[bee_rider]

Modern versions of Fortran are reasonably pretty.

It’s a fairly nice language. You can probably get better performance out of C/C++ with unlimited effort. But, it is really nice for allowing computational scientists to get, like, 95% of the way there.

I think it actually suffers from the reputation as this ancient/super hardcore performance language. The name comes from “Formula Translating System,” which implies… it was written for people who speak human languages first!

[sitzkrieg]

ive maintained a simulation software where the core is written in fortran. its using some intel math library that is expensive that i cannot recall, does immense calculations and makes faster binaries than c on every compiler we tried

[bee_rider]

Interesting.

MKL is Intel’s famous numerical library (it includes things like BLAS “basic linear algebra subroutines” and fast Fourier transforms). It is availible for free, but IIRC they had some support plans maybe, maybe that’s what you are remembering?

It is closed source, but you can look at the source of the best open source competitor libflame/BLIS, and see that most of the performance comes from C and assembly.

It is difficult to beat “unlimited effort” C, but not many program really justify that treatment.

[foxglacier]

MKL used to not be free. You had to buy it from a local reseller for a few hundred dollars per developer.

[extraduder_ire]

Have you tried using the restrict keyword everywhere you can in c?

In Fortran, arrays are not allowed to overlap which allows some optimisations. c has rules in the spec about how memory accesses must occur, and overlapping arrays being possible prevents some compiler optimisations. The restrict keyword is you promising that the memory at some pointer won't be accessed through another pointer.

You can compare two implementations in Fortran/c using godbolt to see how each of them compile.

[pklausler]

Dummy arguments may not alias anything else, including other dummy arguments, in conforming Fortran if either are modified, with some exceptions. But there are many ways in which arrays can overlap that don’t involve dummy arguments. GNU Fortran optimizes ASSOCIATE names as if they were free of aliasing, too, but that is a bug.

[sitzkrieg]

i apologize i missed this. the core hot loop was fairly straightforward to optimize and audit all aliasing. we ported from c89 to all cutting edge (at time) c99+ compilers. we still couldnt quite eek out that minor difference. the intel compiler unsurprisingly generated the most close asm for the machine

the fortran library we only had one license on a physical machine, i had to travel for one extensive recompilation of that side lol! it wasnt the library mentioned below, i would have to ask a collegue.