NVIDIA Tesla Data Centre GPU Accelerators

Accelerate the most demanding HPC and hyperscale data centre workloads with NVIDIA Tesla GPU accelerators. Data scientists and researchers can now crunch through petabytes of data an order of magnitude faster than with traditional CPUs in applications ranging from engineering, scientific modelling, energy exploration and deep learning.

Scan Computers sells the complete range of NVIDIA Tesla GPU accelerators and NVIDIA Tesla Certified Servers by 3XS Systems. Please call 01204 474747 or email [email protected] to discuss your requirements.

NVIDIA Tesla Data Centre GPU Accelerators
Tesla V100 Tesla V100
The NVIDIA Tesla V100 is the world’s most advanced data centre GPU. Powered by the latest NVIDIA Volta GPU architecture, the Tesla V100 offers the performance of up to 100 CPUs in a single GPU—enabling data scientists, researchers, and engineers to tackle challenges that were once thought impossible.

Tesla V100 is the flagship product of Tesla data centre computing platform for deep learning, HPC, and graphics. The Tesla platform accelerates over 450 HPC applications and every major deep learning framework. It is available in servers and cloud services, delivering dramatic performance gains and cost savings opportunities.
Peak Performance
7 teraFLOPS double-precision
14 teraFLOPS single-precision
112 teraFLOPS half-precision

Architecture
Volta

Cores
5120 CUDA + 640 Tensor

Memory
32GB or 16GB HBM2
Tesla P100 Tesla P100
The NVIDIA Tesla P100 is powered by the Pascal architecture and designed to boost throughput and save money for HPC and hyperscale data centers. The most powerful member of this family, the Tesla P100 for enables a single node to replace half a rack of commodity CPU nodes by delivering lightning-fast performance in a broad range of HPC applications. Handling the same workload with far fewer nodes means customers can save up to 70% in overall data centre costs.
Peak Performance
4.7 teraFLOPS double-precision
9.3 teraFLOPS single-precision
18.7 teraFLOPS half-precision

Architecture
Pascal

Cores
3584 CUDA

Memory
16GB or 12GB HBM2