GPU-STREAM
Version: 2.0
Implementation: CUDA
Running kernels 100 times
Precision: double
Array size: 268.4 MB (=0.3 GB)
Total size: 805.3 MB (=0.8 GB)
Using OpenCL device DEVICE EMULATION MODE
Driver: PGI
Function    MBytes/sec  Min (sec)   Max         Average     
Copy        21626.429   0.02482     0.03784     0.02526     
Mul         21321.415   0.02518     0.02603     0.02551     
Add         23394.375   0.03442     0.03588     0.03506     
Triad       23527.878   0.03423     0.03550     0.03486