Topics /
The most popular blog posts about systems & performance on Hacker News. 287 posts.
This is week "1111111111" in the GPS system. Tomorrow morning it will roll over to week "0000000000". How well will various systems handle this change? Not well, judging by what we've seen so far!
[Discuss this article and read other’s comments on the subject on this thread on Hacker News.] The three fundamental building blocks of computers, CPU, I/O and RAM can come under pressure due to co…
The libsodium cryptographic library added support for WebAssembly back in 2017.
This is a post about performance. Most of the time when worrying about the performance of a piece of code the overwhelming advice should be (with apologies to Brendan Gregg) don’t worry about it, yet. However there is one area where I counsel developers to think about the performance implications of a design, and that…
Note: I also posted a separate review of some A2 'Application Performance' class cards, see this post: A2-class microSD cards offer no better performance for the Raspberry Pi. As a part-time tinkerer and full-time developer, I have been fascinated by single board computers (SBCs) since the first Raspberry Pi was…
Synchronizing threads at a lower level.
This is one post in a series about programming models and languages for distributed computing that I’m writing as part of my history of distributed programming techniques.Relevant ReadingTrill: A h...
Your Linux Toolbox: a box set of my free zines
The urge to replace the mainframe has reinvented the mainframe and its problems.
I recently decided to learn more about Rust, and wrote a high performance RaptorQ (RFC6330) library. RaptorQ is a fountain code, and the core of the algorithm is a lot of matrix math over GF(256) – which translates into lots of XORs and reads from lookup tables. After getting the initial implementation working, I set…
Designing far memory data structures: think outside the box Aguilera et al., HotOS’19 Last time out we looked at some of the trade-offs between RInKs and LInKs, and the advantages of local in…
Suppose you’re a savvy C++ developer who knows all about data-oriented design and the importance of optimizing for cache locality if you want a prayer of running fast on modern hardware. Now suppose you want to go beyond basics—”just use std::vector ” is a good starting point, but you want more!
Here’s a fun bit of trivia: malloc on Linux never fails [due to the obvious cause]. In this post, we’ll show that this indeed is the case, and explore why…
(First, as a public service message, if you're running Linux on a G5 you may wish to update the kernel .) I'm a big fan of NetBSD . I've ru...
This post is about uninitialized memory, but also about the semantics of highly optimized “low-level” languages in general. I will try to convince you that reasoning by “what the hardware d...
A performance comparison between three different methods of deploying an API on AWS
Task Manager can be lacking as a memory tracker. Let's cover alternatives to replace it. First, let’s discuss how memory allocations work in Windows.
We all have stories, as engineers, of fixing some crazy thing at the last minute right before the demo goes up. We have all encountered situations where we needed to fix something that was our fault and we needed to fix it now.
Code that shows how floating point arithmetic can go wrong, and how C and C++ can return different results for similar code.
Paul Khuong's personal blog. Some Lisp, some optimisation, mathematical or computer.
A paper on debugging non-deterministic concurrency issues interactively.
I have always wanted the Cone compiler to be fast. Faster build times make it easier and more pleasant for the programmer to iterate and experiment quickly. Compilers built for speed, such as Turbo Pascal, D and Go, win praise and loyalty. Languages that struggle more with this, like C++ or Rust, get regular…
Solving problems by identifying underlying systems
The current article describes a series of Java Virtual Machine (JVM) Garbage Collectors (GC) micro-benchmarks and their results, using a different set of patterns. For the current issue, I included all Garbage Collectors from AdoptOpenJDK 64-Bit Server VM version 13 (build 13+33) :
I wrote a couple of years ago about the troubles I had finding a good libc for embedded systems , and for the last year or so I've been using something I called 'newlib-nano', which was newlib with the stdio from avrlibc bolted on. That library has worked pretty well, and required very little work to ship.
