THE GREENDROID MOBILE APPLICATION PROCESSOR
The GreenDroid mobile application processor is a 45-nm multicore research prototype that targets the Android mobile-phone software stack and can execute general-purpose mobile programs with 11 times less energy than today’s most energy-efficient designs, at similar or better performance levels. It does this through the use of a hundred or so automatically generated, highly specialized, energy-reducing cores, called conservation cores. Our research attacks a key technological problem for microprocessor architects, which we call the utilization wall. 1 The utilization wall says that, with each process generation, the percentage of transistors that a chip design can switch at full frequency drops exponentially because of power constraints. A direct consequence of this is dark silicon—large swaths of a chip’s silicon area that must remain mostly passive to stay within the chip’s power budget. Currently, only about 1 percent of a modest-sized 32-nm mobile chip can switch at full frequency within a 3-W power budget. With each process generation, dark silicon gets exponentially cheaper, whereas the power budget is becoming exponentially more valuable. Our research leverages two key insights. First, it makes sense to find architectural techniques that trade this cheap resource, dark silicon, for the more valuable resource, energy efficiency. Second, specialized logic can attain 10x to 1000x better energy efficiency over general-purpose processors. Our approach is to fill a chip’s dark silicon area with specialized cores to save energy on common applications. These cores are automatically generated from the code base that the processor is intended to run—that is, the Android mobile-phone software stack. The cores feature a focused reconfigurability so that they can remain useful even as the code they target evolves.Source :
The Utilization Wall
Although Moore’s law continues to offer exponential increases in transistor count— especially with the promise of 3D integration—CMOS scaling has broken down. We refer to CMOS scaling as the scaling of transistor properties as set down by Dennard in his 1974 paper.2 It is this breakdown of CMOS scaling that led to the industrial shift from single-threaded to multicore processors around 2005. (The ‘‘Understanding the Origins of the Utilization Wall’’ sidebar explains this breakdown in greater detail.) Although a fixed-size chip’s computing capabilities continue to increase exponentially at 2.8. The utilization wall problem is already apparent indirectly through the product lines of major processor manufacturers. Processor frequencies haven’t increased for almost half a decade, and the number of cores on a chip hasn’t been scaling at the same rate as the increase in the number of transistors. An increasing percentage of each chip is being dedicated to cache or lowactivity logic such as memory controllers and portions of the processor’s chipset. Recently, Intel’s Nehalem architecture has featured a Turbo Boost mode that runs some cores faster if the others are switched off. All of these observations show that the utilization wall is strongly shaping the evolution of processor designs. CMOS scaling theory indicates that things are going to get exponentially worse. Future architectures that try to maximize the benefit due to new process generations will need to be consciously designed to leverage many, many transistors, in a way that uses only a tiny fraction of them at a time. GreenDroid’s conservation cores have these exact properties and can be used to relax the utilization wall’s extreme power constraints.