Automatic Tuning of Compilers Using Machine Learning (SpringerBriefs in Applied Sciences and Technology)

This book explores break-through approaches to tackling and mitigating the well-known problems of compiler optimization using design space exploration and machine learning techniques. It demonstrates that not all the optimization passes are suitable for use within an optimization sequence and that, in fact, many of the available passes tend to counteract one another. After providing a comprehensive survey of currently available methodologies, including many experimental comparisons with state-of-the-art compiler frameworks, the book describes new approaches to solving the problem of selecting the best compiler optimizations and the phase-ordering problem, allowing readers to overcome the enormous complexity of choosing the right order of optimizations for each code segment in an application. As such, the book offers a valuable resource for a broad readership, including researchers interested in Computer Architecture, Electronic Design Automation and Machine Learning, as well as computer architects and compiler developers.

本書探討了使用設計空間探索和機器學習技術來解決和減輕編譯器優化中眾所周知的問題的突破性方法。它證明了並非所有的優化過程都適合在優化序列中使用，事實上，許多可用的過程往往相互抵消。在提供了目前可用方法的全面調查後，包括與最先進的編譯器框架進行的許多實驗比較，本書描述了解決選擇最佳編譯器優化和階段排序問題的新方法，使讀者能夠克服為應用程序中的每個代碼段選擇正確的優化順序所帶來的巨大複雜性。因此，本書為廣大讀者提供了寶貴的資源，包括對計算機架構、電子設計自動化和機器學習感興趣的研究人員，以及計算機架構師和編譯器開發人員。