Pramod Kumbhar

> If possible it would be great if you can run the code again with GOTCHA_DEBUG=3 set as an environment variable and send us the debug output Certainly! Here is...

I have to see if it’s possible/easy to extract a small reproducer. A certainly doable/straightforward thing would be to provide a docker container as a reproducer. Would that help?

Sorry for delay. We will try to create one and share with you.

I think we can close this issue. @alkino provided details and helped to fix LLNL/GOTCHA/issues/142.

There are also FMT related ones now: ```console "/home/kumbhar/workarena/repos/bbp/nrn/external/fmt/include/fmt/format.h", line 594: warning: routine is both "inline" and "noinline" [inline_gnu_noinline_conflict] FMT_CONSTEXPR FMT_NOINLINE auto copy_noinline(InputIt begin, InputIt end, ^ Remark: individual warnings...

@ramcdougal: I don't have an idea for `(1)` but for `(2)` created https://github.com/neuronsimulator/nrn/pull/2944. I didn't check much details but I assume `(2)` is not causing any failures.

> By disabling sse features I mean that we still have scalar epilogue loop to process and optimise But with instance size of `20000000`, epilogue loop is not executed i.e....

Copying from Slack: The --backend XX option is working somehow funny. We [disables cpu features](https://github.com/BlueBrain/nmodl/blob/524b2920db1437944800fb380dbb8fe0d7655c01/src/codegen/llvm/llvm_benchmark.cpp) based on this option and that causes always to use SSE registers. So if we...

yes, exactly! I saw the same. When you implemented this, did you see how clang or other frameworks "prefer" specific instruction set? I just started skimming through numba but haven't...

@JCGoran : Apologies for not able to provide this earlier. As mentioend during the standup, I scanned the commits and here is my summary. I might have missed few things...