Midwest Research Computing and Data Consortium
Research Cloud Infrastructure Manager at Indiana University Bloomington
Exploring the Landscape of Midwest Research Computing and Data Consortium
This is a series where we’re diving into the world of the Midwest Research Computing and Data Consortium, exploring its members, the challenges, and future prospects. We had the opportunity to speak with Jeremy Fischer, Research Cloud Infrastructure Manager at Indiana University Bloomington, who shared his insights on the field. Edited excerpts below:
Journey from Audio Engineering to Research Cloud Infrastructure
My journey into IT was somewhat unconventional. While pursuing my undergraduate degree in Audio Engineering, I worked part-time for the university’s computing services. This experience, starting from support to LAN and Unix support and eventually leading to managing enterprise services, paved my path to where I am now. Starting in support provided me with a unique perspective, making me a better system administrator and manager because I know what it’s like to be on the front end of things, taking heat from users (laughs).
Leading Jetstream2: A Unique Cloud Resource
Jetstream2 is unique in the NSF-funded infrastructure as the only cloud resource among traditional HPC resources. This uniqueness is both a challenge and a blessing. While it sometimes struggles for recognition alongside HPC resources, it fills a niche for persistent services and prototyping, offering types of services that traditional HPC can’t easily provide.
The Importance of Collaboration in Research
Collaboration is crucial everywhere in research and we’re focusing on automation and data sharing to make collaboration easier. The flexibility and accessibility of Jetstream have fostered cooperation in research and software development, enhancing the quality of scientific research and tools available for it. For instance, Jetstream2 offers shared volumes and a shared application store.
Reducing Barriers to Science and Education
Both Jetstream and Jetstream2 have contributed significantly to education, providing core hours for educational purposes across all fields of science. In general, it’s hard to get GPU resources right now, but by subdividing GPUs we make it possible for an educator to be able to get a class of 20 students, 50 students, or 100 students, and they can have a slice of a real GPU that will act like a real production level, enterprise level GPU. By making advanced computing resources accessible for educational purposes, we’re supporting the training of the next generation of researchers.
Future of Cloud Infrastructure and HPC Barriers
On the non-technical side, it’s difficult getting the word out to everyone that there is a resource here, paid for by the National Science Foundation and freely available for use by US-based researchers. Looking forward, we aim to reduce the technical and non-technical barriers in HPC and cloud resources, making advanced computing more accessible to all researchers.
Advice for Aspiring Professionals
The most important trait is a desire to always know more. For anyone interested in this field, basic programming skills and an understanding of security theory are crucial. Continuous learning and embracing the never-ending nature of challenges are what make this field exciting and rewarding. We’re open to working with anyone interested in research computing and cloud infrastructure. Our goal is to speed up the ‘time to science,’ which includes educating researchers and training the next generation. We believe in the power of collaboration to make research and education more effective and accessible.