KernelName,Count,Sum(ns),Mean(ns),Median(ns),Pct "void benchmark_func(int, int*) [clone .kd]",1,3356652.0,3356652.0,3356652.0,7.843408309322819 "void benchmark_func, 256, 8u, 512u>(HIP_vector_type, HIP_vector_type*) [clone .kd]",1,1725607.0,1725607.0,1725607.0,4.032184534597456 "void benchmark_func(double, double*) [clone .kd]",1,1714726.0,1714726.0,1714726.0,4.006759162585779 "void benchmark_func(int, int*) [clone .kd]",1,1698726.0,1698726.0,1698726.0,3.969372345915726 "void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1674567.0,1674567.0,1674567.0,3.912920589419989 "void benchmark_func(float, float*) [clone .kd]",1,1665446.0,1665446.0,1665446.0,3.891607767242017 "void benchmark_func, 256, 8u, 256u>(HIP_vector_type, HIP_vector_type*) [clone .kd]",1,885604.0,885604.0,885604.0,2.069369649391574 "void benchmark_func(double, double*) [clone .kd]",1,879523.0,879523.0,879523.0,2.055160322380912 "void benchmark_func(int, int*) [clone .kd]",1,869123.0,869123.0,869123.0,2.0308588915453782 "void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",1,858403.0,858403.0,858403.0,2.005809724376443