In JDK 5.0, the Java platform libraries were upgraded to facilitate coarse-grained parallelism; these mechanisms facilitated the creation of multi-threaded server applications that partitioned work along task-level boundaries. As Moore's Law continues to give us more and more cores, applications may seek to extract finer-grained parallelism. This talk will explore language and library improvements in JDK 7 and beyond that facilitate the exploitation of data-level parallelism in the Java language and other languages running on the JVM.
Keywords: Parallelism, fork join, recursive decomposition, Java
Target audience: Anyone who wants to make their applications scale better on multicore systems
Biography: Brian Goetz
Brian Goetz has been a professional software developer for 20 years. He is the author of the best-selling book "Java Concurrency In Practice", as well as over 75 articles on software development. He is a frequent presenter at major industry conferences, and serves on numerous JCP expert groups. Brian is a Sr. Staff Engineer at Oracle.
Software Passion: Seeking programming models where code that looks right is right.
Java Concurrency in Practice: www.jcip.net