Revised and updated with improvements conceived in parallel programming courses, The Art of Multiprocessor Programming is an authoritative guide to multicore programming. Multicore systems introduce new issues not present in single-core machines, as well as more advanced tools and knowledge that is required to program them effectively. The book provides comprehensive coverage of the principles and algorithmic techniques necessary for effective multiprocessor programming. Students and professionals alike will benefit from the thorough coverage of the essential issues that arise in programming multiprocessor.FeaturesThis edition contains new and substantially revised chapters on concurrency in C++, data-parallel programming, and hardware transactional memory.It includes updates and corrections throughout, based on feedback provided by parallel programming classrooms since 2008.Readers will learn the fundamentals of programming multiple threads and accessing shared memory.Mainstream concurrent data structures and the key elements of their design, as well as synchronization techniques, from simple locks to transactional memory systems, are explored.