Prior Art

Benchmark Tracking Tools

• General

  • Bencher - Continuous Benchmarking: Catch performance regressions in CI
  • benchmark-action/github-action-benchmark - GitHub Action for continuous benchmarking to keep performance
  • conbench/conbench - Language-independent Continuous Benchmarking (CB) Framework
  • Hyperfoil/Horreum - Benchmark results repository service
  • It4innovations/snailwatch - Continuous performance monitoring service
  • nyrkio/nyrkio - Nyrkiö is an open source platform for detecting performance changes
  • smarr/ReBench - Execute and document benchmarks reproducibly

• Benchmark Harness Specific

  • airspeed-velocity/asv - Airspeed Velocity: A simple Python benchmarking tool with web-based reporting
  • bamlab/flashlight - Flashlight is a Lighthouse-like tool for mobile apps. No installation required.
  • benchhub/benchhub - A service for running database benchmarks and saving the result
  • bheisler/criterion.rs - Statistics-driven benchmarking library for Rust
  • boa-dev/criterion-compare-action - Compare the performance of Rust project branches
  • bobheadxi/gobenchdata - Run Go benchmarks, publish results to an interactive web app, and check for performance regressions in your pull requests
  • callstack/reassure - Performance testing companion for React and React Native
  • codingberg/benchgraph - Visualization of Golang benchmark output using Google charts
  • CodSpeed - CodSpeed provides integrated CI tools for software engineering teams to anticipate the impacts of the next delivery on system performance.
  • Cybench - Continuous performance regression testing for Java CI/CD pipelines
  • dandavison/chronologer - Visualize performance benchmarks over git commit history
  • dapplion/benchmark - JS/TS benchmarking solution to track performance regressions in CI
  • distributed-system-analysis/pbench - A benchmarking and performance analysis framework
  • icebob/bench-bot - Benchmark runner robot. Continuous benchmarking for benchmarkify the benchmark framework for NodeJS
  • jsperf/jsperf.com - jsPerf aims to provide an easy way to create and share test cases, comparing the performance of different JavaScript snippets by running benchmarks.
  • jumaffre/cimetrics - Track your metrics in GitHub PR to avoid unwanted regressions
  • knqyf263/cob - Continuous Benchmark for Go Project
  • moditect/jfrunit - A JUnit extension for asserting JDK Flight Recorder events
  • NimbleDroid - Functional Performance Testing for Android & iOS
  • novadiscovery/benchgraph - A lightewight tool for visualizing your benchmarks history
  • OctoPerf - Simplify your load testing experience
  • ocurrent/current-bench - Experimental continuous benchmarking infrastructure using OCurrent pipelines
  • OpenBenchmarking.org - Storage of Phoronix Test Suite benchmark result data (including optional system logs, etc)
  • OpenEBench - OpenEBench is the ELIXIR gateway to benchmarking communities, software monitoring, and quality metrics for life sciences tools and workflows.
  • Orijtech bencher - Continuous benchmarking for the Go programming language
  • Perfbench - Perfbench is an interactive online C++ code profiling tool.
  • Performance Analysis - Diagnose & prevent performance regressions
  • python/codespeed - A fork of Codespeed that includes the instances run at https://speed.python.org/ and https://speed.pypy.org
  • tobami/codespeed - A web application to monitor and analyze the performance of your code
  • trytouca/trytouca - Continuous Regression Testing for Engineering Teams
  • Unity-Technologies/PerformanceBenchmarkReporter - Establish benchmark samples and measurements using the Performance Testing package, then use these benchmark values to compare subsequent performance test results in an html output utilizing graphical visualizations

• Web Specific

  • Contentsquare - Speed Analysis is not only about Synthetic Monitoring but also offers powerful Real User Monitoring capabilities, a great fit for brands leading the way on customer experience across the world.
  • Iron/Out - Faster websites equals better business results: improve user experience, increase conversion rate and page experience ranking, lower the bounce rate
  • MeasureWorks - Track user behavior with End-2-End observability to continuously optimize your online performance
  • SpeedCurve - See how people experience the speed of your website, then identify and fix performance issues
  • ubenchan/frontend - Beautiful browser benchmarks
  • WebPageTest - Run a free website speed test from around the globe using real browsers at consumer connection speeds with detailed optimization recommendations

