| 2270 | }; |
| 2271 | |
| 2272 | tensor_core_scale_t tensor_core_scale(int sm_capability) { |
| 2273 | if (sm_capability >= 90) return tensor_core_scale_t::warpgroup_k; |
| 2274 | if (sm_capability >= 80) return tensor_core_scale_t::warp_k; |
| 2275 | if (sm_capability >= 70) return tensor_core_scale_t::quadpair_k; |
| 2276 | return tensor_core_scale_t::single_k; |
| 2277 | } |
| 2278 | |
| 2279 | /** |
| 2280 | * @brief Runs the benchmark loop for precompiled CUDA C++ kernels using |
no outgoing calls
no test coverage detected