Question: utilization_watcher algorithm design

[Forsworns]

I found that the algorithm you used is much different from the implementation of vcuda-controller. Why g_total_cuda_cores is multiplied by 2 here? And why the original implementation of vcuda is removed, are they not suitable in your case? Hope you can share your experience on the algorithm design, thanks :)

HAMi-core/src/multiprocess/multiprocess_utilization_watcher.c

Line 213 in a9ab3b1

g_total_cuda_cores *= 2;

And their utilization_watcher is

https://github.com/tkestack/vcuda-controller/blob/72e0115d5884f22469de857271c002c84c0d0543/src/hijack_call.c#L303

[AllenXu93]

Same question