KernelName,Count,Sum(ns),Mean(ns),Median(ns),Pct
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,3359807.0,3359807.0,3359807.0,7.8432640011997155
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1726223.0,1726223.0,1726223.0,4.029762041076459
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1715503.0,1715503.0,1715503.0,4.004736856566497
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,1700143.0,1700143.0,1700143.0,3.968879875776104
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1674383.0,1674383.0,1674383.0,3.908744730908884
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1666543.0,1666543.0,1666543.0,3.89044273029712
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,885591.0,885591.0,885591.0,2.067358038746409
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,880472.0,880472.0,880472.0,2.055408046255132
"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",1,870392.0,870392.0,870392.0,2.0318769026114363
"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",1,860791.0,860791.0,860791.0,2.009463955178587