Calcul Haute Performance : Caractérisation d’architectures et optimisation d’applications pour les futures générations de supercalculateurs

Information systems and High-Performance Computing (HPC) infrastructures play an active role in the improvement of scientific knowledge and the evolution of our societies. The field of HPC is expanding rapidly and users need increasingly powerful architectures to analyze the tsunami of data (numerical simulations, IOT), to make more complex decisions (artificial intelligence), and to make them faster (connected cars, weather).In this thesis work, we discuss several challenges (power consumption, cost, complexity) for the development of new generations of Exascale supercomputers. While industrial applications do not manage to achieve more than 10% of the theoretical performance, we show the need to rethink the architecture of platforms, in particular by using energy-optimized architectures. We then present some of the emerging technologies that will allow their development: 3D memories (HBM), Storage Class Memory (SCM) or photonic interconnection technologies. These new technologies associated with a new communication protocol (Gen-Z) will help to optimally execute the different parts of an application. However, in the absence of a method for fine characterization of code performance, these emerging architectures are potentially condemned since few experts know how to exploit them.Our contribution consists in the development of benchmarks and performance analysis tools. The first aim is to finely characterize specific parts of the microarchitecture. Two microbenchmarks have thus been developed to characterize the memory system and the floating point unit (FPU). The second family of tools is used to study the performance of applications. A first tool makes it possible to monitor the memory bus traffic, a critical resource of modern architectures. A second tool can be used to profile applications by extracting and characterizing critical loops (hot spots).To take advantage of the heterogeneity of platforms, we propose a 5-step methodology to identify and characterize these new platforms, to model the performance of an application, and finally to port its code to the selected architecture. Finally, we show how the tools can help developers to extract the maximum performance from an architecture. By providing our tools in open source, we want to sensitize users to this approach and develop a community around the work of performance characterization and analysis.