• Project Specific

  • apache/arrow-datafusion - A /benchmark GitHub command to compare benchmark between base and PR commits
  • BrowserBench - Speedometer is a browser benchmark that measures the responsiveness of web applications
  • corecheck/corecheck - Test coverage and more for Bitcoin Core including continuous benchmarking
  • deno.land benchmarks - As part of Deno’s continuous integration and testing pipeline we measure the performance of certain key metrics of the runtime. You can view these benchmarks here.
  • diesel-rs/metrics - The numbers collected by diesel continuous scheduled benchmark actions to track changes over time
  • Elasticsearch Benchmarks - The results of the Elasticsearch nightly benchmarks based on the main branch as of that point in time
  • golang/benchmarks - Benchmarks for the Go perf dashboard
  • Google Chrome V8 - CSuite: Local benchmarking for V8 performance analysis
  • lampepfl/bench-data - Continuous benchmarking data for Dotty Benchmarks
  • Lucene Nightly Benchmarks - Each night, an automated Python tool checks out the Lucene/Solr trunk source code and runs multiple benchmarks
  • Myoldmopar/EnergyPlusBuildResults - Build, test, and performance results dashboard for EnergyPlus
  • OpenTelemetry Benchmarks - The OpenTelemetry Collector runs load tests on every commit to the opentelemetry-collector-contrib repository
  • parse-community/benchmark - Parse Server Continuous Benchmark
  • python/pyperformance - Python Performance Benchmark Suite
  • pytorch/benchmark - TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.
  • PyPy Speed Center - A fork of Codespeed of PyPy
  • Python Speed Center - A fork of Codespeed for Python
  • rust-lang/rustc-perf - Website for graphing performance of rustc
  • Shopify/yjit-bench - Set of benchmarks for the YJIT CRuby JIT compiler and other Ruby implementations seen at speed.yjit.org
  • Skia Perf - Skia Perf is a web application for analyzing and viewing performance metrics produced by Skia’s testing infrastructure
  • Supabench - App by Supabase team to run benchmarks automatically in CI
  • Vitess Are We Fast Yet - Automated benchmarking system that tests Vitess’s performance on a nightly basis
  • rustls/rustls-bench-app - Continuous benchmarking for the Rustls project
  • ziglang/gotta-go-fast - Performance Tracking for Zig

🐰 A special thank you to Continuous Benchmark! Some of their test files are used for our Benchmark Harness Adapters.

Benchmark Tracking Posts

• Microsoft

  • Performance regression tests at Microsoft Security

• Facebook

  • Mobile performance: Tooling infrastructure at Facebook
  • BrowserLab: Automated regression detection for the web
  • MobileLab: Highly accurate testing to prevent mobile performance regressions

• Apple

  • WebKit Regression Testing
  • WebKit’s no performance regression policy

• Amazon

  • Performance Efficiency: Benchmark existing workloads

• Netflix

  • Fixing Performance Regressions Before they Happen

• Google

  • Chrome: Addressing Performance Regressions
  • Android Developers: Run benchmarks in Continuous Integration
  • Flutter/Skia: Detecting Benchmark Regression
  • Android Developers: Fighting regressions with Benchmarks in CI

• Dropbox

  • Athena: Our automated build health management system
  • Keeping sync fast with automated performance regression detection

• Elastic

  • How we perform continuous performance testing on Enterprise Search

• MongoDB

  • Reducing Variability in Performance Tests on EC2: Setup and Key Results
  • Using Change Point Detection to Find Performance Regressions
  • Creating a virtuous cycle in performance testing
  • The Use of Change Point Detection to Identify Software Performance Regressions in a Continuous Integration System (video)
  • Automated system performance testing at MongoDB
  • Creating a Virtuous Cycle in Performance Testing at MongoDB (video)
  • Automated Triage of Performance Change Points Using Time Series Analysis and Machine Learning: Data Challenge Paper
  • Characterizing and Triaging Change Points
  • Beware of the Interactions of Variability Layers When Reasoning about Evolution of MongoDB
  • Change Point Detection for MongoDB Time Series Performance Regression
  • Performance Testing at MongoDB

• Academic

  • Producing Wrong Data Without Doing Anything Obviously Wrong!
  • Locating Performance Regression Root Causes in the Field Operations of Web-Based Systems: An Experience Report
  • Stabilizer: Statistically Sound Performance Evaluation
  • A Nonparametric Approach for Multiple Change Point Analysis of Multivariate Data
  • Automated Detection of Performance Regressions Using Regression Models on Clustered Performance Counters
  • Robust benchmarking in noisy environments
  • Virtual Machine Warmup Blows Hot and Cold
  • BenchHub: store database benchmark result in database
  • Continuous Benchmarking: Using System Benchmarking in Build Pipelines
  • Towards Continuous Benchmarking: An Automated Performance Evaluation Framework for High Performance Software
  • Duet Benchmarking: Improving Measurement Accuracy in the Cloud
  • Search-based detection of code changes introducing performance regression
  • Hunter: Using Change Point Detection to Hunt for Performance Regressions
  • ElastiBench: Scalable Continuous Benchmarking on Cloud FaaS Platforms
  • Increasing Efficiency and Result Reliability of Continuous Benchmarking for FaaS Applications

