Top all-time · #53
Daniel Lemire
Personal blog · lemire.meprogrammingsystemsmath
Daniel Lemire's personal blog at lemire.me covers programming, systems and math. Since 2010, 512 different Hacker News readers have linked it 1,701 times, most often “Reusing a thread in C++ for better performance”. No feed was found, so read it on the site itself.
Rarely recommended · 4 of 40 sampled comments recommend it?
Why HN links it
HN readers link Daniel Lemire's blog as a source for applied performance work: SIMD, fast parsing, RNGs and how real processors and caches behave versus big-O expectations.
- Recommended for · 4 comments
- Praised as brilliant and applied, a source for SIMD work, and a great example of hardware-aware performance work.
Summarised by Claude from a sample of 40 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Reusing a thread in C++ for better performance23 people · 25 mentions · first linked 2019-02-21
- A fast alternative to the modulo reduction (2016)14 people · 15 mentions · first linked 2018-07-06
- Fast Float Parsing in Practice11 people · 11 mentions · first linked 2020-03-10
- AVX-512: when and how to use these new instructions8 people · 12 mentions · first linked 2018-09-07
- Data alignment for speed: myth or reality? (2012)8 people · 8 mentions · first linked 2018-10-26
- Nearly Divisionless Random Integer Generation on Various Systems8 people · 8 mentions · first linked 2019-06-07
- How fast is C++26's std:hive?7 people · 8 mentions · first linked 2026-08-02
- Why I still program6 people · 7 mentions · first linked 2011-06-06
- The Go Compiler Needs to Be Smarter6 people · 6 mentions · first linked 2020-06-04
- I do not use a debugger (2016)6 people · 6 mentions · first linked 2019-05-04
What Hacker News says?
The information in the above post is a merger of like, 20 different sources of information. Your standard cryptographic books from any undergraduate program will tell you about the basics of confusion / diffusion, but I don't think the concept is very difficult at all. Invertibility is hugely important but not discussed very much. It seems like crypto-experts 'obviously' know about it so they just don't talk about i…
Comment linking /blog/2016/08/09/how-many-reversible-integer-operations-do-you-know/
on “Show HN: SHA-256 explained step-by-step visually”Submitted How did AMD Ryzen get 50% faster in two years? as a story · 487 points
HN discussionUnless you're benchmarking single-threaded SIMD: https://lemire.me/blog/2020/12/13/arm-macbook-vs-intel-macbo...
Comment linking /blog/2020/12/13/arm-macbook-vs-intel-macbook-a-simd-benchmark/
on “Xiaomi: New CPU matches Apple cores single threaded, much faster multithreaded”Submitted Xor Filters: Faster and Smaller Than Bloom Filters as a story · 457 points
HN discussionHTML + CSS seems to be Turing complete : http://lemire.me/blog/2011/03/08/breaking-news-htmlcss-is-tu... As does SQL : http://stackoverflow.com/questions/900055/is-sql-or-even-tsq...
Comment linking /blog/2011/03/08/breaking-news-htmlcss-is-turing-complete/
on “Ask HN: Is web programming a series of hacks on hacks?”Submitted Intel will add deep-learning instructions to its processors as a story · 389 points
HN discussionDaniel Lemire's blog is brilliant: https://lemire.me/blog/
Comment linking /blog/
on “Ask HN: Favorite Blogs by Individuals?”Submitted Memory access on the Apple M1 processor as a story · 372 points
HN discussion> I've experienced a huge amount of friction trying to enable features that cost something resembling 0.5% of fleet performance, even when they provide massive benefits. 12% loss would be laughed out of the room. A 12% difference in performance between two compilers, for some given application, is possible even between two of the best optimising compilers available. A 12% performance lag does not necessarily relegat…
Comment linking /blog/2023/02/27/visual-studio-versus-clangcl/
on “11 year old unsoundness bugs found in Rust borrow checker”Submitted Peer-reviewed papers are getting increasingly boring as a story · 364 points
HN discussionhttps://lemire.me/blog/
Comment linking /blog/
on “Ask HN: What are good solo developer blogs that you enjoy reading?”Submitted How to Learn Efficiently as a story · 336 points
HN discussionThe content of the orignal post may be questionable, but I feel it was written in a way that would trigger a heated debate. For that, mission accomplished. There has been many wise comments, but they all choose to take a branch of the post to dig into. Not to blame them, as the question raised here is basically: The software industry has huge impact on human lives but such impact has not been materialized in terms o…
Comment linking /blog/archives/2011/08/22/linux-and-the-financial-crisis/
on “If Software Is Eating The World, Why Don't Coders Get Any Respect?”Submitted Stop spending so much time being trolled by billionaire corps as a story · 291 points
HN discussionI vote that we add our blogs / other good blogs we have come across as children on this comment. I'll start, here's mine: - https://slightknack.dev/blog Here are some others: - https://journal.stuffwithstuff.com - https://www.gwern.net/index - https://danluu.com - https://tonsky.me/ - https://lemire.me/blog/ - https://waitbutwhy.com/ - https://www.kalzumeus.com/archive/ - https://blog.codinghorror.com/
Comment linking /blog/
on “If I could bring one thing back to the internet it would be blogs (2020)”Submitted Fast UTF-8 validation as a story · 266 points
HN discussionIf this kind of work is interesting to you, you might like Daniel Lemire's blog ( https://lemire.me/blog/ ). He's a professor, but his work is highly applied and immediately usable. He manages to find and demonstrate a lot of code where we assume the big-O performance, but the reality of modern processors and caching (etc.) mean very difference performance in practice.
Comment linking /blog/
on “Simdjson – Parsing Gigabytes of JSON per Second”Submitted Simdjson 0.3: Faster JSON parser as a story · 258 points
HN discussionI might go so far as to post to branchfree.org, and Daniel posts at https://lemire.me/blog/ so either of those, plus github, ought to cover it.
Comment linking /blog/
on “Simdjson – Parsing Gigabytes of JSON per Second”Submitted ARM MacBook vs. Intel MacBook: A SIMD Benchmark as a story · 256 points
HN discussionI disagree with such a blanket statement. Interfaces must remain simple, while implementations are free to be as complex as needed. Take a look at this article -- clearly the SIMD code is dense to get through, but it's very-much-so worth it for the performance gains. https://lemire.me/blog/2017/01/20/how-quickly-can-you-remove...
Comment linking /blog/2017/01/20/how-quickly-can-you-remove-spaces-from-a-string/
on “The Efficiency-Destroying Magic of Tidying Up”- ot · 2014-05-27
Submitted You shouldn’t use a spreadsheet for important work as a story · 245 points
HN discussion Thinking about it more, Daniel Lemire publishes very applied algorithmic stuff: https://lemire.me/en/#publications A lot of his work is in the journal "Experimental Algorithmics", so I guess there are a substantial number of people working in this way. I don't know this field very well, and I don't know if there are general principles that have been extracted from their work.
Comment linking /en/
on “CS 168: The Modern Algorithmic Toolbox”Submitted Scan HTML faster with SIMD instructions – Chrome edition as a story · 241 points
HN discussion1. [Damian Gryski]( https://github.com/dgryski ) - implements a bunch of modern academic papers (mostly in go). Also his twitter has a bunch more stuff. 2. [Daniel Lemire]( http://lemire.me/en/ ) - comp sci professor who frequently blogs about interesting db/indexing topics
Comment linking /en/
on “Ask HN: Which developers do you closely follow?”Submitted Go generics are not bad as a story · 232 points
HN discussionI think one way to 'treat' this would be to acknowledge that certain things just cannot be optimized easily with outside incentives, and to simply accept that there will be some inevitable waste when you let 'good people do their job as best as they can'. It's ironic that we fret so much about professors that 'retire on the job', but at the same time think it is perfectly fine to steal time from the motivated resear…
Comment linking /blog/2009/09/15/the-hard-truth-about-research-grants/
on “Every attempt to manage academia makes it worse”Submitted Apple’s M1 processor and the full 128-bit integer product as a story · 230 points
HN discussionIn my experience the M1 does have competitive SIMD performance? https://dougallj.wordpress.com/2022/04/01/converting-integer... https://dougallj.wordpress.com/2022/05/22/faster-crc32-on-th... https://lemire.me/blog/2020/12/13/arm-macbook-vs-intel-macbo... (I later optimised the slower benchmark in that post: https://github.com/simdjson/simdjson/pull/1708 ) Obviously the GPU will be better, but at one point I compare…
Comment linking /blog/2020/12/13/arm-macbook-vs-intel-macbook-a-simd-benchmark/
on “Linux M1 GPU driver passes 99% of the dEQP-GLES2 compliance tests”Submitted C23: A Slightly Better C as a story · 216 points
HN discussion
