# Get Started

## **Introduction**

A cost-effective way to run high-performance computations

Level up your cloud servers with GPU accelerators. Graphical processing units are mostly used for deep machine learning, architectural visualization, video processing, and scientific computing. 

![GPU Image 1](images/gpu12.png)  
![GPU Image 2](images/gpun.png)

## TESLA

![Tesla GPU](images/gpu11.png)

We provide servers that are specifically designed for machine learning and deep learning purposes, and are equipped with the following distinctive features:

- Modern hardware based on the NVIDIA GPU chip set, which has a high operation speed.
- The newest Tesla V100 & T4 cards with their high processing power.
- Bundled with CUDA technology 

## **CUDA**

Parallel computing architecture designed by NVIDIA. The implementation of this architecture allowed a significant increase in the performance of GPU computing.

### Advantages of CUDA

- Using the common programming language C
- Applying technologies such as Parallel Data Cache and Thread Execution Manager
- Default libraries for FFT and BLAS
- Unification of hardware and software parts for GPU computing
- Multi-GPU Support
- Hardware Debugging
- Excellent scalability to different projects
- Special CUDA driver

All our GPU plans support NVIDIA® CUDA-capable and cuDNN with the latest version.

- Pre-installed with Nvidia-Docker2
- Includes NVIDIA® GPU Cloud (NGC) Catalog CLI, a command-line interface for managing content within the NGC Registry
- Includes development tools based on the programming languages Python 2, Python 3, and C++

You can choose OS flavors like Ubuntu 16, Ubuntu 18.04, CentOS 7, or Windows 2016 with NVIDIA TESLA V100 and T4 GPU Servers.


---