Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
hachyderm.io is one of the many independent Mastodon servers you can use to participate in the fediverse.
Hachyderm is a safe space, LGBTQIA+ and BLM, primarily comprised of tech industry professionals world wide. Note that many non-user account types have restrictions - please see our About page.

Administered by:

Server stats:

9K
active users

hachyderm.io: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#benchmarking

0 posts0 participants0 posts today
PUPUWEB Blog<p>Meta plans to launch <a href="https://mastodon.social/tags/Llama4" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Llama4</span></a> later this month after multiple delays, citing underperformance in reasoning &amp; math benchmarks. 🤖📉 <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/TechNews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TechNews</span></a> <a href="https://mastodon.social/tags/LlamaAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LlamaAI</span></a> <a href="https://mastodon.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://mastodon.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://mastodon.social/tags/AIResearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIResearch</span></a></p>
N-gated Hacker News<p>🚀 Behold, yet another mind-blowing reinvention of the <a href="https://mastodon.social/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> wheel, this time bedazzled with <a href="https://mastodon.social/tags/Go" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Go</span></a> glitter! 🌟 Perfect for those who need to benchmark how quickly they can waste their time in the <a href="https://mastodon.social/tags/CLI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CLI</span></a>. 🤖🔧<br><a href="https://github.com/ConduitIO/benchi" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/ConduitIO/benchi</span><span class="invisible"></span></a> <a href="https://mastodon.social/tags/glitter" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>glitter</span></a> <a href="https://mastodon.social/tags/innovation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>innovation</span></a> <a href="https://mastodon.social/tags/tech" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tech</span></a> <a href="https://mastodon.social/tags/news" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>news</span></a> <a href="https://mastodon.social/tags/HackerNews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HackerNews</span></a> <a href="https://mastodon.social/tags/ngated" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ngated</span></a></p>
Xavier B.<p><span class="h-card" translate="no"><a href="https://mastodon.social/@mariejulien" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>mariejulien</span></a></span> À mon avis tu n'as pas encore trouvé ton PMF (Pouët/Market Fit).</p><p><a href="https://boitam.eu/tags/knowYourAudience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>knowYourAudience</span></a> <a href="https://boitam.eu/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://boitam.eu/tags/notInKansasAnymore" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>notInKansasAnymore</span></a></p>
Joseph Simons 🍁 🌱<p>"In its <a href="https://mstdn.ca/tags/Municipal" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Municipal</span></a> <a href="https://mstdn.ca/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> 2024 Study, the <a href="https://mstdn.ca/tags/CanadianHomeBuildersAssociation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CanadianHomeBuildersAssociation</span></a> has ranked <a href="https://mstdn.ca/tags/Edmonton" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Edmonton</span></a> as the most builder-friendly city in <a href="https://mstdn.ca/tags/Canada" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Canada</span></a> for the second straight year. Edmonton ranked sixth for planning features, fourth for approval time, second for high-rise fees, and sixth for low-rise government fees."</p><p><a href="https://www.chba.ca/assets/pdf/CHBA+Municipal+Benchmarking+Study-3rd+Edition-2024/?utm_source=Taproot+Edmonton&amp;utm_campaign=11a28a527e-TAPROOTYEG_PULSE_2025_03_27&amp;utm_medium=email&amp;utm_term=0_ef1adf0932-11a28a527e-438152299&amp;mc_cid=11a28a527e&amp;mc_eid=2af62197a9" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">chba.ca/assets/pdf/CHBA+Munici</span><span class="invisible">pal+Benchmarking+Study-3rd+Edition-2024/?utm_source=Taproot+Edmonton&amp;utm_campaign=11a28a527e-TAPROOTYEG_PULSE_2025_03_27&amp;utm_medium=email&amp;utm_term=0_ef1adf0932-11a28a527e-438152299&amp;mc_cid=11a28a527e&amp;mc_eid=2af62197a9</span></a></p>
C++Now<p>C++Now 2025 SESSION ANNOUNCEMENT: Explore microbenchmark With beman.inplace_vector by River Wu</p><p><a href="https://schedule.cppnow.org/session/2025/explore-microbenchmark-with-beman-inplace_vector/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">schedule.cppnow.org/session/20</span><span class="invisible">25/explore-microbenchmark-with-beman-inplace_vector/</span></a></p><p>Register now at <a href="https://cppnow.org/registration/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">cppnow.org/registration/</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://mastodon.social/tags/cplusplus" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cplusplus</span></a> <a href="https://mastodon.social/tags/cpp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cpp</span></a> <a href="https://mastodon.social/tags/cpp26" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cpp26</span></a></p>
