
=== Device Timing Summary ===

                Total Execution Time (ns):             89614076
Total Device Time for CL GPU backend (ns):             46625120

== CL GPU Backend ==

              Kernel,       Calls,           Time (ns),    Time (%),        Average (ns),            Min (ns),            Max (ns)
                GEMM,           4,            44280640,       94.97,            11070160,             9633280,            12989120
clEnqueueWriteBuffer,           8,             1406560,        3.02,              175820,              153040,              203600
 clEnqueueReadBuffer,           4,              937920,        2.01,              234480,              222400,              240080


