Abstract
Computing systems are widely used in medical diagnosis, climate prediction, autonomous vehicles, etc. As the key part of electronics, the performance of computing systems is crucial in the intellectualization of the equipment. The conflict between performance, efficiency, and cost can be solved by choosing an appropriate computing system architecture. In order to provide useful advice and instructions for the designers to fabricate high-performance computing systems, this paper reviews the Chiplet-based computing system architectures, including computing architecture and memory architecture. Firstly, the computing architecture used for high-performance computing, mobile, and PC is presented and summarized. Secondly, the memory architecture based on mainstream memory and emerging non-volatile memory used for data storing and processing are introduced, and the key parameters of memory are compared and discussed. Finally, this paper is concluded, and the future perspectives of computing system architecture based on Chiplet are presented.
Highlights
Electronic equipment is becoming more intellectualized with the development of 5G, artificial intelligence (AI), and big data
Precision equipment can be designed by using a computing system; high-performance computing systems are crucial in electronic equipment [4]
Loi et al [42] proved 3D memory architecture has a smaller delay than 2D architecture with a bus model, and the performance is significantly improved in intensive applications, as the frequency increases
Summary
Electronic equipment is becoming more intellectualized with the development of 5G, artificial intelligence (AI), and big data. It shows that the computing system architecture based on Chiplet has performance and hardware utilization, as well as lower cost. Chiplets to design a high-performance computing architecture, as shown, which can improve computing speed by 22.8% with an energy efficiency of 0.5 pj/bit. It integrates high-throughput and energy-efficient GPU Chiplet, high-performance multi-core CPU. The system can achieve a bandwidth of 3 TB/s and power consumption of 160 W at 1 GHz. Lin et al [22] designed a Chiplet-based high-performance computing architecture, which integrates four 7 nm ARM Cortex-A72 cores in two computing Chiplets. There are already solutions for these problems; the Chiplet-based reconfigurable computing system design technology has obvious technical advantages
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call