Links

Debugging and Performance Analysis Tools

• MUST
  “Marmot Umpire Scalable Tool”. Detects usage errors of the Message Passing Interface (MPI) and reports them to the user. Version 1.10 played well with SWIFT. Very useful to find errors, detect deadlocks, and check source code for valid usage. Github mirror to tutorial.

• MAQAO
  “Modular Assembly Quality Analyzer and Optimizer” is a performance analysis and optimization framework operating at binary level with a focus on core performance. Very user friendly, very beginner friendly. Will e.g. give you suggestions how to re-write your loops so that they vectorize, or what compiler flags to use.

• POP
  “Perfomance Optimisation and Productivity - A centre of excellence in HPC”. Learning material and documentation on performance analysis, performance metrics. Includes tutorials for MPI, OpenMPI, and tutorials and user guides performance analysis tools such as Scalasca and Score-P.

• Darshan
  (github) A lightweight lightweight I/O characterization tool and profiler.

Lectures, Lecture Notes, and Books

• Lecture notes on theoretical astrophysics: kinetic theory, astro fluid dynamics, radiative transfer and collisionless dynamics by Romain Teyssier
• The Art of HPC by Victor Eijkhout

Miscellaneous

• M. Schaller’s Simulation Sizes Collection
• Niko Sarcevic’s HEP/Astro/Cosmo open source software collection
• My gdb cheat sheet
• Colossus - A powerful online cosmology calculator
• Scientific Visualisation Handbook - Book containing myriad of beatutiful python+matplotlib scientific visualisations, including the source code