Report an Error

NVIDIA Tesla S1075

Graphics Processor
GT200B x4
Cores
240 x4
TMUs
80 x4
ROPs
32 x4
Memory Size
4 GB x4
Memory Type
GDDR3
Bus Width
512 bit x4
GPU Chip
GPU
The Tesla S1075 was a professional graphics card by NVIDIA, launched on June 1st, 2008. Built on the 55 nm process, and based on the GT200B graphics processor, the card supports DirectX 11.1. Even though it supports DirectX 11, the feature level is only 10_0, which can be problematic with many DirectX 11 & DirectX 12 titles. The GT200B graphics processor is a large chip with a die area of 470 mm² and 1,400 million transistors. Tesla S1075 combines four graphics processors to increase performance. It features 240 shading units, 80 texture mapping units, and 32 ROPs, per GPU. NVIDIA has paired 16 GB GDDR3 memory with the Tesla S1075, which are connected using a 512-bit memory interface per GPU (each GPU manages 4,096 MB). The GPU is operating at a frequency of 610 MHz, memory is running at 800 MHz.
Being a dual-slot card, its power draw is rated at 800 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Tesla S1075 is connected to the rest of the system using a PCI-Express 2.0 x16 interface.

Graphics Processor

GPU Name
GT200B
Architecture
Tesla 2.0
Foundry
TSMC
Process Size
55 nm
Transistors
1,400 million
Density
3.0M / mm²
Die Size
470 mm²
Chip Package
BGA-1981

