Report an Error

NVIDIA Tesla S1075

NVIDIA Tesla S1075 Image NVIDIA GT200B Image
The Tesla S1075 was a professional graphics card by NVIDIA, launched in June 2008. Built on the 55 nm process, and based on the GT200B graphics processor, 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. 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 placed 16,384 MB GDDR3 memory on the card, 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.
We recommend the NVIDIA Tesla S1075 for gaming with highest details at resolutions up to, and including, 5760x1080.
Being a dual-slot card, its power draw is rated at 800 W maximum. Tesla S1075 is connected to the rest of the system using a PCIe 2.0 x16 interface.

Graphics Processor

GPU Name: GT200B
Process Size: 55 nm
Transistors: 1,400 million
Die Size: 470 mm²

Graphics Card

Released: Jun 1st, 2008
Production Status: End-of-life
Bus Interface: PCIe 2.0 x16

Clock Speeds

GPU Clock: 610 MHz
Shader Clock: 1296 MHz
Memory Clock: 800 MHz
1600 MHz effective

Memory

Memory Size: 4096 MB x4
Memory Type: GDDR3
Memory Bus: 512 bit x4
Bandwidth: 102 GB/s x4

Render Config

Shading Units: 240 x4
TMUs: 80 x4
ROPs: 32 x4
SM Count: 10 x4
Pixel Rate: 19.5 GPixel/s x4
Texture Rate: 48.8 GTexel/s x4
Floating-point performance: 622.1 GFLOPS x4

Board Design

Slot Width: Dual-slot
TDP: 800 W

Graphics Features

DirectX: 10.0
OpenGL: 3.3
OpenCL: n/a
Shader Model: 4.0

VGA BIOS

Find graphics card BIOS for this card.

GPU-Z Validation

Find GPU-Z validations for this card.

GT200B GPU Notes

Compute Capability: CUDA 1.3

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