Vectorized and performance-portable Quicksort (2022)

Python sets and dictionaries can have quadratic-time performance

Apple says new A20 Pro chip can sustain twice the performance of the iPhone 16 Pro, deliver 40% faster graphics

When ORM Becomes OMG- Performance Pitfalls in JPA and Friends by Jos Roseboom

Microsoft promises faster Windows 11 boot times and better performance on 8GB PCs

High-performance garbage collection for C++

How Do HashMaps Work Under the Hood? (putting together a toy implementation in Rust to understand performance optimization, collisions, and time complexities)

Rust SQLx Performance

When the brain is unsure which information matters, visual features that are normally encoded separately become mixed within the same neurons, causing irrelevant information to interfere with perception and reducing performance on uncertain or multitasking tasks

Comparing performance of different offline first solutions

PISA 2025 Students' reading and mathematics performance declined across the OECD

WebLLM: high-performance in-browser LLM inference engine

Benchspotter: a companion app for performance work in go

Experimental Evaluation Methodology for the Era of No Steady Performance [pdf]

I created chrono-ta, a high-performance, timestamp-aware TA library

Researchers developed a 15–20-minute training programme that improves people’s ability to distinguish between real and AI-generated faces, with performance improving from below chance to above chance, while computer models trained on the same cues reached 94% accuracy

Performance Characterization of SPEC CPU 2026 on AMD EPYC 9755 Processor

Performance Benchmarking: gRPC+Protobuf vs. HTTP+JSON

Hyper: A High Performance Programming Language for AI

Splunk SHC Upgrade Performance — Comparing search runtime from 9.3.3 to 10.2.5

Performance plotting techniques

Sieving and Factorization performance vs c?

Tagisan (tgs): High-performance Multi-LLM Swarms & Mixture-of-Agents in Rust

DIO: High Performance Go IO toolkit

Danube v0.16.0 , focused on performance with zero-copy I/O and memory optimizations.

I wrote a high-performance bloom filter specialized on IPv4 that beats general-purpose crates in throughput while still delivering a somewhat decent FPR.

Hyper: A High-Performance Programming Language for AI

protobuf in kube-rs, community question (performance related issues)

How I made Rustdoc 33% faster in one week

Saving 100 terabytes of memory by optimizing 1.1.1.1's DNS cache

More →