
=== API Timing Summary ===

             Total Execution Time (ns):           1349818700
    Total API Time for L0 backend (ns):                 2400
Total API Time for CL CPU backend (ns):                49700
Total API Time for CL GPU backend (ns):            156338400

== L0 Backend ==

   Function,        Calls,            Time (ns),      Time (%),         Average (ns),             Min (ns),             Max (ns)
zeDriverGet,            1,                 2400,    100.000000,                 2400,                 2400,                 2400

== CL CPU Backend ==

      Function,       Calls,           Time (ns),    Time (%),        Average (ns),            Min (ns),            Max (ns)
clGetDeviceIDs,           1,               49700,      100.00,               49700,               49700,               49700

== CL GPU Backend ==

                          Function,       Calls,           Time (ns),    Time (%),        Average (ns),            Min (ns),            Max (ns)
                          clFinish,           4,            99202300,       63.45,            24800575,            23985400,            26389000
                  clReleaseContext,           1,            45225600,       28.93,            45225600,            45225600,            45225600
               clEnqueueReadBuffer,           4,             5093500,        3.26,             1273375,              894700,             1929300
                    clCreateBuffer,          12,             3411100,        2.18,              284258,               47400,              543700
              clEnqueueWriteBuffer,           8,             1272800,        0.81,              159100,               40700,              796800
                    clBuildProgram,           1,              984100,        0.63,              984100,              984100,              984100
                   clCreateContext,           1,              417900,        0.27,              417900,              417900,              417900
            clEnqueueNDRangeKernel,           4,              397900,        0.25,               99475,               12000,              235100
                clReleaseMemObject,          12,              140300,        0.09,               11691,                1800,               65400
                    clCreateKernel,           1,               50700,        0.03,               50700,               50700,               50700
                  clReleaseProgram,           1,               33700,        0.02,               33700,               33700,               33700
         clCreateProgramWithSource,           1,               19800,        0.01,               19800,               19800,               19800
           clGetEventProfilingInfo,           8,               19600,        0.01,                2450,                 200,                4900
                    clSetKernelArg,          16,               14700,        0.01,                 918,                 200,                3300
                   clGetKernelInfo,           4,               12600,        0.01,                3150,                1600,                5300
                    clReleaseEvent,           4,               12200,        0.01,                3050,                2800,                3300
                   clReleaseKernel,           1,               10200,        0.01,               10200,               10200,               10200
             clReleaseCommandQueue,           1,                7000,        0.00,                7000,                7000,                7000
clCreateCommandQueueWithProperties,           1,                4800,        0.00,                4800,                4800,                4800
                    clGetDeviceIDs,           2,                4400,        0.00,                2200,                 300,                4100
                   clGetDeviceInfo,           3,                3200,        0.00,                1066,                 300,                1800

