This session discusses how to implement a high-level parallel API (such as parallel_for, parallel_while, or parallel_scan) and math calculation based on a thread pool and task in OpenJDK that aligns with the development of multicores and parallel computing. At present, programmers have to use a schedule strategy statically in code instead of choosing it dynamically based on the core number and load balance on the computer with the current Java concurrent package. In the design presented in the session, the function parallel_for(array, task) is a high-level API that can divide the task range dynamically, based on the condition of and load on different computers.
Presented by Richard Ning at JavaOne 2013
Clipping is a handy way to collect important slides you want to go back to later.