NVIDIA® Tesla® V100

Every industry wants intelligence. Within their ever-growing oceans of data lie insights that can revolutionize entire industries. Personalized cancer therapy, predicting the next big hurricane, virtual personal assistants conversing naturally. These opportunities can become a reality when data scientists are given the tool they need to realize their life’s work.

NVIDIA® Tesla® V100 is the world’s most advanced data center GPU ever built to accelerate AI, HPC, and Graphics. Powered by the latest GPU architecture, NVIDIA VoltaTM, Tesla V100 offers the performance of 100 CPUs in a single GPU—enabling data scientists, researchers, and engineers to tackle challenges that were once impossible.

NVIDIA Tesla V100 Volta GPU Penguin Computing AI Deep Learning Accelerated
NVIDIA Tesla V100 Volta GPU Penguin Computing AI Deep Learning Accelerated
NVIDIA Tesla V100 Volta GPU Penguin Computing AI Deep Learning Accelerated

Tesla V100 Specifications

  • 5120 CUDA cores
  • 640 New Tensor Cores
  • 7.5 TeraFLOPS double-precision performance with NVIDIA GPU Boost
  • 15 TeraFLOPS single-precision performance with NVIDIA GPU Boost
  • 120 TeraFLOPS mixed-precision deep learning performance with NVIDIA GPU Boost
  • 300 GB/s bi-directional interconnect bandwidth with NVIDIA NVLink
  • 900 GB/s memory bandwidth with CoWoS HBM2 Stacked Memory
  • 16 GB of CoWoS HBM2 Stacked Memory
  • 300 Watt

Tesla V100 Form Factors

  • Tesla V100 for NVLink: Ultimate performance for deep learning
  • Tesla V100 for PCIe: Highest versatility for all workloads

Selected Tesla V100 Servers

Relion® XO1114GT

The Penguin Computing® Relion® XO1114GT is an Open Compute Server, part of Penguin Computing TundraTM Extreme Scale (ES) Family. It is a 1OU, 4x GPU server powered by Intel® Xeon® Processor Scalable Family. It is a high density server targeting high performance computing and deep learning applications. Relion XO1114GT supports Intel Xeon Scalable processors with integrated Intel Omni-Path Architecture to take advantage of natively supported 100G network fabric built right into the processor.

Relion® XO1114GTS

The Penguin Computing® Relion® XO1114GTS is an Open Compute Server, part of the Penguin Computing® TundraTM Extreme Scale (ES) Family. It is a 1OU, 4x NVIDIA® Tesla® V100-SXM2 server powered by Intel Xeon Processor Scalable Family. It is a high density server targeting high performance computing and deep learning applications.

Relion® XE1114GT

The Penguin Computing® Relion® XE1114GT is a 1U, 4x GPU server powered by the Intel® Xeon® Processor Scalable Family, targeting enterprise customers and highly optimized deep learning applications. Relion XE1114GT supports up to 4x PCIe GPU in a balance PCIe Topology.

Relion® XE1114GTS

The Penguin Computing® Relion® XE1114GTS is a 1U, 4x NVIDIA® Tesla® V100-SXM2 server powered by the Intel® Xeon® Processor Scalable Family, targeting enterprise customers and deep learning applications. Relion XE1114GTS support latest NVLINK2 providing lowest latency P2P performance that can operate under single CPU root complex.

Relion® XE4118GT

The Penguin Computing® Relion® XE4118GT is a 4U, 8x GPU server powered by the Intel® Xeon® Processor Scalable Family, targeting enterprise customers and deep learning applications. Relion XE4118GT supports Intel Xeon Scalable processors with integrated Intel Omni-Path Architecture to take advantage of natively supported 100G network fabric built right into the processor.

Relion® XE4118GTS

The Penguin Computing® Relion® XE4118GTS is a 4U, 8x NVIDIA® Tesla® V100-SXM2 server powered by the Intel® Xeon® Processor Scalable Family, targeting enterprise customers and deep learning applications. Relion XE4118GTS support latest NVLINK2 providing lowest latency P2P performance.

NVIDIA Tesla V100

Relion XE2112TM

With acceleration options of either the Tesla V100 GPU or the Tesla P100 GPU, this 2U server targets enterprise customer and highly optimized for hyper-scale deployment. Relion XE2112 supports Intel Xeon Scalable processors with integrated Intel Omni-Path Architecture to take advantage of natively supported 100G network fabric built right into the processor.