Powered by:
Open Science Grid
Center for High Throughput Computing

Large-Scale Computing Request Form

Please fill out the below form in order to provide us with information about the large-scale computing work you would like to do (to the best of your knowledge). Your request will be received by a Research Computing Facilitator with the Center for High Throughput Computing (CHTC), who will contact you to set up a consultation, during which time the relevant server accounts will be created. A faculty sponsor (usually, a faculty advisor or project PI) will need to be present for only the first meeting that CHTC has with a new research group.

New accounts for researchers in the same group (after that group is initially set up) can be requested by filling out the below form again, or by sending an email to chtc@cs.wisc.edu with the PI named and cc'd. CHTC staff meet with all new users, and meetings with multiple new users at the same time are even better.

Please note that if you are unsure of an answer to a below question, you can answer 'I don't know'. One of CHTC's Research Computing Facilitators would be happy to help you work out the details.

About you and your research:

Full Name:
UW NetID: @wisc.edu (What is a NetID?)
Preferred Email:
Principal Investigator (Faculty Advisor) for your research:
(Please enter "Self" if you are the PI)
How did you hear about us?
Best times to schedule an initial consultation? (The PI will need to be present if we haven't met with them before.)
Briefly describe your research to help us answer the question, "What research does CHTC help with?":
Why do you need to use large-scale computing for this research?

About Your Computing Work

Program name(s) and coding language(s)
Are there any special dependencies or compiling considerations you've had to deal with?
Tell us where you've run similar computing work before: desktop, shared cluster, etc.? Linux, Windows, Mac?
Do you typically run your program(s) with multiple processors working/communicating with one another? If so, how have you accomplished that? (OpenMP/MPI, etc?):
Could your computing work be broken up into many separate, but complete 'pieces' that don't rely on one another? If so, how many pieces can this computing work be broken into?
Typical input and output size for each 'piece' (can be a range):
Typical RAM and number of CPU cores necessary for each 'piece'?
How long does one piece run in your typical setup?
Is there anything else you'd like to share about your computing practices or methods?
Based upon information on our Large-Scale Computing Page, is your computing work best described as 'high-throughput' computing, 'high-performance' computing, or both?
I'm not sure