Faces of HPC: Ben Eagan
Ben Eagan is the High Performance Computing Developer for Geosoft, a geophysics software company. Growing up with a love for the outdoors has provided Ben with a unique and creative approach to problem solving in HPC.
Ben Eagan has a degree in Physics as well as an MSc in HPC. Coming into HPC from physics and now working in geophysics as an HPC specialist. Ben has come across Imposter Syndrome during his career and discusses how it can have a particular impact in a field that is as multi-disciplinary as HPC.
Tell a bit about yourself – where you’re from, what you’ve studied and where, and what some of your outside interests are.
I am from Canada, and studied Physics at Queen’s University. I went to the University of Edinburgh for my Master’s in High Performance Computing. Edinburgh was a great place to study for a folk music and history fan like myself. I also enjoy hiking, mountain biking, and photography.
What is your current job? Describe what you do in HPC. Is this your main interest, or something you fell into?
I am the High Performance Computing Developer at a company called Geosoft. Geosoft is an old company with lots of scientific workflows. My role is to port these to HPC hardware, either using our cloud compute servers, or the users multi-core and GPU hardware. Geophysics is new to me and has been fun to learn, but the HPC involved is my main interest. I found this job through a recommendation on LinkedIn.
How did you become interested in HPC? Briefly describe your path into HPC.
In my Physics undergraduate studies, I did as much computational physics as I could manage. The ability to use simulations to test theories really fascinated me. So when I graduated, I did some searching for ways to get better at writing scientific software, which lead me straight to HPC.
As part of this project we want to celebrate the diversity of HPC, in particular to promote equality across the nine “protected” characteristics of the UK Equality Act, which are replicated in world-wide equality legislation. Do you feel an affiliation with this matter, and if so how has this interacted with or impacted your job in the HPC community?’
In physicist Neil Turok’s book The Universe Within, he discusses the how upbringings and beliefs have an impact on problem solving methods. In science we need as many perspectives as we can get. I do not personally relate to any protected characteristics, but I embrace the goal completely and support equality at every opportunity.
Is there something about you that’s given you a unique or creative approach to what you do?
I was raised in a small town surrounded by farms and barns. Growing up, I built a lot of tree forts, skateboard ramps, catapults, etc. I believe this has encouraged me to play with hardware as well as software without worrying about doing a perfect job.
Were there any challenges when you first entered the field? How have you overcome these, or do they continue to challenge you?
Imposter syndrome is something we all face. The more technical jargon there is the easier it is for this feeling to persist, and HPC puts you in the middle of both Scientists and Computer Scientists. Due to the collaborative nature of HPC, you have to accept you can’t be an expert in everything, and learn to openly share your shortfalls. Learning to spot imposter syndrome also allows you to help mitigate it for your peers, and makes one realize how pervasive the feeling is.
What’s the best thing about working in HPC?
The best part of the HPC industry is the types of problems we get to solve. If someone is seeking out HPC resources, there is a good chance they have an interesting problem on their hands!
If there’s one thing about HPC you could change, what would it be?
I wish there was a stronger emphasis on good software practices. A lot of Scientists see testing, version control, and documentation as a second priority. As a result, many problems are being constantly re-implemented, and a lot of good work gets lost because the challenge of technical transfer is too great.
What’s next for you in HPC – where does your career lead you?
I would like to focus on C++17 language changes that introduce lambda operations and execution policies. If GP-GPU code can accept lambda functions, I believe a great deal of complexity associated with GP-GPU development will disappear. I am also excited by advances in machine learning, and the similarities to matrix solver methods. I hope to combine these techniques sometime soon.