Giuseppe Di Guglielmo - Columbia Univ., New York, NY
Davide Giri - Columbia Univ., New York, NY
Paolo Mantovani - Columbia Univ., New York, NY
Heterogeneous systems-on-chip empower all modern intelligent systems. We start by explaining the implications of the ever-increasing variety of specialized accelerators present in SoCs: the price for the efficiency gain they offer is the complexity of system integration. To address this challenge, we developed Embedded Scalable Platforms. By combining a scalable architecture with a system-level methodology, ESP simplifies the design of individual accelerators and automates their hardware/software integration.
First, we discuss the properties of ESP that are key for open-source hardware, including flexibility, modularity, scalability and reusability. Then, we demonstrate the main features of the open-source ESP infrastructure, including integration of third-party RISC-V cores and accelerators developed with various design flows (high-level synthesis, Chisel, RTL), system-level ESP services for managing heterogeneity, and reconfigurable cache-coherence models for accelerators. Finally, we illustrate the ESP software-stack templates that enable system-level simulation for testing accelerators with bare-metal applications and full-system FPGA-based emulation for software development.
The open source ESP release is available here.
Luca P. Carloni is Professor of Computer Science at Columbia University in the City of New York. He holds a Laurea Degree in Electronics Engineering from the University of Bologna and the MS and PhD degrees in Electrical Engineering and Computer Sciences from UC Berkeley. His research interests are in system-on-chip platforms and distributed embedded systems. He coauthored over one hundred and forty refereed papers. Luca received the NSF CAREER Award, the ONR Young Investigator Award, and an Alfred P. Sloan Research Fellowship. In 2013, Luca served as general chair of Embedded Systems Week. Luca is an IEEE Fellow.
Giuseppe Di Guglielmo received the Laurea degree (summa cum laude) and the PhD degree in Computer Science from the University of Verona, Italy in 2005 and 2009, respectively. He is currently an Associate Research Scientist with the Department of Computer Science, Columbia University, New York. His PhD thesis was on the verification and validation of system-level hardware design. His current research topics include the design, validation, and security of hardware accelerators. He is also interested in the acceleration of machine learning applications for physics and robotics with high-level synthesis and FPGA platforms. He has authored over 50 publications.
Davide Giri is a PhD student in Computer Science at Columbia University. He received the MS degree in electronic engineering from Politecnico di Torino and the MS degree in electrical and computer engineering from the University of Illinois at Chicago. His research interests include architectures and system-level design methodologies for heterogeneous system-on-chip. Contact him at firstname.lastname@example.org.
Paolo Mantovani is an Associate Research Scientist at Columbia University. He earned the MS in Electronic Engineering at Politecnico di Torino and the PhD in Computer Science at Columbia University. His PhD and current research interests include architecture design and system-level methodologies for the integration and programming of heterogeneous computing platforms. Paolo contributes to the open-source hardware community as the main architect of the `Embedded Scalable Platforms` architecture and FPGA emulation infrastructure.