MIT Randomizes Tasks To Speed Massive Multicore Processors

itwbennett writes Researchers at the Massachusetts Institute of Technology have created a data structure that they claim can help large multicore processors churn through their workloads more effectively. Their trick? Do away with the traditional first-come, first-served work queue and assign tasks more randomly. The SprayList algorithm allows processors with many cores to spread out their work so they don't stumble over one another, creating bottlenecks that hamper performance.

Comments

Re:I don't know enough about this stuff

[fey000]

If I'm not mistaken, you are thinking about branch prediction, not out-of-order-executions in an otherwise serial pipe.

To elaborate, OOE deals with computing as much as possible without having to wait for a result first.
Branch prediction is a cache separate from the execution tray that attempts to predict the outcome of an if/switch or other branching evaluation and then load the pipelines to the execution tray with the computations following that branching, since the time it takes to evaluate an if/switch can be long, and without a prediction the cpu would have to stall until the evaluation is complete.