You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using ytopt for running a few thousand sampling tests. I want to know if there is any way to run them in parallel or speed up the searching somehow.
I have inputs such that almost 60% of sampling inputs are false positives, so even reducing them from the total sampling space would also be another pointer I wish to know if any.
I tried to use the conditionals and forbidden but they don't seem to be applicable for the use case which I am trying to get working, my usecase is that I want to keep the multiplication of tx * ty which are 2 integer hyperparameters below 1024 which refers to the threadIdx.x andthreadIdx.ywhich should be less than 1024 the total thread limit on a GPU, any suggestions would be helpful.
Thanks
The text was updated successfully, but these errors were encountered:
Sorry for the late response. Yes, you can try our latest development https://github.com/ytopt-team/ytopt-libensemble to run them in parallel to speed up the search and evaluation processes. For your case, you can add the constraint in your parameter configuration space to make sure x * y < 1024 using LessThanCondition.
I am using
ytopt
for running a few thousand sampling tests. I want to know if there is any way to run them in parallel or speed up the searching somehow.I have inputs such that almost 60% of sampling inputs are false positives, so even reducing them from the total sampling space would also be another pointer I wish to know if any.
I tried to use the
conditionals
andforbidden
but they don't seem to be applicable for the use case which I am trying to get working, my usecase is that I want to keep the multiplication oftx * ty
which are 2 integer hyperparameters below 1024 which refers to thethreadIdx.x
andthreadIdx.y
which should be less than 1024 the total thread limit on a GPU, any suggestions would be helpful.Thanks
The text was updated successfully, but these errors were encountered: