Picollo is a new library for serious performance work in .NET. Picollo stands for Performance Instrumentation and Continuous Observation for Low-Level Optimization. It allows you to measure code performance with cycle-level precision, moving the time resolution to the picosecond level.

The initial public release of Picollo v0.1.0 contains two components. First, a modern version of an HDR histogram, which is much faster for recording data and easier to use. It has a thread-local implementation that allows scaling metrics collection across many threads with minimal impact on performance of the existing code. Second, a set of APIs for `perf_event_open`, including fast-path reads, that give raw access to PMU counters from .NET on Linux, WSL included.

At the start of the New Year, GitHub exploded with The One Billion Row Challenge started by Gunnar Morling. Originally it was a Java-only competition, but others wanted to have fun as well. Please read these links first if you do not know about this challenge and its rules.

I also fell down this rabbit hole. I wrote one of the fastest managed 1BRC implementation that performs well not only on the specific dataset that everyone was optimizing for but also on more generic data. Furthermore, at the initial time of writing (the post date) my results were close to the C++ implementation for the default data and were faster in the case of more complex data.

In this blog series, I will experiment with Rust as a safer and simpler C/C++ replacement. The idea is to combine a couple of C dependencies in Rust, to do some work using the dependencies in Rust and to expose a final API from a Rust library via C ABI. Then I will consume the same exported Rust methods from a number of modern languages/platforms such as C#, Python, Java, Nodejs, R, Go and even back from C/C++.