 260
29%
Radeon HD 4870
30%
Radeon Vega 8
30%
GeForce GTX 550 Ti
30%
GeForce GTX 650
30%
Radeon HD 5830
32%
Radeon HD 6790
34%
Radeon HD 4890
34%
GeForce GTX 460
36%
Radeon RX Vega 11
36%
GeForce GT 1030
36%
GeForce GTX 275
37%
Radeon HD 7770 GHz Edition
37%
GeForce GTX 280
37%
GeForce GTX 465
38%
Radeon HD 6850
39%
GeForce GTX 285
40%
Radeon HD 5850
43%
GeForce GTX 650 Ti
44%
Radeon HD 7790
44%
Radeon RX 550
46%
GeForce GTX 470
46%
Radeon HD 6870
47%
Radeon HD 5870
51%
GeForce GTX 560 Ti
52%
Radeon HD 4870 X2
53%
GeForce GTX 750 Ti
53%
Radeon HD 6950
54%
GeForce GTX 295
56%
GeForce GTX 650 Ti Boost
56%
Radeon HD 7850
57%
GeForce GTX 480
58%
Radeon HD 6970
60%
Radeon R7 265
62%
Radeon RX 460
63%
Radeon R7 370
63%
GeForce GTX 660
63%
GeForce GTX 570
63%
Radeon RX 560
64%
GeForce GTX 950
68%
Radeon HD 7870 GHz Edition
69%
Radeon R9 270X
70%
GeForce GTX 660 Ti
71%
GeForce GTX 580
71%
GeForce GTX 1050
72%
Radeon HD 7950
72%
GeForce GTX 1630
74%
Radeon HD 5970
74%
GeForce GTX 760
76%
GeForce GTX 670
81%
GeForce GTX 960
84%
Radeon R9 380
86%
Radeon R9 285
86%
Radeon HD 7970
87%
GeForce GTX 680
88%
GeForce GTX 1050 Ti
90%
GeForce GTX 770
92%
Radeon HD 6990
94%
Radeon R9 280X
97%
GeForce GTX 590
98%
Radeon HD 7970 GHz Edition
98%
Tesla K20m
100%
GeForce GTX 780
109%
Arc A380
109%
Radeon RX 6400
110%
GeForce GTX 1650
113%
Radeon RX 470
120%
Radeon R9 290
121%
Radeon RX 570
128%
Radeon R9 390
129%
Radeon R9 290X
130%
GeForce GTX 970
132%
GeForce GTX TITAN
134%
GeForce GTX 780 Ti
135%
Radeon R9 390X
137%
Radeon HD 7990
138%
Radeon RX 480
139%
GeForce GTX 690
140%
GeForce GTX 1060 6 GB
144%
Radeon RX 5500 OEM
146%
Radeon RX 580
147%
Radeon RX 5500 XT
148%
Radeon RX 6500 XT
150%
GeForce GTX 980
150%
GeForce GTX 1650 SUPER
152%
Radeon R9 FURY
152%
Radeon RX 590
159%
Radeon R9 295X2
168%
GeForce GTX 1660
168%
Radeon R9 FURY X
170%
GeForce GTX 980 Ti
173%
GeForce GTX TITAN X
178%
GeForce GTX 1660 SUPER
183%
GeForce GTX 1070
193%
GeForce GTX 1660 Ti
193%
GeForce RTX 3050 8 GB
196%
Radeon RX Vega 56
206%
GeForce GTX 1070 Ti
218%
Radeon RX 5600 XT
222%
Radeon RX Vega 64
225%
GeForce GTX 1080
228%
GeForce RTX 2060
228%
Radeon RX 5700
237%
Arc A580
238%
Radeon RX 6600
247%
GeForce RTX 2060 SUPER
256%
GeForce RTX 2070
259%
Radeon RX 5700 XT
259%
GeForce RTX 3060 12 GB
264%
Arc A750
273%
Radeon VII
274%
TITAN X Pascal
282%
Radeon RX 6600 XT
284%
GeForce GTX 1080 Ti
290%
Arc A770
293%
GeForce RTX 2070 SUPER
293%
Radeon RX 6650 XT
308%
Radeon RX 7600
312%
GeForce RTX 4060
313%
GeForce RTX 2080
315%
Radeon RX 7600 XT
322%
GeForce RTX 2080 SUPER
331%
GeForce RTX 3060 Ti
339%
Radeon RX 6700 XT
351%
Radeon RX 6750 XT
372%
GeForce RTX 4060 Ti 8 GB
376%
GeForce RTX 2080 Ti
379%
GeForce RTX 3070
397%
GeForce RTX 3070 Ti
424%
Radeon RX 7700 XT
429%
Radeon RX 6800
437%
GeForce RTX 4070
484%
Radeon RX 6800 XT
497%
GeForce RTX 3080
515%
Radeon RX 7800 XT
521%
Radeon RX 6900 XT
535%
GeForce RTX 4070 SUPER
562%
Radeon RX 7900 GRE
573%
GeForce RTX 3080 Ti
577%
Radeon RX 6950 XT
578%
GeForce RTX 3090
588%
GeForce RTX 4070 Ti
603%
GeForce RTX 4070 Ti SUPER
659%
Radeon RX 7900 XT
677%
GeForce RTX 3090 Ti
682%
GeForce RTX 4080
766%
GeForce RTX 4080 SUPER
778%
Radeon RX 7900 XTX
785%
GeForce RTX 4090
963%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
706 MHz
Memory Clock
1300 MHz
5.2 Gbps effective

Memory

Memory Size
5 GB
Memory Type
GDDR5
Memory Bus
320 bit
Bandwidth
208.0 GB/s

Render Config

Shading Units
2496
TMUs
208
ROPs
40
SMX Count
13
L1 Cache
16 KB (per SMX)
L2 Cache
1280 KB

Theoretical Performance

Pixel Rate
36.71 GPixel/s
Texture Rate
146.8 GTexel/s
FP32 (float)
3.524 TFLOPS
FP64 (double)
1,175 GFLOPS (1:3)

Board Design

Slot Width
Dual-slot
Length
267 mm
10.5 inches
TDP
225 W
Suggested PSU
550 W
Outputs
No outputs
Power Connectors
1x 6-pin + 1x 8-pin
Board Number
P2081 SKU 208

Graphics Features

DirectX
12 (11_0)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2.175
CUDA
3.5
Shader Model
6.5 (5.1)

GK110 GPU Notes

NVENC: 1st Gen
NVDEC: 1st Gen
PureVideo HD: VP5
VDPAU: Feature Set D

L1 Cache is configurable from 16 KB up to 48 KB per SMX

GK110 has 5 GPCs each capable of 8 pixels per clock. This limits complete GPU to 40 pixels per clock and because of that it can't feed all 48 ROPs when they all require data at the same time.
Additional ROPs however can be used for MSAA (because it doesn't require additional data from rasterizers, while giving more work to ROPs.)

Latest Drivers:
Windows XP / Server 2003 x64:
Quadro Release R319 U2 (321.01)

Windows Vista:
GeForce Release 365.19
Quadro Release R346 U7 (348.40) / R352 BETA (352.86)

Windows 7 / 8 / 8.1 / 10 / 11 (x32 / x64):
GeForce Release 391.35 / 475.06
Quadro Release R390 U9 (392.37) / R470 U16 (474.82)
Data Center Release 427.11
Tesla Release 441.22

Windows 10 / 11 x64:
GeForce Release 475.06
Quadro Release R470 U16 (474.82)
Data Center Release 474.82
Nov 3rd, 2024 22:19 CST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts