1681
No-Panic Rust: A Nice Technique for Systems Programming
Can Rust replace C? This is a question that has been on my mind for many years,as I created and now am tech lead forupb, a C libraryfor Protocol Buffers. Th...
Topics /
Systems & Performance
The most popular blog posts about systems & performance on Hacker News. 4,387 posts.
1682
Curious lack of sprintf scaling
Some days ago I noticed that on a Mac, doing snprintf calls from multiple threads shows curious lack of scaling ( see tweet ). Replacing snprintf with {fmt} library can speed up the OBJ exporter in Blender 3.2 by 3-4 times . This could have been the end of the story, filed under a “eh, sprintf is bad!” drawer, but I…
1683
Run OpenBSD on DigitalOcean for $4/month
My homepage now runs on OpenBSD with httpd(8) and Let's Encrypt via acme-client(1) . I previously hosted it on GitHub Pages and then eventually moved to Cloudflare Pages because both options were free and easy. Free and easy is cool, and I understand that writing software full-time leaves us wanting absolutely nothing…
1684
Optimizing Postgres table layout for maximum efficiency
Introduction When modeling a Postgres database, you probably don’t give much thought to the order of columns in your tables. After all, it seems like the kind of thing that wouldn’t affect storage or performance. But what if I told you that simply reordering your columns could reduce the size of your tables and…
1685
1686
1687
How to make Firefox builds 17% faster
In the previous post, I mentioned that buildcache has some unique properties compared to ccache and sccache. One of them is its Lua plugin system, which lets you write custom wrappers for programs that aren’t compilers in the traditional sense. With Bug 2027655 now merged, we can use this to cache Firefox’s WebIDL…
1688
1689
Build your own operating system
Ten years ago (around the year 2001) I wrote a simple x86 protected-mode OS just to find out how operating systems work. That was really gr...
1690
Distributed Consensus – How Shared Data Is Stored
If you don’t work in computers, you probably haven’t spent much time thinking about how data gets stored on computers or in the cloud. I’m…
1691
Benchmarking the Apple M1 Max
💻 Casino brand Royal reels casino 🎯 Alternative names Royal reels, Royal reels casino Australia, Royal Reels pokies, Royal reels online casino 📅 Launch year 2021 🔗 Royal reels mirrors 17, 18, 19, 21, 22, 23, 24, 26 🌐 Supported regions Australia and most international markets, excluding restricted jurisdictions under…
1692
1693
Make your program slower with threads
Years ago, while taking a numerical methods course, I wrote some code to calculate the expected number of shared birthdays in a group. The code is very simple: each attempt constructs a vector of N birthdays, then counts the duplicates. The outer loop runs millions of attempts, and calculates the mean number of shared…
1694
Compiler Optimizations are Awesome
Another reason for optimizing compilers: It allows us to write simple and obvious code expecting that the compiler will do the optimization. This both reduces the initial defect count and makes the code more maintainable in the long-run. Note that these are also often the simplest optimizations (e.g. a calculation…
1695
“iCloud Backup”
Last year, I bought my 87-year-old grandfather an iPad 2 to replace the who-knows-what PC that was frustrating him constantly. He only used the PC for email and playing music, so it was a no-brainer.
1696
Node.js: Some quick optimization advice
#NodeJS : A quick optimization advice Can you spot the difference between these two files : that can explain a 50% performance gain : If you don’t, it’s normal, you try to read the code …
1697
1698
Some thoughts on Spectre and Meltdown
The story of these attacks starts in late 2004. I had submitted my doctoral thesis and had a few months before flying back to Oxford for my defense, so I turned to some light reading: Intel's latest "Optimization Manual", full of tips on how to write faster code. (Eking out every last nanosecond of performance has…
1699
Who has the fastest F1 website (2021)
Deep-diving on the load performance of F1 websites.
1700
Python, C, Assembly – Faster Cosine Similarity
From pure Python to AVX-512 assembly, optimizing cosine similarity reveals a 2,500x speedup through SIMD, FP16, and VNNI instructions on modern Intel CPUs.
1701
Investigating a vanishing BIOS on the Fujitsu Lifebook AH532
A few months ago, I got given a laptop with a very interesting condition. The BIOS setup menu was supposedly inaccessible, and nothing apart from the default boot option works. Time to investigate to see what is actually happening and what we can do about it.
1702
Girls just wanna have fast MPMC queues with bounded waiting
Disclaimer: An earlier version of this post claimed the structure is wait-free, this is incorrect. Being wait-free requires that failure or suspension of any thread can’t cause failure or suspension of another thread. This queue in fact does not fulfill that requirement. The main section which discusses the wait…
1703
1704
Using LD_PRELOAD to cheat, inject features and investigate programs
This post assumes some basic C skills. Linux puts you in full control. This is not always seen from everyone’s perspective, but a power user loves to be in control. I’m going to show yo…
1705
Near-lossless image formats using ultra-fast LZ codecs
I think simple ultra-high speed lossy (or near-lossless) image codecs, built from the new generation of fast LZ codecs, are going to become ...
1706
15 years of FP64 segmentation, and why the Blackwell Ultra breaks the pattern
Buy an RTX 5090, the fastest consumer GPU money can buy, and you get 104.8 TFLOPS of FP32 compute. Ask it to do double-precision math and you get 1.64 TFLOPS. That 64:1 gap is not a technology limitation. For fifteen years, the FP64:FP32 ratio has been slowly getting wider on consumer GPUs, widening the divide between…
1707
A quick tutorial on implementing C memory management functions
This is basically an expanded explanation of what I did after reading this tutorial by Marwan Burelle and then sitting down and trying to write my own implementation, so the steps are going to be fairly similar. The main implementation differences are that my version is simpler and more vulnerable to memory…
1708
Bloaty McBloatface: a size profiler for binaries
I’m very excited to announce that today I’m open-sourcing atool I’ve been working on for several months at Google.It’s called Bloaty McBloatface, and it lets...
1709
Why was Apache Kafka created?
The story behind how LinkedIn created Apache Kafka
1710
A FreeBSD 10 Desktop How-To
A guide to a full-featured modern desktop FreeBSD installation