Year: 2019
Type: conference-paper
Abstract: In High Performance Computing, it is often useful to fine tune an application code via recompilation of specific computational intensive code fragments to leverage runtime knowledge. Traditional compilers rarely provide such capabilities, while solutions such as LIBVC allow C/C++ code to employ dynamic compilation. We evaluate the impact of the introduction of Just-in-Time (JIT) compilation in a framework supporting partial dynamic (re-) compilation of functions to provide continuous optimization in high performance environments. We show that JIT solutions can have comparable performance in terms of code quality and smaller compilation overhead w.r.t. the LIBVC alternatives. We further demonstrate the strength of our approach against a state-of-the-art interpreter-based dynamic evaluation solution.
Authors: Marco Festa, Nicole Gervasoni, Stefano Cherubin, Giovanni Agosta
Institution: Politecnico di Milano
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: European Commission
OpenAlex ID: W2921326579