-
Notifications
You must be signed in to change notification settings - Fork 33
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Pops init on demand #282
base: master
Are you sure you want to change the base?
Pops init on demand #282
Conversation
Is it really worth optimizing out the simple reading of vmesh extents etc? That's quite limited reads, isn't it? |
When extracting a time series of a bulk value over a thousand files? I'd hope it'd help a bit. |
Test, open a full set of bulk files as readers import pytools as pt
import glob
import cProfile
fns = glob.glob('/wrk-vakka/group/spacephysics/vlasiator/3D/FHA/bulk1/bulk1.*.vlsv')
print("Opening readers on ",len(fns),"files")
cProfile.run('readers = [pt.vlsvfile.VlsvReader(f) for f in fns]', sort='cumulative') I ran the same script for both unoptimized and unoptimized branches twice in succession to try and keep the Vakka filesystem pre-heated; the first script runs were 61.075 seconds and 14.501 seconds, pre-heated ones 19.727 seconds and 2.359 seconds respectively. Below the pre-heated full outputs, notably: 2118622 vs 458154 function calls Unoptimized:
Optimized:
|
... for less reads when creating VlsvReaders.