colramos-amd
1.5 KiB
1.5 KiB
| 1 | KernelName | Count | Sum(ns) | Mean(ns) | Median(ns) | Pct |
|---|---|---|---|---|---|---|
| 2 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 1 | 6054191.0 | 6054191.0 | 6054191.0 | 9.190496154853548 |
| 3 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 1 | 4526683.0 | 4526683.0 | 4526683.0 | 6.871679916563736 |
| 4 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 1 | 3050055.0 | 3050055.0 | 3050055.0 | 4.630101486654755 |
| 5 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 1 | 3041896.0 | 3041896.0 | 3041896.0 | 4.617715809009724 |
| 6 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 1 | 2280142.0 | 2280142.0 | 2280142.0 | 3.4613437672382776 |
| 7 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 1 | 1548145.0 | 1548145.0 | 1548145.0 | 2.350144002667862 |
| 8 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 1 | 1540308.0 | 1540308.0 | 1540308.0 | 2.3382471334799577 |
| 9 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 1 | 1538867.0 | 1538867.0 | 1538867.0 | 2.33605963973238 |
| 10 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 1 | 1535187.0 | 1535187.0 | 1535187.0 | 2.3304732573652123 |
| 11 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 1 | 1171510.0 | 1171510.0 | 1171510.0 | 1.7783975018912486 |