Dark Mode

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

CahillMeyer/ccm-modern-cpp-benchmarks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

9 Commits

Repository files navigation

CCM Code | Modern C++ Benchmarks

This repository contains reproducible benchmarks demonstrating the performance impact of modernizing Legacy C++ codebases.

We use these benchmarks to validate architectural decisions for High-Frequency Trading (HFT) and Embedded Computer Vision projects.

Philosophy

"Fast" is not an opinion. It is a measurement. We compare idiomatic "Legacy" C++ (typical of C++98/11 codebases) against "Modern" C++20/23 patterns to quantify the benefits of modernization--specifically focusing on P99 Latency and Memory Fragmentation.

Benchmarks

Case Study Focus Legacy Approach Modern Approach (C++20) Result
01. Malloc Latency P99 Latency Heap Allocation (std::vector) Stack Arena (std::pmr) 1.4x Faster

Build & Run

All benchmarks use Google Benchmark. The build system automatically fetches dependencies.

git clone [https://github.com/cahillmeyer/ccm-modern-cpp-benchmarks.git](https://github.com/cahillmeyer/ccm-modern-cpp-benchmarks.git)
cd ccm-modern-cpp-benchmarks/01-malloc-latency
mkdir build && cd build
cmake .. -DCMAKE_BUILD_TYPE=Release
make
./bench_malloc_vs_pmr

Engineering for Performance

"Fast" is a measurement, not an opinion. If your system requires deterministic, high-throughput performance--whether in High-Frequency Trading or Embedded Computer Vision--your choice of C++ patterns matters.

CCMCode helps engineering teams identify and eliminate these bottlenecks.

Performance & Consulting

I help engineering teams identify and eliminate bottlenecks in latency-critical systems.

  • Need a Performance Audit? I offer one-time Architecture Reviews to analyze your legacy C++ codebase. Book via GitHub Sponsors
  • Support the Data: Sponsor monthly to fund new benchmark scenarios.
  • Enterprise Modernization: For full-scale refactoring projects, contact info@ccmcode.dev.

Contact CCM Code | High-Performance C++ Engineering.

About

High-performance C++ benchmarks quantifying the impact of modern standards and architectural patterns on latency-critical systems.

Topics

Resources

Readme

License

MIT license

Stars

Watchers

Forks

Releases

No releases published

Sponsor this project

Packages

Contributors