This commit is contained in:
2025-09-21 20:19:17 +08:00
parent e72ed61b5d
commit aab5a3a910

View File

@@ -0,0 +1,15 @@
#ifndef _CUDA_UTILS_H
#define _CUDA_UTILS_H
#include <cmath>
#define TOTAL_THREADS 1024
#define THREADS_PER_BLOCK 256
#define DIVUP(m,n) ((m) / (n) + ((m) % (n) > 0))
inline int opt_n_threads(int work_size) {
const int pow_2 = std::log(static_cast<double>(work_size)) / std::log(2.0);
return max(min(1 << pow_2, TOTAL_THREADS), 1);
}
#endif