Skip to content
Main menu hidden.
Published: 2024-05-31 Updated: 2024-06-12, 08:00

Math lecture gave ideas for collaborations

NEWS The Department of Computing Science at Umeå University is celebrating its 30th anniversary by organising popular breakfast talks, ‘Breakfast Talks in Computing Science’. Professor Paolo Bientinesi, group leader, expert in high performance computing and director of the High Performance Computing Centre North (HPC2N), talked about the efficiency of different programming languages for linear algebra computations.

The Department of Computing Science is celebrating its 30th anniversary as a department by, among other things, highlighting its own research through popular science breakfast lectures, ‘Breakfast Talks in Computing Science.’ These are intended for the general public as well as for staff and students at the university.

Paolo Bientinesi, Professor of Computing Science specialising in High Performance Computing and Director of the High Performance Computing Centre North (HPC2N) was the first speaker. He sees the breakfast lectures as a good initiative.

‘Our department has been expanding rapidly and in all sorts of directions. These talks provide an opportunity to learn more about each other's interests, strengths and experiences,’ he says.

Under the title ‘Can We Trust Programming Languages to Compute Efficiently?’, he talked about the problem of how different programming languages handle mathematical computations. The starting point of the lecture was how to solve linear algebra problems with different approaches. Paolo explained and reasoned about the problem to an audience of around 40 people.

An interested and diverse audience

Paolo reflected on his breakfast talk and shared his impressions of the audience.

‘The room was completely full, which is always a nice feeling. I saw doctoral students from many different research groups, master students, as well as several senior professors,‘ said Paolo. He appreciated the broad mix of audience members, only a few of whom were familiar with the topic.

After the talk, he received very positive feedback. ‘Many people appreciated the historical perspective, and the fact that the overall content of my lecture was clear even with little knowledge of numerical linear algebra,’ he added. 

Mathematical modelling in biological research

One of the listeners was Hemamshu Ratnakaram, a doctoral student at the Department of Forest Genetics and Plant Physiology, Swedish University of Agricultural Sciences. As a biologist, he is researching how the outer protective layer of plants affects their growth and development. The information he obtains from his research is then processed using a number of computational methods for further analysis. He found the talk interesting and has gained a broader view of how different computer systems handle complex mathematical calculations in different ways.

‘Even though I have some mathematical background, I can't exactly understand the limitations of our mathematical models and that's where a collaboration with the Computing Science department is interesting,’ says Hemamshu.

As he gets further into his research, he is interested in connecting with experts in the Department of Computing Science and HPC2N.

 ‘With researchers like Paolo Bientinesi and his deep knowledge of complex calculations and processing of large data sets, a collaboration can provide better results and understanding of the research I am doing,’ he says.

Interdisciplinary collaboration opportunities

As team leader and director of HPC2N, Paolo Bientinesi strongly believes that talks like this can lead to collaborations between departments and across faculties.

’ Both HPC2N and my research group act as support for other researchers. We don't discover new medicines or materials ourselves; we are the ones who enable others to solve mathematical operations correctly and efficiently on a variety of computational platforms,’ he said.

He emphasised that these types of non-technical talks should allow researchers in other departments to see what they can gain from collaboration. 


Clip from Breakfast talk 1

BReakfast talk in CS:_ Paolo Bientinesi

Can we trust programming languages to compute efficiently?

Long gone are the times when computers were only accessible by selected researchers at a handful of institutions; nowadays, just about every researcher has access to powerful computing devices.

Over the course of the years, as computers became more widespread, programming languages also evolved. Traditional programming languages (e.g., C and Fortran) are being progressively replaced by "high-level" languages and frameworks (e.g., Matlab, Python, R, Julia, TensorFlow) that far are more user-friendly. Thanks to convenient and intuitive syntax, these languages make it easy for programmers to express new and complicated ideas with ease, thus greatly improving their productivity. Indeed, programmers can now work with complex data types directly, without any need for loops and intricate indexing.

However, by adopting high-level languages, programmers delegate to compilers more responsibility for the translation of programs into efficient low-level code. In this presentation, we focus on vector and matrix computations, which are at the heart of disciplines such as statistics, data science, signal processing, and countless other applications in science and engineering. We investigate whether or not programmers can trust popular programming languages to generate fast code. Maybe surprisingly, the answer is a resounding no. Because of this, this talk is of importance to both users and developers, as the gains in productivity are likely paired with unexpected losses in computer efficiency, i.e., unnecessarily high energy consumption.

Short Biography
Paolo Bientinesi is professor in High-Performance Computing at the Department of Computing Science, Umeå University, and director of the High-Performance Computing Center North (HPC2N).

He completed his Laurea degree in computer science at the University of Pisa (Italy, 1998), and received his Ph.D. from The University of Texas at Austin (US, 2006). Before moving to Sweden, he was professor at RWTH Aachen University (Germany, 2008).

His research interests include matrix and tensor operations, automatic algorithm & code generation, performance modeling, and computer music. Paolo leads the research group High-Performance and Automatic Computing (HPAC, hpac.cs.umu.se, https://github.com/HPAC).