B166IR<p><a href="https://youtu.be/J4qwuCXyAcU" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/J4qwuCXyAcU</span><span class="invisible"></span></a></p><p>In this video, Ollama vs. LM Studio (GGUF), showing that their performance is quite similar, with LM Studio’s tok/sec output used for consistent benchmarking.</p><p>What’s even more impressive? The Mac Studio M3 Ultra pulls under 200W during inference with the Q4 671B R1 model. That’s quite amazing for such performance!</p><p><a href="https://k2pk.com/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> <a href="https://k2pk.com/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://k2pk.com/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://k2pk.com/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> <a href="https://k2pk.com/tags/LMStudio" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LMStudio</span></a> <a href="https://k2pk.com/tags/GGUF" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GGUF</span></a> <a href="https://k2pk.com/tags/MLX" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MLX</span></a> <a href="https://k2pk.com/tags/TechReview" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TechReview</span></a> <a href="https://k2pk.com/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://k2pk.com/tags/MacStudio" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MacStudio</span></a> <a href="https://k2pk.com/tags/M3Ultra" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>M3Ultra</span></a> <a href="https://k2pk.com/tags/LocalLLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LocalLLM</span></a> <a href="https://k2pk.com/tags/AIbenchmarks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIbenchmarks</span></a> <a href="https://k2pk.com/tags/EnergyEfficient" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>EnergyEfficient</span></a> <a href="https://k2pk.com/tags/linux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>linux</span></a></p>
HGPU group<p>A Microbenchmark Framework for Performance Evaluation of OpenMP Target Offloading</p><p><a href="https://mast.hpc.social/tags/OpenMP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenMP</span></a> <a href="https://mast.hpc.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://mast.hpc.social/tags/Performance" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Performance</span></a> <a href="https://mast.hpc.social/tags/Package" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Package</span></a></p><p><a href="https://hgpu.org/?p=29809" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">hgpu.org/?p=29809</span><span class="invisible"></span></a></p>
Habr<p>[Перевод] Оценка больших языковых моделей в 2025 году: пять методов</p><p>Большие языковые модели (LLM) в последнее время стремительно развиваются и несут в себе потенциал для кардинального преобразования ИИ. Точная оценка моделей LLM крайне важна, поскольку: • Компании должны выбирать генеративные AI-модели для внедрения в работу. Базовых моделей LLM сейчас множество, и для каждой есть различные их модификации. • После выбора модели будет проходить fine-tuning. И если производительность модели не измерена с достаточной точностью, пользователи не смогут оценить эффективность своих усилий. Таким образом, необходимо определить: • Оптимальные методы оценки моделей • Подходящий тип данных для обучения и тестирования моделей Поскольку оценка систем LLM является многомерной задачей, важно разработать комплексную методологию измерения их производительности. В этой статье рассматриваются основные проблемы существующих методов оценки и предлагаются решения для их устранения.</p><p><a href="https://habr.com/ru/articles/887290/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">habr.com/ru/articles/887290/</span><span class="invisible"></span></a></p><p><a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://zhub.link/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://zhub.link/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://zhub.link/tags/finetuning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>finetuning</span></a> <a href="https://zhub.link/tags/bleu" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>bleu</span></a> <a href="https://zhub.link/tags/rouge" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>rouge</span></a> <a href="https://zhub.link/tags/%D0%B1%D0%B5%D0%BD%D1%87%D0%BC%D0%B0%D1%80%D0%BA%D0%B8%D0%BD%D0%B3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>бенчмаркинг</span></a></p>
Andrew Jones (hpcnotes)<p>UK based <a href="https://mast.hpc.social/tags/HPC" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HPC</span></a> benchmarking role at Microsoft</p><p>Requires real experience with hands on HPC <a href="https://mast.hpc.social/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> - porting, compiling, tuning, performance analysis etc. of scientific codes on HPC systems</p><p><a href="https://buff.ly/fKfQz6j" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">buff.ly/fKfQz6j</span><span class="invisible"></span></a></p>
Habr<p>[Перевод] Бенчмаркинг AI-агентов: оценка производительности в реальных задачах</p><p>AI-агенты уже решают реальные задачи — от обслуживания клиентов до сложной аналитики данных. Но как убедиться, что они действительно эффективны? Ответ заключается в комплексной оценке AI-агентов. Чтобы AI-система была надежной и последовательной, важно понимать типы AI-агентов и уметь их правильно оценивать. Для этого используются продвинутые методики и проверенные фреймворки оценки AI-агентов. В этой статье мы рассмотрим ключевые метрики, лучшие практики и основные вызовы, с которыми сталкиваются компании при оценке AI-агентов в корпоративных средах.</p><p><a href="https://habr.com/ru/articles/886198/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">habr.com/ru/articles/886198/</span><span class="invisible"></span></a></p><p><a href="https://zhub.link/tags/ai_agent" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai_agent</span></a> <a href="https://zhub.link/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://zhub.link/tags/%D0%B8%D0%B8_%D0%B0%D0%B3%D0%B5%D0%BD%D1%82%D1%8B" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ии_агенты</span></a> <a href="https://zhub.link/tags/%D0%B1%D0%B5%D0%BD%D1%87%D0%BC%D0%B0%D1%80%D0%BA%D0%B8%D0%BD%D0%B3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>бенчмаркинг</span></a> <a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a></p>
Wizards Anonymous<p>Curious which <a href="https://mastodon.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> options <a href="https://mastodon.social/tags/Wizards" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Wizards</span></a> prefer to utilize for <a href="https://mastodon.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://mastodon.social/tags/Disk" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Disk</span></a> / <a href="https://mastodon.social/tags/SSD" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SSD</span></a>. :)</p>
HGPU group<p>Evaluating the Performance of the DeepSeek Model in Confidential Computing Environment</p><p><a href="https://mast.hpc.social/tags/Security" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Security</span></a> <a href="https://mast.hpc.social/tags/DeepSeek" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DeepSeek</span></a> <a href="https://mast.hpc.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://mast.hpc.social/tags/Cloud" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cloud</span></a> <a href="https://mast.hpc.social/tags/Performance" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Performance</span></a> <a href="https://mast.hpc.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a></p><p><a href="https://hgpu.org/?p=29782" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">hgpu.org/?p=29782</span><span class="invisible"></span></a></p>
Andrew Jones (hpcnotes)<p>Olga Pearce from LLNL giving a talk on <a href="https://mast.hpc.social/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> for <a href="https://mast.hpc.social/tags/HPC" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HPC</span></a> at <a href="https://mast.hpc.social/tags/MW25NZ" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MW25NZ</span></a></p><p>Proposing a specification for running HPC benchmarks - benchpark - to help automation, reuse, reproducibility, tracking, etc.</p>
Jeff Fortin T.<p>The rabbithole investigation of Nautilus' very slow cold-disk-cache folders loading performance continued this week end.<br>Latest findings here: <a href="https://gitlab.gnome.org/GNOME/nautilus/-/issues/3374#note_2345406" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">gitlab.gnome.org/GNOME/nautilu</span><span class="invisible">s/-/issues/3374#note_2345406</span></a></p><p><a href="https://mastodon.social/tags/GNOMEFiles" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GNOMEFiles</span></a> <a href="https://mastodon.social/tags/Nautilus" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Nautilus</span></a> <a href="https://mastodon.social/tags/GNOME" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GNOME</span></a> <a href="https://mastodon.social/tags/performance" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>performance</span></a> <a href="https://mastodon.social/tags/Sysprof" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Sysprof</span></a> <a href="https://mastodon.social/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://mastodon.social/tags/filesystems" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>filesystems</span></a></p>
James Young<p>Surely someone's looked into this: if I wanted to store millions or billions of files on a filesystem, I wouldn't store them in one single subdirectory / folder. I'd split them up into nested folders, so each folder held, say, 100 or 1000 or n files or folders. What's the optimum n for filesystems, for performance or space? <br>I've idly pondered how to experimentally gather some crude statistics, but it feels like I'm just forgetting to search some obvious keywords. <br><a href="https://mefi.social/tags/BillionFileFS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BillionFileFS</span></a> <a href="https://mefi.social/tags/linux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>linux</span></a> <a href="https://mefi.social/tags/filesystems" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>filesystems</span></a> <a href="https://mefi.social/tags/optimization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>optimization</span></a> <a href="https://mefi.social/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a></p>
HGPU group<p>Thesis: Modernization and Optimization of MPI Codes</p><p><a href="https://mast.hpc.social/tags/MPI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MPI</span></a> <a href="https://mast.hpc.social/tags/OpenMP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenMP</span></a> <a href="https://mast.hpc.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://mast.hpc.social/tags/Performance" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Performance</span></a> <a href="https://mast.hpc.social/tags/Package" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Package</span></a></p><p><a href="https://hgpu.org/?p=29718" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">hgpu.org/?p=29718</span><span class="invisible"></span></a></p>
Stefan Marr<p>Our benchmarking tool got a new release, ReBench 1.3</p><p>Important changes:<br> - better support for environment variables<br> - more predictable handling of build commands<br> - support for machine-specific settings<br> - tool to reduce measurement noise is more robust</p><p><a href="https://github.com/smarr/ReBench/releases/tag/v1.3.0" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/smarr/ReBench/relea</span><span class="invisible">ses/tag/v1.3.0</span></a></p><p><a href="https://mastodon.acm.org/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://mastodon.acm.org/tags/languageImplementation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>languageImplementation</span></a> <a href="https://mastodon.acm.org/tags/experiments" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>experiments</span></a> <a href="https://mastodon.acm.org/tags/science" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>science</span></a></p>
Microsoft DevBlogs<p>Join the conversation and optimize your projects! </p><p><a href="https://dotnet.social/tags/VisualStudio" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VisualStudio</span></a> <a href="https://dotnet.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://dotnet.social/tags/PerformanceOptimization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PerformanceOptimization</span></a></p><p>This thread was auto-generated from the original post, which can be found here: <a href="https://devblogs.microsoft.com/visualstudio/benchmarking-with-visual-studio-profiler/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">devblogs.microsoft.com/visuals</span><span class="invisible">tudio/benchmarking-with-visual-studio-profiler/</span></a>.</p>
Leiden Madtrics<p>📢 New blogpost!</p><p>Benchmarking - an appropriate method for evaluating research units? Thed van Leeuwen and Frank van Vree explore possibilities and caveats, particularly in the context of the Dutch Strategy Evaluation Protocol (SEP).</p><p>You can read the bi-lingual post here:<br>𝘌𝘕𝘎 👉 <a href="https://www.leidenmadtrics.nl/articles/benchmarking-in-research-evaluations-we-can-do-without-it" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">leidenmadtrics.nl/articles/ben</span><span class="invisible">chmarking-in-research-evaluations-we-can-do-without-it</span></a><br>𝘕𝘓 👉 <a href="https://www.leidenmadtrics.nl/articles/benchmarking-bij-onderzoeksevaluaties-we-kunnen-zonder" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">leidenmadtrics.nl/articles/ben</span><span class="invisible">chmarking-bij-onderzoeksevaluaties-we-kunnen-zonder</span></a></p><p>**<a href="https://social.cwts.nl/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a>** **<a href="https://social.cwts.nl/tags/ResearchEvaluation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ResearchEvaluation</span></a>**</p>
Christos Argyropoulos MD, PhD<p>5 of these methods can leverage multithreaded (MT) <a href="https://mstdn.science/tags/BLAS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BLAS</span></a> with a sweet spot ~ 6 threads for the 40% of the time spent in MT regions. E5-2697 has 36/72 (physical/logical) cores, so the avg case scenario is one in which 0.4x3x6 cores +2 (serial methods) tie up ~ 9.2 cores ~13% of the 72 logical cores. So far the back of envelope calculation, i.e. if I run 5 out of the 2100 design points in parallel, I will stay within 15% of resource use is holding rather well! <a href="https://mstdn.science/tags/benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benchmarking</span></a> <a href="https://mstdn.science/tags/hpc" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hpc</span></a> <a href="https://mstdn.science/tags/rstats" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>rstats</span></a></p>
ExploreLive feeds
About