Ubuntu16.04.6 Tesla V100-SXM2-16GB CUDA 10.1 Samples nobody benchmark 単精度 倍精度で動作させてみた 9033.258 5196.411 GFLOP/s

user0034@10-111-34-13:~$ cat /etc/os-release
NAME=”Ubuntu”
VERSION=”16.04.6 LTS (Xenial Xerus)”
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME=”Ubuntu 16.04.6 LTS”
VERSION_ID=”16.04″
HOME_URL=”http://www.ubuntu.com/”
SUPPORT_URL=”http://help.ubuntu.com/”
BUG_REPORT_URL=”http://bugs.launchpad.net/ubuntu/”
VERSION_CODENAME=xenial
UBUNTU_CODENAME=xenial
user0034@10-111-34-13:~$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Sun_Jul_28_19:07:16_PDT_2019
Cuda compilation tools, release 10.1, V10.1.243
user0034@10-111-34-13:~$

■単精度結果 =9033.258 single-precision GFLOP/s at 20 flops per interaction

■倍精度結果 =5196.411 double-precision GFLOP/s at 30 flops per interaction

データ詳細

Ubuntu16.04.6 Tesla V100-SXM2-16GB CUDA 10.1 Samples nobody benchmark 単精度 倍精度 9033.258 5196.411 GFLOPs

GPU温度推移

Ubuntu16.04.6 Tesla V100-SXM2-16GB CUDA 10.1 Samples nobody benchmark 単精度 倍精度 9033.258 5196.411 GFLOPs nvidia-smi