Futures, Scheduling, and Work Distribution.ppt

Art of Multiprocessor Programming Futures, Scheduling, and Work Distribution Companion slides for The Art of Multiprocessor Programming by Maurice Herlihy Nir Shavit How to write Parallel Apps? How to split a program into parallel parts In an effective way Thread management Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Matrix Multiplication Thread Overhead Threads Require resources Memory for stacks Setup, teardown Scheduler overhead Worse for short-lived threads Thread Pools More sensible to keep a pool of long-lived threads Threads assigned short-lived tasks Runs the task Rejoins pool Waits for next assignment Thread Pool = Abstraction Insulate programmer from platform Big machine, big pool And vice-versa Portable code Runs well on any platform No need to mix algorithm/platform concerns ExecutorService Interface In java.util.concurrent Task = Runnable object If no result value expected Calls run() method. Task = CallableT object If result value of type T expected Calls T call() method. FutureT FutureT FutureT Future? Future? Future? Note Executor Service submissions Like New England traffic signs Are purely advisory in nature The executor Like the New England driver Is free to ignore any such advice And could execute tasks sequentially … Matrix Addition Matrix Addition Matrix Addition Task Matrix Addition Task Matrix Addition Task Matrix Addition Task Matrix Addition Task Dependencies Matrix example is not typical Tasks are independent Don’t need results of one task … To complete another Often tasks are not independent Fibonacci Note potential parallelism Dependencies Disclaimer This Fibonacci implementation is Egregiously inefficient So don’t deploy it! But illustrates our point How to deal with dependencies Exercise: Make this implementation efficient! Multithreaded Fibonacci Multithrea