Report an Error

NVIDIA Tesla M2090

Graphics Processor
GF110
Cores
512
TMUs
64
ROPs
48
Memory Size
6 GB
Memory Type
GDDR5
Bus Width
384 bit
GPU Chip
GPU
The Tesla M2090 was a professional graphics card by NVIDIA, launched on July 25th, 2011. Built on the 40 nm process, and based on the GF110 graphics processor, the card supports DirectX 12. The GF110 graphics processor is a large chip with a die area of 520 mm² and 3,000 million transistors. It features 512 shading units, 64 texture mapping units, and 48 ROPs. NVIDIA has paired 6 GB GDDR5 memory with the Tesla M2090, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 651 MHz, memory is running at 924 MHz (3.7 Gbps effective).
Being a dual-slot card, the NVIDIA Tesla M2090 draws power from 1x 6-pin + 1x 8-pin power connector, with power draw rated at 250 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla M2090 is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 248 mm in length, and features a dual-slot cooling solution.

Graphics Processor

GPU Name
GF110
Architecture
Fermi 2.0
Foundry
TSMC
Process Size
40 nm
Transistors
3,000 million
Density
5.8M / mm²
Die Size
520 mm²
Chip Package
BGA-1981

Graphics Card

Release Date
Jul 25th, 2011
Generation
Tesla Fermi
(x20xx)
Predecessor
Tesla
Successor
Tesla Kepler
Production
End-of-life
Bus Interface
PCIe 2.0 x16

Relative Performance

GeForce 210
5%
GeForce 9400 GT
6%
Radeon HD 4550
8%
Radeon HD 5450
10%
Radeon HD 6450
12%
GeForce GT 520
12%
GeForce GT 220
15%
GeForce GT 430
20%
Radeon HD 5570
20%
Radeon HD 4670
22%
GeForce GT 440
23%
GeForce GT 240
23%
GeForce 9600 GT
27%
Radeon HD 5670
29%
GeForce GT 640
31%
GeForce 9800 GT
32%
Radeon HD 6670
33%
Radeon HD 4830
34%
Radeon HD 4770
36%
Radeon HD 4850
38%
GeForce GTS 250
39%
GeForce GTS 450
40%
Radeon HD 5750
42%
Radeon HD 7750
48%
Radeon HD 5770
48%
GeForce GTX 260
49%
Radeon HD 4870
50%
Radeon Vega 8
50%
GeForce GTX 550 Ti
50%
GeForce GTX 650
51%
Radeon HD 5830
54%
Radeon HD 6790
56%
Radeon HD 4890
57%
GeForce GTX 460
59%
Radeon RX Vega 11
60%
GeForce GT 1030
60%
GeForce GTX 275
61%
Radeon HD 7770 GHz Edition
61%
GeForce GTX 280
61%
GeForce GTX 465
62%
Radeon HD 6850
65%
GeForce GTX 285
67%
Radeon HD 5850
72%
GeForce GTX 650 Ti
73%
Radeon HD 7790
73%
Radeon RX 550
76%
GeForce GTX 470
76%
Radeon HD 6870
79%
Radeon HD 5870
84%
GeForce GTX 560 Ti
87%
Radeon HD 4870 X2
87%
GeForce GTX 750 Ti
89%
Radeon HD 6950
89%
GeForce GTX 295
92%
GeForce GTX 650 Ti Boost
94%
Radeon HD 7850
94%
GeForce GTX 480
96%
Tesla M2090
100%
Radeon HD 6970
100%
Radeon R7 265
102%
Radeon RX 460
104%
Radeon R7 370
104%
GeForce GTX 660
104%
GeForce GTX 570
105%
Radeon RX 560
106%
GeForce GTX 950
113%
Radeon HD 7870 GHz Edition
114%
Radeon R9 270X
117%
GeForce GTX 660 Ti
118%
GeForce GTX 580
119%
GeForce GTX 1050
120%
Radeon HD 7950
120%
GeForce GTX 1630
122%
Radeon HD 5970
122%
GeForce GTX 760
126%
GeForce GTX 670
135%
GeForce GTX 960
139%
Radeon R9 380
142%
Radeon R9 285
143%
Radeon HD 7970
145%
GeForce GTX 680
146%
GeForce GTX 1050 Ti
150%
GeForce GTX 770
153%
Radeon HD 6990
157%
Radeon R9 280X
161%
GeForce GTX 590
163%
Radeon HD 7970 GHz Edition
163%
GeForce GTX 780
181%
Arc A380
181%
Radeon RX 6400
183%
GeForce GTX 1650
187%
Radeon RX 470
199%
Radeon R9 290
202%
Radeon RX 570
212%
Radeon R9 390
215%
Radeon R9 290X
216%
GeForce GTX 970
219%
GeForce GTX TITAN
222%
GeForce GTX 780 Ti
225%
Radeon R9 390X
228%
Radeon HD 7990
229%
Radeon RX 480
230%
GeForce GTX 690
232%
GeForce GTX 1060 6 GB
239%
Radeon RX 5500 OEM
242%
Radeon RX 580
245%
Radeon RX 5500 XT
247%
Radeon RX 6500 XT
249%
GeForce GTX 980
250%
GeForce GTX 1650 SUPER
252%
Radeon R9 FURY
253%
Radeon RX 590
264%
Radeon R9 295X2
278%
GeForce GTX 1660
280%
Radeon R9 FURY X
283%
GeForce GTX 980 Ti
288%
GeForce GTX TITAN X
295%
GeForce GTX 1660 SUPER
304%
GeForce GTX 1070
321%
GeForce GTX 1660 Ti
321%
GeForce RTX 3050 8 GB
327%
Radeon RX Vega 56
342%
GeForce GTX 1070 Ti
363%
Radeon RX 5600 XT
368%
Radeon RX Vega 64
373%
GeForce GTX 1080
378%
GeForce RTX 2060
378%
Radeon RX 5700
394%
Arc A580
395%
Radeon RX 6600
411%
GeForce RTX 2060 SUPER
425%
GeForce RTX 2070
431%
Radeon RX 5700 XT
431%
GeForce RTX 3060 12 GB
439%
Arc A750
454%
Radeon VII
456%
TITAN X Pascal
468%
Radeon RX 6600 XT
473%
GeForce GTX 1080 Ti
482%
Arc A770
487%
GeForce RTX 2070 SUPER
487%
Radeon RX 6650 XT
512%
Radeon RX 7600
518%
GeForce RTX 4060
521%
GeForce RTX 2080
524%
Radeon RX 7600 XT
535%
GeForce RTX 2080 SUPER
549%
GeForce RTX 3060 Ti
563%
Radeon RX 6700 XT
583%
Radeon RX 6750 XT
618%
GeForce RTX 4060 Ti 8 GB
625%
GeForce RTX 2080 Ti
630%
GeForce RTX 3070
659%
GeForce RTX 3070 Ti
705%
Radeon RX 7700 XT
713%
Radeon RX 6800
726%
GeForce RTX 4070
805%
Radeon RX 6800 XT
825%
GeForce RTX 3080
857%
Radeon RX 7800 XT
865%
Radeon RX 6900 XT
889%
GeForce RTX 4070 SUPER
934%
Radeon RX 7900 GRE
952%
GeForce RTX 3080 Ti
960%
Radeon RX 6950 XT
961%
GeForce RTX 3090
978%
GeForce RTX 4070 Ti
1002%
GeForce RTX 4070 Ti SUPER
1095%
Radeon RX 7900 XT
1124%
GeForce RTX 3090 Ti
1134%
GeForce RTX 4080
1273%
GeForce RTX 4080 SUPER
1292%
Radeon RX 7900 XTX
1304%
GeForce RTX 4090
1599%
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
651 MHz
Shader Clock
1301 MHz
Memory Clock
924 MHz
3.7 Gbps effective

Memory

Memory Size
6 GB
Memory Type
GDDR5
Memory Bus
384 bit
Bandwidth
177.4 GB/s

Render Config

Shading Units
512
TMUs
64
ROPs
48
SM Count
16
L1 Cache
64 KB (per SM)
L2 Cache
768 KB

Theoretical Performance

Pixel Rate
20.83 GPixel/s
Texture Rate
41.66 GTexel/s
FP32 (float)
1,332 GFLOPS
FP64 (double)
666.1 GFLOPS (1:2)

Board Design

Slot Width
Dual-slot
Length
248 mm
9.8 inches
TDP
250 W
Suggested PSU
600 W
Outputs
No outputs
Power Connectors
1x 6-pin + 1x 8-pin
Board Number
P1030 SKU 214

Graphics Features

DirectX
12 (11_0)
OpenGL
4.6
OpenCL
1.1
Vulkan
N/A
CUDA
2.0
Shader Model
5.1

GF110 GPU Notes

PureVideo HD: VP4
VDPAU: Feature Set C

GF110 has 4 GPCs each capable of 8 pixels per clock. This limits complete GPU to 32 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.)

The complete die contains 64 texture address units and 256 texture filtering units.
Apr 19th, 2024 15:51 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts