UCL for Code in Research

Peter Schmidt

The companion podcast for courses on programming from the Advanced Research Computing Centre of the University College of London, UK. 

  1. 12 DE MAR.

    7/10 Oh please, make it faster...performance in C++

    How can we measure the performance (run-time, memory usage etc) of our C++ code? And what does performance mean, anyway. These and other questions are the topic of this episode - with my guest Klaus Iglberger, C++ engineer, tutor and mentor.  Memory https://en.wikipedia.org/wiki/Non-uniform_memory_access something about memory accesshttps://dl.acm.org/doi/10.1145/216585.216588 Ań article on 'Hitting the memory wall' how fast can memory access be?https://www.ibm.com/docs/en/xl-c-and-cpp-aix/13.1.3?topic=performance-managing-memory-efficiently-c-only what can we do to make memory usage more efficient Tools https://valgrind.org Valgrind profilerhttps://www.intel.com/content/www/us/en/developer/tools/oneapi/vtune-profiler.html vtune profilerhttps://ftp.gnu.org/old-gnu/Manuals/gprof-2.9.1/html_mono/gprof.html gprof profiler from GNUhttps://quick-bench.com Quick online Benchmarking toolhttps://godbolt.org see what your compiler actually doeshttps://github.com/google/googletest Google C++ test frameworkhttps://github.com/boost-ext/ut UT test frameworkhttps://github.com/google/benchmark Google benchmark toolhttps://github.com/catchorg/Catch2 catch2 frameworkhttps://learn.microsoft.com/en-us/visualstudio/profiling Profiling with Visual StudioMisc https://medium.com/swlh/reliable-performance-testing-in-c-1df7a3ba398 article on performance testinghttps://scholarworks.umt.edu/cgi/viewcontent.cgi?referer=&httpsredir=1&article=1375&context=tme Historical review of complexity evaluationshttps://web.mit.edu/16.070/www/lecture/big_o.pdf The Big O NotationDon't be shy - say Hi This podcast is brought to you by the Advanced Research Computing Centre of the University College London, UK. Producer and Host: Peter Schmidt

    32min

Sobre

The companion podcast for courses on programming from the Advanced Research Computing Centre of the University College of London, UK.