Extend CuPy benchmark with more operations

[pentschev]

No description provided.

[quasiben]

Thanks @pentschev -- should I add this to the nightly runs ?

[pentschev]

Thanks @pentschev -- should I add this to the nightly runs ?

I think that's not necessary for now, I'm mostly adding this as part of the PTDS work, I think it may be more useful once we have actual support for that in CuPy, RMM, etc.

[codecov-io]

Codecov Report

Merging #488 (8ae2a16) into branch-0.18 (32d9d33) will increase coverage by 0.72%.
The diff coverage is n/a.

@@               Coverage Diff               @@
##           branch-0.18     #488      +/-   ##
===============================================
+ Coverage        90.42%   91.14%   +0.72%     
===============================================
  Files               15       18       +3     
  Lines             1128     1446     +318     
===============================================
+ Hits              1020     1318     +298     
- Misses             108      128      +20     

Impacted Files	Coverage Δ
dask_cuda/device_host_file.py	90.69% <0.00%> (-8.17%)	⬇️
dask_cuda/cuda_worker.py	76.66% <0.00%> (-0.35%)	⬇️
dask_cuda/cli/dask_cuda_worker.py	96.92% <0.00%> (ø)
dask_cuda/proxify_host_file.py	100.00% <0.00%> (ø)
dask_cuda/get_device_memory_objects.py	89.04% <0.00%> (ø)
dask_cuda/proxify_device_objects.py	85.71% <0.00%> (ø)
dask_cuda/local_cuda_cluster.py	81.17% <0.00%> (+0.68%)	⬆️
dask_cuda/proxy_object.py	90.62% <0.00%> (+2.82%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 32d9d33...8ae2a16. Read the comment docs.