$ show AndreyAkinshin/perfolizer
Perfolizer is a .NET performance-analysis toolkit extracted from BenchmarkDotNet. It provides statistical estimators (quantiles, MAD, variance), significance tests (Mann-Whitney, Welch), and specialized data structures such as Rqq for efficient range quantile queries. The repository is organized as a main class library, a demo executable, and two test projects, with CI that builds, tests, and publishes NuGet packages. Despite being labeled experimental, the codebase is actively developed, versioned, and shipped as a NuGet package.
The LLM identified 3 files worth highlighting for reuse:
Perfonar's table system provides column definitions, cloudscapes for shared metadata, and markdown/JSON output. It is self-contained and could be extracted into a standalone structured-reporting library for any .NET project that needs reproducible table formatting.
Rqq is a specialized tree-based data structure for efficient range quantile queries, built on QuickSelectAdaptive. It demonstrates non-obvious algorithmic engineering and is reusable wherever repeated quantile queries over mutable or queryable data ranges are needed, though it carries TODOs for further optimization.
Implements adaptive selection algorithms including median-of-ninthers and expand-partition logic. This is a high-performance, self-contained order-statistics component that can be extracted and reused in any .NET application requiring fast selection or quantile computation.