Faces of HPC: Manos Farsarakis
Manos Farsarakis is an Applications Consultant at EPCC, the Scottish Supercomputing Centre at the University of Edinburgh. Prior to working in EPCC Manos completed an MSc in High Performance Computing, also at EPCC, during which time we his team won the Student Cluster Competition at ISC 2014 by breaking the world record for the fastest low-energy cluster at a competition.
Having completed a BSc in Physics at the University of Crete, Manos moved to Edinburgh in 2013. Working at EPCC Manos provides training for ARCHER, the UK National supercomputing service, and providing technical consultancy on a range of HPC projects.
Tell us a bit about yourself.
I was born on an American AF base in Germany and raised in the south of Greece where I completed a BSc in Physics at the University of Crete. During my studies, I was also a teacher in my spare time.
Despite enjoying teaching, I felt that that my own education wasn’t complete; so I moved to Edinburgh to study the MSc in High Performance Computing at EPCC. I would say the most memorable moment of my studies at the University of Edinburgh was when my team won the Student Cluster Competition at the 2014 International Supercomputing Conference in Germany, breaking the world record for the fastest low-energy cluster at the competition.
What is your current job?
After completing the MSc I stayed at Edinburgh as an Applications Developer, later progressing to Applications Consultant. It is a very rewarding experience overall. With my work at the University of Edinburgh, I can take part in ground-breaking research, while at the same time I can continue to enjoy my love of teaching but on a greater and more varied scale. I teach Software and Data Carpentry workshops around the UK as part of the ARCHER supercomputing service, I participate in training for the MSc in High Performance Computing, and I am currently very excited about the launch of our upcoming MOOC on Supercomputing.
How did you become interested in HPC?
Having completed my BSc in Physics and before applying to any MSc programmes, I asked myself which part of my studies I enjoyed the most. The answer was quite obvious: Anything computational. It was no coincidence that I had taken every programming related optional course offered at my department. Though most of these courses focused on numerical analysis and basic programming language learning, I also spent some time on online courses for parallel computing. I was immediately fascinated by the added complexity of splitting up a problem to orchestrate a problem’s distributed solution and bringing all the pieces back together. It was a difficult puzzle which I really enjoyed trying to solve. Needless to say, I was very excited when I received an offer from The University of Edinburgh to study on the MSc in High Performance Computing and am delighted that I have now been part of developing an online course on Supercomputing myself.
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?’
Beyond the world of high performance computing, I have recently taken on the voluntary role of Communications and Media Officer for the University of Edinburgh’s Staff Pride Network, which exists to support LGBT+ staff and allies. It has been interesting, fun and educational for me to interact with so many wonderfully different people. Coming from Greece, where the professional work reality is quite different, I have been inspired by the warmth with which the University has embraced the network and supported the incredible members in their efforts to organise events and engage with the community.
Were there any challenges when you first entered the field?
I think the main challenge I had was with basic programming skills which computer science graduates might not have. Coming from a background in Physics, I faced the problems many STEM scientists run into when their work turns out to be much more computationally oriented than their studies prepared them for. For example, during the first part of my MSc, though I would catch on to the complex HPC-specific parts of courses and coursework fairly quickly, I could easily spend half my time on a project trying to sort out something trivial like how to set up a Makefile. This is one reason I later became involved in Software Carpentry and ultimately Data Carpentry. I now lead Software Carpentry and Data Carpentry workshops for the ARCHER service where the aim is to teach fundamental software development and data skills to researchers of many disciplines.
What’s the best thing about working in HPC?
I get to keep active in the field, collaborating with colleagues and other institutions on projects such as the Intel Parallel Computing Centre – a sponsored lab that focuses on modernising apps – and NEXTGenIO, a Horizon 2020 funded project looking at finding solutions for the IO challenges facing HPC. I get to work with universities and industrial partners from around the world, looking at cutting-edge and future technologies in this field.
If there’s one thing about HPC you could change, what would it be?
Legacy code. :)
What’s next for you in HPC – where does your career lead you?
I love learning new things. A few years ago, that new thing was HPC and I never could have dreamed the things I have experienced thanks to it. Today, that new thing is HPC with Data Science and I can’t wait to see where that may take me.
This interview has been adapted from an interview for the University of Edinburgh ‘Staff Spotlight’ series: http://www.ed.ac.uk/alumni/services/staff-spotlight/pride-in-his-work