Optimizing CNNs Throughput on Bandwidth-Constrained Distributed Multi-FPGA Architectures

Existing multi-FPGA architectures often leverage high-speed interconnect technologies to achieve higher performance by exploiting ample communication bandwidth. In this paper, we propose an effective mapping approach for accelerating CNNs on bandwidth-constrained distributed multi-FPGA architectures. We formulate the system-level mapping problem and then introduce a method based on Genetic Algorithm (GA) and Mixed-Integer Nonlinear Programming (MINLP) to attain optimal solutions.