06-10-2017, 11:34 AM
Engineering is a compensation study. In computer engineering, compensation has traditionally been between performance, measured in instructions per second, and price. Due to the manufacturing technology, the price is closely related to the size of the chips and the number of transistors. With the advent of embedded systems, new compensation has become the focus of design. This new compensation is between performance and power or power consumption.
The computational requirements of early embedded systems are generally modest, and the performance-power trade-off tends to be weighted toward power. "High performance" and "energy efficiency" were generally opposed concepts.
However, new classes of embedded applications are emerging that have no significant energy constraints, but also require considerable computational resources. Devices such as space vehicles, cell phones, automotive control systems and portable consumer electronics require or benefit from high-performance processors. Future generations of such devices should continue this trend.
The processors of these devices must be able to provide high performance with low power dissipation. In addition, these devices show great fluctuations in their performance requirements. Often, a device will have very low performance demands for most of its operation, but it will experience periodic or asynchronous "spikes" when high performance is required to meet the deadline or handle some interrupt event.
These devices not only require a fundamental improvement in performance power compensation, but also require a processor that can dynamically adjust their performance and power characteristics to provide the compensation that best fits the system requirements at that time.
In addition to exploring several mechanisms to fundamentally improve performance, the MORPH project gave birth to the idea of "gear shifting" as an analogy to runtime reconfiguration. Realizing that real-world applications vary their performance requirements dramatically over time, one of the project's main goals was to design microarchitectures that could be tuned to provide the minimum required performance at the lowest energy cost.
The MORPH project explored a number of microarchitecture techniques to achieve this goal, such as cache hierarchies and the exploitation of bit-cutting activity. One technique, the multi-cluster architectures, is the direct predecessor of this work. In addition to the microarchitecture changes, MORPH also conducted a survey of embedded realistic applications that may be limited. In addition, we explored the design implications of a runtime system with energy consumption.
The computational requirements of early embedded systems are generally modest, and the performance-power trade-off tends to be weighted toward power. "High performance" and "energy efficiency" were generally opposed concepts.
However, new classes of embedded applications are emerging that have no significant energy constraints, but also require considerable computational resources. Devices such as space vehicles, cell phones, automotive control systems and portable consumer electronics require or benefit from high-performance processors. Future generations of such devices should continue this trend.
The processors of these devices must be able to provide high performance with low power dissipation. In addition, these devices show great fluctuations in their performance requirements. Often, a device will have very low performance demands for most of its operation, but it will experience periodic or asynchronous "spikes" when high performance is required to meet the deadline or handle some interrupt event.
These devices not only require a fundamental improvement in performance power compensation, but also require a processor that can dynamically adjust their performance and power characteristics to provide the compensation that best fits the system requirements at that time.
In addition to exploring several mechanisms to fundamentally improve performance, the MORPH project gave birth to the idea of "gear shifting" as an analogy to runtime reconfiguration. Realizing that real-world applications vary their performance requirements dramatically over time, one of the project's main goals was to design microarchitectures that could be tuned to provide the minimum required performance at the lowest energy cost.
The MORPH project explored a number of microarchitecture techniques to achieve this goal, such as cache hierarchies and the exploitation of bit-cutting activity. One technique, the multi-cluster architectures, is the direct predecessor of this work. In addition to the microarchitecture changes, MORPH also conducted a survey of embedded realistic applications that may be limited. In addition, we explored the design implications of a runtime system with energy consumption.