Section: New Results

Towards an Easier Way to Program FPGAs in an HPC Context

Participants : Georgios Christodoulis, Manuel Selva, Francois Broquedis, Frederic Desprez, Olivier Muller [TIMA] .

Heterogeneity in HPC nodes appears as a promising solution to improve the execution of a wide range of scientific applications, regarding both performance and energy consumption. Unlike CPUs and GPUs, FPGAs can be configured to fit the application needs, making them an appealing target to extend traditional heterogeneous HPC architectures. However, exploiting them requires an in-depth knowledge of low-level hardware and high expertise on vendor-provided tools, which should not be the primary concern of HPC application programmers. In the context of the Persyval HEAVEN project, we proposed a framework enabling a more straightforward development of scientific applications over FPGA enhanced platforms. Our solution requires the minimum knowledge of the underlying architecture, as well as fewer changes to the existing code. To fulfill these requirements, we extended the StarPU task programming library that initially targets heterogeneous architectures to support FPGAs. We used Vivado HLS, a high-level synthesis tool to deliver efficient hardware implementations of the tasks from high-level languages like C/C++. Our solution, validated on a blocking version of the matrix multiplication algorithm, offers an easier way to exploit FPGAs from an HPC application. We also conducted some preliminary experiments to validate our proof-of-concept implementation regarding performance.

This work has been published in the 13th International Symposium on Reconfigurable Communication-centric Systems-on-Chip and obtained the best paper award.