Topics /
The most popular blog posts about systems & performance on Hacker News. 569 posts.
As our first quantized models in this Llama category, these instruction-tuned models retain the quality and safety of the original 1B and 3B models, while achieving 2-4x speedup.
This is the fascinating story of how researchers used Bloom filters cleverly to make SQLite 10x faster for analytical queries. These are my five-minute notes on the paper SQLite: Past, Present, and Future
How is a binary executable organized? Let's explore it!
How I solved the One Billion Row Challenge (1BRC) in Go nine times, from a simple unoptimised version that takes 1 minute 45 seconds, to an optimised and parallelised version that takes 3.4 seconds.
Apple uses Cassandra and FoundationDB for CloudKit, their cloud backend service. We take a look into how exactly each is used within their cloud and the problems they've solved.
Competitiveness is a vice of mine. When I heard that a friend got Linux to boot off of NFS, I had to one-up her. I had to prove that I could create...
OpenZFS 2.3.0 will be released any day now, and it includes the new “Fast Dedup” feature. My team at Klara spent many months in 2023 and 2024 working on it, and we reckon it’s pretty good, a huge step up from the old dedup as well as being a solid base for further improvements. I’ve been watching various forums and…
Calculations in Google Sheets were initially done on the server, then on the client in JavaScript, and now on the client in WebAssembly Garbage Collection. This case study explains how and why.
"Wal2" mode is very similar to "wal" mode. To change a database to wal2 mode, use the command:
Introduction to implementing USB devices. Minimal overview of hardware and software with an example with STM32 microcontroller. Also contains an index to very detailed guides for more information.
Recently, I got a new laptop and had to set it up so I could start using it. But I wasn't really in the mood to go through the same old steps which I had explained in this post earlier . I was complaining about this to my colleague, and there came the suggestion of why not copy the entire disk to the new laptop…
Hello friends, this is the first of two, possibly three (if and when I have time to finish the Windows research) writeups. We will start with targeting GNU/Lin…
Engineer Bo Ingram shares insight into how Discord shoulders its traffic and provides a platform for our users to communicate.
A common refrain is that threads can do everything that async/await can, but simpler. So why would anyone choose async/await?
By all accounts, Pat Gelsinger is affable, technically sharp, hard-working, and decent. Those who have worked for him praise him as a singularly good manager. In January 2021, when Gelsinger was abruptly named the CEO of Intel, this is more or less all I knew of him — and I found myself urgently needing to learn much…
My 4U 71 TiB ZFS NAS built with twenty-four 4 TB drives is over 10 years old and still going strong.
Some engineering patterns that sound good but almost never work as intended
For the past two years Charles Zhang and I have been working on getting my game engine, Trial, running on the Nintendo Switch. The primary challenge in doing this is porting the underlying Common Lisp runtime to work on this platform. We knew going into this that it was going to be hard, but it has proven to be quite…
An analysis of the Croatian classic.
Ceph is an open source distributed storage system designed to evolve with data.
One of the many enjoyable things about databases is that they generally try to separate how data is represented internally (say on disk) from how it is used. To the point that it has become the norm to not even store the data on the same hardware that is running the queries.
A tale about exploiting KernelCTF Mitigation, Debian, and Ubuntu instances with a double-free in nf_tables in the Linux kernel, using novel techniques like Dirty Pagedirectory. All without even having to recompile the exploit for different kernel targets once.
Datomic is a general-purpose database intended for systems of record. In many ways, Datomic is unusual. At any instant in time, the state of the database is represented by a set of [entity, attribute, value] ( EAV ) triples, known as datoms . Each datom declares that some entity (like a person) has a particular…
Yet another programming blog. Thoughts on software and related misadventures.
A detailed blog post on optimizing multi-threaded matrix multiplication for x86 processors to achieve OpenBLAS/MKL-like performance. Tags: High-performance GEMM on CPU, Fast GEMM on CPU, High-performance matrix multiplication on CPU, Fast Matrix Multiplication on CPU, Matrix multiplication in C, GEMM in C, Matrix…
