yngtdd / hyperspace Goto Github PK

Is there a way to change the HyperSpace models to use less than a node per process? This will be the case for XSEDE-Bridges if we decide to run simulations, as we won't have enough nodes to spawn 16 MPI processes in which each process takes a node. Also for Summit the number of cores/node will fluctuate anywhere from 42 cores to 128 cores. Ideally we would want to have each process use the same number of cores, but we should benchmark what is the sweet spot on the optimal number of cores per process.

how to fix this issue？

For the purpose of performing strong scaling experiments using HyperSpace, I propose the following:

HyperSpace as it is has a method called “hyperdrive” which runs each subspace/optimization on its own single rank/core. There is also “dualdrive” which runs 2 subspaces/optimizations per rank/core.

In order to perform strong scaling, we would need to create more of this functions, e.g. quadrive, octadrive, etc (I made those names up), so we can run 4 optimizations per rank, 8 optimizations per rank, 16 optimizations per rank, etc.

Eventually, we would like to name this method something like “multipledrive”, and specify the number of optimizations we would like per rank/core as an argument.

You can see a more detailed conversation about the topic in the following issue:

Yeah, that would be possible. In the case that `num_subspaces > num_ranks`, we could place the remaining `num_subspaces - num_ranks` on ranks that already have a search space to work on. I don't think that would take much to make that happen.

Originally posted by @yngtodd in #23 (comment)

In addition to current packages, based on my experience some machines will also require installing cython

When I do from hyperspace.space.skopt.mapping_space import check_dimension, fold_spaces, the hyperband module appears to have a syntax issue:

.../hyperband.py", line 69
    print(f'Rank {rank} Iteration number: {i}, Func value: {result.fun}')

Latin hypercube sampling currently handlings integer and real valued dimensions.

Possible steps for categorical dimensions:

• Create helper function that maps categorical dimensions to integer (based on index).
• Handle categorical dimensions inside of lhs_start()

When I run python ~~~/benchmarks/rastigrin/benchmark.py

I met bellow error

ImportError: cannot import name 'robodrive'

Hello,

I used to use the package

scikit-optimize 0.5.2

and it worked fine.

When I try my same experiment but using

scikit-optimize 0.7.4

I have the following error:

File "/home/karahbit/ve-radical.hpo/lib/python3.6/site-packages/skopt/space/space.py", line 234, in __init__
    self.log_base = np.log10(base)
TypeError: loop of ufunc does not support argument 0 of type NoneType which has no callable log10 method
AttributeError: 'NoneType' object has no attribute 'log10'

If I go back to 0.5.2, it stills works fine.

I am leaving this issue open here just in case.