Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Collective Tuning Initiative
open-in-new
<p>The Collective Tuning Initiative is a community-driven initiative started by <a href="/facts/Grigori_Fursin/gEohJxR3">Grigori Fursin</a> to develop free and <a href="/facts/Open-source/7X9rCdz4">open-source</a> research tools with a unified <a href="/facts/API/GMlN4vUr">API</a> for collaborative characterization, optimization and co-design of computer systems. They enable sharing of benchmarks, data sets and optimization cases from the community in the Collective Optimization Database through unified web services to predict better optimizations or architecture designs (provided there is enough information collected in the repository from multiple users). Using common research-and-development tools should help to improve the quality and reproducibility of computer systems' research and development and accelerate innovation in this area. This approach helped establish Reproducibility Initiatives and Artifact Evaluation at several <a href="/facts/Association_for_Computing_Machinery/abI2atlP">ACM-sponsored</a> conferences to encourage sharing of artifacts and validation of experimental results from accepted papers. </p><p>The tools and repository include: </p> <ul><li><i>Collective Optimization Database</i>: an open repository to share optimization cases from the community, provide web services and <a href="/facts/Plug-in_(computing)/351Du3Wu">plugins</a> to analyze collected performance numbers and predict compiler optimizations to speed up applications based on statistical and machine-learning techniques</li> <li><i>Machine learning-based program optimization predictor</i>: web-service that suggests optimization-improving factors such as execution time, code size and compilation time, based on similarities between programs (program features)</li> <li><i>Continuous Collective Compilation Framework</i>: automates and distributes exploration of large optimization spaces and compiler auto-tuning across multiple users</li> <li><i><a href="/facts/Interactive_Compilation_Interface/Iaf6Dw2Y">Interactive Compilation Interface</a></i>: converts production compilers into interactive research toolsets using an event-driven plugin system to avoid the development of new research compilers from scratch</li> <li><i>Collective benchmark with multiple data sets</i>: enables realistic benchmarking and research on iterative compilation and run-time adaptation.</li> <li><i>Universal Adaptation Framework</i>: Enables run-time adaptation and optimization of statically-compiled programs for heterogeneous, multi-core computer architectures.</li></ul> <p>All above tools became a part of the (<a href="/facts/Collective_Knowledge_(software)/B2yme9Qz">Collective Knowledge framework</a>) released in 2015. </p>