NVIDIA Tesla V100 DGXS 32 GB

FP16 throughput

1.3×10¹⁴ FLOP/s

Memory

29.8 GB

TDP

250 W

NVIDIA Tesla V100 DGXS 32 GB is an AI accelerator designed by NVIDIA (GPU), released in March 2018. It is built on a 12 nm process at TSMC, packing 21.1B transistors.

It delivers 1.3×10¹⁴ FLOP/s of tensor FP16/BF16 throughput. It carries 29.8 GB of memory at 835 GB/s of bandwidth. Its thermal design power is 250 W.

Full record

Manufacturer: NVIDIA
Type: GPU
Release date: Mar 27, 2018
Tensor FP16/BF16: 1.3×10¹⁴ FLOP/s
FP32: 1.6×10¹³ FLOP/s
FP64: 7.8×10¹² FLOP/s
Memory: 29.8 GB
Memory bandwidth: 835 GB
TDP: 250 W
Process node: 12 nm
Transistors (millions): 21,100
Die size (mm2): 815
Foundry: TSMC
Tensor cores: 640