Skip to main content
8 events
when toggle format what by license comment
Oct 7, 2020 at 19:06 comment added David Mårtensson The most important part is the "Short answer: yes" As the OP question was 2do I ever have a reason". And yes there are situations where it will be viable and even recomended to use more threats than cores but which situations is a much longer answer without upper bond :)
Sep 11, 2020 at 13:05 comment added Mast @YvesDaoust Cast not away therefore your boldness, which hath great recompense of reward.
Sep 10, 2020 at 11:14 comment added Gwyneth Llewelyn @taciteloquence the few things I remember from my university days was a lesson about what used to be simply called 'network computing': unlike single-physical-CPU systems, they're chaotic and totally unpredictable. There is no such thing as a 'controlled benchmark experiment' — you can establish a few baselines, sure, but real life will always be different from what you can assemble in a lab.
Sep 10, 2020 at 10:29 comment added taciteloquence @YvesDaoust, this is especially true for parallelized algorithms, where it is far harder to set up "controlled" benchmark experiments.
Sep 9, 2020 at 9:49 comment added Yves Daoust @qwr: another great truth is that benchmarking is terribly difficult. In particular when developing general purpose solutions such that you don't know the problem size and specifics in advance (and sometimes even have no idea of realistic problems). Some understanding of the trends in behavior is not luxury.
Sep 4, 2020 at 13:25 comment added J... @qwr An adage also known as : "One experiment is worth a thousand expert opinions"
Sep 3, 2020 at 7:43 comment added qwr This answer contains a great truth: benchmarking beats lots of theory and speculation.
Sep 1, 2020 at 18:19 history answered Iron Gremlin CC BY-SA 4.0