GPU-STREAM
Version: 0.9
Implementation: OpenCL
Precision: double

Running kernels 10 times
Array size: 400.0 MB (=0.4 GB)
Total size: 1200.0 MB (=1.2 GB)
Using OpenCL device Tesla K40c
Function    MBytes/sec  Min (sec)   Max         Average     
Copy        190354.872  0.00441     0.00443     0.00442     
Mul         190199.107  0.00441     0.00443     0.00442     
Add         190946.380  0.00659     0.00660     0.00660     
Triad       190991.101  0.00659     0.00661     0.00660