A ‘butterfly mind’ finds freedom in the diversity of the HPC landscape.
Guest post by: Alisa Alering, Science Node
First published on Science Node on 1st October 2019
Our Paths to HPC series, presented in collaboration with Women in HPC, showcases women working in high-performance computing. Our hope is that by highlighting these trailblazers—and the sometimes unique paths they followed into the field—other women will feel inspired to envision themselves in similar roles.
Today we talk with Weronika Filinger, HPC applications consultant, Edinburgh Parallel Computing Centre (EPCC), The University of Edinburgh.
What was your path to working with HPC?
Although, I studied mathematical physics in my undergrad, I ended up selecting a computational physics topic for my master thesis. I wrote a code simulating bootstrap percolation on complex networks and very quickly realized that a standard workstation or a laptop were not powerful enough for my simulations. My supervisor helped me to get access to one of the compute clusters available to university researchers, and that was my first contact with HPC.
Later I discovered that EPCC runs an MSc degree program in HPC so I applied, got in, finished it, and was offered a job. My path was rather straightforward, and I think typical for many scientists getting into HPC: our need for HPC put us on this path and we simply moved forward. I never imagined I would be doing any sort of software development but I’m glad I do.
What do you like about working with HPC?
I have a butterfly mind so focusing all my energies on one thing only is actually very tiring, sometimes even demotivating.
I have many interests, and I like to be involved in many different things. That’s exactly what my job allows me to do!
The HPC landscape is very diverse in terms of technologies, scientific domains, and roles you can fill. Sometimes it does feel like a mix-n-match kind of job—one day you can work on improving the performance of MD (molecular dynamics) code on GPUs (graphics processing units), the next you implement a graph algorithm for a new type of architecture, or help a health researcher run her analysis of movement data on a cluster, or read about benchmarking of FPGAs (field-programmable gate arrays), or design an online course on supercomputing.
Over the last 5 years, I’ve worked on a number of projects involving different programming languages, methodologies, technologies, and scientific domains. My main project at the moment is DEEP-EST, and I just took over teaching an online course which is part of our online MSc.
Besides doing my technical work, teaching, and outreach, I’m also involved in the Women in HPC organization, ACM SIGHPC Education Chapter, International HPC Certification Program, and International HPC Summer School. I really cannot think of another job that would allow me to do so many different things and travel so much.
Sometimes you don’t need anyone to show you the way, you just need the space to explore on your own without being blocked or restricted.
What are some of the challenges you have faced in following this path?
When I started working I didn’t really realize the importance of networking and socializing within a workplace. I was interacting with a small group of people only and that meant I missed out on some opportunities. People need to know you to think of you when something comes along. When I finally got a chance to go to the SC conference, I made sure to expand my network outside as well.
The other two challenges are more observations than things I actually struggle with. Boring things are, well boring. Working in HPC doesn’t always mean doing exciting things, there is also a fair bit of drudgery to it. After all, someone has to make sure that things work the way they should or work on not-so-exciting projects. Almost nothing works out of the box, the documentation is rarely what you would hope for, and you often need to figure things out on your own. All of that can be very frustrating. That’s fine, it’s part of the job.
However, sometimes I feel there is an invisible line drawn between people working on exciting projects and people who end up doing the mundane tasks to ensure everything gets done, and it’s hard to cross that line. Also, I often feel that people working at HPC centres are jacks of all trades and masters of none. We dabble in so many different things that sometimes it’s difficult for us to say we are experts in any of them.
Any mentors or role models you would like to thank?
I’m incredibly lucky to have parents who encouraged me to do everything and anything I was interested in. This freedom is so deeply ingrained in my thought process that I do it instinctively, and regardless of what others may think. I hadn’t realized the importance of role models and mentors until fairly recently when I became involved in a couple of mentoring programs.
I’ve learned a lot from being a mentor. I always felt things were simple: either I was interested in something or I wasn’t, and my actions followed suit. Now I know that being allowed to follow my interests was the best thing that could have happened to me.
I don’t want to diminish the importance of mentors and role models, but sometimes you don’t need anyone to show you the way, you just need the space to explore on your own without being blocked or restricted. I’m very grateful to the many people who supported me over the years and let me grow my way.
About the author: Alisa Alering, Managing Editor, Science Node
Originally trained as a librarian, Alisa loves tracking down the science behind her stories and learning something new about technology every day. With previous experience as a freelance writer and photo editor, she has held positions at Indiana University Press, PBS, and Google and earned degrees from Penn State and Indiana University. She particularly enjoys writing about women and diversity in technology, digital humanities, and the intersection of science and the natural world.
About Science Node
Science Node is an online magazine that connects the global research community, exploring how tech works and showing why it matters to our everyday lives. sciencenode.org