• Others

  • Accurate and efficient software microbenchmarks
  • Are your memory-bound benchmarking timings normally distributed?
  • Automated performance regression testing with Reassure
  • automatically prevent performance regressions
  • Automating Speed: A Proven Approach to Preventing Performance Regressions in Kafka Streams
  • Autonomously Finding Performance Regressions In The Linux Kernel
  • Benchmarking C++ Code at CppCon 2015
  • Building an Open Source, Continuous Benchmark System
  • CI for performance: Reliable benchmarking in noisy environments
  • Compare and optimize your code with Datadog Profile Comparison
  • Continuous Benchmarking for OCaml Projects
  • Continuous benchmarking for rustls
  • Continuous Performance Regression Testing for CI/CD
  • Created GitHub Action for continuous benchmarking
  • Demanding the impossible rigorous database benchmarking
  • Exploring the Rust compiler benchmark suite
  • Get a performance score for your app
  • Is GitHub Actions suitable for running benchmarks?
  • Lighthouse for mobile apps
  • Measuring and Improving React Native Performance
  • Microbenchmarking calls for idealized conditions
  • Minimum Times Tend to Mislead When Benchmarking
  • Paired benchmarking. How to measure performance
  • Performance in Continuous Integration
  • Performance Regression Testing
  • Performance testing in CI: Let’s break the build!
  • Performance Testing in the CI/CD Pipeline
  • Performance-Regression Pitfalls Every Project Should Avoid
  • Regression Testing of Performance - SmartBear TestComplete
  • Storing Continuous Benchmarking Data in Prometheus
  • The mean misleads: why the minimum is the true measure of a function’s run time
  • Towards Continuous Performance Regression Testing

Benchmark Comparisons

• BurntSushi/rebar - A biased barometer for gauging the relative speed of some regex engines on a curated set of tasks.
• CH-benCHmark - Operational and real-time Business Intelligence (BI) mixed workload SQL benchmarks
• ClickBench - A Benchmark For Analytical DBMS
• denosaurs/bench - Comparing deno & node HTTP frameworks
• diesel-rs/diesel_bench - A benchmark suite for relational database connection crates in Rust
• HewlettPackard/netperf - Netperf is a benchmark that can be used to measure the performance of many different types of networking. It provides tests for both unidirectional throughput, and end-to-end latency
• krausest/js-framework-benchmark - A comparison of the performance of a few popular javascript frameworks
• parttimenerd/temci - An advanced benchmarking tool
• PerfKit Benchmarker (PKB) - A set of benchmarks to measure and compare cloud offerings. The benchmarks use default settings to reflect what most users will see.
• Programming Language Benchmarks - Yet another implementation of computer language benchmarks game
• rosetta-rs/argparse-rosetta-rs - Comparison of Rust argparse APIs
• rosetta-rs/hashing-rosetta-rs - Comparison of Rust hash comparison vs direct string comparison
• rosetta-rs/md-rosetta-rs - Comparison of Rust Markdown APIs
• rosetta-rs/parse-rosetta-rs - Comparison of Rust parser APIs
• rosetta-rs/string-rosetta-rs - Comparison of Rust string types
• rosetta-rs/template-benchmarks-rs - Comparison of Rust template engines
• Standard Performance Evaluation Corporation (SPEC) - A non-profit consortium that establishes and maintains standardized benchmarks and performance evalutation tools for new generations of computing systems
• TechEmpower/FrameworkBenchmarks - In the following tests, we have measured the performance of several web application platforms, full-stack frameworks, and micro-frameworks (collectively, “frameworks”).
• timescale/tsbs - Time Series Benchmark Suite, a tool for comparing and evaluating databases for time series data
• The Computer Language Benchmarks Game - Which programming language is fastest?
• TPC - Benchmarking and load testing for the worlds most popular databases supporting Oracle Database, Microsoft SQL Server, IBM Db2, PostgreSQL, MySQL and MariaDB
• Top500 - Ranks and details the 500 most powerful non-distributed computer systems in the world

Benchmark Harnesses

• Android

  • Macrobenchmark - Writing a Macrobenchmark
  • Microbenchmark - Microbenchmark Overview

• C

  • akopytov/sysbench - Scriptable database and system performance benchmark
  • gormanm/mmtests - Benchmarking framework primarily aimed at Linux kernel testing
  • Linux kernel perf bench - This command includes a number of multi-threaded microbenchmarks to exercise different subsystems in the Linux kernel and system calls.
  • LinuxPerfStudy/LEBench - An analysis of performance evolution of Linux’s core operations
  • Phoronix Test Suite - Open-Source, Automated Benchmarking
  • RRZE-HPC/likwid - Performance monitoring and benchmarking suite

