
Python for High-Performance and Scientific Computing. Workshops and BoF sessions held in conjunction with @Supercomputing
United States of America
Joined August 2011
- Tweets379
- Following841
- Followers1.5K
- Likes164
PyHPC retweeted
Python HPC bechmarks v3 are out now!
github.com/dionhaefner/pyhpc…
Δ:
- @PyTorch with greatly improved CPU performance
- @numba_jit still best on CPU, JAX right behind
- @PyTorch and JAX kings of GPU (⬆️20%)
- TPUs got a lot faster (⬆️10x)
- Bohrium & Theano are 💀/ long live Aesara
PyHPC retweeted
Featured in this issue: code generation for finite-element simulation, boundary element solver using OpenCL and @numba_jit, Python at petascale with @PyFR_Solver—all are not-to-miss! ieeexplore.ieee.org/xpl/tocr…
PyHPC retweeted
A new #CiSEmag issue has hit @IEEEXplore—it comes with six articles on the theme of "Scientific Computing With #Python on High-Performance Heterogeneous Systems."
Read the editors' introduction: doi.org/10.1109/MCSE.2021.30…
PyHPC retweeted
A nice blog post comparing parallel-computing engines in Python
cosmiccoding.com.au/tutorial…
Happy to see loky appreciated.
via @glemaitre58
PyHPC retweeted
Hey there @PythonHPC and #Python community, we're close to the deadline for @Supercomputing workshop deadlines. Are folks interested in a #pyHPC workshop this year vs a BoF? Anyone interested in helping organize? Anyone working on papers or have something in mind for a keynote?
PyHPC retweeted
We are thrilled to announce that SC20 will be a fully virtual conference! For more information, including FAQs, visit our announcement on the SC20 blog. okt.to/JTxIy1
PyHPC retweeted
How should we be interacting with #supercomputers in ~3 years time?
Adopt modern productivity focused languages (eg Julia), stick to proven #Fortran+MPI, use #software abstractions (or domain specific libs), or maybe voice control?
Share + comment + #vote now ...
#HPC
40%Productivity languages
28%Fortran + MPI (or equiv)
6%Voice control
27%Abstractions/frameworks
210 votes • Final results PyHPC retweeted
Great work! Rarely was a conclusion so true as in @wesmckinn's @PythonHPC 2011 paper on @pandas_dev: "In our opinion, pandas provides a solid foundation upon which a very powerful data analysis ecosystem can be established." (dlr.de/sc/desktopdefault.asp…) #PyHPC #Python #DataScience
Pandas 1.0 is here!
* Read the release notes: pandas.pydata.org/pandas-doc…
* Read the blogpost reflecting on what 1.0 means to our project: dev.pandas.io/pandas-blog/pa…
* Install with conda / PyPI: pandas.pydata.org/pandas-doc…
Thanks to our 300+ contributors to this release.
PyHPC retweeted
The website for #euroscipy2020 is online euroscipy.org/2020/
PyHPC retweeted
Summer internship projects @NERSC for 2020 in Data and Analytics have just been posted: Python+GPUs, deep learning, Jupyter in HPC, climate data science, AI I/O workload analysis, big data portals & more! Link: nersc.gov/research-and-devel… @ProjectJupyter @PythonHPC
PyHPC retweeted
Our worksflows and distributing computing group leader, @rosabadia, is now giving a BOF on Python for High Performance and Scientific Computing @bsc_compss #SC19
PyHPC retweeted
.@OllyPerksHPC kicks off the #PyHPC @Supercomputing BoF, taking about the performance of python in ARM. What an amazing turnout! The #pyHPCCommunity rocks!
PyHPC retweeted
The CUDA + Python marriage is really a big deal #sc19
PyHPC retweeted
Two short blogposts on Python + HPC:
1. Five reasons to keep your HPC center rather than transition to the cloud
mrocklin.github.com/blog/wor…
2. How to retrofit an HPC center for interactive data science with Conda, Jupyter{Hub,Lab}, and Dask
matthewrocklin.com/blog/work…
PyHPC retweeted
I said "killer app" in 2014, remember? #Jupyter
Data from the GitHub Archive and GHTorrent projects. Analysis by @benfrederickson.
PyHPC retweeted
The #SC18 Website is live now! We can't wait to see you all again next year in Dallas! ow.ly/vT6330gCOEB #LifeAfterSC #HPCInspires
PyHPC retweeted
Replying to @PythonHPC
Slides of my talk—
Barba, Lorena A. (2017): The Sustainability Problem. @figshare.
doi.org/10.6084/m9.figshare.…
PyHPC retweeted
Given @ProjectJupyter current burn rate, $100M/yr is one estimate of funding suggested to sustain open src ecosystem - @LorenaABarba on sustainability at PyHPC during #SC17 – at Denver, CO
PyHPC retweeted
Support Open Source on #GivingTuesday by donating to or fundraising for NumFOCUS: flipcause.com/secure/cause_p…
PyHPC retweeted
Only 2 days until Workshops and Tutorials open at #SC17 - set up your schedule now to ensure you don't miss a thing! ow.ly/iqDK30gv1ok


























