Conference call notes 20170329

(back to Conference calls)

Notes on the 73rd EasyBuild conference call, Wednesday March 29th 2017 (5pm - 6pm CET)

Attendees

Alphabetical list of attendees (??):

• Damian Alvarez (JSC, Germany)
• Davide
• Markus Geimer (JSC, Germany)
• Kenneth Hoste (HPC-UGent, Belgium)

Agenda

• report on benchmarking of Python/numpy built with GCC/Intel compilers + Intel MKL by Damian
• boegelbot reporting broken unit tests in PRs
• moderator for EB conf calls on April 12th & 26th?
• Q&A

Notes

Benchmarking of Python/numpy

• JSC is testing the performance of a python installation in GCCcore, but a numpy library in the top level of the toolchain hierarchy (in a bundle with other scipy-stack libraries).
  • The benchmarking was done using https://github.com/serge-sans-paille/numpy-benchmarks
  • Most benchmarks perform satisfactorily
    • Significant slowdown in functions that rely on symbols defined by libm
  • What happened before (interpreter compiled with icc):
    • Everything was compiled with icc, so libimf was used instead of libm
  • What happened after having a base python in GCCcore:
    • Even though numpy itself was compiled with icc, when launching the interpreter (compiled with gcc), libm was loaded, and the exp and related symbols are picked from there, instead of the faster libimf
  • Workaround at the moment:
    • The python module defines PYTHONPATH (to use all the modules installed there)
    • The SciPy-Stack bundle installs a python interpreter compiled with icc, that gets precedence over the one loaded in GCCcore
  • See https://github.com/numpy/numpy/issues/8823

boegelbot reporting broken unit tests in PRs

• e.g. https://github.com/hpcugent/easybuild-easyconfigs/pull/4346#issuecomment-287622541

Q&A