Graphics Card

Release Date
Jun 1st, 2008
Generation
Tesla
(x10xx)
Successor
Tesla Fermi
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
13%
GeForce GT 220
16%
GeForce GT 430
21%
Radeon HD 5570
21%
Radeon HD 4670
23%
GeForce GT 440
24%
GeForce GT 240
24%
GeForce 9600 GT
28%
Radeon HD 5670
30%
GeForce GT 640
32%
GeForce 9800 GT
33%
Radeon HD 6670
34%
Radeon HD 4830
35%
Radeon HD 4770
38%
Radeon HD 4850
40%
GeForce GTS 250
41%
GeForce GTS 450
42%
Radeon HD 5750
43%
Radeon HD 7750
49%
Radeon HD 5770
50%
GeForce GTX 260
51%
Radeon HD 4870
51%
Radeon Vega 8
51%
GeForce GTX 550 Ti
52%
GeForce GTX 650
52%
Radeon HD 5830
55%
Radeon HD 6790
58%
Radeon HD 4890
59%
GeForce GTX 460
62%
Radeon RX Vega 11
62%
GeForce GT 1030
63%
GeForce GTX 275
63%
Radeon HD 7770 GHz Edition
63%
GeForce GTX 280
63%
GeForce GTX 465
65%
Radeon HD 6850
68%
GeForce GTX 285
69%
Radeon HD 5850
74%
GeForce GTX 650 Ti
76%
Radeon HD 7790
76%
Radeon RX 550
79%
GeForce GTX 470
79%
Radeon HD 6870
82%
Radeon HD 5870
87%
GeForce GTX 560 Ti
90%
Radeon HD 4870 X2
90%
GeForce GTX 750 Ti
92%
Radeon HD 6950
93%
GeForce GTX 295
96%
GeForce GTX 650 Ti Boost
97%
Radeon HD 7850
98%
GeForce GTX 480
99%
Tesla S1075
100%
Radeon HD 6970
104%
Radeon R7 265
106%
Radeon RX 460
108%
Radeon R7 370
108%
GeForce GTX 660
108%
GeForce GTX 570
108%
Radeon RX 560
110%
GeForce GTX 950
117%
Radeon HD 7870 GHz Edition
118%
Radeon R9 270X
121%
GeForce GTX 660 Ti
122%
GeForce GTX 580
123%
GeForce GTX 1050
124%
Radeon HD 7950
124%
GeForce GTX 1630
127%
Radeon HD 5970
127%
GeForce GTX 760
130%
GeForce GTX 670
140%
GeForce GTX 960
144%
Radeon R9 380
148%
Radeon R9 285
148%
Radeon HD 7970
150%
GeForce GTX 680
151%
GeForce GTX 1050 Ti
155%
GeForce GTX 770
159%
Radeon HD 6990
163%
Radeon R9 280X
167%
GeForce GTX 590
169%
Radeon HD 7970 GHz Edition
169%
GeForce GTX 780
187%
Arc A380
188%
Radeon RX 6400
190%
GeForce GTX 1650
194%
Radeon RX 470
206%
Radeon R9 290
209%
Radeon RX 570
220%
Radeon R9 390
223%
Radeon R9 290X
224%
GeForce GTX 970
227%
GeForce GTX TITAN
230%
GeForce GTX 780 Ti
233%
Radeon R9 390X
237%
Radeon HD 7990
238%
Radeon RX 480
239%
GeForce GTX 690
241%
GeForce GTX 1060 6 GB
247%
Radeon RX 5500 OEM
251%
Radeon RX 580
254%
Radeon RX 5500 XT
256%
Radeon RX 6500 XT
258%
GeForce GTX 980
259%
GeForce GTX 1650 SUPER
261%
Radeon R9 FURY
262%
Radeon RX 590
274%
Radeon R9 295X2
289%
GeForce GTX 1660
290%
Radeon R9 FURY X
294%
GeForce GTX 980 Ti
298%
GeForce GTX TITAN X
306%
GeForce GTX 1660 SUPER
315%
GeForce GTX 1070
333%
GeForce GTX 1660 Ti
333%
GeForce RTX 3050 8 GB
338%
Radeon RX Vega 56
355%
GeForce GTX 1070 Ti
376%
Radeon RX 5600 XT
382%
Radeon RX Vega 64
387%
GeForce GTX 1080
392%
GeForce RTX 2060
392%
Radeon RX 5700
408%
Arc A580
409%
Radeon RX 6600
426%
GeForce RTX 2060 SUPER
441%
GeForce RTX 2070
446%
Radeon RX 5700 XT
447%
GeForce RTX 3060 12 GB
455%
Arc A750
470%
Radeon VII
473%
TITAN X Pascal
485%
Radeon RX 6600 XT
490%
GeForce GTX 1080 Ti
500%
Arc A770
505%
GeForce RTX 2070 SUPER
505%
Radeon RX 6650 XT
531%
Radeon RX 7600
537%
GeForce RTX 4060
540%
GeForce RTX 2080
543%
Radeon RX 7600 XT
554%
GeForce RTX 2080 SUPER
570%
GeForce RTX 3060 Ti
583%
Radeon RX 6700 XT
604%
Radeon RX 6750 XT
641%
GeForce RTX 4060 Ti 8 GB
648%
GeForce RTX 2080 Ti
653%
GeForce RTX 3070
683%
GeForce RTX 3070 Ti
731%
Radeon RX 7700 XT
739%
Radeon RX 6800
753%
GeForce RTX 4070
834%
Radeon RX 6800 XT
855%
GeForce RTX 3080
888%
Radeon RX 7800 XT
897%
Radeon RX 6900 XT
922%
GeForce RTX 4070 SUPER
968%
Radeon RX 7900 GRE
986%
GeForce RTX 3080 Ti
995%
Radeon RX 6950 XT
996%
GeForce RTX 3090
1013%
GeForce RTX 4070 Ti
1039%
GeForce RTX 4070 Ti SUPER
1135%
Radeon RX 7900 XT
1166%
GeForce RTX 3090 Ti
1176%
GeForce RTX 4080
1320%
GeForce RTX 4080 SUPER
1340%
Radeon RX 7900 XTX
1352%
GeForce RTX 4090
1658%
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
610 MHz
Shader Clock
1296 MHz
Memory Clock
800 MHz
1600 Mbps effective

Memory

Memory Size
4 GB
Memory Type
GDDR3
Memory Bus
512 bit
Bandwidth
102.4 GB/s

Render Config

Shading Units
240
TMUs
80
ROPs
32
SM Count
30
L2 Cache
256 KB

Theoretical Performance

Pixel Rate
19.52 GPixel/s
Texture Rate
48.80 GTexel/s
FP32 (float)
622.1 GFLOPS
FP64 (double)
77.76 GFLOPS (1:8)

Board Design

Slot Width
Dual-slot
TDP
800 W
Suggested PSU
1200 W
Outputs
No outputs

Graphics Features

DirectX
11.1 (10_0)
OpenGL
3.3
OpenCL
1.1
Vulkan
N/A
CUDA
1.3
Shader Model
4.0

GT200B GPU Notes

PureVideo HD: VP2
VDPAU: Feature Set A

GT200B, commonly printed on the chip package as G200-xxx-Bx is an optical shrink of the G200 core to the newer 55 manufacturing process of TSMC. It helped shrink the core's energy and thermal footprints to a level that even facilitated building a dual-GPU accelerator
Apr 27th, 2024 00:55 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts