Produktbeskrivning

NVIDIA Tesla V100S with 32 GB HBM2 memory is an extremely advanced data center GPU ever built to accelerate AI, HPC, and graphics. Powered by NVIDIA Volta, advanced GPU architecture, Tesla V100S offers powerful performance enabling data scientists, researchers, and engineers to tackle challenges that were once thought impossible. Tesla V100S is the flagship product of Tesla data center computing platform for deep learning, HPC, and graphics. It is available everywhere from desktops to servers to cloud services, delivering both dramatic performance gains and cost savings opportunities.

 

Egenskaper

Volta architecture
By pairing CUDA Cores and Tensor Cores within a unified architecture, a single server with Tesla V100 GPUs can replace hundreds of commodity CPU servers for traditional HPC and Deep Learning.

Tensor Core
Equipped with 640 Tensor Cores, Tesla V100 delivers 120 TeraFLOPS of deep learning performance.

Next generation NVLink
NVIDIA NVLink in Tesla V100 delivers high throughput - Tesla V100 accelerators can be interconnected to unleash better application performance on a single server.

High memory bandwidth
With a combination of improved raw bandwidth and high DRAM utilization efficiency Tesla V100 delivers high memory bandwidth over Pascal GPUs.

Maximum efficiency mode
The maximum efficiency mode allows data centers to achieve high compute capacity per rack within the existing power budget. In this mode, Tesla V100 runs at peak processing efficiency, providing advanced performance at half the power consumption.

Programmability
Tesla V100 is architected from the ground up to simplify programmability. Its independent thread scheduling enables finer-grain synchronization and improves GPU utilization by sharing resources among small jobs.

 

Teknisk specifikation

Typ av enhet	GPU-beräkningsprocessor - fläktlös
Busstyp	PCI Express 3.0 x16
Grafikmotor	NVIDIA Tesla V100S
CUDA-kärnor	5120
Egenskaper	Kylfläns utan fläkt, Nvidia CUDA-teknik, Error Correcting Codes (ECC) Memory, kylfläns för dubbel kortplats, Nvidia Volta GPU Architecture, 8,2 Tflops flyttalsberäkningar med dubbelprecision, 16,4 Tflops mex enkelprecisions-flytpunktsåtergivning, 130 Tflops tensorprestanda

Teknik	HBM2
Bussbredd	4096-bitars
Bandbredd	1134 GBps

Energiförbrukning vid drift	250 Watt
Inkluderade tillbehör	Dubbel 8-stifts PCIe till 8-stifts CPU-strömadapter
Djup	26.77 cm
Höjd	11.115 cm
Vikt	1.196 kg

Service och support	Begränsad garanti - 3 år