Comment (by Roland Haas):

@Erik Schnetter says:

i found a way to put binary blobs directly into object files, without generating C code in between. this should speed up generating the Formaline objects for our source code quite a bit. thsi project https://git.astron.nl/RD/tensor-core-correlator uses it; look how the `libtcc/TCcorrelator.cu` CUDA file is "compiled".

‌

--
Ticket URL: https://bitbucket.org/einsteintoolkit/tickets/issues/1568/reduce-overhead-of-formaline