Platy’s Web Excursions

Share this post

Web Excursions 2022-04-16

platylinks.substack.com

Web Excursions 2022-04-16

Platy Hsu
Apr 17, 2022
Share this post

Web Excursions 2022-04-16

platylinks.substack.com

Explainer: Benchmarks – The Eclectic Light Company

  • There are two basic ways to tackle the assessment of performance:

    • test each individual step, such as GPU and disk performance, one at a time, and

    • test them altogether by performing the whole task.

    • These form the two main types of benchmark: synthetic, and application.

  • Synthetic benchmarks are specially constructed to test individual aspects of overall performance.

    • Historically important examples include Whetstone and Dhrystone benchmarks,

      • which for many years were popular benchmarks for floating-point and integer performance of CPUs, respectively.

    • As processors have advanced, these have become more complex.

    • While synthetic benchmarks are ideal for discovering performance bottlenecks, and comparing variants of the same core architecture,

    • they tell you precious little about the overall performance you could expect when running apps.

  • For that you should turn to application benchmarks.

    • The most meaningful application benchmarks for any user are carefully timed tests of real-world tasks which take time,

      • in a production version of the app normally used.

      • These are highly individual.

  • Intermediate benchmarks

    • Between synthetic and application benchmarks is an uncomfortable compromise in tests

      • which aim to assess performance on standardised app tasks.

    • Among the most popular, on Macs at least, is Primate Labs’ Geekbench 5.

    • These assemble a series of representative tasks in a performance category,

      • such as CPU and ‘Compute’,

      • to generate a score which can be compared across different platforms and architectures

    • These don’t provide the same depth and detail as synthetic benchmarks should,

      • and don’t tell you whether the tasks you use in your main working apps will be faster or slower on another system.

    • However, they’re the only way of drawing comparisons between completely different platforms.

    • How you interpret observed differences is another problem.

  • Perhaps the greatest shortcoming of all benchmarks is how poorly they translate into the perception of performance by the user.

    • the psychology of computer performance, and how even small delays in the human interface are amplified.

  • Comparing GPUs is even more tricky, because of the variation in different tests.

    • Mac GPUs, particularly those in Apple Silicon models, rely on Metal for best performance,

    • but some graphics benchmarks don’t even run on the GPU, and others use cross-platform libraries such as OpenCL, which is deprecated by Apple so unlikely to achieve good performance on GPUs in M1 models

  • benchmark testing [is arguably] just a sophisticated form of confirmation bias


DuckDuckGo Removes Pirate Sites and YouTube-DL from Its Search Results

  • Privacy-centered search engine DuckDuckGo has completely removed the search results for many popular pirates sites including The Pirate Bay, 1337x, and Fmovies.

    • Several YouTube ripping services have disappeared, too and even the homepage of the open-source software youtube-mp3 is unfindable.

  • This first became apparent when it removed several search shortcuts for ‘pirate’ sites.

    • These “bangs” were seen as a potential copyright infringement liability.

  • DuckDuckGo ended up removing roughly 2,000 bangs for popular sites including The Pirate Bay, 1337x, and RARBG.

    • At the time, the search engine stressed that these sites were still listed in search results.

    • However, that appears to have changed now.

  • searching for “site:thepiratebay.org” is supposed to return all results DuckDuckGo has indexed for The Pirate Bay’s main domain name.

    • In this case, there are none.

  • When we do similar searches for 1337x.to, NYAA.se, Fmovies.to, Lookmovie.io, and 123moviesfree.net, no results appear.

    • For RarBG.to and Fitgirl-repacks we only get one result, instead of the hundreds of thousands we see on other search engines.

  • Even several popular stream-rippers have been completely wiped from the search results.

    • That includes 2conv.com, Flvto.bid, and several others.

  • The most surprising omission, by far, is that the official site for the open-source software youtube-dl is not indexed by DuckDuckGo.

    • This site certainly doesn’t host or link to any copyright-infringing material.

Share this post

Web Excursions 2022-04-16

platylinks.substack.com
Comments
TopNewCommunity

No posts

Ready for more?

© 2023 Platy Hsu
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing