Nvidia Tesla

From Wikipedia, the free encyclopedia

(Redirected from NVIDIA Tesla)

300px

The Tesla GPU is NVIDIA's third brand of GPUs. It's based on the G80 and Quadro and is NVIDIA's first dedicated General Purpose GPU. The NVIDIA Tesla is named after the inventor Nikola Tesla.

1 Tesla Overview
2 Specifications and Configurations^[3]
3 See also
4 External links
5 References

Tesla Overview

Because of the very high computational power (measured in FLOPS rating) compared to recent microprocessors, the Tesla products are intended for the high performance computing market. The lack of ability to output images to a display (such as a monitor) ^[1] is the main difference between Tesla products and ordinary video cards. The primary function of Tesla products are to aid in simulations, large scale calculations (especially floating-point calculations), and image generation for professional and scientific fields ^[2], with the use of CUDA.

Specifications and Configurations^[3]

Configuration	Model	# of GPUs	Core clock in MHz (each)	Shaders		Memory					Processing Power (GigaFLOPS, total)	Form factor
Configuration	Model	# of GPUs	Core clock in MHz (each)	Thread Processors (total)	Clock in MHz (each)	Bandwidth max (GB/s)	Bus type	Bus width (bit)	Total size (MiB)	Clock (MHz)	Processing Power (GigaFLOPS, total)	Form factor
GPU Computing Processor	C870	1	600	128	1350	76.8	GDDR3	384	1536	1600	518.4	Full-height video card
Deskside Supercomputer	D870	2	600	256	1350	76.8	GDDR3	384	3072	1600	1036.8	Deskside system or Rack unit
GPU Computing Server	S870	4	600	512	1350	76.8	GDDR3	384	6144	1600	2073.6	1U Rack

Notes

All specifications not specified by NVIDIA assumed to be based on the GeForce 8800GTX
For the basic specifications of Tesla, refer to the GPU Computing Processor specifications.
An 8 GPU version of the Tesla S870 is planned for the future.