InfoQ Homepage Performance Content on InfoQ
-
Mold is a New Linux Linker Aiming to Outperform Lld
Mold, a modern drop-in replacement for current Unix linkers, has reached version 1.0. Written by the original creator of the LLVM lld linker, mold aims to be several times faster than its predecessor.
-
AMD Introduces Its Deep-Learning Accelerator Instinct MI200 Series GPUs
In its recent Accelerated Data Center Premiere Keynote, AMD unveiled its MI200 accelerator series Instinct MI250x and slightly lower-end Instinct MI250 GPUs. Designed with CDNA-2 architecture and TSMC’s 6nm FinFET lithography, the high-end MI250X provides 47.9 TFLOPs peak double precision performance and memory that will allow training larger deep networks by minimizing model sharding.
-
Comparative Study of 11 CSS-in-JS Libraries - Andrei Pfeiffer at React Finland 2021
Andrei Pfeiffer recently presented the results of a comparative study of 11 CSS-in-JS libraries. In his talk at React Finland 2021, Pfeiffer focused on the distinction between static and runtime CSS-in-JS libraries and further explained how each category and browser caching relate to performance.
-
Google Introduces Minimum Instances to Reduce Cold Starts
Google’s Function as a Service (FaaS) offering Cloud Functions now supports minimum (“min”) instances. With this new feature, Google aims to take away a well-known friction point of FaaS called "cold-starts".
-
Chrome Browser Extensions Study Reveals Performance Impact of Popular Extensions
DebugBear recently published the results of a study reviewing the impact of the 1000 most popular Chrome extensions on browser performance and end-user experience. Some extensions may delay the page loading time by up to 4 seconds. Others shorten battery life by causing more than 20 seconds of CPU activity on page load.
-
Experiences from Measuring the DevOps Four Key Metrics: Identifying Areas for Improvement
Measuring the four key metrics of IT helped a company to assess the performance of their software delivery process. Continuous observation of these metrics supports decisions on where to invest and guides performance improvements.
-
Microsoft Announces the General Availability of Azure ND A100 V4 Cloud GPU Instances
Recently Microsoft announced the general availability of the Azure ND A100 v4 Cloud GPU instances—powered by NVIDIA A100 Tensor Core GPUs. These Virtual Machines (VMs) are targeted at customers with high performance and demanding workloads like Artificial Intelligence (AI) and Machine Learning (ML) workloads.
-
Next.js 11 Released with New Script and Image Loading Strategies
The Next.js team recently released Next.js 11. The new version strives to improve actual and perceived performance for developers and end-users (start-up time, third-party scripts loading, image and placeholder loading). Next.js v11 also provides an experimental codemod that migrates a Create React App application to Next.js.
-
V8 Gets a Non-Optimizing Compiler Stage to Improve Performance
The latest version of the JavaScript V8 engine, V8 9.1, introduces a new intermediate compiler stage, called Sparkplug, that improves performance on real-world benchmarks by 5-15%, says V8 engineer Leszek Swirski. It will be available in the upcoming Chrome 91.
-
Facebook Compression Algorithm Zstandard 1.5 Improves Performance
Facebook open sourced Zstandard almost six years ago with the aim of outperforming Zlib in both speed and efficiency. Zstandard 1.5 improves compression speed at intermediate compression levels, compression ratio at higher levels, and brings faster decompression speed.
-
Rendering Large Logs in the Browser for GitHub Actions
Rendering large logs in a browser can be a complex task if you want a rich UI including coloring, grouping, search, and permalinks, says GitHub engineer Alberto Gimeno. This is why after testing with both a React and plain JS library, they opted to build their own.
-
NumPy 1.20 Released with Runtime SIMD Support and Type Annotations
NumPy 1.20 was recently released with new features focusing on performance and documentation. Developers can now use type annotations for NumPy functions. A wider use of SIMD (Single Instruction, Multiple Data) instructions increases the execution speed of universal functions (ufunc). NumPy’s documentation additionally sees significant improvements.
-
How Using Modern JavaScript May Improve Performance
Houssein Djirdeh and Jason Miller recently explained at the Chrome Developer Summit 2020 how modern JavaScript may shorten the size and improve the performance of web applications. The estimator.dev website provides Google’s estimation of the potential savings and suggests plugins that help materialize those savings.
-
Cockroach Labs 2021 Cloud Report: GCP Outpaces Azure and AWS
Cockroach Labs recently released their annual cloud report identifying Google Cloud Platform as the best overall provider. The 2021 Cloud Report compares AWS, Azure, and GCP on benchmarks that reflect critical applications and workloads.
-
Embracing Observability in Distributed Systems at InfoQ Live (Virtual Event on Feb 16th)
InfoQ Live, the one-day virtual event designed for the modern software practitioner, returns on Feb 16th, 2021. The focus of this edition is to explore and discover practical ways you can use and integrate observability into your distributed system architecture. Join us on Feb 16th from 9 am EDT / 3 PM CEST. Register for only $19.95.