Unlike Julia, the Fortran compiler development efforts are not centralized. From what I have learned over the past years, some are very good at debugging (like NAG, GFortran) and some others are historically known for better optimizations (like Intel, Cray, IBM, PGI, …). But these could change at any time. Having and maintaining multiple high-quality compilers takes a lot of effort. For benchmarking purposes, it makes sense to compile Fortran code with all available compilers and report the best result. I think this issue highlights the importance of such activities as Google Summer of Code 2021
3 Likes