
=== Device Timing Summary ===

                Total Execution Time (ns):           1169230000
Total Device Time for CL GPU backend (ns):             91672091

== CL GPU Backend ==

              Kernel,       Calls,           Time (ns),    Time (%),        Average (ns),            Min (ns),            Max (ns)
                GEMM,           4,            84431196,       92.10,            21107799,            20856041,            21550937
 clEnqueueReadBuffer,           4,             5139701,        5.61,             1284925,             1006200,             1493901
clEnqueueWriteBuffer,           8,             2101194,        2.29,              262649,              199687,              366406


