OMP_NUM_THREADS=128 numactl -m 1 ./gpu-stream-kokkos
GPU-STREAM
Version: 2.0
Implementation: KOKKOS
Running kernels 100 times
Precision: double
Array size: 268.4 MB (=0.3 GB)
Total size: 805.3 MB (=0.8 GB)
Function    MBytes/sec  Min (sec)   Max         Average
Copy        284255.707  0.00189     0.00209     0.00199
Mul         259925.621  0.00207     0.00483     0.00426
Add         301882.418  0.00267     0.00295     0.00279
Triad       293037.412  0.00275     0.00314     0.00293