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 Tesla K40m Driver: 7050 Function MBytes/sec Min (sec) Max Average Copy 194135.310 0.00277 0.00278 0.00277 Mul 194049.073 0.00277 0.00280 0.00278 Add 190956.372 0.00422 0.00423 0.00422 Triad 190822.844 0.00422 0.00423 0.00422