AnaCoNGA: Analytical HW-CNN Co-Design Using Nested Genetic Algorithms
Nael Fasfous1, Manoj Rohit Vemparala2, Alexander Frickenstein2, Emanuele Valpreda4, Driton Salihu1, Julian Höfer3, Anmol Singh2, Naveen-Shankar Nagaraja2, Hans-Joerg Voegel2, Nguyen Anh Vu Doan1, Maurizio Martina4, Juergen Becker3 and Walter Stechele1
1Department of Electrical and Computer Engineering, Technical University of Munich, Germany
2Autonomous Driving, BMW Group, Germany
2Department of Electrical Engineering and Information Technology, Karlsruhe Institute of Technology, Germany
4Department of Electronics and Telecommunications, Politecnico di Torino, Italy
ABSTRACT
We present AnaCoNGA, an analytical co-design methodology, which enables two genetic algorithms to evaluate the fitness of design decisions on layer-wise quantization of a neural network and hardware (HW) resource allocation. We embed a hardware architecture search (HAS) algorithm into a quantization strategy search (QSS) algorithm to evaluate the hardware design Pareto-front of each considered quantization strategy. We harness the speed and flexibility of analytical HW-modeling to enable parallel HW-CNN co-design. With this approach, the QSS is focused on seeking high-accuracy quantization strategies which are guaranteed to have efficient hardware designs at the end of the search. Through AnaCoNGA, we improve the accuracy by 2.88 p.p. with respect to a uniform 2-bit ResNet20 on CIFAR-10, and achieve a 35% and 37% improvement in latency and DRAM accesses, while reducing LUT and BRAM resources by 9% and 59% respectively, when compared to a standard edge variant of the accelerator.
