Why are CUDA kernels hard to optimize?
Explosive datacenter demand has caused developers to leave no stone unturned in search of higher efficiencies. The DeepSeek team, not satisfied with Nvidia’s CUDA libraries, used a virtualized form of assembly language (PTX) to write kernel codes to accelerate their AI computations. Others have attempted to generate optimized kernels using
Read moreDiagnosing and Fixing a Page Fault Performance Issue with Arm64 Atomics
Learn why ARM64 atomic instructions cause double page faults on Ampere CPUs, fragmenting huge pages and reducing performance. Explore the technical root cause and practical solutions. Continue reading Diagnosing and Fixing a Page Fault Performance Issue with Arm64 Atomics on SitePoint.
Read moreThe biggest math symbol
The biggest math symbol that I can think of is the Riemann P-symbol The symbol is also known as the Papperitz symbol because Erwin Papperitz invented the symbol for expressing solutions to Bernard Riemann’s differential equation. Before writing out Riemann’s differential equation, we note that the equation has regular singular
Read moreFrom punch cards to prompts: a history of how software got better
Ryan welcomes Darko Mesaroš, Principal Developer Advocate at AWS and all around computer history buff, to chat about history of software development improvements and how they made developers made more productive.
Read moreBusiness operations manager interview questions: 20+ examples and answers
A business operations manager is the steady hand that keeps an organization running smoothly. From streamlining processes to aligning departments, they serve as the problem-solvers who bring order to complexity and keep teams moving forward. The right hire for this role can boost productivity, strengthen team morale, and drive healthier
Read moreHow Developers Can Use Tracing in the UI to Add Backend-style Observability
Unlock full-stack observability with frontend tracing using OpenTelemetry (OTel). Learn how to connect user interactions to backend services, debug slow applications, and improve performance monitoring. Continue reading How Developers Can Use Tracing in the UI to Add Backend-style Observability on SitePoint.
Read moreWhat is Generative Engine Optimization (GEO)?
Discover Generative Engine Optimization (GEO) - the next evolution beyond traditional SEO. Learn how to optimize your brand for AI-powered search tools like ChatGPT, Claude, and Google's SGE. Continue reading What is Generative Engine Optimization (GEO)? on SitePoint.
Read moreYou can’t have everything you want: beta edition
The beta distribution is a conjugate prior for a binomial likelihood function, so it makes posterior probability calculations trivial: you simply add your data to the distribution parameters. If you start with a beta(α, β) prior distribution on a proportion θ, then observe s successes and f failures, the posterior distribution
Read moreMore on seed phrase words
Last week I wrote about how the English seed phrase words for crypto wallets, proposed in BIP39, are not ideal for memorization. This post gives a few more brief thoughts based on these words. Prefix uniqueness The BIP39 words have a nice property that I didn’t mention: the words are
Read moreSvelte was built on “slinging code for the sheer love of it”
Rich Harris, creator of Svelte and software engineer at Vercel, joins Ryan on the show to dive into the evolution and future of web frameworks. They discuss the birth and growth of Svelte during the rise of mobile, the challenges of building robust and efficient web applications, how companies can
Read more