Announcements for users
The center just acquired a new server configured for GPU processing. It has 48 processing cores, 392GB of ram and 8 nvidia 2080-ti GPUs. It is specifically configured for deep learning research. It’s primary user is the marketing department.
A new VMWARE server has been added to the Stern Cloud. It has a 16GB Nvidia V100 GPU which is directly attached to the virtual machine Comp7gpu1. The GPU can be accessed from a grid job, by adding #$ -l GPU=1,h_vmem=64gb to the grid submission script. matlab, tensorflow and pytorch have all been tested on… Read More ›
NYU/ITS (Information Technology Services) have recently added two major new facilities. 1) They have retired one of their HPC clusters and replaced it with a much more powerful cluster, mercer. Mercer is a 394-node, 5812-core heterogeneous cluster based on Intel x86_64 architecture. It is partially owned by several research projects. but time is available to… Read More ›
UCLA SAS materials https://www.ats.ucla.edu/stat/SAS/sk/default.htm Is a complete intro and overview to SAS. It has examples, videos, data sets etc. A good way to both get started with SAS, as well as find advanced techniques.
Hadoop is a linux based processing system, so to use it you need to be reasonably familiar with unix/linux commands. The login system for the hadoop cluster is bigdata.stern.nyu.edu. It has a large storage area (/bigtemp) for temporary file storage, since most users home directories are limited in space. (< 1GB) The /bigtemp area can… Read More ›
The Hadoop cluster at Stern has been retired. Users should now use the new PEEL cluster at the NYU HPC.
The Center now has a Hadoop cluster running which can be used for large i/o intensive workloads. This infrastructure is based on the open source apache hadoop. In this environment, a data file is split across many systems, and a program is sent to all of the nodes a file is on rather than bringing… Read More ›
The Stern Center for Research Computing now has 5 large servers providing a cloud computing environment for Stern researchers. Researchers needing specialized servers can have them quickly implemented in the cloud, without purchasing new hardware. We now have about 100 virtual servers running in the Stern Cloud. Any intel based OS can generally be supported,… Read More ›
An add-on to SAS has been purchased by members of the IOMS Department. It has a graphics interface to the SAS Data Mining Procedures. Users wishing to use it need to have their account enabled by Dan Graham (firstname.lastname@example.org).