An Open-Source FPGA Platform for Shared-Memory Heterogeneous Many-Core Architecture Exploration
Rafael Tornero, David Rodríguez, José Maria Martínez, José Flich · 2023
Many-core architectures, especially those with heterogeneous components, are gaining momentum due to the benefits of having an Open Source Instruction Set Architecture (ISA), such as RISC-V. In this paper we present a new computing platform for developing and analysing future heterogeneous architectures where specific custom accelerators are integrated with more standard RISC-V computing cores. The platform implements a coherent shared memory model which simplifies programmability and enables efficient communication support to all heterogeneous components. We detail the network and memory subsystems and provide preliminary evaluation results showing the benefits when using two systolic accelerators managed by two computing cores.