Report an Error

NVIDIA Quadro FX 3800

GT200B
Graphics Processor
192
Cores
64
TMUs
16
ROPs
1024 MB
Memory Size
GDDR3
Memory Type
256 bit
Bus Width
NVIDIA Quadro FX 3800 Photo NVIDIA GT200B Photo
The Quadro FX 3800 was a enthusiast-class professional graphics card by NVIDIA, launched in March 2009. Built on the 55 nm process, and based on the GT200B graphics processor, in its G200-835-B2 variant, the card supports DirectX 10.0. The GT200B graphics processor is a large chip with a die area of 470 mm² and 1,400 million transistors. Unlike the fully unlocked GeForce GTX 275, which uses the same GPU but has all 240 shaders enabled, NVIDIA has disabled some shading units on the Quadro FX 3800 to reach the product's target shader count. It features 192 shading units, 64 texture mapping units and 16 ROPs. NVIDIA has placed 1,024 MB GDDR3 memory on the card, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 600 MHz, memory is running at 800 MHz.
Being a single-slot card, the NVIDIA Quadro FX 3800 draws power from 1x 6-pin power connectors, with power draw rated at 108 W maximum. Display outputs include: 1x DVI, 2x DisplayPort. Quadro FX 3800 is connected to the rest of the system using a PCI-Express 2.0 x16 interface. The card measures 198 mm in length, and features a single-slot cooling solution. Its price at launch was 799 US Dollars.

Graphics Processor

GPU Name
GT200B
GPU Variant
G200-835-B2
Architecture
Tesla 2.0
Foundry
TSMC
Process Size
55 nm
Transistors
1,400 million
Die Size
470 mm²

Graphics Card

Release Date
Mar 30th, 2009
Generation
Quadro FX
(x800)
Production
End-of-life
Launch Price
799 USD
Bus Interface
PCIe 2.0 x16

Relative Performance

10%
13%
16%
21%
24%
26%
32%
42%
42%
46%
48%
49%
57%
60%
65%
67%
70%
72%
77%
81%
83%
85%
88%
100%
Quadro FX 3800
101%
101%
103%
104%
105%
106%
107%
113%
119%
121%
125%
126%
127%
129%
129%
129%
132%
138%
141%
151%
154%
154%
160%
161%
166%
177%
183%
184%
187%
188%
195%
197%
199%
202%
212%
216%
219%
219%
220%
221%
238%
240%
246%
249%
250%
252%
253%
257%
258%
265%
285%
293%
300%
302%
305%
308%
315%
323%
331%
339%
344%
344%
381%
419%
425%
453%
456%
462%
468%
472%
474%
481%
483%
486%
490%
516%
527%
533%
533%
587%
597%
607%
652%
717%
742%
799%
799%
843%
941%
986%
1012%
1103%
1254%
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
600 MHz
Shader Clock
1204 MHz
Memory Clock
800 MHz
1600 MHz effective

Memory

Memory Size
1024 MB
Memory Type
GDDR3
Memory Bus
256 bit
Bandwidth
51.20 GB/s

Render Config

Shading Units
192
TMUs
64
ROPs
16
SM Count
8

Theoretical Performance

Pixel Rate
9.600 GPixel/s
Texture Rate
38.40 GTexel/s
FP32 (float) performance
462.3 GFLOPS
FP64 (double) performance
57.79 GFLOPS (1:8)

Board Design

Slot Width
Single-slot
Length
7.8 inches
198 mm
TDP
108 W
Outputs
1x DVI
2x DisplayPort
Power Connectors
1x 6-pin
Board Number
P755

Graphics Features

DirectX
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