Low Power Multicore Processors for Embedded Systems
A multicore chip is one of the most promising approaches to achieve high performance. Formerly, frequency scaling was the best approach. However, the scaling has hit the power wall, and frequency enhancement is slowing down. Further, the performance of a single processor core is proportional to the square root of its area, known as Pollack’s rule , and the power is roughly proportional to the area. This means lower performance processors can achieve higher power efficiency. Therefore, we should make use of the multicore chip with relatively low performance processors.
The power wall is not a problem only for high-end server systems. Embedded systems also face this problem for further performance improvements . MIPS is the abbreviation of million instructions per second, and a popular integer-performance measure of embedded processors. The same performance processors should take the same time for the same program, but the original MIPS varies, reflecting the number of instructions executed for a program. Therefore, the performance of a Dhrystone benchmark relative to that of a VAX 11/780 minicomputer is broadly used [3, 4]. This is because it achieved 1 MIPS, and the relative performance value is called VAX MIPS or DMIPS, or simply MIPS. Then GIPS (giga-instructions per second) is used instead of the MIPS to represent higher performance.
Figure 1.1 roughly illustrates ...