Check out the great write up from Univa about our use of cloud computing for high-performance computing. We have been using UniCloud to provide a seamless cloud computing solution to Wharton researchers. https://blogs.univa.com/2017/09/leading-us-into-the-cloud-a-new-case-study-featuring-the-wharton-school/
News
More RAM for All
We recently adjusted the amount of RAM / memory available to all users of the High-Performance Computing Cluster (HPCC). The default all.q job queue cap has been raised from 640GB to 1024GB, a whole terabyte of memory! Additionally, if you are not familiar with the short.q job queue, please give…Read More
Amazon Web Services (AWS) Archiving
via S3 + Glacier via Bucket Lifecycle Rules Since Amazon’s Glacier can be a good bit more difficult to work with directly than their S3, unless you have trivially small needs or untrivially deep pockets I recommend a hybrid solution: S3 + Glacier. I prefer to use S3 via the awscli Python module for…Read More
WRDS “Value Add” Products Presentation
We’re pleased to announce that WRDS (Wharton Research Data Services) will be here at Wharton presenting an overview of several new and powerful “Value Add” products that they have created for their researchers (that means you!). Please join us for this overview and Q & A session with Luis Palacios, PhD…Read More
Naive Bayes Classification Across Multiple Features
Working with Jehoshua Eliashberg and Jeremy Fan within the Marketing Department I have developed a reusable Naive Bayes classifier that can handle multiple features. This is a useful algorithm to calculate the probability that each of a set of documents or texts belongs to a set of categories using the Bayesian method. The package…Read More
[DEPRECATED] EPO PATSTAT 2016b (Fall) is Here!
2018-10: PATSTAT IS DEPRECATED AT Wharton! Please contact research-computing@wharton.upenn.edu for alternative patent data methods. We currently recommend Google BigQuery. Wharton Research Computing is excited to announce the European Patent Office’s PATSTAT Fall 2016 (2016b) worldwide patent data. We have loaded Fall 2016 PATSTAT onto our HPC systems, including: raw CSV files (in ZIPs) at /data/PATSTAT/patstat2016b indexed tables…Read More
Julia is Here!
Welcome to Julia Julia is now installed across all compute servers of Wharton’s HPC systems. From the Julia Website: Julia is a high-level, high-performance dynamic programming language for technical computing, with syntax that is familiar to users of other technical computing environments. It provides a sophisticated compiler, distributed parallel execution,…Read More
[DEPRECATED] Worldwide Patents Database: PATSTAT
2018-10: PATSTAT IS DEPRECATED AT Wharton! Please contact research-computing@wharton.upenn.edu for alternative patent data methods. We currently recommend Google BigQuery. Wharton Research Computing is delighted to announce the acquisition and hosting of a patents database that covers industrialized nations as well as the leading developing nations. PATSTAT is created by the…Read More
More Memory for High-Performance Computing Cluster
We have added 1.5 terabytes of memory to The Wharton High-Performance Computing Cluster (HPCC). This upgrade takes the system to over 6TB of total available memory for our research computing needs. After the upgrade, we now have three compute nodes with half a terabyte of memory each! This is a…Read More
WRDS Data Directly from Python, R, and MATLAB
DEPRECATED! We’re working on documentation for connecting to WRDS via their newer PostgreSQL service See https://wrds-www.wharton.upenn.edu/pages/support/programming-wrds/ for details for newest methods … some adjustments to the WRDS documentation are needed, generally installing any libraries, packages, or modules required (Python: ‘wrds’, R: RPostgres, etc.) Original Article (DEPRECATED): Using Wharton Research Computing’s…Read More