brandongc

The "trivial" implementation also does not give equivalent results to `log2` from libm for numbers other than those special cases. Consider ```fortran module m_libm interface function libm_log2(x) bind(C, name="log2") use,...

Thanks for the detailed reply (including pointing out some errors on my part). Hopefully this points to the utility of a high quality implementation of `log2` for inclusion in stdlib....

By this logic there is no point in having any features in fortran that exist in any C standard library. I don't know the full history of including a variety...

Looks like we lost some replies to this issue. I will attempt to summarize some of the points made so they are not lost: 1. Naive comparison of results of...

Thanks for the pointer! I had not seen that talk or code.

@tom95858 From what I understand you already talked with Eric about this? I didn't see a public issue with the request so apologies if there is already one somewhere.

The papi native equivalents for those perf events are: KNL ``` knl_unc_imc[0-5]::UNC_M_CAS_COUNT:[RD|WR] knl_unc_edc_eclk[0-7]::UNC_E_[RPQ|WPQ]_INSERTS ``` Haswell ``` hswep_unc_imc[0-7]::UNC_M_CAS_COUNT:[RD|WR] ```

Sorry, I don't have any logs/ errors from when we tried this at the moment (it was some time ago). I think the issue is with the assumption that all...

It would be great to have this in the PAPI sampler as well, but initially we could proceed with just syspapi.

Hi Tom, No pressure, but for our own planning is there any time frame for this? Or something else we can provide to help? Thanks, Brandon