Accelerate the solution of artificial intelligence, HPC, data science and graphics tasks
Graphics servers with Tesla V100
All graphics servers with Tesla V100 are based on two Intel Xeon Gold 6240 CPUs with a base clock speed of 2.6 GHz and a maximum clock speed with Turbo Boost technology of 3.9 GHz.
Each processor contains two Intel® AVX-512 units and supports Intel® AVX-512 Deep Learning Boost functions. This set of instructions speeds up multiplication and addition operations with reduced accuracy, which are used in many internal cycles of the deep learning algorithm.
Each server has 512 GB of DDR4 ECC Reg 2933 MHz RAM. Local storage with a total capacity of 1920 GB is organized on Intel® solid-state drives, designed specifically for data centers.
GPU Tesla V100
Equipped with 43 thousand Tensor cores, the Tesla V100 is the first accelerator to overcome the performance barrier of 100 tera-operations per second (TOPS) in deep learning tasks. Models that took weeks to train on previous generation systems can now be trained in just a few days. Thanks to such a serious reduction in the time spent on training algorithms, artificial intelligence will help solve completely new problems.
HPC (High Performance Computing) is the fundamental pillar of modern science. From weather forecasting and the creation of new medicines to the search for energy sources, scientists are constantly using large computing systems to model our world and predict events in it. Artificial intelligence expands the capabilities of HPC, allowing scientists to analyze large amounts of data and extract useful information where simulations alone cannot provide a complete picture of what is happening.
The Tesla V100 graphics accelerator is designed to provide a fusion of HPC and artificial intelligence. This is a solution for HPC systems, which will perfectly prove itself both in computing for simulations and data processing for extracting useful information from them. By combining CUDA and Tensor cores in one architecture, a server equipped with Tesla V100 graphics accelerators can replace hundreds of traditional CPU servers, performing traditional HPC and artificial intelligence tasks. Now every scientist can afford a supercomputer that will help in solving the most difficult problems.
Video memory capacity
Type of video memory
GPU performance benchmarks
Performance benchmarks results in a virtual environment for 1 Tesla V100 graphics card.
Matrix multiply example
Basic configurations with Tesla V100 32 GB
Subscribe to the availability notification
Specify the number of required flavors . When they become available, you will receive a notification by email.
You successfully subscribed on notification.
You already subscribed on notification.
You already have reached the limit of TeslaV100 flavors.