• C++

  • catchorg/Catch2 - A modern, C++-native, test framework for unit-tests, TDD, and BDD - using C++14, C++17, and later
  • DigitalInBlue/Celero - C++ Benchmark Authoring Library/Framework
  • facebook/folly/Benchmark.h - Provides a simple framework for writing and executing benchmarks
  • google/benchmark - A microbenchmark support library for C++
  • iboB/picobench - A micro microbenchmarking library for C++11 in a single header file
  • ivafanas/sltbench - C++ benchmark tool. Practical, stable and fast performance testing framework.
  • libnonius/nonius - A C++ micro-benchmarking framework

• C#

  • donet/BenchmarkDotNet - Powerful .NET library for benchmarking
  • Unity-Technologies/PerformanceBenchmarkReporter - Establish benchmark samples and measurements using the Performance Testing package, then use these benchmark values to compare subsequent performance test results in an html output utilizing graphical visualizations
  • xunit/xunit - xUnit.net is a free, open source, community-focused unit testing tool for .NET

• Elixir

  • alco/benchfella - Microbenchmarking tool for Elixir
  • bencheeorg/benchee - Easy and extensible benchmarking in Elixir providing you with lots of statistics!

• Functions as a Service (FaaS)

  • vhive-serverless/STeLLAR - STeLLAR: Open-source framework for serverless clouds benchmarking

• Go

  • Benchmarks - Go test benchmarks

• Haskell

  • haskell/criterion - A powerful but simple library for measuring the performance of Haskell code

• Java

  • moditect/jfrunit - A JUnit extension for asserting JDK Flight Recorder events
  • openjdk/jmh - JMH is a Java harness for building, running, and analyzing nano/micro/milli/macro benchmarks written in Java and other languages targeting the JVM

• JavaScript

  • bestiejs/benchmark.js - A benchmarking library. As used on jsPerf.com
  • callstack/reassure - Performance testing companion for React and React Native
  • console.time/console.timeEnd - A method to start/stop a timer you can use to track how long an operation takes
  • deno bench - Deno has a built-in benchmark runner that you can use for checking performance of JavaScript or TypeScript code.
  • evanwashere/mitata - cross-runtime benchmarking lib and cli
  • Node.js Performance Measurement API - This module provides an implementation of a subset of the W3C Web Performance APIs as well as additional APIs for Node.js-specific performance measurements.
  • RafaelGSS/bench-node - The bench-node module gives the ability to measure performance of JavaScript code.
  • ShogunPanda/cronometro - Simple benchmarking suite powered by HDR histograms.
  • tinylibs/tinybench - A simple, tiny and lightweight benchmarking library!
  • v8/web-tooling-benchmark - JavaScript benchmark for common web developer workloads
  • vitest bench - vitest bench uses tinybench library under the hood
  • yamiteru/isitfast - A modular benchmarking library with V8 warmup and cpu/ram denoising for the most accurate and consistent results.

• Julia

  • JuliaCI/BenchmarkTools.jl - A benchmarking framework for the Julia language

• Python

  • airspeed-velocity/asv - Airspeed Velocity: A simple Python benchmarking tool with web-based reporting
  • ionelmc/pytest-benchmark - py.test fixture for benchmarking code
  • timeit - This module provides a simple way to time small bits of Python code

• Ruby

  • ruby/benchmark - Methods for benchmarking Ruby code, giving detailed reports on the time taken for each task

• Rust

  • bazhenov/tango - Rust pairwise microbenchmarking harness
  • bheisler/criterion.rs - Statistics-driven benchmarking library for Rust
  • bheisler/iai - Experimental one-shot benchmarking/profiling harness for Rust
  • bluss/bencher - bencher is just a port of the libtest (unstable) benchmark runner to Rust stable releases. cargo bench on stable. “Not a better bencher!” = No feature development. Go build a better stable benchmarking library.
  • BurntSushi/cargo-benchcmp - A small utility to compare Rust micro-benchmarks
  • iai-callgrind/iai-callgrind - High-precision and consistent benchmarking framework/harness for Rust
  • jbreitbart/criterion-perf-events - A plugin for Criterion.rs to measure Linux perf events
  • libtest bench - The libtest harness supports running benchmarks for functions annotated with the #[bench] attribute. Benchmarks are currently unstable, and only available on the nightly channel.
  • ThijsRay/coppers - Coppers is a custom test harnass for Rust that measures the energy usage of your test suite.
  • nvzqz/divan - Comfy benchmarking for Rust projects
  • sarah-ek/diol - diol is a benchmarking library for Rust.

• Shell

  • Gabriella439/bench - Command-line benchmark tool
  • sharkdp/hyperfine - A command-line benchmarking tool

• SQL

  • ClickHouse/ClickBench - ClickBench: a Benchmark For Analytical Databases
  • TPC-Council/HammerDB - HammerDB Database Load Testing and Benchmarking Tool

• Swift

  • apple/swift - The Swift Benchmark Suite
  • google/swift-benchmark - A swift library to benchmark code snippets