chibi@1804:~$ cat /etc/os-release
NAME=”Ubuntu”
VERSION=”18.04.1 LTS (Bionic Beaver)”
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME=”Ubuntu 18.04.1 LTS”
VERSION_ID=”18.04″
HOME_URL=”https://www.ubuntu.com/”
SUPPORT_URL=”https://help.ubuntu.com/”
BUG_REPORT_URL=”https://bugs.launchpad.net/ubuntu/”
PRIVACY_POLICY_URL=”https://www.ubuntu.com/legal/terms-and-policies/privacy-policy”
VERSION_CODENAME=bionic
UBUNTU_CODENAME=bionic
chibi@1804:~$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018
Cuda compilation tools, release 10.0, V10.0.130
chibi@1804:~$ sudo hddtemp /dev/sda
[sudo] chibi のパスワード:
/dev/sda: TS128GSSD370S: 19°C
chibi@1804:~/NVIDIA_CUDA-10.0_Samples/5_Simulations/nbody$ ./nbody -benchmark -fp64 -numbodies=2
56000 -numdevices=2
Run “nbody -benchmark [-numbodies=<numBodies>]” to measure performance.
-fullscreen (run n-body simulation in fullscreen mode)
-fp64 (use double precision floating point values for simulation)
-hostmem (stores simulation data in host memory)
-benchmark (run benchmark to measure performance)
-numbodies=<N> (number of bodies (>= 1) to run in simulation)
-device=<d> (where d=0,1,2…. for the CUDA device to use)
-numdevices=<i> (where i=(number of CUDA devices > 0) to use for simulation)
-compare (compares simulation results running once on the default GPU and once on the CPU)
-cpu (run n-body simulation on the CPU)
-tipsy=<file.bin> (load a tipsy model file for simulation)
NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.
number of CUDA devices = 2
> Windowed mode
> Simulation data stored in system memory
> Double precision floating point simulation
> 2 Devices used for simulation
GPU Device 0: “TITAN V” with compute capability 7.0
> Compute 7.0 CUDA device: [TITAN V]
> Compute 7.0 CUDA device: [TITAN V]
number of bodies = 256000
256000 bodies, total time for 10 iterations: 2789.158 ms
= 234.967 billion interactions per second
= 7049.009 double-precision GFLOP/s at 30 flops per interaction
chibi@1804:~/NVIDIA_CUDA-10.0_Samples/5_Simulations/nbody$ ./nbody -benchmark -numbodies=256000 -numdevices=2
Run “nbody -benchmark [-numbodies=<numBodies>]” to measure performance.
-fullscreen (run n-body simulation in fullscreen mode)
-fp64 (use double precision floating point values for simulation)
-hostmem (stores simulation data in host memory)
-benchmark (run benchmark to measure performance)
-numbodies=<N> (number of bodies (>= 1) to run in simulation)
-device=<d> (where d=0,1,2…. for the CUDA device to use)
-numdevices=<i> (where i=(number of CUDA devices > 0) to use for simulation)
-compare (compares simulation results running once on the default GPU and once on the CPU)
-cpu (run n-body simulation on the CPU)
-tipsy=<file.bin> (load a tipsy model file for simulation)
NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.
number of CUDA devices = 2
> Windowed mode
> Simulation data stored in system memory
> Single precision floating point simulation
> 2 Devices used for simulation
GPU Device 0: “TITAN V” with compute capability 7.0
> Compute 7.0 CUDA device: [TITAN V]
> Compute 7.0 CUDA device: [TITAN V]
number of bodies = 256000
256000 bodies, total time for 10 iterations: 765.143 ms
= 856.520 billion interactions per second
= 17130.392 single-precision GFLOP/s at 20 flops per interaction
データ詳細 Ubuntu18.04.1 TITAN Vx2 CUDA 10.0 Samples nbody benchmark 倍精度7049.009 GFLOP s 単精度17130.392 GFLOP s