Try to use avx_hs() - slow and requires alignment 4096 bits < (l.size*l.siz...

AlexeyAB

2018-08-08 a284a7da8d1facbf984a22302665a2a50295a687

 src/darknet.c

@@ -377,6 +377,7 @@
#else
    if(gpu_index >= 0){
        cuda_set_device(gpu_index);
        check_error(cudaSetDeviceFlags(cudaDeviceScheduleBlockingSync));
    }
#endif