Tech3d ago·39 sources

Scientists are exploring new avenues for computing power as Moore's Law, which predicted the doubling of transistors on a chip every two years, approaches its physical limits. Professor Tom Conte of Georgia Tech is involved in the International Roadmap for Devices and Systems, an initiative by the Institute of Electrical and Electronics Engineers (IEEE) to forecast computing advancements beyond traditional silicon chips. The project aims to identify new benchmarks and technologies to accelerate computing, moving away from the sole focus on shrinking transistors. Ideas being considered include biologically inspired computing (neuromorphic computing), quantum computing, graphene-based devices, and approximate computing, which leverages the fact that many computations do not require perfect precision. These approaches aim to address the increasing demand for computing power and the associated energy inefficiency of current technologies, particularly for applications like big data analytics, machine learning, and high-performance simulations. The goal is to detach future computing growth from the limitations of traditional semiconductor technology.