4 Dec 2019

XENON NVIDIA Tesla V100S Volta GPU_banner

16+ TFLOPs and Over 1 TB/s Memory Bandwidth To Servers

NVIDIA has released a new configuration of its Volta-based Tesla graphics card known as the Tesla V100S. The new server aimed solution carries the same specifications of the full Volta GPU, but offers much faster clock frequencies for both GPU and memory. The new Tesla V100S is available as a standalone product and can be integrated into XENON’s line of GPU servers and supercomputers. Contact XENON for more information.



Tesla V100 PCle Tesla V100 SXM2 Tesla V100S PCle
GPU Architecture NVIDIA Volta
NVIDIA Tensor Cores 640
NVIDIA CUDA® Cores 5,120
Double-Precision Performance 7 TFLOPS 7.8 TFLOPS 8.2 TFLOPS
Single-Precision Performance 14 TFLOPS 15.7 TFLOPS 16.4 TFLOPS
Tensor Performance 112 TFLOPS 125 TFLOPS 130 TFLOPS
GPU Memory 32GB /16GB HBM2 32GB HBM2
Memory Bandwidth 900 GB/sec 1134 GB/sec
Interconnect Bandwidth 32 GB/sec 300 GB/sec 32 GB/sec
System Interface PCIe Gen3 NVIDIA NVLink PCIe Gen3
Form Factor PCIe Full Height/Length SXM2 PCIe Full Height/Length
Max Power Comsumption 250 W 300 W 250 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL™, OpenACC
XENON NVIDIA_data center tesla v100 inference performance chartXENON NVIDIA data center tesla v100 training performance chartXENON NVIDIA tesla v100 chart updates hpc