Events

Online-seminar "Supercomputing Software for Moore and Beyond"

Dear Colleagues,
on Wednesday, February 15 at 17:00 MSK within the consortium "Network and Cloud Technologies" online-seminar from SIAG/Supercomputing will take place.
The seminar is one of a series of seminars "Supercomputing Spotlights". Supercomputing Spotlights is a new webinar series featuring short presentations that highlight the impact and successes of high-performance computing (HPC) throughout our world. Presentations, emphasizing achievements and opportunities in HPC, are intended for the broad international community, especially students and newcomers to the field. Supercomputing Spotlights is an outreach initiative of SIAM Activity Group on Supercomputing ... Join us!

Topic: "Supercomputing Software for Moore and Beyond"

Speaker: Didem Unat, Koç University, Turkey

Annotation:

Thanks to the predictable trend of Moore’s Law during the past decades, supercomputers have shown great performance increases, opening the doors for incredible innovations and discoveries. However, due to unavoidable limits in chip manufacturing and rising energy consumption, the techno-economical model of Moore’s Law is (arguably) ending, stagnating the growth of computing and thus supercomputers. Regardless of the pessimism around Moore’s Law, as a community, we need to prepare our applications for what’s there and what’s upcoming. The arithmetic processing capabilities and complexity of systems continue to increase as multicore and accelerators are added to systems. Moreover, the improvement rates of both memory bandwidth and latency are much slower than that of the computing power, and the Post-Moore era makes data locality even more important. These trends urgently call for innovative software solutions to improve the usability and efficiency of supercomputers, and require doubling software efforts for more data locality-aware and seamless cooperation on both existing and emerging architectures. In this talk, I will explain the history of supercomputing in the context of data locality, our community efforts in the PADAL-series of workshops, and how we have shifted over the years from compute-centric to more data locality-centric programming.

Register