A Methodology and ecosystem for many-core programming

Computers are going through a radical redesign process, leading to novel architectures with large numbers of small cores. Examples of such many-cores are Graphics Processing Units and the Intel Xeon Phi, which are used by about 65% of the top 50 fastest supercomputers. Many-cores can give spectacular performance results, but their programming model is totally different from traditional CPUs. It currently takes an unacceptable amount of time for application programmers to obtain sufficient performance on these devices. The key problem is the lack of methodology to easily develop efficient many-core kernels. We will therefore develop a programming methodology and compiler ecosystem that guide application developers to effectively write efficient scientiffc programs for many-cores, starting with a methodology and compiler that we have developed recently. We will apply this methodology to two highly diverse applications for which performance currently is key: Bioinformatics and Natural Language Processing (NLP). We will extend our compiler ecosystem to address the applications’ requirements in three directions: kernel fusion, distributed execution, and generation of human-readable target code. The project should provide applications and eScientists with a sound methodology and the relevant understanding to enable practical use of these game-changing manycores, boosting the performence of current and future programs.

Subcribe and stay informed about all our researchprojects and achievements

Recent news

WheelPower: wheelchair sports and data science push it to the limit
The Netherlands won 59 medals and finished fifth in the medal standings at the 2021 Tokyo Paralympic Games. TeamNL athletes captured 25 gold, 17 silver and 17 bronze medals. To maintain and even strengthen this position in this rapidly professionalis...
31 October 2022
How can mathematics solve your data science challenge? Sign up for the Study Group
Mathematics provides a surprising amount of techniques to solve challenges in data science. Does your company have such challenges but no time to look into them? Or would you like to strengthen your contacts in the academic world? Would you like to m...
27 October 2022
Project Update: Inquiry into effectiveness and efficiency of self-monitoring based management of Multiple Sclerosis
In late September 2022 - in the middle of this project around digital self-monitoring - we spoke to Lotte Krabbenborg (Radboud University) and Sonja Cloosterman (MS sherpa, formerly Orikami). Lotte Krabbenborg is associate professor of Science in Soc...
24 October 2022

Actuele themas

eScience