colramos-amd
1.3 KiB
1.3 KiB
| 1 | KernelName | Count | Sum(ns) | Mean(ns) | Median(ns) | Pct |
|---|---|---|---|---|---|---|
| 2 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 1 | 3357916.0 | 3357916.0 | 3357916.0 | 7.842647975878232 |
| 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 1 | 1724957.0 | 1724957.0 | 1724957.0 | 4.028757873790466 |
| 4 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 1 | 1715198.0 | 1715198.0 | 1715198.0 | 4.005965045858917 |
| 5 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 1 | 1697917.0 | 1697917.0 | 1697917.0 | 3.965604060154942 |
| 6 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 1 | 1674397.0 | 1674397.0 | 1674397.0 | 3.910671453028183 |
| 7 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 1 | 1665278.0 | 1665278.0 | 1665278.0 | 3.88937338991641 |
| 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 1 | 885918.0 | 885918.0 | 885918.0 | 2.069123530634504 |
| 9 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 1 | 878719.0 | 878719.0 | 878719.0 | 2.052309761982058 |
| 10 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 1 | 869759.0 | 869759.0 | 869759.0 | 2.0313830545051976 |
| 11 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 1 | 859359.0 | 859359.0 | 859359.0 | 2.007093126183842 |