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 K20X Driver: 7050 Function MBytes/sec Min (sec) Max Average Copy 181833.763 0.00295 0.00298 0.00297 Mul 181354.354 0.00296 0.00305 0.00297 Add 179955.484 0.00448 0.00449 0.00448 Triad 179798.066 0.00448 0.00450 0.00449 Application 1396457 resources: utime ~3s, stime ~1s, Rss ~871996, inblocks ~690, outblocks ~1373