Contents I. Introduction
In the last couple of decades, technological advances in the ICT sector have been the dominant factors in global economic growth, not to mention an increase in the quality of life for billions of people. At the heart of this advance lies Moore’s Law, which states that the number of transistors in an integrated chip will double every 18 to 24 months with each step in the silicon manufacturing technology node. However, due to the fundamental limitations of scaling at the atomic scale, coupled with heat density problems of packing an ever-increasing number of transistors in a unit area, Moore’s Law has slowed down in the last two years or so and will soon stop altogether [1]. The implication is that, in the future, the number of transistors that could be incorporated into a processor chip will not increase. This development threatens the future of the ICT sector as a whole. As a solution to this challenge, there has recently been a dramatic increase in efforts toward heterogeneous computing, including the integration of heterogeneous cores on die, utilizing general-purpose GPUs and combining CPUs, GPUs and FPGAs in integrated SoCs.
