http://hexus.net/tech/news/cpu/98668-researchers-break-multi-core-cpu-bottleneck/
 

One possible solution, devised by Intel and at NC State scientists, is moving the software queue to hardware. As explained in the above linked report, "This effectively turned three multistep ­software-queue operations into three simple instructions: Add data to the queue, take data from the queue, and put data close to where it's going to be needed next."In practical use a hardware queue management device (QMD) noticeably sped up tasks using data processing simulations. With QMD more cores show stronger gains – a 16 core CPU with QMD performed 20 times faster, for example. Furthermore, as the QMD is capable of simple computational functions it can aggregate data from multiple cores, expediting some basic computational functions.

 
Edit: Revised title.

I have wondered for a few years why we didn't have something like this. It was apparent that programmers weren't using multi core well. Thus I always wondered why not have a dedicated core that passes the work around to all the other cores.

At one point I remember Amd talking about doing something like this back in roughly 2009. Seems that it never took off but we are finally seeing the results of the idea.